2016-04-27 18:37:12

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 00/15] perf-probe --cache and SDT support

Hi,

Here is the 5th version of the patchset for probe-cache and
initial SDT support which are going to be perf-cache finally.

The previous version is here; https://lkml.org/lkml/2016/4/26/179

This version fixes a build bug on "make build-test", removed
accepted patches, and fold buildid-cache style change and backward
compatibility patches.
IOW, just a cleanup version :)

TODOs are here, but I think it should involve kernel-side change
to complete.
- (perf record) Support SDT event recording directly
- (perf record) Support @FILE/@BUILDID suffix to record specific SDTs.
- (perf record) Try to unregister SDT events after record.
- (ftrace) Support multiple SDTs on single event.

Thank you,

---

Hemant Kumar (1):
perf/sdt: ELF support for SDT

Masami Hiramatsu (14):
perf probe: Use strbuf for making strings
perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid
perf-buildid-cache: Use lsdir for looking up buildid caches
perf probe: Add --cache option to cache the probe definitions
perf probe: Use cache entry if possible
perf probe: Show all cached probes
perf probe: Remove caches when --cache is given
perf probe: Add group name support
perf buildid-cache: Scan and import user SDT events to probe cache
perf probe: Accept %sdt and %cached event name
perf-list: Show SDT and pre-cached events
perf-list: Skip SDTs placed in invalid binaries
perf probe: Allow wildcard for cached events
perf probe: Support @BUILDID or @FILE suffix for SDT events


tools/perf/Documentation/perf-probe.txt | 24 +
tools/perf/builtin-list.c | 4
tools/perf/builtin-probe.c | 30 +
tools/perf/util/build-id.c | 278 ++++++++++---
tools/perf/util/build-id.h | 6
tools/perf/util/dso.h | 5
tools/perf/util/parse-events.c | 83 ++++
tools/perf/util/parse-events.h | 2
tools/perf/util/probe-event.c | 684 ++++++++++++++++++++++---------
tools/perf/util/probe-event.h | 9
tools/perf/util/probe-file.c | 492 ++++++++++++++++++++++
tools/perf/util/probe-file.h | 41 ++
tools/perf/util/probe-finder.c | 14 -
tools/perf/util/symbol-elf.c | 252 +++++++++++
tools/perf/util/symbol.c | 15 -
tools/perf/util/symbol.h | 22 +
16 files changed, 1689 insertions(+), 272 deletions(-)

--
Masami Hiramatsu


2016-04-27 18:37:22

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 01/15] perf probe: Use strbuf for making strings

From: Masami Hiramatsu <[email protected]>

Replace many fixed-length char array with strbuf to
stringify perf_probe_event and probe_trace_event etc.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>

---
Changes in v4:
- Update for the latest kernel.
- Remove "probe-event.c" from title and body, because
this also changes probe-finder.c too :)

Changes in v3:
- Remove unneeded strbuf_release(). (Thanks Namhyung!)

Changes in v2:
- Make perf_probe_event__sprintf() simpler.
---
tools/perf/util/probe-event.c | 246 ++++++++++++++--------------------------
tools/perf/util/probe-event.h | 2
tools/perf/util/probe-finder.c | 14 +-
3 files changed, 93 insertions(+), 169 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a977462..85d82f4 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1673,69 +1673,51 @@ out:
}

/* Compose only probe arg */
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa)
{
struct perf_probe_arg_field *field = pa->field;
- int ret;
- char *tmp = buf;
+ struct strbuf buf;
+ char *ret;

+ strbuf_init(&buf, 64);
if (pa->name && pa->var)
- ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var);
+ strbuf_addf(&buf, "%s=%s", pa->name, pa->var);
else
- ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
+ strbuf_addstr(&buf, pa->name ?: pa->var);

while (field) {
if (field->name[0] == '[')
- ret = e_snprintf(tmp, len, "%s", field->name);
+ strbuf_addstr(&buf, field->name);
else
- ret = e_snprintf(tmp, len, "%s%s",
- field->ref ? "->" : ".", field->name);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
+ strbuf_addf(&buf, "%s%s", field->ref ? "->" : ".",
+ field->name);
field = field->next;
}

- if (pa->type) {
- ret = e_snprintf(tmp, len, ":%s", pa->type);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
- }
+ if (pa->type)
+ strbuf_addf(&buf, ":%s", pa->type);
+
+ ret = strbuf_detach(&buf, NULL);

- return tmp - buf;
-error:
- pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
return ret;
}

/* Compose only probe point (not argument) */
static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
{
- char *buf, *tmp;
- char offs[32] = "", line[32] = "", file[32] = "";
- int ret, len;
-
- buf = zalloc(MAX_CMDLEN);
- if (buf == NULL) {
- ret = -ENOMEM;
- goto error;
- }
- if (pp->offset) {
- ret = e_snprintf(offs, 32, "+%lu", pp->offset);
- if (ret <= 0)
- goto error;
- }
- if (pp->line) {
- ret = e_snprintf(line, 32, ":%d", pp->line);
- if (ret <= 0)
- goto error;
+ struct strbuf buf;
+ char *tmp;
+ int len;
+
+ strbuf_init(&buf, 64);
+ if (pp->function) {
+ strbuf_addstr(&buf, pp->function);
+ if (pp->offset)
+ strbuf_addf(&buf, "+%lu", pp->offset);
+ else if (pp->line)
+ strbuf_addf(&buf, ":%d", pp->line);
+ else if (pp->retprobe)
+ strbuf_addstr(&buf, "%return");
}
if (pp->file) {
tmp = pp->file;
@@ -1744,25 +1726,12 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
tmp = strchr(pp->file + len - 30, '/');
tmp = tmp ? tmp + 1 : pp->file + len - 30;
}
- ret = e_snprintf(file, 32, "@%s", tmp);
- if (ret <= 0)
- goto error;
+ strbuf_addf(&buf, "@%s", tmp);
+ if (!pp->function && pp->line)
+ strbuf_addf(&buf, ":%d", pp->line);
}

- if (pp->function)
- ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function,
- offs, pp->retprobe ? "%return" : "", line,
- file);
- else
- ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
- if (ret <= 0)
- goto error;
-
- return buf;
-error:
- pr_debug("Failed to synthesize perf probe point: %d\n", ret);
- free(buf);
- return NULL;
+ return strbuf_detach(&buf, NULL);
}

#if 0
@@ -1791,45 +1760,30 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev)
#endif

static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
- char **buf, size_t *buflen,
- int depth)
+ struct strbuf *buf, int depth)
{
- int ret;
if (ref->next) {
depth = __synthesize_probe_trace_arg_ref(ref->next, buf,
- buflen, depth + 1);
+ depth + 1);
if (depth < 0)
goto out;
}
-
- ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset);
- if (ret < 0)
- depth = ret;
- else {
- *buf += ret;
- *buflen -= ret;
- }
+ strbuf_addf(buf, "%+ld(", ref->offset);
out:
return depth;
-
}

static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
- char *buf, size_t buflen)
+ struct strbuf *buf)
{
struct probe_trace_arg_ref *ref = arg->ref;
- int ret, depth = 0;
- char *tmp = buf;
+ int depth = 0;

/* Argument name or separator */
if (arg->name)
- ret = e_snprintf(buf, buflen, " %s=", arg->name);
+ strbuf_addf(buf, " %s=", arg->name);
else
- ret = e_snprintf(buf, buflen, " ");
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
+ strbuf_addch(buf, ' ');

/* Special case: @XXX */
if (arg->value[0] == '@' && arg->ref)
@@ -1837,60 +1791,41 @@ static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,

/* Dereferencing arguments */
if (ref) {
- depth = __synthesize_probe_trace_arg_ref(ref, &buf,
- &buflen, 1);
+ depth = __synthesize_probe_trace_arg_ref(ref, buf, 1);
if (depth < 0)
return depth;
}

/* Print argument value */
if (arg->value[0] == '@' && arg->ref)
- ret = e_snprintf(buf, buflen, "%s%+ld", arg->value,
- arg->ref->offset);
+ strbuf_addf(buf, "%s%+ld", arg->value, arg->ref->offset);
else
- ret = e_snprintf(buf, buflen, "%s", arg->value);
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
+ strbuf_addstr(buf, arg->value);

/* Closing */
- while (depth--) {
- ret = e_snprintf(buf, buflen, ")");
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
- }
+ while (depth--)
+ strbuf_addch(buf, ')');
/* Print argument type */
- if (arg->type) {
- ret = e_snprintf(buf, buflen, ":%s", arg->type);
- if (ret <= 0)
- return ret;
- buf += ret;
- }
+ if (arg->type)
+ strbuf_addf(buf, ":%s", arg->type);

- return buf - tmp;
+ return 0;
}

char *synthesize_probe_trace_command(struct probe_trace_event *tev)
{
struct probe_trace_point *tp = &tev->point;
- char *buf;
- int i, len, ret;
-
- buf = zalloc(MAX_CMDLEN);
- if (buf == NULL)
- return NULL;
-
- len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
- tev->group, tev->event);
- if (len <= 0)
- goto error;
+ struct strbuf buf;
+ char *ret = NULL;
+ int i;

/* Uprobes must have tp->module */
if (tev->uprobes && !tp->module)
- goto error;
+ return NULL;
+
+ strbuf_init(&buf, 32);
+ strbuf_addf(&buf, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+ tev->group, tev->event);
/*
* If tp->address == 0, then this point must be a
* absolute address uprobe.
@@ -1904,34 +1839,23 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev)

/* Use the tp->address for uprobes */
if (tev->uprobes)
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
- tp->module, tp->address);
+ strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address);
else if (!strncmp(tp->symbol, "0x", 2))
/* Absolute address. See try_to_find_absolute_address() */
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s0x%lx",
- tp->module ?: "", tp->module ? ":" : "",
- tp->address);
+ strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "",
+ tp->module ? ":" : "", tp->address);
else
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
- tp->module ?: "", tp->module ? ":" : "",
- tp->symbol, tp->offset);
-
- if (ret <= 0)
- goto error;
- len += ret;
+ strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "",
+ tp->module ? ":" : "", tp->symbol, tp->offset);

- for (i = 0; i < tev->nargs; i++) {
- ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
- MAX_CMDLEN - len);
- if (ret <= 0)
+ for (i = 0; i < tev->nargs; i++)
+ if (synthesize_probe_trace_arg(&tev->args[i], &buf) < 0)
goto error;
- len += ret;
- }

- return buf;
+ ret = strbuf_detach(&buf, NULL);
error:
- free(buf);
- return NULL;
+ strbuf_release(&buf);
+ return ret;
}

static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
@@ -2013,7 +1937,7 @@ static int convert_to_perf_probe_point(struct probe_trace_point *tp,
static int convert_to_perf_probe_event(struct probe_trace_event *tev,
struct perf_probe_event *pev, bool is_kprobe)
{
- char buf[64] = "";
+ struct strbuf buf = STRBUF_INIT;
int i, ret;

/* Convert event/group name */
@@ -2036,9 +1960,9 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev,
if (tev->args[i].name)
pev->args[i].name = strdup(tev->args[i].name);
else {
- ret = synthesize_probe_trace_arg(&tev->args[i],
- buf, 64);
- pev->args[i].name = strdup(buf);
+ strbuf_init(&buf, 32);
+ ret = synthesize_probe_trace_arg(&tev->args[i], &buf);
+ pev->args[i].name = strbuf_detach(&buf, NULL);
}
if (pev->args[i].name == NULL && ret >= 0)
ret = -ENOMEM;
@@ -2216,37 +2140,37 @@ static int perf_probe_event__sprintf(const char *group, const char *event,
const char *module,
struct strbuf *result)
{
- int i, ret;
- char buf[128];
- char *place;
+ int i;
+ char *buf;

- /* Synthesize only event probe point */
- place = synthesize_perf_probe_point(&pev->point);
- if (!place)
- return -EINVAL;
+ if (asprintf(&buf, "%s:%s", group, event) < 0)
+ return -errno;
+ strbuf_addf(result, " %-20s (on ", buf);
+ free(buf);

- ret = e_snprintf(buf, 128, "%s:%s", group, event);
- if (ret < 0)
- goto out;
+ /* Synthesize only event probe point */
+ buf = synthesize_perf_probe_point(&pev->point);
+ if (!buf)
+ return -ENOMEM;
+ strbuf_addstr(result, buf);
+ free(buf);

- strbuf_addf(result, " %-20s (on %s", buf, place);
if (module)
strbuf_addf(result, " in %s", module);

if (pev->nargs > 0) {
strbuf_add(result, " with", 5);
for (i = 0; i < pev->nargs; i++) {
- ret = synthesize_perf_probe_arg(&pev->args[i],
- buf, 128);
- if (ret < 0)
- goto out;
+ buf = synthesize_perf_probe_arg(&pev->args[i]);
+ if (!buf)
+ return -ENOMEM;
strbuf_addf(result, " %s", buf);
+ free(buf);
}
}
strbuf_addch(result, ')');
-out:
- free(place);
- return ret;
+
+ return 0;
}

/* Show an event */
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e54e7b0..e220962 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -120,7 +120,7 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
/* Events to command string */
char *synthesize_perf_probe_command(struct perf_probe_event *pev);
char *synthesize_probe_trace_command(struct probe_trace_event *tev);
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len);
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);

/* Check the perf_probe_event needs debuginfo */
bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index b3bd0fb..9f68875 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -553,7 +553,7 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
{
Dwarf_Die vr_die;
- char buf[32], *ptr;
+ char *buf, *ptr;
int ret = 0;

/* Copy raw parameters */
@@ -563,13 +563,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
if (pf->pvar->name)
pf->tvar->name = strdup(pf->pvar->name);
else {
- ret = synthesize_perf_probe_arg(pf->pvar, buf, 32);
- if (ret < 0)
- return ret;
+ buf = synthesize_perf_probe_arg(pf->pvar);
+ if (!buf)
+ return -ENOMEM;
ptr = strchr(buf, ':'); /* Change type separator to _ */
if (ptr)
*ptr = '_';
- pf->tvar->name = strdup(buf);
+ pf->tvar->name = buf;
}
if (pf->tvar->name == NULL)
return -ENOMEM;
@@ -1334,8 +1334,8 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
if (ret2 == 0) {
strlist__add(vl->vars,
strbuf_detach(&buf, NULL));
- }
- strbuf_release(&buf);
+ } else
+ strbuf_release(&buf);
}
}


2016-04-27 18:37:35

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

From: Masami Hiramatsu <[email protected]>

Use path/to/bin/buildid/elf instead of path/to/bin/buildid
to store corresponding elf binary.
This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.

Note that the existing caches are not updated until user adds
or updates the cache. Anyway, if there is the old style build-id
cache it falls back to use it. (IOW, it is backward compatible)

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v5:
- Support old style buildid caches.
---
tools/perf/util/build-id.c | 80 ++++++++++++++++++++++++++++++++++----------
tools/perf/util/dso.h | 5 +++
tools/perf/util/symbol.c | 15 ++++++--
3 files changed, 76 insertions(+), 24 deletions(-)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index b6ecf87..b035483 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -144,7 +144,8 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
return ret;
}

-static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
+static char *build_id_cache__linkname(const char *sbuild_id, char *bf,
+ size_t size)
{
char *tmp = bf;
int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
@@ -154,15 +155,45 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
return bf;
}

+static bool __is_regular_file(const char *pathname)
+{
+ struct stat sb;
+ return stat(pathname, &sb) == 0 && S_ISREG(sb.st_mode);
+}
+
+static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
+{
+ return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
+}
+
char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
{
- char build_id_hex[SBUILD_ID_SIZE];
+ bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
+ bool is_vdso = dso__is_vdso((struct dso *)dso);
+ char sbuild_id[SBUILD_ID_SIZE];
+ char *linkname;
+ bool alloc = (bf == NULL);
+ int ret;

if (!dso->has_build_id)
return NULL;

- build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
- return build_id__filename(build_id_hex, bf, size);
+ build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+ linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+ if (!linkname)
+ return NULL;
+
+ /* Check if old style build_id cache */
+ if (__is_regular_file(linkname))
+ ret = asnprintf(&bf, size, "%s", linkname);
+ else
+ ret = asnprintf(&bf, size, "%s/%s", linkname,
+ build_id_cache__basename(is_kallsyms, is_vdso));
+ if (ret < 0 || (!alloc && size < (unsigned int)ret))
+ bf = NULL;
+ free(linkname);
+
+ return bf;
}

bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
@@ -341,7 +372,8 @@ void disable_buildid_cache(void)
}

static char *build_id_cache__dirname_from_path(const char *name,
- bool is_kallsyms, bool is_vdso)
+ bool is_kallsyms, bool is_vdso,
+ const char *sbuild_id)
{
char *realname = (char *)name, *filename;
bool slash = is_kallsyms || is_vdso;
@@ -352,8 +384,9 @@ static char *build_id_cache__dirname_from_path(const char *name,
return NULL;
}

- if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "",
- is_vdso ? DSO__NAME_VDSO : realname) < 0)
+ if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "",
+ is_vdso ? DSO__NAME_VDSO : realname,
+ sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
filename = NULL;

if (!slash)
@@ -372,7 +405,8 @@ int build_id_cache__list_build_ids(const char *pathname,
int ret = 0;

list = strlist__new(NULL, NULL);
- dir_name = build_id_cache__dirname_from_path(pathname, false, false);
+ dir_name = build_id_cache__dirname_from_path(pathname, false, false,
+ NULL);
if (!list || !dir_name) {
ret = -ENOMEM;
goto out;
@@ -407,7 +441,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
{
const size_t size = PATH_MAX;
char *realname = NULL, *filename = NULL, *dir_name = NULL,
- *linkname = zalloc(size), *targetname, *tmp;
+ *linkname = zalloc(size), *tmp;
int err = -1;

if (!is_kallsyms) {
@@ -416,14 +450,22 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
goto out_free;
}

- dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso);
+ dir_name = build_id_cache__dirname_from_path(name, is_kallsyms,
+ is_vdso, sbuild_id);
if (!dir_name)
goto out_free;

+ /* Remove old style build-id cache */
+ if (__is_regular_file(dir_name))
+ if (unlink(dir_name))
+ goto out_free;
+
if (mkdir_p(dir_name, 0755))
goto out_free;

- if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
+ /* Save the allocated buildid dirname */
+ if (asprintf(&filename, "%s/%s", dir_name,
+ build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
filename = NULL;
goto out_free;
}
@@ -437,7 +479,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
goto out_free;
}

- if (!build_id__filename(sbuild_id, linkname, size))
+ if (!build_id_cache__linkname(sbuild_id, linkname, size))
goto out_free;
tmp = strrchr(linkname, '/');
*tmp = '\0';
@@ -446,10 +488,10 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
goto out_free;

*tmp = '/';
- targetname = filename + strlen(buildid_dir) - 5;
- memcpy(targetname, "../..", 5);
+ tmp = dir_name + strlen(buildid_dir) - 5;
+ memcpy(tmp, "../..", 5);

- if (symlink(targetname, linkname) == 0)
+ if (symlink(tmp, linkname) == 0)
err = 0;
out_free:
if (!is_kallsyms)
@@ -474,7 +516,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
bool build_id_cache__cached(const char *sbuild_id)
{
bool ret = false;
- char *filename = build_id__filename(sbuild_id, NULL, 0);
+ char *filename = build_id_cache__linkname(sbuild_id, NULL, 0);

if (filename && !access(filename, F_OK))
ret = true;
@@ -493,7 +535,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
if (filename == NULL || linkname == NULL)
goto out_free;

- if (!build_id__filename(sbuild_id, linkname, size))
+ if (!build_id_cache__linkname(sbuild_id, linkname, size))
goto out_free;

if (access(linkname, F_OK))
@@ -511,7 +553,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
tmp = strrchr(linkname, '/') + 1;
snprintf(tmp, size - (tmp - linkname), "%s", filename);

- if (unlink(linkname))
+ if (rm_rf(linkname))
goto out_free;

err = 0;
@@ -523,7 +565,7 @@ out_free:

static int dso__cache_build_id(struct dso *dso, struct machine *machine)
{
- bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+ bool is_kallsyms = dso__is_kallsyms(dso);
bool is_vdso = dso__is_vdso(dso);
const char *name = dso->long_name;
char nm[PATH_MAX];
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 0953280..76d79d0 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -349,6 +349,11 @@ static inline bool dso__is_kcore(struct dso *dso)
dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
}

+static inline bool dso__is_kallsyms(struct dso *dso)
+{
+ return dso->kernel && dso->long_name[0] != '/';
+}
+
void dso__free_a2l(struct dso *dso);

enum dso_type dso__type(struct dso *dso, struct machine *machine);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 415c4f6..9463c7d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1685,13 +1685,18 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
if (!find_matching_kcore(map, path, sizeof(path)))
return strdup(path);

- scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
+ scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s/kallsyms",
buildid_dir, sbuild_id);
-
+ /* Try old style kallsyms cache */
if (access(path, F_OK)) {
- pr_err("No kallsyms or vmlinux with build-id %s was found\n",
- sbuild_id);
- return NULL;
+ scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
+ buildid_dir, sbuild_id);
+
+ if (access(path, F_OK)) {
+ pr_err("No kallsyms or vmlinux with build-id %s was found\n",
+ sbuild_id);
+ return NULL;
+ }
}

return strdup(path);

2016-04-27 18:37:40

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 03/15] perf-buildid-cache: Use lsdir for looking up buildid caches

From: Masami Hiramatsu <[email protected]>

Use new lsdir() for looking up buildid caches. This changes
logic a bit to ignore all dot files, since the build-id
cache must not start with dot.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/util/build-id.c | 30 +++++-------------------------
1 file changed, 5 insertions(+), 25 deletions(-)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index b035483..848e05f 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -400,38 +400,18 @@ int build_id_cache__list_build_ids(const char *pathname,
{
struct strlist *list;
char *dir_name;
- DIR *dir;
- struct dirent *d;
int ret = 0;

- list = strlist__new(NULL, NULL);
dir_name = build_id_cache__dirname_from_path(pathname, false, false,
NULL);
- if (!list || !dir_name) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!dir_name)
+ return -ENOMEM;

- /* List up all dirents */
- dir = opendir(dir_name);
- if (!dir) {
+ list = lsdir(dir_name, lsdir_no_dot_filter);
+ if (!list)
ret = -errno;
- goto out;
- }
-
- while ((d = readdir(dir)) != NULL) {
- if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
- continue;
- strlist__add(list, d->d_name);
- }
- closedir(dir);
-
-out:
+ *result = list;
free(dir_name);
- if (ret)
- strlist__delete(list);
- else
- *result = list;

return ret;
}

2016-04-27 18:37:57

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 04/15] perf probe: Add --cache option to cache the probe definitions

From: Masami Hiramatsu <[email protected]>

Add --cache option to cache the probe definitions. This
just saves the result of the dwarf analysis to probe cache.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v5:
- Move probe_cache* definitions. (code cleanup)

Changes in v4:
- Remove cache saving failure message.
---
tools/perf/Documentation/perf-probe.txt | 4
tools/perf/builtin-probe.c | 1
tools/perf/util/build-id.c | 13 +
tools/perf/util/build-id.h | 2
tools/perf/util/probe-event.c | 126 +++++++++++--
tools/perf/util/probe-event.h | 5 +
tools/perf/util/probe-file.c | 299 +++++++++++++++++++++++++++++++
tools/perf/util/probe-file.h | 19 ++
8 files changed, 441 insertions(+), 28 deletions(-)

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 3a8a9ba..947db6f 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -109,6 +109,10 @@ OPTIONS
Dry run. With this option, --add and --del doesn't execute actual
adding and removal operations.

+--cache::
+ Cache the probes (with --add option). Any events which successfully added
+ are also stored in the cache file.
+
--max-probes=NUM::
Set the maximum number of probe points for an event. Default is 128.

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 9af859b..6d7ab431 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -512,6 +512,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
"Enable symbol demangling"),
OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
"Enable kernel symbol demangling"),
+ OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
OPT_END()
};
int ret;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 848e05f..588ff01 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -371,9 +371,8 @@ void disable_buildid_cache(void)
no_buildid_cache = true;
}

-static char *build_id_cache__dirname_from_path(const char *name,
- bool is_kallsyms, bool is_vdso,
- const char *sbuild_id)
+char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
+ bool is_kallsyms, bool is_vdso)
{
char *realname = (char *)name, *filename;
bool slash = is_kallsyms || is_vdso;
@@ -402,8 +401,8 @@ int build_id_cache__list_build_ids(const char *pathname,
char *dir_name;
int ret = 0;

- dir_name = build_id_cache__dirname_from_path(pathname, false, false,
- NULL);
+ dir_name = build_id_cache__dirname_from_path(NULL, pathname,
+ false, false);
if (!dir_name)
return -ENOMEM;

@@ -430,8 +429,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
goto out_free;
}

- dir_name = build_id_cache__dirname_from_path(name, is_kallsyms,
- is_vdso, sbuild_id);
+ dir_name = build_id_cache__dirname_from_path(sbuild_id, name,
+ is_kallsyms, is_vdso);
if (!dir_name)
goto out_free;

diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 64af3e2..1841524 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -28,6 +28,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
int perf_session__write_buildid_table(struct perf_session *session, int fd);
int perf_session__cache_build_ids(struct perf_session *session);

+char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
+ bool is_kallsyms, bool is_vdso);
int build_id_cache__list_build_ids(const char *pathname,
struct strlist **result);
bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 85d82f4..dc0265e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -67,7 +67,6 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
return ret;
}

-static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
static struct machine *host_machine;

/* Initialize symbol maps and path of vmlinux/modules */
@@ -1703,7 +1702,7 @@ char *synthesize_perf_probe_arg(struct perf_probe_arg *pa)
}

/* Compose only probe point (not argument) */
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+char *synthesize_perf_probe_point(struct perf_probe_point *pp)
{
struct strbuf buf;
char *tmp;
@@ -1734,30 +1733,36 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
return strbuf_detach(&buf, NULL);
}

-#if 0
char *synthesize_perf_probe_command(struct perf_probe_event *pev)
{
- char *buf;
- int i, len, ret;
+ struct strbuf buf;
+ char *tmp;
+ int i;

- buf = synthesize_perf_probe_point(&pev->point);
- if (!buf)
- return NULL;
+ strbuf_init(&buf, 64);
+ if (pev->event)
+ strbuf_addf(&buf, "%s:%s=", pev->group ?: PERFPROBE_GROUP,
+ pev->event);
+
+ tmp = synthesize_perf_probe_point(&pev->point);
+ if (!tmp)
+ goto out;
+ strbuf_addstr(&buf, tmp);
+ free(tmp);

- len = strlen(buf);
for (i = 0; i < pev->nargs; i++) {
- ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
- pev->args[i].name);
- if (ret <= 0) {
- free(buf);
- return NULL;
- }
- len += ret;
+ tmp = synthesize_perf_probe_arg(pev->args + i);
+ if (!tmp)
+ goto out;
+ strbuf_addf(&buf, " %s", tmp);
+ free(tmp);
}

- return buf;
+ tmp = strbuf_detach(&buf, NULL);
+out:
+ strbuf_release(&buf);
+ return tmp;
}
-#endif

static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
struct strbuf *buf, int depth)
@@ -2000,6 +2005,79 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
memset(pev, 0, sizeof(*pev));
}

+#define strdup_or_goto(str, label) \
+({ char *__p = NULL; if (str && !(__p = strdup(str))) goto label; __p; })
+
+static int perf_probe_point__copy(struct perf_probe_point *dst,
+ struct perf_probe_point *src)
+{
+ dst->file = strdup_or_goto(src->file, out_err);
+ dst->function = strdup_or_goto(src->function, out_err);
+ dst->lazy_line = strdup_or_goto(src->lazy_line, out_err);
+ dst->line = src->line;
+ dst->retprobe = src->retprobe;
+ dst->offset = src->offset;
+ return 0;
+
+out_err:
+ clear_perf_probe_point(dst);
+ return -ENOMEM;
+}
+
+static int perf_probe_arg__copy(struct perf_probe_arg *dst,
+ struct perf_probe_arg *src)
+{
+ struct perf_probe_arg_field *field, **ppfield;
+
+ dst->name = strdup_or_goto(src->name, out_err);
+ dst->var = strdup_or_goto(src->var, out_err);
+ dst->type = strdup_or_goto(src->type, out_err);
+
+ field = src->field;
+ ppfield = &(dst->field);
+ while (field) {
+ *ppfield = zalloc(sizeof(*field));
+ if (!*ppfield)
+ goto out_err;
+ (*ppfield)->name = strdup_or_goto(field->name, out_err);
+ (*ppfield)->index = field->index;
+ (*ppfield)->ref = field->ref;
+ field = field->next;
+ ppfield = &((*ppfield)->next);
+ }
+ return 0;
+out_err:
+ return -ENOMEM;
+}
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+ struct perf_probe_event *src)
+{
+ int i;
+
+ dst->event = strdup_or_goto(src->event, out_err);
+ dst->group = strdup_or_goto(src->group, out_err);
+ dst->target = strdup_or_goto(src->target, out_err);
+ dst->uprobes = src->uprobes;
+
+ if (perf_probe_point__copy(&dst->point, &src->point) < 0)
+ goto out_err;
+
+ dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs);
+ if (!dst->args)
+ goto out_err;
+ dst->nargs = src->nargs;
+
+ for (i = 0; i < src->nargs; i++)
+ if (perf_probe_arg__copy(&dst->args[i], &src->args[i]) < 0)
+ goto out_err;
+ return 0;
+
+out_err:
+ clear_perf_probe_event(dst);
+ return -ENOMEM;
+}
+
void clear_probe_trace_event(struct probe_trace_event *tev)
{
struct probe_trace_arg_ref *ref, *next;
@@ -2403,6 +2481,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
{
int i, fd, ret;
struct probe_trace_event *tev = NULL;
+ struct probe_cache *cache = NULL;
struct strlist *namelist;

fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
@@ -2444,6 +2523,14 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
}
if (ret == -EINVAL && pev->uprobes)
warn_uprobe_event_compat(tev);
+ if (ret == 0 && probe_conf.cache) {
+ cache = probe_cache__new(pev->target);
+ if (cache) {
+ probe_cache__add_entry(cache, pev, tevs, ntevs);
+ probe_cache__commit(cache);
+ probe_cache__delete(cache);
+ }
+ }

strlist__delete(namelist);
close_out:
@@ -2472,9 +2559,6 @@ static int find_probe_functions(struct map *map, char *name,
return found;
}

-#define strdup_or_goto(str, label) \
- ({ char *__p = strdup(str); if (!__p) goto label; __p; })
-
void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
struct probe_trace_event *tev __maybe_unused,
struct map *map __maybe_unused) { }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e220962..c451223 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_conf {
bool show_location_range;
bool force_add;
bool no_inlines;
+ bool cache;
int max_probes;
};
extern struct probe_conf probe_conf;
@@ -121,6 +122,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
char *synthesize_perf_probe_command(struct perf_probe_event *pev);
char *synthesize_probe_trace_command(struct probe_trace_event *tev);
char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
+char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+ struct perf_probe_event *src);

/* Check the perf_probe_event needs debuginfo */
bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3fe6214..bb849c9 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,6 +14,7 @@
* GNU General Public License for more details.
*
*/
+#include <sys/uio.h>
#include "util.h"
#include "event.h"
#include "strlist.h"
@@ -324,3 +325,301 @@ int probe_file__del_events(int fd, struct strfilter *filter)

return ret;
}
+
+static void probe_cache_entry__delete(struct probe_cache_entry *node)
+{
+ if (!list_empty(&node->list))
+ list_del(&node->list);
+ if (node->tevlist)
+ strlist__delete(node->tevlist);
+ clear_perf_probe_event(&node->pev);
+ free(node->spev);
+ free(node);
+}
+
+static struct probe_cache_entry *
+probe_cache_entry__new(struct perf_probe_event *pev)
+{
+ struct probe_cache_entry *ret = zalloc(sizeof(*ret));
+
+ if (ret) {
+ INIT_LIST_HEAD(&ret->list);
+ ret->tevlist = strlist__new(NULL, NULL);
+ if (!ret->tevlist)
+ zfree(&ret);
+ if (ret && pev) {
+ ret->spev = synthesize_perf_probe_command(pev);
+ if (!ret->spev ||
+ perf_probe_event__copy(&ret->pev, pev) < 0) {
+ probe_cache_entry__delete(ret);
+ return NULL;
+ }
+ }
+ }
+
+ return ret;
+}
+
+/* For the kernel probe caches, pass target = NULL */
+static int probe_cache__open(struct probe_cache *pcache, const char *target)
+{
+ char cpath[PATH_MAX];
+ char sbuildid[SBUILD_ID_SIZE];
+ char *dir_name;
+ bool is_kallsyms = !target;
+ int ret, fd;
+
+ if (target)
+ ret = filename__sprintf_build_id(target, sbuildid);
+ else {
+ target = "[kernel.kallsyms]";
+ ret = sysfs__sprintf_build_id("/", sbuildid);
+ }
+ if (ret < 0) {
+ pr_debug("Failed to get build-id from %s.\n", target ?: "kernel");
+ return ret;
+ }
+
+ /* If we have no buildid cache, make it */
+ if (!build_id_cache__cached(sbuildid)) {
+ ret = build_id_cache__add_s(sbuildid, target,
+ is_kallsyms, NULL);
+ if (ret < 0) {
+ pr_debug("Failed to add build-id cache: %s\n", target);
+ return ret;
+ }
+ }
+
+ dir_name = build_id_cache__dirname_from_path(sbuildid, target,
+ is_kallsyms, false);
+ if (!dir_name)
+ return -ENOMEM;
+
+ snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
+ fd = open(cpath, O_CREAT | O_RDWR | O_APPEND, 0644);
+ if (fd < 0)
+ pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
+ free(dir_name);
+ pcache->fd = fd;
+
+ return fd;
+}
+
+static int probe_cache__load(struct probe_cache *pcache)
+{
+ struct probe_cache_entry *entry = NULL;
+ char buf[MAX_CMDLEN], *p;
+ int ret = 0;
+ FILE *fp;
+
+ fp = fdopen(dup(pcache->fd), "r");
+ while (!feof(fp)) {
+ if (!fgets(buf, MAX_CMDLEN, fp))
+ break;
+ p = strchr(buf, '\n');
+ if (p)
+ *p = '\0';
+ if (buf[0] == '#') { /* #perf_probe_event */
+ entry = probe_cache_entry__new(NULL);
+ entry->spev = strdup(buf + 1);
+ ret = parse_perf_probe_command(buf + 1, &entry->pev);
+ if (!entry->spev || ret < 0) {
+ probe_cache_entry__delete(entry);
+ goto out;
+ }
+ list_add_tail(&entry->list, &pcache->list);
+ } else { /* trace_probe_event */
+ if (!entry) {
+ ret = -EINVAL;
+ goto out;
+ }
+ strlist__add(entry->tevlist, buf);
+ }
+ }
+out:
+ fclose(fp);
+ return ret;
+}
+
+static struct probe_cache *probe_cache__alloc(void)
+{
+ struct probe_cache *ret = zalloc(sizeof(*ret));
+
+ if (ret) {
+ INIT_LIST_HEAD(&ret->list);
+ ret->fd = -EINVAL;
+ }
+ return ret;
+}
+
+void probe_cache__delete(struct probe_cache *pcache)
+{
+ struct probe_cache_entry *entry;
+
+ if (!pcache)
+ return;
+
+ while (!list_empty(&pcache->list)) {
+ entry = list_first_entry(&pcache->list, typeof(*entry), list);
+ probe_cache_entry__delete(entry);
+ }
+ if (pcache->fd > 0)
+ close(pcache->fd);
+ free(pcache);
+}
+
+struct probe_cache *probe_cache__new(const char *target)
+{
+ struct probe_cache *pcache = probe_cache__alloc();
+ int ret;
+
+ if (!pcache)
+ return NULL;
+
+ ret = probe_cache__open(pcache, target);
+ if (ret < 0) {
+ pr_debug("Cache open error: %d\n", ret);
+ goto out_err;
+ }
+
+ ret = probe_cache__load(pcache);
+ if (ret < 0) {
+ pr_debug("Cache read error: %d\n", ret);
+ goto out_err;
+ }
+
+ return pcache;
+
+out_err:
+ probe_cache__delete(pcache);
+ return NULL;
+}
+
+static bool streql(const char *a, const char *b)
+{
+ if (a == b)
+ return true;
+
+ if (!a || !b)
+ return false;
+
+ return !strcmp(a, b);
+}
+
+static struct probe_cache_entry *
+probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
+{
+ struct probe_cache_entry *entry = NULL;
+ char *cmd = NULL;
+
+ cmd = synthesize_perf_probe_command(pev);
+ if (!cmd)
+ return NULL;
+
+ list_for_each_entry(entry, &pcache->list, list) {
+ /* Hit if same event name or same command-string */
+ if ((pev->event &&
+ (streql(entry->pev.group, pev->group) &&
+ streql(entry->pev.event, pev->event))) ||
+ (!strcmp(entry->spev, cmd)))
+ goto found;
+ }
+ entry = NULL;
+
+found:
+ free(cmd);
+ return entry;
+}
+
+int probe_cache__add_entry(struct probe_cache *pcache,
+ struct perf_probe_event *pev,
+ struct probe_trace_event *tevs, int ntevs)
+{
+ struct probe_cache_entry *entry = NULL;
+ char *command;
+ int i, ret = 0;
+
+ if (!pcache || !pev || !tevs || ntevs <= 0) {
+ ret = -EINVAL;
+ goto out_err;
+ }
+
+ /* Remove old cache entry */
+ entry = probe_cache__find(pcache, pev);
+ if (entry)
+ probe_cache_entry__delete(entry);
+
+ ret = -ENOMEM;
+ entry = probe_cache_entry__new(pev);
+ if (!entry)
+ goto out_err;
+
+ for (i = 0; i < ntevs; i++) {
+ if (!tevs[i].point.symbol)
+ continue;
+
+ command = synthesize_probe_trace_command(&tevs[i]);
+ if (!command)
+ goto out_err;
+ strlist__add(entry->tevlist, command);
+ free(command);
+ }
+ list_add_tail(&entry->list, &pcache->list);
+ pr_debug("Added probe cache: %d\n", ntevs);
+ return 0;
+
+out_err:
+ pr_debug("Failed to add probe caches\n");
+ if (entry)
+ probe_cache_entry__delete(entry);
+ return ret;
+}
+
+static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
+{
+ struct str_node *snode;
+ struct iovec iov[3];
+ int ret;
+
+ pr_debug("Writing cache: #%s\n", entry->spev);
+ iov[0].iov_base = (void *)"#"; iov[0].iov_len = 1;
+ iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
+ iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
+ ret = writev(fd, iov, 3);
+ if (ret < 0)
+ return ret;
+
+ strlist__for_each(snode, entry->tevlist) {
+ iov[0].iov_base = (void *)snode->s;
+ iov[0].iov_len = strlen(snode->s);
+ iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;
+ ret = writev(fd, iov, 2);
+ if (ret < 0)
+ return ret;
+ }
+ return 0;
+}
+
+int probe_cache__commit(struct probe_cache *pcache)
+{
+ struct probe_cache_entry *entry;
+ int ret = 0;
+
+ /* TBD: if we do not update existing entries, skip it */
+ ret = lseek(pcache->fd, 0, SEEK_SET);
+ if (ret < 0)
+ goto out;
+
+ ret = ftruncate(pcache->fd, 0);
+ if (ret < 0)
+ goto out;
+
+ list_for_each_entry(entry, &pcache->list, list) {
+ ret = probe_cache_entry__write(entry, pcache->fd);
+ pr_debug("Cache committed: %d\n", ret);
+ if (ret < 0)
+ break;
+ }
+out:
+ return ret;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 18ac9cf..d2b8791d 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -5,6 +5,19 @@
#include "strfilter.h"
#include "probe-event.h"

+/* Cache of probe definitions */
+struct probe_cache_entry {
+ struct list_head list;
+ struct perf_probe_event pev;
+ char *spev;
+ struct strlist *tevlist;
+};
+
+struct probe_cache {
+ int fd;
+ struct list_head list;
+};
+
#define PF_FL_UPROBE 1
#define PF_FL_RW 2

@@ -18,5 +31,11 @@ int probe_file__get_events(int fd, struct strfilter *filter,
struct strlist *plist);
int probe_file__del_strlist(int fd, struct strlist *namelist);

+struct probe_cache *probe_cache__new(const char *target);
+int probe_cache__add_entry(struct probe_cache *pcache,
+ struct perf_probe_event *pev,
+ struct probe_trace_event *tevs, int ntevs);
+int probe_cache__commit(struct probe_cache *pcache);
+void probe_cache__delete(struct probe_cache *pcache);

#endif

2016-04-27 18:37:59

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 05/15] perf probe: Use cache entry if possible

From: Masami Hiramatsu <[email protected]>

Before analyzing debuginfo, try to find a corresponding entry
from probe cache always. This does not depend on --cache,
the --cache enables to store/update cache, but looking up
the cache is always enabled.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/util/probe-event.c | 72 ++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/probe-file.c | 20 +++++++++++
tools/perf/util/probe-file.h | 5 ++-
3 files changed, 93 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index dc0265e..0cd709e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2443,17 +2443,24 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
char buf[64];
int ret;

+ /* If probe_event or trace_event already have the name, reuse it */
if (pev->event)
event = pev->event;
- else
+ else if (tev->event)
+ event = tev->event;
+ else {
+ /* Or generate new one from probe point */
if (pev->point.function &&
(strncmp(pev->point.function, "0x", 2) != 0) &&
!strisglob(pev->point.function))
event = pev->point.function;
else
event = tev->point.realname;
+ }
if (pev->group)
group = pev->group;
+ else if (tev->group)
+ group = tev->group;
else
group = PERFPROBE_GROUP;

@@ -2500,7 +2507,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
for (i = 0; i < ntevs; i++) {
tev = &tevs[i];
/* Skip if the symbol is out of .text or blacklisted */
- if (!tev->point.symbol)
+ if (!tev->point.symbol && !pev->uprobes)
continue;

/* Set new name for tev (and update namelist) */
@@ -2812,6 +2819,62 @@ errout:

bool __weak arch__prefers_symtab(void) { return false; }

+static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
+ struct probe_trace_event **tevs)
+{
+ struct probe_cache *cache;
+ struct probe_cache_entry *entry;
+ struct probe_trace_event *tev;
+ struct str_node *node;
+ int ret, i;
+
+ cache = probe_cache__new(pev->target);
+ if (!cache)
+ return 0;
+
+ entry = probe_cache__find(cache, pev);
+
+ if (!entry && !pev->event &&
+ (!pev->point.file && pev->point.function && !pev->point.retprobe &&
+ !pev->point.line && !pev->point.offset && !pev->point.lazy_line)) {
+ entry = probe_cache__find_by_name(cache, pev->group,
+ pev->point.function);
+ }
+ if (!entry) {
+ ret = 0;
+ goto out;
+ }
+
+ ret = strlist__nr_entries(entry->tevlist);
+ if (ret > probe_conf.max_probes) {
+ pr_debug("Too many entries matched in the cache of %s\n",
+ pev->target ? : "kernel");
+ ret = -E2BIG;
+ goto out;
+ }
+
+ *tevs = zalloc(ret * sizeof(*tev));
+ if (!*tevs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ i = 0;
+ strlist__for_each(node, entry->tevlist) {
+ tev = &(*tevs)[i++];
+ ret = parse_probe_trace_command(node->s, tev);
+ if (ret < 0)
+ goto out;
+ /* Set the uprobes attribute as same as original */
+ tev->uprobes = pev->uprobes;
+ }
+ ret = i;
+
+out:
+ probe_cache__delete(cache);
+ return ret;
+}
+
static int convert_to_probe_trace_events(struct perf_probe_event *pev,
struct probe_trace_event **tevs)
{
@@ -2834,6 +2897,11 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
if (ret > 0)
return ret;

+ /* At first, we need to lookup cache entry */
+ ret = find_probe_trace_events_from_cache(pev, tevs);
+ if (ret > 0)
+ return ret; /* Found in probe cache */
+
if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
ret = find_probe_trace_events_from_map(pev, tevs);
if (ret > 0)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index bb849c9..0d1298f 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -506,7 +506,7 @@ static bool streql(const char *a, const char *b)
return !strcmp(a, b);
}

-static struct probe_cache_entry *
+struct probe_cache_entry *
probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
{
struct probe_cache_entry *entry = NULL;
@@ -531,6 +531,24 @@ found:
return entry;
}

+struct probe_cache_entry *
+probe_cache__find_by_name(struct probe_cache *pcache,
+ const char *group, const char *event)
+{
+ struct probe_cache_entry *entry = NULL;
+
+ list_for_each_entry(entry, &pcache->list, list) {
+ /* Hit if same event name or same command-string */
+ if (streql(entry->pev.group, group) &&
+ streql(entry->pev.event, event))
+ goto found;
+ }
+ entry = NULL;
+
+found:
+ return entry;
+}
+
int probe_cache__add_entry(struct probe_cache *pcache,
struct perf_probe_event *pev,
struct probe_trace_event *tevs, int ntevs)
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index d2b8791d..1385c8b 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -37,5 +37,8 @@ int probe_cache__add_entry(struct probe_cache *pcache,
struct probe_trace_event *tevs, int ntevs);
int probe_cache__commit(struct probe_cache *pcache);
void probe_cache__delete(struct probe_cache *pcache);
-
+struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
+ struct perf_probe_event *pev);
+struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
+ const char *group, const char *event);
#endif

2016-04-27 18:38:10

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 06/15] perf probe: Show all cached probes

From: Masami Hiramatsu <[email protected]>

perf probe --list shows all cached probes when --cache
is given. Each caches are shown with on which binary that
probed. e.g.
-----
# perf probe --cache vfs_read \$params
# perf probe --cache -x /lib64/libc-2.17.so getaddrinfo \$params
# perf probe --cache --list
/[kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1):
vfs_read $params
/usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc):
getaddrinfo $params
-----
Note that $params requires debuginfo.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/Documentation/perf-probe.txt | 8 ++-
tools/perf/builtin-probe.c | 2 -
tools/perf/util/build-id.c | 79 ++++++++++++++++++++++++++++++-
tools/perf/util/build-id.h | 3 +
tools/perf/util/probe-event.c | 3 +
tools/perf/util/probe-file.c | 67 ++++++++++++++++++++++++++
tools/perf/util/probe-file.h | 1
7 files changed, 156 insertions(+), 7 deletions(-)

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 947db6f..5a70d45 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -67,7 +67,10 @@ OPTIONS

-l::
--list[=[GROUP:]EVENT]::
- List up current probe events. This can also accept filtering patterns of event names.
+ List up current probe events. This can also accept filtering patterns of
+ event names.
+ When this is used with --cache, perf shows all cached probes instead of
+ the live probes.

-L::
--line=::
@@ -110,8 +113,9 @@ OPTIONS
adding and removal operations.

--cache::
- Cache the probes (with --add option). Any events which successfully added
+ (With --add) Cache the probes. Any events which successfully added
are also stored in the cache file.
+ (With --list) Show cached probes.

--max-probes=NUM::
Set the maximum number of probe points for an event. Default is 128.
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 6d7ab431..53e380c0e 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,7 +44,7 @@

#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
#define DEFAULT_FUNC_FILTER "!_*"
-#define DEFAULT_LIST_FILTER "*:*"
+#define DEFAULT_LIST_FILTER "*"

/* Session management structure */
static struct {
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 588ff01..a7da315 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -144,8 +144,7 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
return ret;
}

-static char *build_id_cache__linkname(const char *sbuild_id, char *bf,
- size_t size)
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size)
{
char *tmp = bf;
int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
@@ -161,6 +160,29 @@ static bool __is_regular_file(const char *pathname)
return stat(pathname, &sb) == 0 && S_ISREG(sb.st_mode);
}

+char *build_id_cache__origname(const char *sbuild_id)
+{
+ char *linkname;
+ char buf[PATH_MAX];
+ char *ret = NULL, *p;
+
+ linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+ if (!linkname)
+ return NULL;
+
+ if (readlink(linkname, buf, PATH_MAX) < 0)
+ goto out;
+ /* The link should be "../..<origpath>/<sbuild_id>" */
+ p = strrchr(buf, '/'); /* Cut off the "/<sbuild_id>" */
+ if (p) {
+ *p = '\0';
+ ret = strdup(buf + 5); /* Skip "../.." */
+ }
+out:
+ free(linkname);
+ return ret;
+}
+
static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
{
return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
@@ -371,6 +393,59 @@ void disable_buildid_cache(void)
no_buildid_cache = true;
}

+int build_id_cache__list_all(struct strlist **result)
+{
+ struct strlist *toplist, *list, *bidlist;
+ struct str_node *nd, *nd2;
+ char *topdir, *linkdir;
+ char sbuild_id[SBUILD_ID_SIZE];
+ int ret = 0;
+
+ /* Open the top-level directory */
+ if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0)
+ return -errno;
+ toplist = lsdir(topdir, lsdir_no_dot_filter);
+ if (!toplist) {
+ pr_debug("Failed to opendir %s\n", topdir);
+ ret = -errno;
+ goto out;
+ }
+ bidlist = strlist__new(NULL, NULL);
+ strlist__for_each(nd, toplist) {
+ if (asprintf(&linkdir, "%s/%s", topdir, nd->s) < 0) {
+ ret = -errno;
+ goto out;
+ }
+ /* Open the lower-level directory */
+ list = lsdir(linkdir, lsdir_no_dot_filter);
+ if (!list) {
+ pr_debug("Failed to open %s: %d\n", linkdir, -errno);
+ goto next;
+ }
+ strlist__for_each(nd2, list) {
+ ret = snprintf(sbuild_id, SBUILD_ID_SIZE, "%s%s",
+ nd->s, nd2->s);
+ if (ret != SBUILD_ID_SIZE - 1) {
+ pr_debug("%s/%s is not buildid cache\n",
+ nd->s, nd2->s);
+ continue;
+ }
+ strlist__add(bidlist, sbuild_id);
+ }
+ strlist__delete(list);
+next:
+ free(linkdir);
+ }
+
+ *result = bidlist;
+out:
+ if (toplist)
+ strlist__delete(toplist);
+ free(topdir);
+
+ return ret;
+}
+
char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso)
{
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 1841524..2c98a39 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -28,8 +28,11 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
int perf_session__write_buildid_table(struct perf_session *session, int fd);
int perf_session__cache_build_ids(struct perf_session *session);

+char *build_id_cache__origname(const char *sbuild_id);
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso);
+int build_id_cache__list_all(struct strlist **result);
int build_id_cache__list_build_ids(const char *pathname,
struct strlist **result);
bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0cd709e..8bea724 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2335,6 +2335,9 @@ int show_perf_probe_events(struct strfilter *filter)

setup_pager();

+ if (probe_conf.cache)
+ return probe_cache__show_all_caches(filter);
+
ret = init_probe_symbol_maps(false);
if (ret < 0)
return ret;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 0d1298f..72d58e7 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -365,10 +365,17 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
{
char cpath[PATH_MAX];
char sbuildid[SBUILD_ID_SIZE];
- char *dir_name;
+ char *dir_name = NULL;
bool is_kallsyms = !target;
int ret, fd;

+ if (target && build_id_cache__cached(target)) {
+ /* This is a cached buildid */
+ strncpy(sbuildid, target, SBUILD_ID_SIZE);
+ dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
+ goto found;
+ }
+
if (target)
ret = filename__sprintf_build_id(target, sbuildid);
else {
@@ -392,8 +399,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)

dir_name = build_id_cache__dirname_from_path(sbuildid, target,
is_kallsyms, false);
- if (!dir_name)
+found:
+ if (!dir_name) {
+ pr_debug("Failed to get cache from %s\n", target);
return -ENOMEM;
+ }

snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
fd = open(cpath, O_CREAT | O_RDWR | O_APPEND, 0644);
@@ -641,3 +651,56 @@ int probe_cache__commit(struct probe_cache *pcache)
out:
return ret;
}
+
+static int probe_cache__show_entries(struct probe_cache *pcache,
+ struct strfilter *filter)
+{
+ struct probe_cache_entry *entry;
+ char buf[128], *ptr;
+
+ list_for_each_entry(entry, &pcache->list, list) {
+ if (entry->pev.event) {
+ ptr = buf;
+ snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
+ } else
+ ptr = entry->spev;
+ if (strfilter__compare(filter, ptr))
+ printf("%s\n", entry->spev);
+ }
+ return 0;
+}
+
+/* Show all cached probes */
+int probe_cache__show_all_caches(struct strfilter *filter)
+{
+ struct probe_cache *pcache;
+ struct strlist *bidlist;
+ struct str_node *nd;
+ char *buf;
+ int ret;
+
+ buf = strfilter__string(filter);
+ pr_debug("list cache with filter: %s\n", buf);
+ free(buf);
+
+ ret = build_id_cache__list_all(&bidlist);
+ if (ret < 0) {
+ pr_debug("Failed to get buildids: %d\n", ret);
+ return ret == -ENOENT ? 0 : ret;
+ }
+ strlist__for_each(nd, bidlist) {
+ pcache = probe_cache__new(nd->s);
+ if (!pcache)
+ continue;
+ if (!list_empty(&pcache->list)) {
+ buf = build_id_cache__origname(nd->s);
+ printf("%s (%s):\n", buf, nd->s);
+ free(buf);
+ probe_cache__show_entries(pcache, filter);
+ }
+ probe_cache__delete(pcache);
+ }
+ strlist__delete(bidlist);
+
+ return 0;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 1385c8b..ac70446 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -41,4 +41,5 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
struct perf_probe_event *pev);
struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
const char *group, const char *event);
+int probe_cache__show_all_caches(struct strfilter *filter);
#endif

2016-04-27 18:38:19

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 07/15] perf probe: Remove caches when --cache is given

From: Masami Hiramatsu <[email protected]>

perf-probe --del removes caches when --cache is given.
Note that the delete pattern is not same as normal events.

If you cached probes with event name, --del "eventname"
works as expected. However, if you skipped it, the cached
probes doesn't have actual event name. In that case
--del "probe-desc" is required (wildcard is acceptable).
For example a cache entry has the probe-desc "vfs_read $params",
you can remove it with --del 'vfs_read*'.

-----
# perf probe --cache --list
/[kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1):
vfs_read $params
/usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc):
getaddrinfo $params

# perf probe --cache --del vfs_read\*
Removed event: probe:vfs_read

# perf probe --cache --list
/[kernel.kallsyms] (1466a0a250b5d0070c6d0f03c5fed30b237970a1):
/usr/lib64/libc-2.17.so (c31ffe7942bfd77b2fca8f9bd5709d387a86d3bc):
getaddrinfo $params
-----

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v4:
- move del_perf_probe_caches() into builtin-probe.c since
command-line related delete procedure is there now.
---
tools/perf/Documentation/perf-probe.txt | 1 +
tools/perf/builtin-probe.c | 27 +++++++++++++++++++++++++
tools/perf/util/probe-file.c | 33 +++++++++++++++++++++++--------
tools/perf/util/probe-file.h | 2 ++
4 files changed, 55 insertions(+), 8 deletions(-)

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 5a70d45..8d09173 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -116,6 +116,7 @@ OPTIONS
(With --add) Cache the probes. Any events which successfully added
are also stored in the cache file.
(With --list) Show cached probes.
+ (With --del) Remove cached probes.

--max-probes=NUM::
Set the maximum number of probe points for an event. Default is 128.
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 53e380c0e..8f61525 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -363,6 +363,30 @@ out_cleanup:
return ret;
}

+static int del_perf_probe_caches(struct strfilter *filter)
+{
+ struct probe_cache *cache;
+ struct strlist *bidlist;
+ struct str_node *nd;
+ int ret;
+
+ ret = build_id_cache__list_all(&bidlist);
+ if (ret < 0) {
+ pr_debug("Failed to get buildids: %d\n", ret);
+ return ret;
+ }
+
+ strlist__for_each(nd, bidlist) {
+ cache = probe_cache__new(nd->s);
+ if (!cache)
+ continue;
+ probe_cache__remove_entries(cache, filter);
+ probe_cache__commit(cache);
+ probe_cache__delete(cache);
+ }
+ return 0;
+}
+
static int perf_del_probe_events(struct strfilter *filter)
{
int ret, ret2, ufd = -1, kfd = -1;
@@ -375,6 +399,9 @@ static int perf_del_probe_events(struct strfilter *filter)

pr_debug("Delete filter: \'%s\'\n", str);

+ if (probe_conf.cache)
+ return del_perf_probe_caches(filter);
+
/* Get current event names */
ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
if (ret < 0)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 72d58e7..46f006e 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -396,7 +396,6 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
return ret;
}
}
-
dir_name = build_id_cache__dirname_from_path(sbuildid, target,
is_kallsyms, false);
found:
@@ -652,19 +651,37 @@ out:
return ret;
}

+static bool probe_cache_entry__compare(struct probe_cache_entry *entry,
+ struct strfilter *filter)
+{
+ char buf[128], *ptr = entry->spev;
+
+ if (entry->pev.event) {
+ snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
+ ptr = buf;
+ }
+ return strfilter__compare(filter, ptr);
+}
+
+int probe_cache__remove_entries(struct probe_cache *pcache,
+ struct strfilter *filter)
+{
+ struct probe_cache_entry *entry, *tmp;
+
+ list_for_each_entry_safe(entry, tmp, &pcache->list, list) {
+ if (probe_cache_entry__compare(entry, filter))
+ probe_cache_entry__delete(entry);
+ }
+ return 0;
+}
+
static int probe_cache__show_entries(struct probe_cache *pcache,
struct strfilter *filter)
{
struct probe_cache_entry *entry;
- char buf[128], *ptr;

list_for_each_entry(entry, &pcache->list, list) {
- if (entry->pev.event) {
- ptr = buf;
- snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
- } else
- ptr = entry->spev;
- if (strfilter__compare(filter, ptr))
+ if (probe_cache_entry__compare(entry, filter))
printf("%s\n", entry->spev);
}
return 0;
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index ac70446..e6fd9b9 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -37,6 +37,8 @@ int probe_cache__add_entry(struct probe_cache *pcache,
struct probe_trace_event *tevs, int ntevs);
int probe_cache__commit(struct probe_cache *pcache);
void probe_cache__delete(struct probe_cache *pcache);
+int probe_cache__remove_entries(struct probe_cache *pcache,
+ struct strfilter *filter);
struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
struct perf_probe_event *pev);
struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,

2016-04-27 18:38:29

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 08/15] perf/sdt: ELF support for SDT

From: Hemant Kumar <[email protected]>

This patch serves the initial support to identify and list SDT events in binaries.
When programs containing SDT markers are compiled, gcc with the help of assembler
directives identifies them and places them in the section ".note.stapsdt". To find
these markers from the binaries, one needs to traverse through this section and
parse the relevant details like the name, type and location of the marker. Also,
the original location could be skewed due to the effect of prelinking. If that is
the case, the locations need to be adjusted.

The functions in this patch open a given ELF, find out the SDT section, parse the
relevant details, adjust the location (if necessary) and populate them in a list.

A typical note entry in ".note.stapsdt" section is as follows :


|--nhdr.n_namesz--|
------------------------------------
| nhdr | "stapsdt" |
----- |----------------------------------|
| | <location> <base_address> |
| | <semaphore> |
nhdr.n_descsize | "provider_name" "note_name" |
| | <args> |
----- |----------------------------------|
| nhdr | "stapsdt" |
|...

The above shows an excerpt from the section ".note.stapsdt".
'nhdr' is a structure which has the note name size (n_namesz), note
description size (n_desc_sz) and note type (n_type). So, in order to
parse the note note info, we need nhdr to tell us where to start from.
As can be seen from <sys/sdt.h>, the name of the SDT notes given is "stapsdt".
But this is not the identifier of the note.
After that, we go to description of the note to find out its location, the
address of the ".stapsdt.base" section and the semaphore address.
Then, we find the provider name and the SDT marker name and then follow the
arguments.

Signed-off-by: Hemant Kumar <[email protected]>
Reviewed-by: Masami Hiramatsu <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
---
tools/perf/util/symbol-elf.c | 252 ++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/symbol.h | 22 ++++
2 files changed, 274 insertions(+)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3f9d679..11aff8e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1780,6 +1780,258 @@ void kcore_extract__delete(struct kcore_extract *kce)
unlink(kce->extract_filename);
}

+/**
+ * populate_sdt_note : Parse raw data and identify SDT note
+ * @elf: elf of the opened file
+ * @data: raw data of a section with description offset applied
+ * @len: note description size
+ * @type: type of the note
+ * @sdt_notes: List to add the SDT note
+ *
+ * Responsible for parsing the @data in section .note.stapsdt in @elf and
+ * if its an SDT note, it appends to @sdt_notes list.
+ */
+static int populate_sdt_note(Elf **elf, const char *data, size_t len,
+ struct list_head *sdt_notes)
+{
+ const char *provider, *name;
+ struct sdt_note *tmp = NULL;
+ GElf_Ehdr ehdr;
+ GElf_Addr base_off = 0;
+ GElf_Shdr shdr;
+ int ret = -EINVAL;
+
+ union {
+ Elf64_Addr a64[NR_ADDR];
+ Elf32_Addr a32[NR_ADDR];
+ } buf;
+
+ Elf_Data dst = {
+ .d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT,
+ .d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT),
+ .d_off = 0, .d_align = 0
+ };
+ Elf_Data src = {
+ .d_buf = (void *) data, .d_type = ELF_T_ADDR,
+ .d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0,
+ .d_align = 0
+ };
+
+ tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note));
+ if (!tmp) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ INIT_LIST_HEAD(&tmp->note_list);
+
+ if (len < dst.d_size + 3)
+ goto out_free_note;
+
+ /* Translation from file representation to memory representation */
+ if (gelf_xlatetom(*elf, &dst, &src,
+ elf_getident(*elf, NULL)[EI_DATA]) == NULL) {
+ pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1));
+ goto out_free_note;
+ }
+
+ /* Populate the fields of sdt_note */
+ provider = data + dst.d_size;
+
+ name = (const char *)memchr(provider, '\0', data + len - provider);
+ if (name++ == NULL)
+ goto out_free_note;
+
+ tmp->provider = strdup(provider);
+ if (!tmp->provider) {
+ ret = -ENOMEM;
+ goto out_free_note;
+ }
+ tmp->name = strdup(name);
+ if (!tmp->name) {
+ ret = -ENOMEM;
+ goto out_free_prov;
+ }
+
+ if (gelf_getclass(*elf) == ELFCLASS32) {
+ memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
+ tmp->bit32 = true;
+ } else {
+ memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr));
+ tmp->bit32 = false;
+ }
+
+ if (!gelf_getehdr(*elf, &ehdr)) {
+ pr_debug("%s : cannot get elf header.\n", __func__);
+ ret = -EBADF;
+ goto out_free_name;
+ }
+
+ /* Adjust the prelink effect :
+ * Find out the .stapsdt.base section.
+ * This scn will help us to handle prelinking (if present).
+ * Compare the retrieved file offset of the base section with the
+ * base address in the description of the SDT note. If its different,
+ * then accordingly, adjust the note location.
+ */
+ if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
+ base_off = shdr.sh_offset;
+ if (base_off) {
+ if (tmp->bit32)
+ tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
+ tmp->addr.a32[1];
+ else
+ tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
+ tmp->addr.a64[1];
+ }
+ }
+
+ list_add_tail(&tmp->note_list, sdt_notes);
+ return 0;
+
+out_free_name:
+ free(tmp->name);
+out_free_prov:
+ free(tmp->provider);
+out_free_note:
+ free(tmp);
+out_err:
+ return ret;
+}
+
+/**
+ * construct_sdt_notes_list : constructs a list of SDT notes
+ * @elf : elf to look into
+ * @sdt_notes : empty list_head
+ *
+ * Scans the sections in 'elf' for the section
+ * .note.stapsdt. It, then calls populate_sdt_note to find
+ * out the SDT events and populates the 'sdt_notes'.
+ */
+static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes)
+{
+ GElf_Ehdr ehdr;
+ Elf_Scn *scn = NULL;
+ Elf_Data *data;
+ GElf_Shdr shdr;
+ size_t shstrndx, next;
+ GElf_Nhdr nhdr;
+ size_t name_off, desc_off, offset;
+ int ret = 0;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL) {
+ ret = -EBADF;
+ goto out_ret;
+ }
+ if (elf_getshdrstrndx(elf, &shstrndx) != 0) {
+ ret = -EBADF;
+ goto out_ret;
+ }
+
+ /* Look for the required section */
+ scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL);
+ if (!scn) {
+ ret = -ENOENT;
+ goto out_ret;
+ }
+
+ if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) {
+ ret = -ENOENT;
+ goto out_ret;
+ }
+
+ data = elf_getdata(scn, NULL);
+
+ /* Get the SDT notes */
+ for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off,
+ &desc_off)) > 0; offset = next) {
+ if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) &&
+ !memcmp(data->d_buf + name_off, SDT_NOTE_NAME,
+ sizeof(SDT_NOTE_NAME))) {
+ /* Check the type of the note */
+ if (nhdr.n_type != SDT_NOTE_TYPE)
+ goto out_ret;
+
+ ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off),
+ nhdr.n_descsz, sdt_notes);
+ if (ret < 0)
+ goto out_ret;
+ }
+ }
+ if (list_empty(sdt_notes))
+ ret = -ENOENT;
+
+out_ret:
+ return ret;
+}
+
+/**
+ * get_sdt_note_list : Wrapper to construct a list of sdt notes
+ * @head : empty list_head
+ * @target : file to find SDT notes from
+ *
+ * This opens the file, initializes
+ * the ELF and then calls construct_sdt_notes_list.
+ */
+int get_sdt_note_list(struct list_head *head, const char *target)
+{
+ Elf *elf;
+ int fd, ret;
+
+ fd = open(target, O_RDONLY);
+ if (fd < 0)
+ return -EBADF;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (!elf) {
+ ret = -EBADF;
+ goto out_close;
+ }
+ ret = construct_sdt_notes_list(elf, head);
+ elf_end(elf);
+out_close:
+ close(fd);
+ return ret;
+}
+
+/**
+ * cleanup_sdt_note_list : free the sdt notes' list
+ * @sdt_notes: sdt notes' list
+ *
+ * Free up the SDT notes in @sdt_notes.
+ * Returns the number of SDT notes free'd.
+ */
+int cleanup_sdt_note_list(struct list_head *sdt_notes)
+{
+ struct sdt_note *tmp, *pos;
+ int nr_free = 0;
+
+ list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
+ list_del(&pos->note_list);
+ free(pos->name);
+ free(pos->provider);
+ free(pos);
+ nr_free++;
+ }
+ return nr_free;
+}
+
+/**
+ * sdt_notes__get_count: Counts the number of sdt events
+ * @start: list_head to sdt_notes list
+ *
+ * Returns the number of SDT notes in a list
+ */
+int sdt_notes__get_count(struct list_head *start)
+{
+ struct sdt_note *sdt_ptr;
+ int count = 0;
+
+ list_for_each_entry(sdt_ptr, start, note_list)
+ count++;
+ return count;
+}
+
void symbol__elf_init(void)
{
elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index c8e4397..6fae31c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -331,4 +331,26 @@ void arch__elf_sym_adjust(GElf_Sym *sym);

int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);

+/* structure containing an SDT note's info */
+struct sdt_note {
+ char *name; /* name of the note*/
+ char *provider; /* provider name */
+ bool bit32; /* whether the location is 32 bits? */
+ union { /* location, base and semaphore addrs */
+ Elf64_Addr a64[3];
+ Elf32_Addr a32[3];
+ } addr;
+ struct list_head note_list; /* SDT notes' list */
+};
+
+int get_sdt_note_list(struct list_head *head, const char *target);
+int cleanup_sdt_note_list(struct list_head *sdt_notes);
+int sdt_notes__get_count(struct list_head *start);
+
+#define SDT_BASE_SCN ".stapsdt.base"
+#define SDT_NOTE_SCN ".note.stapsdt"
+#define SDT_NOTE_TYPE 3
+#define SDT_NOTE_NAME "stapsdt"
+#define NR_ADDR 3
+
#endif /* __PERF_SYMBOL */

2016-04-27 18:38:38

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 09/15] perf probe: Add group name support

From: Masami Hiramatsu <[email protected]>

Allow user to set group name for adding new event.
Note that user must ensure that the group name doesn't
conflict with existing group name carefully.
E.g. Existing group name can conflict with other events.
Especially, using the group name reserved for kernel
modules can hide kernel embedded events when loading
modules.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v4:
- Update Documentation/perf-probe.txt too.
---
tools/perf/Documentation/perf-probe.txt | 10 ++++++----
tools/perf/util/probe-event.c | 23 ++++++++++++++---------
2 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 8d09173..7a258e9 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -143,16 +143,18 @@ PROBE SYNTAX
Probe points are defined by following syntax.

1) Define event based on function name
- [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+ [[GROUP:]EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]

2) Define event based on source file with line number
- [EVENT=]SRC:ALN [ARG ...]
+ [[GROUP:]EVENT=]SRC:ALN [ARG ...]

3) Define event based on source file with lazy pattern
- [EVENT=]SRC;PTN [ARG ...]
+ [[GROUP:]EVENT=]SRC;PTN [ARG ...]


-'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
+Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
+modules.
'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function.
It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 8bea724..b2c6a4a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1208,10 +1208,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
bool file_spec = false;
/*
* <Syntax>
- * perf probe [EVENT=]SRC[:LN|;PTN]
- * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
- *
- * TODO:Group name support
+ * perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
+ * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
*/
if (!arg)
return -EINVAL;
@@ -1220,11 +1218,19 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
if (ptr && *ptr == '=') { /* Event name */
*ptr = '\0';
tmp = ptr + 1;
- if (strchr(arg, ':')) {
- semantic_error("Group name is not supported yet.\n");
- return -ENOTSUP;
- }
+ ptr = strchr(arg, ':');
+ if (ptr) {
+ *ptr = '\0';
+ if (!is_c_func_name(arg))
+ goto not_fname;
+ pev->group = strdup(arg);
+ if (!pev->group)
+ return -ENOMEM;
+ arg = ptr + 1;
+ } else
+ pev->group = NULL;
if (!is_c_func_name(arg)) {
+not_fname:
semantic_error("%s is bad for event name -it must "
"follow C symbol-naming rule.\n", arg);
return -EINVAL;
@@ -1232,7 +1238,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
pev->event = strdup(arg);
if (pev->event == NULL)
return -ENOMEM;
- pev->group = NULL;
arg = tmp;
}


2016-04-27 18:38:48

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 10/15] perf buildid-cache: Scan and import user SDT events to probe cache

From: Masami Hiramatsu <[email protected]>

perf buildid-cache --add <binary> scans given binary and add
the SDT events to probe cache. "sdt_" prefix is appended for
all SDT providers to avoid event-name clash with other pre-defined
events. It is possible to use the cached SDT events as other cached
events, via perf probe --add "sdt_<provider>:<event>=<event>".

e.g.
----
# perf buildid-cache --add /lib/libc-2.17.so
# perf probe --cache --list | head -n 5
/usr/lib/libc-2.17.so (a6fb821bdf53660eb2c29f778757aef294d3d392):
sdt_libc:setjmp=setjmp
sdt_libc:longjmp=longjmp
sdt_libc:longjmp_target=longjmp_target
sdt_libc:memory_heap_new=memory_heap_new
# perf probe -x /usr/lib/libc-2.17.so \
-a sdt_libc:memory_heap_new=memory_heap_new
Added new event:
sdt_libc:memory_heap_new (on memory_heap_new
in /usr/lib/libc-2.17.so)

You can now use it in all perf tools, such as:

perf record -e sdt_libc:memory_heap_new -aR sleep 1

# perf probe -l
sdt_libc:memory_heap_new (on new_heap+183 in /usr/lib/libc-2.17.so)
----

Note that SDT event entries in probe-cache file is somewhat different
from normal cached events. Normal one starts with "#", but SDTs are
starting with "%".

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v4:
- Fix a bug to copy correct group name to entries.
- Fix to consolidate same-name entries.
---
tools/perf/util/build-id.c | 27 +++++++++++++++--
tools/perf/util/probe-file.c | 67 ++++++++++++++++++++++++++++++++++++++++--
tools/perf/util/probe-file.h | 2 +
3 files changed, 90 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a7da315..49a467b9 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -17,6 +17,7 @@
#include "tool.h"
#include "header.h"
#include "vdso.h"
+#include "probe-file.h"


static bool no_buildid_cache;
@@ -490,6 +491,23 @@ int build_id_cache__list_build_ids(const char *pathname,
return ret;
}

+#ifdef HAVE_LIBELF_SUPPORT
+static void build_id_cache__add_sdt_cache(const char *sbuild_id,
+ const char *realname)
+{
+ struct probe_cache *cache;
+
+ cache = probe_cache__new(sbuild_id);
+ if (!cache)
+ return;
+ if (probe_cache__scan_sdt(cache, realname) >= 0)
+ probe_cache__commit(cache);
+ probe_cache__delete(cache);
+}
+#else
+#define build_id_cache__add_sdt_cache(sbuild_id, realname) do { } while (0)
+#endif
+
int build_id_cache__add_s(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso)
{
@@ -533,20 +551,23 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
goto out_free;
}

+ /* Make a symbolic link */
if (!build_id_cache__linkname(sbuild_id, linkname, size))
goto out_free;
+
tmp = strrchr(linkname, '/');
*tmp = '\0';
-
if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
goto out_free;
-
*tmp = '/';
tmp = dir_name + strlen(buildid_dir) - 5;
memcpy(tmp, "../..", 5);
-
if (symlink(tmp, linkname) == 0)
err = 0;
+
+ /* Update SDT cache */
+ build_id_cache__add_sdt_cache(sbuild_id, realname);
+
out_free:
if (!is_kallsyms)
free(realname);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 46f006e..c10a647 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -428,9 +428,12 @@ static int probe_cache__load(struct probe_cache *pcache)
p = strchr(buf, '\n');
if (p)
*p = '\0';
- if (buf[0] == '#') { /* #perf_probe_event */
+ /* #perf_probe_event or %sdt_event */
+ if (buf[0] == '#' || buf[0] == '%') {
entry = probe_cache_entry__new(NULL);
entry->spev = strdup(buf + 1);
+ if (buf[0] == '%')
+ entry->sdt = true;
ret = parse_perf_probe_command(buf + 1, &entry->pev);
if (!entry->spev || ret < 0) {
probe_cache_entry__delete(entry);
@@ -602,14 +605,72 @@ out_err:
return ret;
}

+static unsigned long long sdt_note__get_addr(struct sdt_note *note)
+{
+ return note->bit32 ? (unsigned long long)note->addr.a32[0]
+ : (unsigned long long)note->addr.a64[0];
+}
+
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
+{
+ struct probe_cache_entry *entry = NULL;
+ struct list_head sdtlist;
+ struct sdt_note *note;
+ char *buf;
+ char sdtgrp[64];
+ int ret;
+
+ INIT_LIST_HEAD(&sdtlist);
+ ret = get_sdt_note_list(&sdtlist, pathname);
+ if (ret < 0) {
+ pr_debug("Failed to get sdt note: %d\n", ret);
+ return ret;
+ }
+ list_for_each_entry(note, &sdtlist, note_list) {
+ ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider);
+ if (ret < 0)
+ break;
+ /* Try to find same-name entry */
+ entry = probe_cache__find_by_name(pcache, sdtgrp, note->name);
+ if (!entry) {
+ entry = probe_cache_entry__new(NULL);
+ if (!entry) {
+ ret = -ENOMEM;
+ break;
+ }
+ entry->sdt = true;
+ ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp,
+ note->name, note->name);
+ if (ret < 0)
+ break;
+ entry->pev.event = strdup(note->name);
+ entry->pev.group = strdup(sdtgrp);
+ list_add_tail(&entry->list, &pcache->list);
+ }
+ ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
+ sdtgrp, note->name, pathname,
+ sdt_note__get_addr(note));
+ if (ret < 0)
+ break;
+ strlist__add(entry->tevlist, buf);
+ free(buf);
+ entry = NULL;
+ }
+ if (entry)
+ probe_cache_entry__delete(entry);
+ cleanup_sdt_note_list(&sdtlist);
+ return ret;
+}
+
static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
{
struct str_node *snode;
struct iovec iov[3];
+ const char *prefix = entry->sdt ? "%" : "#";
int ret;

- pr_debug("Writing cache: #%s\n", entry->spev);
- iov[0].iov_base = (void *)"#"; iov[0].iov_len = 1;
+ pr_debug("Writing cache: %s%s\n", prefix, entry->spev);
+ iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1;
iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
ret = writev(fd, iov, 3);
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index e6fd9b9..93aa193 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -8,6 +8,7 @@
/* Cache of probe definitions */
struct probe_cache_entry {
struct list_head list;
+ bool sdt;
struct perf_probe_event pev;
char *spev;
struct strlist *tevlist;
@@ -35,6 +36,7 @@ struct probe_cache *probe_cache__new(const char *target);
int probe_cache__add_entry(struct probe_cache *pcache,
struct perf_probe_event *pev,
struct probe_trace_event *tevs, int ntevs);
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname);
int probe_cache__commit(struct probe_cache *pcache);
void probe_cache__delete(struct probe_cache *pcache);
int probe_cache__remove_entries(struct probe_cache *pcache,

2016-04-27 18:38:57

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 11/15] perf probe: Accept %sdt and %cached event name

From: Masami Hiramatsu <[email protected]>

To improbe usability, support %[PROVIDER:]SDTEVENT format to
add new probes on SDT and cached events.

e.g.
----
# perf probe -x /lib/libc-2.17.so %lll_lock_wait_private
Added new event:
sdt_libc:lll_lock_wait_private (on %lll_lock_wait_private in
/usr/lib/libc-2.17.so)

You can now use it in all perf tools, such as:

perf record -e sdt_libc:lll_lock_wait_private -aR sleep 1

# perf probe -l | more
sdt_libc:lll_lock_wait_private (on __lll_lock_wait_private+21
in /usr/lib/libc-2.17.so)
----

Note that this is not only for SDT events, but also normal
events with event-name.

e.g. define "myevent" on cache (-n doesn't add the real probe)
----
# perf probe -x ./perf --cache -n --add 'myevent=dso__load $params'
----
Reuse the "myevent" from cache as below.
----
# perf probe -x ./perf %myevent
----

TODO:
Wildcard is not supported yet.

Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/Documentation/perf-probe.txt | 3 +
tools/perf/util/probe-event.c | 78 ++++++++++++++++++++++---------
tools/perf/util/probe-event.h | 1
tools/perf/util/probe-file.c | 9 ++++
4 files changed, 69 insertions(+), 22 deletions(-)

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 7a258e9..43523be 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -151,6 +151,8 @@ Probe points are defined by following syntax.
3) Define event based on source file with lazy pattern
[[GROUP:]EVENT=]SRC;PTN [ARG ...]

+ 4) Pre-defined SDT events
+ %[PROVIDER:]SDTEVENT

'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
@@ -158,6 +160,7 @@ modules.
'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function.
It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
+'SDTEVENT' and 'PROVIDER' is the pre-defined event name which is defined by user SDT (Statically Defined Tracing) or the pre-cached probes with event name.

PROBE ARGUMENT
--------------
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b2c6a4a..1a9ea2b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1199,6 +1199,34 @@ err:
return err;
}

+static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
+{
+ char *ptr;
+
+ ptr = strchr(*arg, ':');
+ if (ptr) {
+ *ptr = '\0';
+ if (!is_c_func_name(*arg))
+ goto ng_name;
+ pev->group = strdup(*arg);
+ if (!pev->group)
+ return -ENOMEM;
+ *arg = ptr + 1;
+ } else
+ pev->group = NULL;
+ if (!is_c_func_name(*arg)) {
+ng_name:
+ semantic_error("%s is bad for event name -it must "
+ "follow C symbol-naming rule.\n", *arg);
+ return -EINVAL;
+ }
+ pev->event = strdup(*arg);
+ if (pev->event == NULL)
+ return -ENOMEM;
+
+ return 0;
+}
+
/* Parse probepoint definition. */
static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
{
@@ -1206,38 +1234,43 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
char *ptr, *tmp;
char c, nc = 0;
bool file_spec = false;
+ int ret;
+
/*
* <Syntax>
* perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
* perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
+ * perf probe %[GRP:]SDT_EVENT
*/
if (!arg)
return -EINVAL;

+ if (arg[0] == '%') {
+ pev->sdt = true;
+ arg++;
+ }
+
ptr = strpbrk(arg, ";=@+%");
- if (ptr && *ptr == '=') { /* Event name */
- *ptr = '\0';
- tmp = ptr + 1;
- ptr = strchr(arg, ':');
+ if (pev->sdt) {
if (ptr) {
- *ptr = '\0';
- if (!is_c_func_name(arg))
- goto not_fname;
- pev->group = strdup(arg);
- if (!pev->group)
- return -ENOMEM;
- arg = ptr + 1;
- } else
- pev->group = NULL;
- if (!is_c_func_name(arg)) {
-not_fname:
- semantic_error("%s is bad for event name -it must "
- "follow C symbol-naming rule.\n", arg);
+ semantic_error("%s must contain only an SDT event name.\n", arg);
return -EINVAL;
}
- pev->event = strdup(arg);
- if (pev->event == NULL)
- return -ENOMEM;
+ ret = parse_perf_probe_event_name(&arg, pev);
+ if (ret == 0) {
+ if (asprintf(&pev->point.function, "%%%s", pev->event) < 0)
+ ret = -errno;
+ }
+ return ret;
+ }
+
+ if (ptr && *ptr == '=') { /* Event name */
+ *ptr = '\0';
+ tmp = ptr + 1;
+ ret = parse_perf_probe_event_name(&arg, pev);
+ if (ret < 0)
+ return ret;
+
arg = tmp;
}

@@ -2849,7 +2882,8 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
pev->point.function);
}
if (!entry) {
- ret = 0;
+ /* SDT must be in the cache */
+ ret = pev->sdt ? -ENOENT : 0;
goto out;
}

@@ -2888,7 +2922,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
{
int ret;

- if (!pev->group) {
+ if (!pev->group && !pev->sdt) {
/* Set group name if not given */
if (!pev->uprobes) {
pev->group = strdup(PERFPROBE_GROUP);
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index c451223..2a23efe 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -85,6 +85,7 @@ struct perf_probe_event {
char *group; /* Group name */
struct perf_probe_point point; /* Probe point */
int nargs; /* Number of arguments */
+ bool sdt; /* SDT/cached event flag */
bool uprobes; /* Uprobe event flag */
char *target; /* Target binary */
struct perf_probe_arg *args; /* Arguments */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index c10a647..ee560dd 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -529,6 +529,15 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
return NULL;

list_for_each_entry(entry, &pcache->list, list) {
+ if (pev->sdt) {
+ if (entry->pev.event &&
+ streql(entry->pev.event, pev->event) &&
+ (!pev->group ||
+ streql(entry->pev.group, pev->group)))
+ goto found;
+
+ continue;
+ }
/* Hit if same event name or same command-string */
if ((pev->event &&
(streql(entry->pev.group, pev->group) &&

2016-04-27 18:39:07

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 12/15] perf-list: Show SDT and pre-cached events

From: Masami Hiramatsu <[email protected]>

Show SDT and pre-cached events by perf-list with "sdt". This also
shows the binary and build-id where the events are placed only
when there are same name events on different binaries.
e.g.
----
# perf list sdt

List of pre-defined events (to be used in -e):

sdt_libc:lll_futex_wake [SDT event]
sdt_libc:lll_lock_wait_private [SDT event]
sdt_libc:longjmp [SDT event]
sdt_libc:longjmp_target [SDT event]
...
sdt_libstdcxx:rethrow@/usr/bin/gcc(0cc207fc4b27) [SDT event]
sdt_libstdcxx:rethrow@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
sdt_libstdcxx:throw@/usr/bin/gcc(0cc207fc4b27) [SDT event]
sdt_libstdcxx:throw@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
----

The binary path and build-id are shown in below format;

<GROUP>:<EVENT>@<PATH>(<BUILD-ID>)

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v5:
- Fix a build error for minimal option.

Changes in v4:
- Update patch description.
- Change event list format.
---
tools/perf/builtin-list.c | 4 ++
tools/perf/util/parse-events.c | 83 ++++++++++++++++++++++++++++++++++++++++
tools/perf/util/parse-events.h | 2 +
tools/perf/util/probe-file.h | 9 ++++
4 files changed, 98 insertions(+)

diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 5e22db4..3cba865 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -62,6 +62,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
print_hwcache_events(NULL, raw_dump);
else if (strcmp(argv[i], "pmu") == 0)
print_pmu_events(NULL, raw_dump);
+ else if (strcmp(argv[i], "sdt") == 0)
+ print_sdt_events(NULL, NULL, raw_dump);
else if ((sep = strchr(argv[i], ':')) != NULL) {
int sep_idx;

@@ -76,6 +78,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)

s[sep_idx] = '\0';
print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
+ print_sdt_events(s, s + sep_idx + 1, raw_dump);
free(s);
} else {
if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -89,6 +92,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
print_hwcache_events(s, raw_dump);
print_pmu_events(s, raw_dump);
print_tracepoint_events(NULL, s, raw_dump);
+ print_sdt_events(NULL, s, raw_dump);
free(s);
}
}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bcbc983..f9c8b7b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -20,6 +20,7 @@
#include "pmu.h"
#include "thread_map.h"
#include "cpumap.h"
+#include "probe-file.h"
#include "asm/bug.h"

#define MAX_NAME_LEN 100
@@ -1976,6 +1977,86 @@ static bool is_event_supported(u8 type, unsigned config)
return ret;
}

+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+ bool name_only)
+{
+ struct probe_cache *pcache;
+ struct probe_cache_entry *ent;
+ struct strlist *bidlist, *sdtlist;
+ struct strlist_config cfg = {.dont_dupstr = true};
+ struct str_node *nd, *nd2;
+ char *buf, *path, *ptr = NULL;
+ bool show_detail = false;
+ int ret;
+
+ sdtlist = strlist__new(NULL, &cfg);
+ if (!sdtlist) {
+ pr_debug("Failed to allocate new strlist for SDT\n");
+ return;
+ }
+ ret = build_id_cache__list_all(&bidlist);
+ if (ret < 0) {
+ pr_debug("Failed to get buildids: %d\n", ret);
+ return;
+ }
+ strlist__for_each(nd, bidlist) {
+ pcache = probe_cache__new(nd->s);
+ if (!pcache)
+ continue;
+ if (!list_empty(&pcache->list))
+ list_for_each_entry(ent, &pcache->list, list) {
+ if (!ent->sdt)
+ continue;
+ if (subsys_glob &&
+ !strglobmatch(ent->pev.group, subsys_glob))
+ continue;
+ if (event_glob &&
+ !strglobmatch(ent->pev.event, event_glob))
+ continue;
+ ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
+ ent->pev.event, nd->s);
+ if (ret > 0)
+ strlist__add(sdtlist, buf);
+ }
+ probe_cache__delete(pcache);
+ }
+ strlist__delete(bidlist);
+
+ strlist__for_each(nd, sdtlist) {
+ buf = strchr(nd->s, '@');
+ if (buf)
+ *(buf++) = '\0';
+ if (name_only) {
+ printf("%s ", nd->s);
+ continue;
+ }
+ nd2 = strlist__next(nd);
+ if (nd2) {
+ ptr = strchr(nd2->s, '@');
+ if (ptr)
+ *ptr = '\0';
+ if (strcmp(nd->s, nd2->s) == 0)
+ show_detail = true;
+ }
+ if (show_detail) {
+ path = build_id_cache__origname(buf);
+ ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
+ if (ret > 0) {
+ printf(" %-50s [%s]\n", buf, "SDT event");
+ free(buf);
+ }
+ } else
+ printf(" %-50s [%s]\n", nd->s, "SDT event");
+ if (nd2) {
+ if (strcmp(nd->s, nd2->s) != 0)
+ show_detail = false;
+ if (ptr)
+ *ptr = '@';
+ }
+ }
+ strlist__delete(sdtlist);
+}
+
int print_hwcache_events(const char *event_glob, bool name_only)
{
unsigned int type, op, i, evt_i = 0, evt_num = 0;
@@ -2158,6 +2239,8 @@ void print_events(const char *event_glob, bool name_only)
}

print_tracepoint_events(NULL, NULL, name_only);
+
+ print_sdt_events(NULL, NULL, name_only);
}

int parse_events__is_hardcoded_term(struct parse_events_term *term)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d740c3c..c08daa9 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -182,6 +182,8 @@ void print_symbol_events(const char *event_glob, unsigned type,
void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
bool name_only);
int print_hwcache_events(const char *event_glob, bool name_only);
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+ bool name_only);
int is_valid_tracepoint(const char *event_string);

int valid_event_mount(const char *eventfs);
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 93aa193..ce98162 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -22,6 +22,8 @@ struct probe_cache {
#define PF_FL_UPROBE 1
#define PF_FL_RW 2

+/* probe-file.c depends on libelf */
+#ifdef HAVE_LIBELF_SUPPORT
int probe_file__open(int flag);
int probe_file__open_both(int *kfd, int *ufd, int flag);
struct strlist *probe_file__get_namelist(int fd);
@@ -46,4 +48,11 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
const char *group, const char *event);
int probe_cache__show_all_caches(struct strfilter *filter);
+#else /* ! HAVE_LIBELF_SUPPORT */
+static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
+{
+ return NULL;
+}
+#define probe_cache__delete(pcache) do {} while(0)
+#endif
#endif

2016-04-27 18:39:18

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 13/15] perf-list: Skip SDTs placed in invalid binaries

From: Masami Hiramatsu <[email protected]>

Skip SDTs placed in invalid (non-exist, or older version)
binaries. Note that perf-probe --cache --list and
perf-probe --cache --del still handle all the caches
including invalid binaries.

Signed-off-by: Masami Hiramatsu <[email protected]>
Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v4:
- Rename a parameter 'valid' to 'validonly' :)
---
tools/perf/builtin-probe.c | 2 +-
tools/perf/util/build-id.c | 27 ++++++++++++++++++++++++++-
tools/perf/util/build-id.h | 2 +-
tools/perf/util/parse-events.c | 2 +-
tools/perf/util/probe-file.c | 2 +-
5 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 8f61525..4a86aea 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -370,7 +370,7 @@ static int del_perf_probe_caches(struct strfilter *filter)
struct str_node *nd;
int ret;

- ret = build_id_cache__list_all(&bidlist);
+ ret = build_id_cache__list_all(&bidlist, false);
if (ret < 0) {
pr_debug("Failed to get buildids: %d\n", ret);
return ret;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 49a467b9..c849253 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -184,6 +184,25 @@ out:
return ret;
}

+static bool build_id_cache__valid_id(char *sbuild_id)
+{
+ char real_sbuild_id[SBUILD_ID_SIZE] = "";
+ char *pathname;
+ bool ret;
+
+ pathname = build_id_cache__origname(sbuild_id);
+ if (!pathname)
+ return false;
+
+ if (filename__sprintf_build_id(pathname, real_sbuild_id) < 0)
+ ret = false;
+ else
+ ret = (strcmp(sbuild_id, real_sbuild_id) == 0);
+ free(pathname);
+
+ return ret;
+}
+
static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
{
return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
@@ -394,7 +413,7 @@ void disable_buildid_cache(void)
no_buildid_cache = true;
}

-int build_id_cache__list_all(struct strlist **result)
+int build_id_cache__list_all(struct strlist **result, bool validonly)
{
struct strlist *toplist, *list, *bidlist;
struct str_node *nd, *nd2;
@@ -402,6 +421,10 @@ int build_id_cache__list_all(struct strlist **result)
char sbuild_id[SBUILD_ID_SIZE];
int ret = 0;

+ /* for filename__ functions */
+ if (validonly)
+ symbol__init(NULL);
+
/* Open the top-level directory */
if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0)
return -errno;
@@ -431,6 +454,8 @@ int build_id_cache__list_all(struct strlist **result)
nd->s, nd2->s);
continue;
}
+ if (validonly && !build_id_cache__valid_id(sbuild_id))
+ continue;
strlist__add(bidlist, sbuild_id);
}
strlist__delete(list);
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 2c98a39..5e29cfc 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -32,7 +32,7 @@ char *build_id_cache__origname(const char *sbuild_id);
char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso);
-int build_id_cache__list_all(struct strlist **result);
+int build_id_cache__list_all(struct strlist **result, bool validonly);
int build_id_cache__list_build_ids(const char *pathname,
struct strlist **result);
bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f9c8b7b..53d52a3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1994,7 +1994,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
pr_debug("Failed to allocate new strlist for SDT\n");
return;
}
- ret = build_id_cache__list_all(&bidlist);
+ ret = build_id_cache__list_all(&bidlist, true);
if (ret < 0) {
pr_debug("Failed to get buildids: %d\n", ret);
return;
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index ee560dd..2437b48 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -770,7 +770,7 @@ int probe_cache__show_all_caches(struct strfilter *filter)
pr_debug("list cache with filter: %s\n", buf);
free(buf);

- ret = build_id_cache__list_all(&bidlist);
+ ret = build_id_cache__list_all(&bidlist, false);
if (ret < 0) {
pr_debug("Failed to get buildids: %d\n", ret);
return ret == -ENOENT ? 0 : ret;

2016-04-27 18:39:26

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 14/15] perf probe: Allow wildcard for cached events

Allo glob wildcard for reusing cached/SDT events. This also
automatically find the target binaries, e.g.

# perf probe -a %sdt_libc:\*

This example adds probes for all SDT in libc.
Note that the SDTs must have been scanned by perf buildid-cache.

Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/util/probe-event.c | 153 ++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/probe-event.h | 1
tools/perf/util/probe-file.c | 33 ++++++++-
tools/perf/util/probe-file.h | 5 +
4 files changed, 183 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1a9ea2b..9ca8392 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -236,7 +236,7 @@ static void clear_perf_probe_point(struct perf_probe_point *pp)
free(pp->lazy_line);
}

-static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
{
int i;

@@ -1206,7 +1206,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
ptr = strchr(*arg, ':');
if (ptr) {
*ptr = '\0';
- if (!is_c_func_name(*arg))
+ if (!pev->sdt && !is_c_func_name(*arg))
goto ng_name;
pev->group = strdup(*arg);
if (!pev->group)
@@ -1214,7 +1214,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
*arg = ptr + 1;
} else
pev->group = NULL;
- if (!is_c_func_name(*arg)) {
+ if (!pev->sdt && !is_c_func_name(*arg)) {
ng_name:
semantic_error("%s is bad for event name -it must "
"follow C symbol-naming rule.\n", *arg);
@@ -1640,6 +1640,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
p = strchr(argv[1], ':');
if (p) {
tp->module = strndup(argv[1], p - argv[1]);
+ if (!tp->module) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ tev->uprobes = (tp->module[0] == '/');
p++;
} else
p = argv[1];
@@ -2485,7 +2490,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
int ret;

/* If probe_event or trace_event already have the name, reuse it */
- if (pev->event)
+ if (pev->event && !pev->sdt)
event = pev->event;
else if (tev->event)
event = tev->event;
@@ -2498,7 +2503,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
else
event = tev->point.realname;
}
- if (pev->group)
+ if (pev->group && !pev->sdt)
group = pev->group;
else if (tev->group)
group = tev->group;
@@ -2860,6 +2865,137 @@ errout:

bool __weak arch__prefers_symtab(void) { return false; }

+/* Concatinate two arrays */
+static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
+{
+ void *ret;
+
+ ret = malloc(sz_a + sz_b);
+ if (ret) {
+ memcpy(ret, a, sz_a);
+ memcpy(ret + sz_a, b, sz_b);
+ }
+ return ret;
+}
+
+static int
+concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
+ struct probe_trace_event **tevs2, int ntevs2)
+{
+ struct probe_trace_event *new_tevs;
+ int ret = 0;
+
+ if (ntevs == 0) {
+ *tevs = *tevs2;
+ *ntevs = ntevs2;
+ *tevs2 = NULL;
+ return 0;
+ }
+
+ if (*ntevs + ntevs2 > probe_conf.max_probes)
+ ret = -E2BIG;
+ else {
+ /* Concatinate the array of probe_trace_event */
+ new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
+ *tevs2, ntevs2 * sizeof(**tevs2));
+ if (!new_tevs)
+ ret = -ENOMEM;
+ else {
+ free(*tevs);
+ *tevs = new_tevs;
+ *ntevs += ntevs2;
+ }
+ }
+ if (ret < 0)
+ clear_probe_trace_events(*tevs2, ntevs2);
+ zfree(tevs2);
+
+ return ret;
+}
+
+/* Try to find probe_trace_event from given probe caches */
+static int find_cached_events(struct perf_probe_event *pev,
+ struct probe_trace_event **tevs,
+ const char *target)
+{
+ struct probe_cache *cache;
+ struct probe_cache_entry *entry;
+ struct probe_trace_event *tmp_tevs = NULL;
+ int ntevs = 0;
+ int ret = 0;
+
+ cache = probe_cache__new(target);
+ if (!cache)
+ return -ENOENT;
+
+ for_each_probe_cache_entry(entry, cache) {
+ /* Skip the cache entry which has no name */
+ if (!entry->pev.event || !entry->pev.group)
+ continue;
+ if (strglobmatch(entry->pev.group, pev->group) &&
+ strglobmatch(entry->pev.event, pev->event)) {
+ ret = probe_cache_entry__get_event(entry, &tmp_tevs);
+ if (ret > 0)
+ ret = concat_probe_trace_events(tevs, &ntevs,
+ &tmp_tevs, ret);
+ if (ret < 0)
+ break;
+ }
+ }
+ probe_cache__delete(cache);
+ if (ret < 0) {
+ clear_probe_trace_events(*tevs, ntevs);
+ zfree(tevs);
+ } else {
+ ret = ntevs;
+ if (target[0] == '/')
+ pev->uprobes = true;
+ }
+
+ return ret;
+}
+
+/* Try to find probe_trace_event from all probe caches */
+static int find_cached_events_all(struct perf_probe_event *pev,
+ struct probe_trace_event **tevs)
+{
+ struct probe_trace_event *tmp_tevs = NULL;
+ struct strlist *bidlist;
+ struct str_node *nd;
+ char *pathname;
+ int ntevs = 0;
+ int ret;
+
+ /* Get the buildid list of all valid caches */
+ ret = build_id_cache__list_all(&bidlist, true);
+ if (ret < 0) {
+ pr_debug("Failed to get buildids: %d\n", ret);
+ return ret;
+ }
+
+ ret = 0;
+ strlist__for_each(nd, bidlist) {
+ pathname = build_id_cache__origname(nd->s);
+ ret = find_cached_events(pev, &tmp_tevs, pathname);
+ if (ret > 0)
+ ret = concat_probe_trace_events(tevs, &ntevs,
+ &tmp_tevs, ret);
+ /* In the case of cnt == 0, we just skip it */
+ free(pathname);
+ if (ret < 0)
+ break;
+ }
+ strlist__delete(bidlist);
+
+ if (ret < 0) {
+ clear_probe_trace_events(*tevs, ntevs);
+ zfree(tevs);
+ } else
+ ret = ntevs;
+
+ return ret;
+}
+
static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
struct probe_trace_event **tevs)
{
@@ -2869,6 +3005,13 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
struct str_node *node;
int ret, i;

+ if (pev->sdt) {
+ /* For SDT/cached events, we use special search functions */
+ if (!pev->target)
+ return find_cached_events_all(pev, tevs);
+ else
+ return find_cached_events(pev, tevs, pev->target);
+ }
cache = probe_cache__new(pev->target);
if (!cache)
return 0;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 2a23efe..39b5a35 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -134,6 +134,7 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
/* Release event contents */
void clear_perf_probe_event(struct perf_probe_event *pev);
void clear_probe_trace_event(struct probe_trace_event *tev);
+void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs);

/* Command string to line-range */
int parse_line_range_desc(const char *cmd, struct line_range *lr);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 2437b48..896d645 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -360,6 +360,31 @@ probe_cache_entry__new(struct perf_probe_event *pev)
return ret;
}

+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+ struct probe_trace_event **tevs)
+{
+ struct probe_trace_event *tev;
+ struct str_node *node;
+ int ret, i;
+
+ ret = strlist__nr_entries(entry->tevlist);
+ if (ret > probe_conf.max_probes)
+ return -E2BIG;
+
+ *tevs = zalloc(ret * sizeof(*tev));
+ if (!*tevs)
+ return -ENOMEM;
+
+ i = 0;
+ strlist__for_each(node, entry->tevlist) {
+ tev = &(*tevs)[i++];
+ ret = parse_probe_trace_command(node->s, tev);
+ if (ret < 0)
+ break;
+ }
+ return i;
+}
+
/* For the kernel probe caches, pass target = NULL */
static int probe_cache__open(struct probe_cache *pcache, const char *target)
{
@@ -528,7 +553,7 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
if (!cmd)
return NULL;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
if (pev->sdt) {
if (entry->pev.event &&
streql(entry->pev.event, pev->event) &&
@@ -558,7 +583,7 @@ probe_cache__find_by_name(struct probe_cache *pcache,
{
struct probe_cache_entry *entry = NULL;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
/* Hit if same event name or same command-string */
if (streql(entry->pev.group, group) &&
streql(entry->pev.event, event))
@@ -711,7 +736,7 @@ int probe_cache__commit(struct probe_cache *pcache)
if (ret < 0)
goto out;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
ret = probe_cache_entry__write(entry, pcache->fd);
pr_debug("Cache committed: %d\n", ret);
if (ret < 0)
@@ -750,7 +775,7 @@ static int probe_cache__show_entries(struct probe_cache *pcache,
{
struct probe_cache_entry *entry;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
if (probe_cache_entry__compare(entry, filter))
printf("%s\n", entry->spev);
}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index ce98162..0faf083 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -21,6 +21,8 @@ struct probe_cache {

#define PF_FL_UPROBE 1
#define PF_FL_RW 2
+#define for_each_probe_cache_entry(entry, pcache) \
+ list_for_each_entry(entry, &pcache->list, list)

/* probe-file.c depends on libelf */
#ifdef HAVE_LIBELF_SUPPORT
@@ -34,6 +36,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
struct strlist *plist);
int probe_file__del_strlist(int fd, struct strlist *namelist);

+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+ struct probe_trace_event **tevs);
+
struct probe_cache *probe_cache__new(const char *target);
int probe_cache__add_entry(struct probe_cache *pcache,
struct perf_probe_event *pev,

2016-04-27 18:39:34

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5 15/15] perf probe: Support @BUILDID or @FILE suffix for SDT events

Support @BUILDID or @FILE suffix for SDT events. This allows
perf to add probes on SDTs/pre-cached events on given FILE
or the file which has given BUILDID (also, this complements
BUILDID.)
For example, both gcc and libstdc++ has same SDTs as below.
If you would like to add a probe on sdt_libstdcxx:catch on gcc,
you can do as below.

----
# perf list sdt | tail -n 6
sdt_libstdcxx:catch@/usr/bin/gcc(0cc207fc4b27) [SDT event]
sdt_libstdcxx:catch@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
sdt_libstdcxx:rethrow@/usr/bin/gcc(0cc207fc4b27) [SDT event]
sdt_libstdcxx:rethrow@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
sdt_libstdcxx:throw@/usr/bin/gcc(0cc207fc4b27) [SDT event]
sdt_libstdcxx:throw@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
# perf probe -a sdt_libstdcxx:catch@0cc
Added new event:
sdt_libstdcxx:catch (on %catch in /usr/bin/gcc)

You can now use it in all perf tools, such as:

perf record -e sdt_libstdcxx:catch -aR sleep 1
----

Signed-off-by: Masami Hiramatsu <[email protected]>
---
tools/perf/util/build-id.c | 40 ++++++++++++++++++++++++++++++++++++++++
tools/perf/util/build-id.h | 1 +
tools/perf/util/probe-event.c | 17 +++++++++++++++--
3 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index c849253..4fec09e 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -472,6 +472,46 @@ out:
return ret;
}

+static bool str_is_build_id(const char *maybe_sbuild_id, size_t len)
+{
+ size_t i;
+
+ for (i = 0; i < len; i++) {
+ if (!isxdigit(maybe_sbuild_id[i]))
+ return false;
+ }
+ return true;
+}
+
+/* Return the valid complete build-id */
+char *build_id_cache__complement(const char *incomplete_sbuild_id)
+{
+ struct strlist *list;
+ struct str_node *nd, *cand = NULL;
+ char *sbuild_id = NULL;
+ size_t len = strlen(incomplete_sbuild_id);
+
+ if (len >= SBUILD_ID_SIZE ||
+ !str_is_build_id(incomplete_sbuild_id, len) ||
+ build_id_cache__list_all(&list, true) < 0)
+ return NULL;
+
+ strlist__for_each(nd, list) {
+ if (strncmp(nd->s, incomplete_sbuild_id, len) != 0)
+ continue;
+ if (cand) { /* Error: There are more than 2 candidates. */
+ cand = NULL;
+ break;
+ }
+ cand = nd;
+ }
+ if (cand)
+ sbuild_id = strdup(cand->s);
+ strlist__delete(list);
+
+ return sbuild_id;
+}
+
char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso)
{
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 5e29cfc..cafab5e 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -33,6 +33,7 @@ char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
char *build_id_cache__dirname_from_path(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso);
int build_id_cache__list_all(struct strlist **result, bool validonly);
+char *build_id_cache__complement(const char *incomplete_sbuild_id);
int build_id_cache__list_build_ids(const char *pathname,
struct strlist **result);
bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9ca8392..29dc153 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1253,8 +1253,21 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
ptr = strpbrk(arg, ";=@+%");
if (pev->sdt) {
if (ptr) {
- semantic_error("%s must contain only an SDT event name.\n", arg);
- return -EINVAL;
+ if (*ptr != '@') {
+ semantic_error("%s must contain only an SDT event name.\n", arg);
+ return -EINVAL;
+ }
+ /* This must be a target file name or build id */
+ tmp = build_id_cache__complement(ptr + 1);
+ if (tmp) {
+ pev->target = build_id_cache__origname(tmp);
+ free(tmp);
+ } else
+ pev->target = strdup(ptr + 1);
+ if (!pev->target)
+ return -ENOMEM;
+ pev->uprobes = 1;
+ *ptr = '\0';
}
ret = parse_perf_probe_event_name(&arg, pev);
if (ret == 0) {

2016-04-27 18:42:20

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 14/15] perf probe: Allow wildcard for cached events


Oops, I missed to fix the SEGV bug.
I'll fix it and resend as 5.1.

Thanks,

On Thu, 28 Apr 2016 03:39:17 +0900
Masami Hiramatsu <[email protected]> wrote:

> Allo glob wildcard for reusing cached/SDT events. This also
> automatically find the target binaries, e.g.
>
> # perf probe -a %sdt_libc:\*
>
> This example adds probes for all SDT in libc.
> Note that the SDTs must have been scanned by perf buildid-cache.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> tools/perf/util/probe-event.c | 153 ++++++++++++++++++++++++++++++++++++++++-
> tools/perf/util/probe-event.h | 1
> tools/perf/util/probe-file.c | 33 ++++++++-
> tools/perf/util/probe-file.h | 5 +
> 4 files changed, 183 insertions(+), 9 deletions(-)
>
> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
> index 1a9ea2b..9ca8392 100644
> --- a/tools/perf/util/probe-event.c
> +++ b/tools/perf/util/probe-event.c
> @@ -236,7 +236,7 @@ static void clear_perf_probe_point(struct perf_probe_point *pp)
> free(pp->lazy_line);
> }
>
> -static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
> +void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
> {
> int i;
>
> @@ -1206,7 +1206,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> ptr = strchr(*arg, ':');
> if (ptr) {
> *ptr = '\0';
> - if (!is_c_func_name(*arg))
> + if (!pev->sdt && !is_c_func_name(*arg))
> goto ng_name;
> pev->group = strdup(*arg);
> if (!pev->group)
> @@ -1214,7 +1214,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> *arg = ptr + 1;
> } else
> pev->group = NULL;
> - if (!is_c_func_name(*arg)) {
> + if (!pev->sdt && !is_c_func_name(*arg)) {
> ng_name:
> semantic_error("%s is bad for event name -it must "
> "follow C symbol-naming rule.\n", *arg);
> @@ -1640,6 +1640,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
> p = strchr(argv[1], ':');
> if (p) {
> tp->module = strndup(argv[1], p - argv[1]);
> + if (!tp->module) {
> + ret = -ENOMEM;
> + goto out;
> + }
> + tev->uprobes = (tp->module[0] == '/');
> p++;
> } else
> p = argv[1];
> @@ -2485,7 +2490,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
> int ret;
>
> /* If probe_event or trace_event already have the name, reuse it */
> - if (pev->event)
> + if (pev->event && !pev->sdt)
> event = pev->event;
> else if (tev->event)
> event = tev->event;
> @@ -2498,7 +2503,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
> else
> event = tev->point.realname;
> }
> - if (pev->group)
> + if (pev->group && !pev->sdt)
> group = pev->group;
> else if (tev->group)
> group = tev->group;
> @@ -2860,6 +2865,137 @@ errout:
>
> bool __weak arch__prefers_symtab(void) { return false; }
>
> +/* Concatinate two arrays */
> +static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
> +{
> + void *ret;
> +
> + ret = malloc(sz_a + sz_b);
> + if (ret) {
> + memcpy(ret, a, sz_a);
> + memcpy(ret + sz_a, b, sz_b);
> + }
> + return ret;
> +}
> +
> +static int
> +concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
> + struct probe_trace_event **tevs2, int ntevs2)
> +{
> + struct probe_trace_event *new_tevs;
> + int ret = 0;
> +
> + if (ntevs == 0) {
> + *tevs = *tevs2;
> + *ntevs = ntevs2;
> + *tevs2 = NULL;
> + return 0;
> + }
> +
> + if (*ntevs + ntevs2 > probe_conf.max_probes)
> + ret = -E2BIG;
> + else {
> + /* Concatinate the array of probe_trace_event */
> + new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
> + *tevs2, ntevs2 * sizeof(**tevs2));
> + if (!new_tevs)
> + ret = -ENOMEM;
> + else {
> + free(*tevs);
> + *tevs = new_tevs;
> + *ntevs += ntevs2;
> + }
> + }
> + if (ret < 0)
> + clear_probe_trace_events(*tevs2, ntevs2);
> + zfree(tevs2);
> +
> + return ret;
> +}
> +
> +/* Try to find probe_trace_event from given probe caches */
> +static int find_cached_events(struct perf_probe_event *pev,
> + struct probe_trace_event **tevs,
> + const char *target)
> +{
> + struct probe_cache *cache;
> + struct probe_cache_entry *entry;
> + struct probe_trace_event *tmp_tevs = NULL;
> + int ntevs = 0;
> + int ret = 0;
> +
> + cache = probe_cache__new(target);
> + if (!cache)
> + return -ENOENT;
> +
> + for_each_probe_cache_entry(entry, cache) {
> + /* Skip the cache entry which has no name */
> + if (!entry->pev.event || !entry->pev.group)
> + continue;
> + if (strglobmatch(entry->pev.group, pev->group) &&
> + strglobmatch(entry->pev.event, pev->event)) {
> + ret = probe_cache_entry__get_event(entry, &tmp_tevs);
> + if (ret > 0)
> + ret = concat_probe_trace_events(tevs, &ntevs,
> + &tmp_tevs, ret);
> + if (ret < 0)
> + break;
> + }
> + }
> + probe_cache__delete(cache);
> + if (ret < 0) {
> + clear_probe_trace_events(*tevs, ntevs);
> + zfree(tevs);
> + } else {
> + ret = ntevs;
> + if (target[0] == '/')
> + pev->uprobes = true;
> + }
> +
> + return ret;
> +}
> +
> +/* Try to find probe_trace_event from all probe caches */
> +static int find_cached_events_all(struct perf_probe_event *pev,
> + struct probe_trace_event **tevs)
> +{
> + struct probe_trace_event *tmp_tevs = NULL;
> + struct strlist *bidlist;
> + struct str_node *nd;
> + char *pathname;
> + int ntevs = 0;
> + int ret;
> +
> + /* Get the buildid list of all valid caches */
> + ret = build_id_cache__list_all(&bidlist, true);
> + if (ret < 0) {
> + pr_debug("Failed to get buildids: %d\n", ret);
> + return ret;
> + }
> +
> + ret = 0;
> + strlist__for_each(nd, bidlist) {
> + pathname = build_id_cache__origname(nd->s);
> + ret = find_cached_events(pev, &tmp_tevs, pathname);
> + if (ret > 0)
> + ret = concat_probe_trace_events(tevs, &ntevs,
> + &tmp_tevs, ret);
> + /* In the case of cnt == 0, we just skip it */
> + free(pathname);
> + if (ret < 0)
> + break;
> + }
> + strlist__delete(bidlist);
> +
> + if (ret < 0) {
> + clear_probe_trace_events(*tevs, ntevs);
> + zfree(tevs);
> + } else
> + ret = ntevs;
> +
> + return ret;
> +}
> +
> static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> struct probe_trace_event **tevs)
> {
> @@ -2869,6 +3005,13 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> struct str_node *node;
> int ret, i;
>
> + if (pev->sdt) {
> + /* For SDT/cached events, we use special search functions */
> + if (!pev->target)
> + return find_cached_events_all(pev, tevs);
> + else
> + return find_cached_events(pev, tevs, pev->target);
> + }
> cache = probe_cache__new(pev->target);
> if (!cache)
> return 0;
> diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
> index 2a23efe..39b5a35 100644
> --- a/tools/perf/util/probe-event.h
> +++ b/tools/perf/util/probe-event.h
> @@ -134,6 +134,7 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
> /* Release event contents */
> void clear_perf_probe_event(struct perf_probe_event *pev);
> void clear_probe_trace_event(struct probe_trace_event *tev);
> +void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs);
>
> /* Command string to line-range */
> int parse_line_range_desc(const char *cmd, struct line_range *lr);
> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> index 2437b48..896d645 100644
> --- a/tools/perf/util/probe-file.c
> +++ b/tools/perf/util/probe-file.c
> @@ -360,6 +360,31 @@ probe_cache_entry__new(struct perf_probe_event *pev)
> return ret;
> }
>
> +int probe_cache_entry__get_event(struct probe_cache_entry *entry,
> + struct probe_trace_event **tevs)
> +{
> + struct probe_trace_event *tev;
> + struct str_node *node;
> + int ret, i;
> +
> + ret = strlist__nr_entries(entry->tevlist);
> + if (ret > probe_conf.max_probes)
> + return -E2BIG;
> +
> + *tevs = zalloc(ret * sizeof(*tev));
> + if (!*tevs)
> + return -ENOMEM;
> +
> + i = 0;
> + strlist__for_each(node, entry->tevlist) {
> + tev = &(*tevs)[i++];
> + ret = parse_probe_trace_command(node->s, tev);
> + if (ret < 0)
> + break;
> + }
> + return i;
> +}
> +
> /* For the kernel probe caches, pass target = NULL */
> static int probe_cache__open(struct probe_cache *pcache, const char *target)
> {
> @@ -528,7 +553,7 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
> if (!cmd)
> return NULL;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> if (pev->sdt) {
> if (entry->pev.event &&
> streql(entry->pev.event, pev->event) &&
> @@ -558,7 +583,7 @@ probe_cache__find_by_name(struct probe_cache *pcache,
> {
> struct probe_cache_entry *entry = NULL;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> /* Hit if same event name or same command-string */
> if (streql(entry->pev.group, group) &&
> streql(entry->pev.event, event))
> @@ -711,7 +736,7 @@ int probe_cache__commit(struct probe_cache *pcache)
> if (ret < 0)
> goto out;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> ret = probe_cache_entry__write(entry, pcache->fd);
> pr_debug("Cache committed: %d\n", ret);
> if (ret < 0)
> @@ -750,7 +775,7 @@ static int probe_cache__show_entries(struct probe_cache *pcache,
> {
> struct probe_cache_entry *entry;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> if (probe_cache_entry__compare(entry, filter))
> printf("%s\n", entry->spev);
> }
> diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
> index ce98162..0faf083 100644
> --- a/tools/perf/util/probe-file.h
> +++ b/tools/perf/util/probe-file.h
> @@ -21,6 +21,8 @@ struct probe_cache {
>
> #define PF_FL_UPROBE 1
> #define PF_FL_RW 2
> +#define for_each_probe_cache_entry(entry, pcache) \
> + list_for_each_entry(entry, &pcache->list, list)
>
> /* probe-file.c depends on libelf */
> #ifdef HAVE_LIBELF_SUPPORT
> @@ -34,6 +36,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
> struct strlist *plist);
> int probe_file__del_strlist(int fd, struct strlist *namelist);
>
> +int probe_cache_entry__get_event(struct probe_cache_entry *entry,
> + struct probe_trace_event **tevs);
> +
> struct probe_cache *probe_cache__new(const char *target);
> int probe_cache__add_entry(struct probe_cache *pcache,
> struct perf_probe_event *pev,
>


--
Masami Hiramatsu <[email protected]>

2016-04-27 19:15:29

by Masami Hiramatsu

[permalink] [raw]
Subject: [PATCH perf/core v5.1 14/15] perf probe: Allow wildcard for cached events

Allo glob wildcard for reusing cached/SDT events. This also
automatically find the target binaries, e.g.

# perf probe -a %sdt_libc:\*

This example adds probes for all SDT in libc.
Note that the SDTs must have been scanned by perf buildid-cache.

Signed-off-by: Masami Hiramatsu <[email protected]>
---
Changes in v5.1:
- Fix a SEGV bug when a group name is omitted. (Thanks Hemant!)
---
tools/perf/util/probe-event.c | 153 ++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/probe-event.h | 1
tools/perf/util/probe-file.c | 33 ++++++++-
tools/perf/util/probe-file.h | 5 +
4 files changed, 183 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 1a9ea2b..11752d2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -236,7 +236,7 @@ static void clear_perf_probe_point(struct perf_probe_point *pp)
free(pp->lazy_line);
}

-static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
{
int i;

@@ -1206,7 +1206,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
ptr = strchr(*arg, ':');
if (ptr) {
*ptr = '\0';
- if (!is_c_func_name(*arg))
+ if (!pev->sdt && !is_c_func_name(*arg))
goto ng_name;
pev->group = strdup(*arg);
if (!pev->group)
@@ -1214,7 +1214,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
*arg = ptr + 1;
} else
pev->group = NULL;
- if (!is_c_func_name(*arg)) {
+ if (!pev->sdt && !is_c_func_name(*arg)) {
ng_name:
semantic_error("%s is bad for event name -it must "
"follow C symbol-naming rule.\n", *arg);
@@ -1640,6 +1640,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
p = strchr(argv[1], ':');
if (p) {
tp->module = strndup(argv[1], p - argv[1]);
+ if (!tp->module) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ tev->uprobes = (tp->module[0] == '/');
p++;
} else
p = argv[1];
@@ -2485,7 +2490,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
int ret;

/* If probe_event or trace_event already have the name, reuse it */
- if (pev->event)
+ if (pev->event && !pev->sdt)
event = pev->event;
else if (tev->event)
event = tev->event;
@@ -2498,7 +2503,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
else
event = tev->point.realname;
}
- if (pev->group)
+ if (pev->group && !pev->sdt)
group = pev->group;
else if (tev->group)
group = tev->group;
@@ -2860,6 +2865,137 @@ errout:

bool __weak arch__prefers_symtab(void) { return false; }

+/* Concatinate two arrays */
+static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
+{
+ void *ret;
+
+ ret = malloc(sz_a + sz_b);
+ if (ret) {
+ memcpy(ret, a, sz_a);
+ memcpy(ret + sz_a, b, sz_b);
+ }
+ return ret;
+}
+
+static int
+concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
+ struct probe_trace_event **tevs2, int ntevs2)
+{
+ struct probe_trace_event *new_tevs;
+ int ret = 0;
+
+ if (ntevs == 0) {
+ *tevs = *tevs2;
+ *ntevs = ntevs2;
+ *tevs2 = NULL;
+ return 0;
+ }
+
+ if (*ntevs + ntevs2 > probe_conf.max_probes)
+ ret = -E2BIG;
+ else {
+ /* Concatinate the array of probe_trace_event */
+ new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
+ *tevs2, ntevs2 * sizeof(**tevs2));
+ if (!new_tevs)
+ ret = -ENOMEM;
+ else {
+ free(*tevs);
+ *tevs = new_tevs;
+ *ntevs += ntevs2;
+ }
+ }
+ if (ret < 0)
+ clear_probe_trace_events(*tevs2, ntevs2);
+ zfree(tevs2);
+
+ return ret;
+}
+
+/* Try to find probe_trace_event from given probe caches */
+static int find_cached_events(struct perf_probe_event *pev,
+ struct probe_trace_event **tevs,
+ const char *target)
+{
+ struct probe_cache *cache;
+ struct probe_cache_entry *entry;
+ struct probe_trace_event *tmp_tevs = NULL;
+ int ntevs = 0;
+ int ret = 0;
+
+ cache = probe_cache__new(target);
+ if (!cache)
+ return -ENOENT;
+
+ for_each_probe_cache_entry(entry, cache) {
+ /* Skip the cache entry which has no name */
+ if (!entry->pev.event || !entry->pev.group)
+ continue;
+ if ((!pev->group || strglobmatch(entry->pev.group, pev->group)) &&
+ strglobmatch(entry->pev.event, pev->event)) {
+ ret = probe_cache_entry__get_event(entry, &tmp_tevs);
+ if (ret > 0)
+ ret = concat_probe_trace_events(tevs, &ntevs,
+ &tmp_tevs, ret);
+ if (ret < 0)
+ break;
+ }
+ }
+ probe_cache__delete(cache);
+ if (ret < 0) {
+ clear_probe_trace_events(*tevs, ntevs);
+ zfree(tevs);
+ } else {
+ ret = ntevs;
+ if (target[0] == '/')
+ pev->uprobes = true;
+ }
+
+ return ret;
+}
+
+/* Try to find probe_trace_event from all probe caches */
+static int find_cached_events_all(struct perf_probe_event *pev,
+ struct probe_trace_event **tevs)
+{
+ struct probe_trace_event *tmp_tevs = NULL;
+ struct strlist *bidlist;
+ struct str_node *nd;
+ char *pathname;
+ int ntevs = 0;
+ int ret;
+
+ /* Get the buildid list of all valid caches */
+ ret = build_id_cache__list_all(&bidlist, true);
+ if (ret < 0) {
+ pr_debug("Failed to get buildids: %d\n", ret);
+ return ret;
+ }
+
+ ret = 0;
+ strlist__for_each(nd, bidlist) {
+ pathname = build_id_cache__origname(nd->s);
+ ret = find_cached_events(pev, &tmp_tevs, pathname);
+ if (ret > 0)
+ ret = concat_probe_trace_events(tevs, &ntevs,
+ &tmp_tevs, ret);
+ /* In the case of cnt == 0, we just skip it */
+ free(pathname);
+ if (ret < 0)
+ break;
+ }
+ strlist__delete(bidlist);
+
+ if (ret < 0) {
+ clear_probe_trace_events(*tevs, ntevs);
+ zfree(tevs);
+ } else
+ ret = ntevs;
+
+ return ret;
+}
+
static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
struct probe_trace_event **tevs)
{
@@ -2869,6 +3005,13 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
struct str_node *node;
int ret, i;

+ if (pev->sdt) {
+ /* For SDT/cached events, we use special search functions */
+ if (!pev->target)
+ return find_cached_events_all(pev, tevs);
+ else
+ return find_cached_events(pev, tevs, pev->target);
+ }
cache = probe_cache__new(pev->target);
if (!cache)
return 0;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 2a23efe..39b5a35 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -134,6 +134,7 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
/* Release event contents */
void clear_perf_probe_event(struct perf_probe_event *pev);
void clear_probe_trace_event(struct probe_trace_event *tev);
+void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs);

/* Command string to line-range */
int parse_line_range_desc(const char *cmd, struct line_range *lr);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 2437b48..896d645 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -360,6 +360,31 @@ probe_cache_entry__new(struct perf_probe_event *pev)
return ret;
}

+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+ struct probe_trace_event **tevs)
+{
+ struct probe_trace_event *tev;
+ struct str_node *node;
+ int ret, i;
+
+ ret = strlist__nr_entries(entry->tevlist);
+ if (ret > probe_conf.max_probes)
+ return -E2BIG;
+
+ *tevs = zalloc(ret * sizeof(*tev));
+ if (!*tevs)
+ return -ENOMEM;
+
+ i = 0;
+ strlist__for_each(node, entry->tevlist) {
+ tev = &(*tevs)[i++];
+ ret = parse_probe_trace_command(node->s, tev);
+ if (ret < 0)
+ break;
+ }
+ return i;
+}
+
/* For the kernel probe caches, pass target = NULL */
static int probe_cache__open(struct probe_cache *pcache, const char *target)
{
@@ -528,7 +553,7 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
if (!cmd)
return NULL;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
if (pev->sdt) {
if (entry->pev.event &&
streql(entry->pev.event, pev->event) &&
@@ -558,7 +583,7 @@ probe_cache__find_by_name(struct probe_cache *pcache,
{
struct probe_cache_entry *entry = NULL;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
/* Hit if same event name or same command-string */
if (streql(entry->pev.group, group) &&
streql(entry->pev.event, event))
@@ -711,7 +736,7 @@ int probe_cache__commit(struct probe_cache *pcache)
if (ret < 0)
goto out;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
ret = probe_cache_entry__write(entry, pcache->fd);
pr_debug("Cache committed: %d\n", ret);
if (ret < 0)
@@ -750,7 +775,7 @@ static int probe_cache__show_entries(struct probe_cache *pcache,
{
struct probe_cache_entry *entry;

- list_for_each_entry(entry, &pcache->list, list) {
+ for_each_probe_cache_entry(entry, pcache) {
if (probe_cache_entry__compare(entry, filter))
printf("%s\n", entry->spev);
}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index ce98162..0faf083 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -21,6 +21,8 @@ struct probe_cache {

#define PF_FL_UPROBE 1
#define PF_FL_RW 2
+#define for_each_probe_cache_entry(entry, pcache) \
+ list_for_each_entry(entry, &pcache->list, list)

/* probe-file.c depends on libelf */
#ifdef HAVE_LIBELF_SUPPORT
@@ -34,6 +36,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
struct strlist *plist);
int probe_file__del_strlist(int fd, struct strlist *namelist);

+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+ struct probe_trace_event **tevs);
+
struct probe_cache *probe_cache__new(const char *target);
int probe_cache__add_entry(struct probe_cache *pcache,
struct perf_probe_event *pev,

2016-04-27 20:32:31

by Hemant Kumar

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 10/15] perf buildid-cache: Scan and import user SDT events to probe cache



On 04/28/2016 12:08 AM, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> perf buildid-cache --add <binary> scans given binary and add
> the SDT events to probe cache. "sdt_" prefix is appended for
> all SDT providers to avoid event-name clash with other pre-defined
> events. It is possible to use the cached SDT events as other cached
> events, via perf probe --add "sdt_<provider>:<event>=<event>".
>
> e.g.
> ----
> # perf buildid-cache --add /lib/libc-2.17.so
> # perf probe --cache --list | head -n 5
> /usr/lib/libc-2.17.so (a6fb821bdf53660eb2c29f778757aef294d3d392):
> sdt_libc:setjmp=setjmp
> sdt_libc:longjmp=longjmp
> sdt_libc:longjmp_target=longjmp_target
> sdt_libc:memory_heap_new=memory_heap_new
> # perf probe -x /usr/lib/libc-2.17.so \
> -a sdt_libc:memory_heap_new=memory_heap_new
> Added new event:
> sdt_libc:memory_heap_new (on memory_heap_new
> in /usr/lib/libc-2.17.so)
>
> You can now use it in all perf tools, such as:
>
> perf record -e sdt_libc:memory_heap_new -aR sleep 1
>
> # perf probe -l
> sdt_libc:memory_heap_new (on new_heap+183 in /usr/lib/libc-2.17.so)
> ----
>
> Note that SDT event entries in probe-cache file is somewhat different
> from normal cached events. Normal one starts with "#", but SDTs are
> starting with "%".
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v4:
> - Fix a bug to copy correct group name to entries.
> - Fix to consolidate same-name entries.

Acked-by: Hemant Kumar <[email protected]>

> ---
> tools/perf/util/build-id.c | 27 +++++++++++++++--
> tools/perf/util/probe-file.c | 67 ++++++++++++++++++++++++++++++++++++++++--
> tools/perf/util/probe-file.h | 2 +
> 3 files changed, 90 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
> index a7da315..49a467b9 100644
> --- a/tools/perf/util/build-id.c
> +++ b/tools/perf/util/build-id.c
> @@ -17,6 +17,7 @@
> #include "tool.h"
> #include "header.h"
> #include "vdso.h"
> +#include "probe-file.h"
>
>
> static bool no_buildid_cache;
> @@ -490,6 +491,23 @@ int build_id_cache__list_build_ids(const char *pathname,
> return ret;
> }
>
> +#ifdef HAVE_LIBELF_SUPPORT
> +static void build_id_cache__add_sdt_cache(const char *sbuild_id,
> + const char *realname)
> +{
> + struct probe_cache *cache;
> +
> + cache = probe_cache__new(sbuild_id);
> + if (!cache)
> + return;
> + if (probe_cache__scan_sdt(cache, realname) >= 0)
> + probe_cache__commit(cache);
> + probe_cache__delete(cache);
> +}
> +#else
> +#define build_id_cache__add_sdt_cache(sbuild_id, realname) do { } while (0)
> +#endif
> +
> int build_id_cache__add_s(const char *sbuild_id, const char *name,
> bool is_kallsyms, bool is_vdso)
> {
> @@ -533,20 +551,23 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
> }
>
> + /* Make a symbolic link */
> if (!build_id_cache__linkname(sbuild_id, linkname, size))
> goto out_free;
> +
> tmp = strrchr(linkname, '/');
> *tmp = '\0';
> -
> if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
> goto out_free;
> -
> *tmp = '/';
> tmp = dir_name + strlen(buildid_dir) - 5;
> memcpy(tmp, "../..", 5);
> -
> if (symlink(tmp, linkname) == 0)
> err = 0;
> +
> + /* Update SDT cache */
> + build_id_cache__add_sdt_cache(sbuild_id, realname);
> +
> out_free:
> if (!is_kallsyms)
> free(realname);
> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> index 46f006e..c10a647 100644
> --- a/tools/perf/util/probe-file.c
> +++ b/tools/perf/util/probe-file.c
> @@ -428,9 +428,12 @@ static int probe_cache__load(struct probe_cache *pcache)
> p = strchr(buf, '\n');
> if (p)
> *p = '\0';
> - if (buf[0] == '#') { /* #perf_probe_event */
> + /* #perf_probe_event or %sdt_event */
> + if (buf[0] == '#' || buf[0] == '%') {
> entry = probe_cache_entry__new(NULL);
> entry->spev = strdup(buf + 1);
> + if (buf[0] == '%')
> + entry->sdt = true;
> ret = parse_perf_probe_command(buf + 1, &entry->pev);
> if (!entry->spev || ret < 0) {
> probe_cache_entry__delete(entry);
> @@ -602,14 +605,72 @@ out_err:
> return ret;
> }
>
> +static unsigned long long sdt_note__get_addr(struct sdt_note *note)
> +{
> + return note->bit32 ? (unsigned long long)note->addr.a32[0]
> + : (unsigned long long)note->addr.a64[0];
> +}
> +
> +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
> +{
> + struct probe_cache_entry *entry = NULL;
> + struct list_head sdtlist;
> + struct sdt_note *note;
> + char *buf;
> + char sdtgrp[64];
> + int ret;
> +
> + INIT_LIST_HEAD(&sdtlist);
> + ret = get_sdt_note_list(&sdtlist, pathname);
> + if (ret < 0) {
> + pr_debug("Failed to get sdt note: %d\n", ret);
> + return ret;
> + }
> + list_for_each_entry(note, &sdtlist, note_list) {
> + ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider);
> + if (ret < 0)
> + break;
> + /* Try to find same-name entry */
> + entry = probe_cache__find_by_name(pcache, sdtgrp, note->name);
> + if (!entry) {
> + entry = probe_cache_entry__new(NULL);
> + if (!entry) {
> + ret = -ENOMEM;
> + break;
> + }
> + entry->sdt = true;
> + ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp,
> + note->name, note->name);
> + if (ret < 0)
> + break;
> + entry->pev.event = strdup(note->name);
> + entry->pev.group = strdup(sdtgrp);
> + list_add_tail(&entry->list, &pcache->list);
> + }
> + ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
> + sdtgrp, note->name, pathname,
> + sdt_note__get_addr(note));
> + if (ret < 0)
> + break;
> + strlist__add(entry->tevlist, buf);
> + free(buf);
> + entry = NULL;
> + }
> + if (entry)
> + probe_cache_entry__delete(entry);
> + cleanup_sdt_note_list(&sdtlist);
> + return ret;
> +}
> +
> static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
> {
> struct str_node *snode;
> struct iovec iov[3];
> + const char *prefix = entry->sdt ? "%" : "#";
> int ret;
>
> - pr_debug("Writing cache: #%s\n", entry->spev);
> - iov[0].iov_base = (void *)"#"; iov[0].iov_len = 1;
> + pr_debug("Writing cache: %s%s\n", prefix, entry->spev);
> + iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1;
> iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
> iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
> ret = writev(fd, iov, 3);
> diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
> index e6fd9b9..93aa193 100644
> --- a/tools/perf/util/probe-file.h
> +++ b/tools/perf/util/probe-file.h
> @@ -8,6 +8,7 @@
> /* Cache of probe definitions */
> struct probe_cache_entry {
> struct list_head list;
> + bool sdt;
> struct perf_probe_event pev;
> char *spev;
> struct strlist *tevlist;
> @@ -35,6 +36,7 @@ struct probe_cache *probe_cache__new(const char *target);
> int probe_cache__add_entry(struct probe_cache *pcache,
> struct perf_probe_event *pev,
> struct probe_trace_event *tevs, int ntevs);
> +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname);
> int probe_cache__commit(struct probe_cache *pcache);
> void probe_cache__delete(struct probe_cache *pcache);
> int probe_cache__remove_entries(struct probe_cache *pcache,
>

--
Thanks,
Hemant Kumar

2016-04-27 20:38:04

by Hemant Kumar

[permalink] [raw]
Subject: Re: [PATCH perf/core v5.1 14/15] perf probe: Allow wildcard for cached events



On 04/28/2016 12:45 AM, Masami Hiramatsu wrote:
> Allo glob wildcard for reusing cached/SDT events. This also
> automatically find the target binaries, e.g.
>
> # perf probe -a %sdt_libc:\*
>
> This example adds probes for all SDT in libc.
> Note that the SDTs must have been scanned by perf buildid-cache.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v5.1:
> - Fix a SEGV bug when a group name is omitted. (Thanks Hemant!)

Thanks for the fix.

Acked-by: Hemant Kumar <[email protected]>

> ---
> tools/perf/util/probe-event.c | 153 ++++++++++++++++++++++++++++++++++++++++-
> tools/perf/util/probe-event.h | 1
> tools/perf/util/probe-file.c | 33 ++++++++-
> tools/perf/util/probe-file.h | 5 +
> 4 files changed, 183 insertions(+), 9 deletions(-)
>
> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
> index 1a9ea2b..11752d2 100644
> --- a/tools/perf/util/probe-event.c
> +++ b/tools/perf/util/probe-event.c
> @@ -236,7 +236,7 @@ static void clear_perf_probe_point(struct perf_probe_point *pp)
> free(pp->lazy_line);
> }
>
> -static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
> +void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
> {
> int i;
>
> @@ -1206,7 +1206,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> ptr = strchr(*arg, ':');
> if (ptr) {
> *ptr = '\0';
> - if (!is_c_func_name(*arg))
> + if (!pev->sdt && !is_c_func_name(*arg))
> goto ng_name;
> pev->group = strdup(*arg);
> if (!pev->group)
> @@ -1214,7 +1214,7 @@ static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> *arg = ptr + 1;
> } else
> pev->group = NULL;
> - if (!is_c_func_name(*arg)) {
> + if (!pev->sdt && !is_c_func_name(*arg)) {
> ng_name:
> semantic_error("%s is bad for event name -it must "
> "follow C symbol-naming rule.\n", *arg);
> @@ -1640,6 +1640,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
> p = strchr(argv[1], ':');
> if (p) {
> tp->module = strndup(argv[1], p - argv[1]);
> + if (!tp->module) {
> + ret = -ENOMEM;
> + goto out;
> + }
> + tev->uprobes = (tp->module[0] == '/');
> p++;
> } else
> p = argv[1];
> @@ -2485,7 +2490,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
> int ret;
>
> /* If probe_event or trace_event already have the name, reuse it */
> - if (pev->event)
> + if (pev->event && !pev->sdt)
> event = pev->event;
> else if (tev->event)
> event = tev->event;
> @@ -2498,7 +2503,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
> else
> event = tev->point.realname;
> }
> - if (pev->group)
> + if (pev->group && !pev->sdt)
> group = pev->group;
> else if (tev->group)
> group = tev->group;
> @@ -2860,6 +2865,137 @@ errout:
>
> bool __weak arch__prefers_symtab(void) { return false; }
>
> +/* Concatinate two arrays */
> +static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
> +{
> + void *ret;
> +
> + ret = malloc(sz_a + sz_b);
> + if (ret) {
> + memcpy(ret, a, sz_a);
> + memcpy(ret + sz_a, b, sz_b);
> + }
> + return ret;
> +}
> +
> +static int
> +concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
> + struct probe_trace_event **tevs2, int ntevs2)
> +{
> + struct probe_trace_event *new_tevs;
> + int ret = 0;
> +
> + if (ntevs == 0) {
> + *tevs = *tevs2;
> + *ntevs = ntevs2;
> + *tevs2 = NULL;
> + return 0;
> + }
> +
> + if (*ntevs + ntevs2 > probe_conf.max_probes)
> + ret = -E2BIG;
> + else {
> + /* Concatinate the array of probe_trace_event */
> + new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
> + *tevs2, ntevs2 * sizeof(**tevs2));
> + if (!new_tevs)
> + ret = -ENOMEM;
> + else {
> + free(*tevs);
> + *tevs = new_tevs;
> + *ntevs += ntevs2;
> + }
> + }
> + if (ret < 0)
> + clear_probe_trace_events(*tevs2, ntevs2);
> + zfree(tevs2);
> +
> + return ret;
> +}
> +
> +/* Try to find probe_trace_event from given probe caches */
> +static int find_cached_events(struct perf_probe_event *pev,
> + struct probe_trace_event **tevs,
> + const char *target)
> +{
> + struct probe_cache *cache;
> + struct probe_cache_entry *entry;
> + struct probe_trace_event *tmp_tevs = NULL;
> + int ntevs = 0;
> + int ret = 0;
> +
> + cache = probe_cache__new(target);
> + if (!cache)
> + return -ENOENT;
> +
> + for_each_probe_cache_entry(entry, cache) {
> + /* Skip the cache entry which has no name */
> + if (!entry->pev.event || !entry->pev.group)
> + continue;
> + if ((!pev->group || strglobmatch(entry->pev.group, pev->group)) &&
> + strglobmatch(entry->pev.event, pev->event)) {
> + ret = probe_cache_entry__get_event(entry, &tmp_tevs);
> + if (ret > 0)
> + ret = concat_probe_trace_events(tevs, &ntevs,
> + &tmp_tevs, ret);
> + if (ret < 0)
> + break;
> + }
> + }
> + probe_cache__delete(cache);
> + if (ret < 0) {
> + clear_probe_trace_events(*tevs, ntevs);
> + zfree(tevs);
> + } else {
> + ret = ntevs;
> + if (target[0] == '/')
> + pev->uprobes = true;
> + }
> +
> + return ret;
> +}
> +
> +/* Try to find probe_trace_event from all probe caches */
> +static int find_cached_events_all(struct perf_probe_event *pev,
> + struct probe_trace_event **tevs)
> +{
> + struct probe_trace_event *tmp_tevs = NULL;
> + struct strlist *bidlist;
> + struct str_node *nd;
> + char *pathname;
> + int ntevs = 0;
> + int ret;
> +
> + /* Get the buildid list of all valid caches */
> + ret = build_id_cache__list_all(&bidlist, true);
> + if (ret < 0) {
> + pr_debug("Failed to get buildids: %d\n", ret);
> + return ret;
> + }
> +
> + ret = 0;
> + strlist__for_each(nd, bidlist) {
> + pathname = build_id_cache__origname(nd->s);
> + ret = find_cached_events(pev, &tmp_tevs, pathname);
> + if (ret > 0)
> + ret = concat_probe_trace_events(tevs, &ntevs,
> + &tmp_tevs, ret);
> + /* In the case of cnt == 0, we just skip it */
> + free(pathname);
> + if (ret < 0)
> + break;
> + }
> + strlist__delete(bidlist);
> +
> + if (ret < 0) {
> + clear_probe_trace_events(*tevs, ntevs);
> + zfree(tevs);
> + } else
> + ret = ntevs;
> +
> + return ret;
> +}
> +
> static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> struct probe_trace_event **tevs)
> {
> @@ -2869,6 +3005,13 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> struct str_node *node;
> int ret, i;
>
> + if (pev->sdt) {
> + /* For SDT/cached events, we use special search functions */
> + if (!pev->target)
> + return find_cached_events_all(pev, tevs);
> + else
> + return find_cached_events(pev, tevs, pev->target);
> + }
> cache = probe_cache__new(pev->target);
> if (!cache)
> return 0;
> diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
> index 2a23efe..39b5a35 100644
> --- a/tools/perf/util/probe-event.h
> +++ b/tools/perf/util/probe-event.h
> @@ -134,6 +134,7 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
> /* Release event contents */
> void clear_perf_probe_event(struct perf_probe_event *pev);
> void clear_probe_trace_event(struct probe_trace_event *tev);
> +void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs);
>
> /* Command string to line-range */
> int parse_line_range_desc(const char *cmd, struct line_range *lr);
> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> index 2437b48..896d645 100644
> --- a/tools/perf/util/probe-file.c
> +++ b/tools/perf/util/probe-file.c
> @@ -360,6 +360,31 @@ probe_cache_entry__new(struct perf_probe_event *pev)
> return ret;
> }
>
> +int probe_cache_entry__get_event(struct probe_cache_entry *entry,
> + struct probe_trace_event **tevs)
> +{
> + struct probe_trace_event *tev;
> + struct str_node *node;
> + int ret, i;
> +
> + ret = strlist__nr_entries(entry->tevlist);
> + if (ret > probe_conf.max_probes)
> + return -E2BIG;
> +
> + *tevs = zalloc(ret * sizeof(*tev));
> + if (!*tevs)
> + return -ENOMEM;
> +
> + i = 0;
> + strlist__for_each(node, entry->tevlist) {
> + tev = &(*tevs)[i++];
> + ret = parse_probe_trace_command(node->s, tev);
> + if (ret < 0)
> + break;
> + }
> + return i;
> +}
> +
> /* For the kernel probe caches, pass target = NULL */
> static int probe_cache__open(struct probe_cache *pcache, const char *target)
> {
> @@ -528,7 +553,7 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
> if (!cmd)
> return NULL;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> if (pev->sdt) {
> if (entry->pev.event &&
> streql(entry->pev.event, pev->event) &&
> @@ -558,7 +583,7 @@ probe_cache__find_by_name(struct probe_cache *pcache,
> {
> struct probe_cache_entry *entry = NULL;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> /* Hit if same event name or same command-string */
> if (streql(entry->pev.group, group) &&
> streql(entry->pev.event, event))
> @@ -711,7 +736,7 @@ int probe_cache__commit(struct probe_cache *pcache)
> if (ret < 0)
> goto out;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> ret = probe_cache_entry__write(entry, pcache->fd);
> pr_debug("Cache committed: %d\n", ret);
> if (ret < 0)
> @@ -750,7 +775,7 @@ static int probe_cache__show_entries(struct probe_cache *pcache,
> {
> struct probe_cache_entry *entry;
>
> - list_for_each_entry(entry, &pcache->list, list) {
> + for_each_probe_cache_entry(entry, pcache) {
> if (probe_cache_entry__compare(entry, filter))
> printf("%s\n", entry->spev);
> }
> diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
> index ce98162..0faf083 100644
> --- a/tools/perf/util/probe-file.h
> +++ b/tools/perf/util/probe-file.h
> @@ -21,6 +21,8 @@ struct probe_cache {
>
> #define PF_FL_UPROBE 1
> #define PF_FL_RW 2
> +#define for_each_probe_cache_entry(entry, pcache) \
> + list_for_each_entry(entry, &pcache->list, list)
>
> /* probe-file.c depends on libelf */
> #ifdef HAVE_LIBELF_SUPPORT
> @@ -34,6 +36,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
> struct strlist *plist);
> int probe_file__del_strlist(int fd, struct strlist *namelist);
>
> +int probe_cache_entry__get_event(struct probe_cache_entry *entry,
> + struct probe_trace_event **tevs);
> +
> struct probe_cache *probe_cache__new(const char *target);
> int probe_cache__add_entry(struct probe_cache *pcache,
> struct perf_probe_event *pev,
>

--
Thanks,
Hemant Kumar

2016-04-27 20:48:04

by Hemant Kumar

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 12/15] perf-list: Show SDT and pre-cached events



On 04/28/2016 12:08 AM, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> Show SDT and pre-cached events by perf-list with "sdt". This also
> shows the binary and build-id where the events are placed only
> when there are same name events on different binaries.
> e.g.
> ----
> # perf list sdt
>
> List of pre-defined events (to be used in -e):
>
> sdt_libc:lll_futex_wake [SDT event]
> sdt_libc:lll_lock_wait_private [SDT event]
> sdt_libc:longjmp [SDT event]
> sdt_libc:longjmp_target [SDT event]
> ...
> sdt_libstdcxx:rethrow@/usr/bin/gcc(0cc207fc4b27) [SDT event]
> sdt_libstdcxx:rethrow@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
> sdt_libstdcxx:throw@/usr/bin/gcc(0cc207fc4b27) [SDT event]
> sdt_libstdcxx:throw@/usr/lib64/libstdc++.so.6.0.20(91c7a88fdf49)
> ----
>
> The binary path and build-id are shown in below format;
>
> <GROUP>:<EVENT>@<PATH>(<BUILD-ID>)
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>

Acked-by: Hemant Kumar <[email protected]>

> ---
> Changes in v5:
> - Fix a build error for minimal option.
>
> Changes in v4:
> - Update patch description.
> - Change event list format.
> ---
> tools/perf/builtin-list.c | 4 ++
> tools/perf/util/parse-events.c | 83 ++++++++++++++++++++++++++++++++++++++++
> tools/perf/util/parse-events.h | 2 +
> tools/perf/util/probe-file.h | 9 ++++
> 4 files changed, 98 insertions(+)
>
> diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
> index 5e22db4..3cba865 100644
> --- a/tools/perf/builtin-list.c
> +++ b/tools/perf/builtin-list.c
> @@ -62,6 +62,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
> print_hwcache_events(NULL, raw_dump);
> else if (strcmp(argv[i], "pmu") == 0)
> print_pmu_events(NULL, raw_dump);
> + else if (strcmp(argv[i], "sdt") == 0)
> + print_sdt_events(NULL, NULL, raw_dump);
> else if ((sep = strchr(argv[i], ':')) != NULL) {
> int sep_idx;
>
> @@ -76,6 +78,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
>
> s[sep_idx] = '\0';
> print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
> + print_sdt_events(s, s + sep_idx + 1, raw_dump);
> free(s);
> } else {
> if (asprintf(&s, "*%s*", argv[i]) < 0) {
> @@ -89,6 +92,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
> print_hwcache_events(s, raw_dump);
> print_pmu_events(s, raw_dump);
> print_tracepoint_events(NULL, s, raw_dump);
> + print_sdt_events(NULL, s, raw_dump);
> free(s);
> }
> }
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index bcbc983..f9c8b7b 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -20,6 +20,7 @@
> #include "pmu.h"
> #include "thread_map.h"
> #include "cpumap.h"
> +#include "probe-file.h"
> #include "asm/bug.h"
>
> #define MAX_NAME_LEN 100
> @@ -1976,6 +1977,86 @@ static bool is_event_supported(u8 type, unsigned config)
> return ret;
> }
>
> +void print_sdt_events(const char *subsys_glob, const char *event_glob,
> + bool name_only)
> +{
> + struct probe_cache *pcache;
> + struct probe_cache_entry *ent;
> + struct strlist *bidlist, *sdtlist;
> + struct strlist_config cfg = {.dont_dupstr = true};
> + struct str_node *nd, *nd2;
> + char *buf, *path, *ptr = NULL;
> + bool show_detail = false;
> + int ret;
> +
> + sdtlist = strlist__new(NULL, &cfg);
> + if (!sdtlist) {
> + pr_debug("Failed to allocate new strlist for SDT\n");
> + return;
> + }
> + ret = build_id_cache__list_all(&bidlist);
> + if (ret < 0) {
> + pr_debug("Failed to get buildids: %d\n", ret);
> + return;
> + }
> + strlist__for_each(nd, bidlist) {
> + pcache = probe_cache__new(nd->s);
> + if (!pcache)
> + continue;
> + if (!list_empty(&pcache->list))
> + list_for_each_entry(ent, &pcache->list, list) {
> + if (!ent->sdt)
> + continue;
> + if (subsys_glob &&
> + !strglobmatch(ent->pev.group, subsys_glob))
> + continue;
> + if (event_glob &&
> + !strglobmatch(ent->pev.event, event_glob))
> + continue;
> + ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
> + ent->pev.event, nd->s);
> + if (ret > 0)
> + strlist__add(sdtlist, buf);
> + }
> + probe_cache__delete(pcache);
> + }
> + strlist__delete(bidlist);
> +
> + strlist__for_each(nd, sdtlist) {
> + buf = strchr(nd->s, '@');
> + if (buf)
> + *(buf++) = '\0';
> + if (name_only) {
> + printf("%s ", nd->s);
> + continue;
> + }
> + nd2 = strlist__next(nd);
> + if (nd2) {
> + ptr = strchr(nd2->s, '@');
> + if (ptr)
> + *ptr = '\0';
> + if (strcmp(nd->s, nd2->s) == 0)
> + show_detail = true;
> + }
> + if (show_detail) {
> + path = build_id_cache__origname(buf);
> + ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
> + if (ret > 0) {
> + printf(" %-50s [%s]\n", buf, "SDT event");
> + free(buf);
> + }
> + } else
> + printf(" %-50s [%s]\n", nd->s, "SDT event");
> + if (nd2) {
> + if (strcmp(nd->s, nd2->s) != 0)
> + show_detail = false;
> + if (ptr)
> + *ptr = '@';
> + }
> + }
> + strlist__delete(sdtlist);
> +}
> +
> int print_hwcache_events(const char *event_glob, bool name_only)
> {
> unsigned int type, op, i, evt_i = 0, evt_num = 0;
> @@ -2158,6 +2239,8 @@ void print_events(const char *event_glob, bool name_only)
> }
>
> print_tracepoint_events(NULL, NULL, name_only);
> +
> + print_sdt_events(NULL, NULL, name_only);
> }
>
> int parse_events__is_hardcoded_term(struct parse_events_term *term)
> diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
> index d740c3c..c08daa9 100644
> --- a/tools/perf/util/parse-events.h
> +++ b/tools/perf/util/parse-events.h
> @@ -182,6 +182,8 @@ void print_symbol_events(const char *event_glob, unsigned type,
> void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
> bool name_only);
> int print_hwcache_events(const char *event_glob, bool name_only);
> +void print_sdt_events(const char *subsys_glob, const char *event_glob,
> + bool name_only);
> int is_valid_tracepoint(const char *event_string);
>
> int valid_event_mount(const char *eventfs);
> diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
> index 93aa193..ce98162 100644
> --- a/tools/perf/util/probe-file.h
> +++ b/tools/perf/util/probe-file.h
> @@ -22,6 +22,8 @@ struct probe_cache {
> #define PF_FL_UPROBE 1
> #define PF_FL_RW 2
>
> +/* probe-file.c depends on libelf */
> +#ifdef HAVE_LIBELF_SUPPORT
> int probe_file__open(int flag);
> int probe_file__open_both(int *kfd, int *ufd, int flag);
> struct strlist *probe_file__get_namelist(int fd);
> @@ -46,4 +48,11 @@ struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
> struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
> const char *group, const char *event);
> int probe_cache__show_all_caches(struct strfilter *filter);
> +#else /* ! HAVE_LIBELF_SUPPORT */
> +static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
> +{
> + return NULL;
> +}
> +#define probe_cache__delete(pcache) do {} while(0)
> +#endif
> #endif
>

--
Thanks,
Hemant Kumar

2016-04-27 20:51:34

by Hemant Kumar

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 11/15] perf probe: Accept %sdt and %cached event name



On 04/28/2016 12:08 AM, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> To improbe usability, support %[PROVIDER:]SDTEVENT format to
> add new probes on SDT and cached events.
>
> e.g.
> ----
> # perf probe -x /lib/libc-2.17.so %lll_lock_wait_private
> Added new event:
> sdt_libc:lll_lock_wait_private (on %lll_lock_wait_private in
> /usr/lib/libc-2.17.so)
>
> You can now use it in all perf tools, such as:
>
> perf record -e sdt_libc:lll_lock_wait_private -aR sleep 1
>
> # perf probe -l | more
> sdt_libc:lll_lock_wait_private (on __lll_lock_wait_private+21
> in /usr/lib/libc-2.17.so)
> ----
>
> Note that this is not only for SDT events, but also normal
> events with event-name.
>
> e.g. define "myevent" on cache (-n doesn't add the real probe)
> ----
> # perf probe -x ./perf --cache -n --add 'myevent=dso__load $params'
> ----
> Reuse the "myevent" from cache as below.
> ----
> # perf probe -x ./perf %myevent
> ----
>
> TODO:
> Wildcard is not supported yet.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>

Acked-by: Hemant Kumar <[email protected]>

> ---
> tools/perf/Documentation/perf-probe.txt | 3 +
> tools/perf/util/probe-event.c | 78 ++++++++++++++++++++++---------
> tools/perf/util/probe-event.h | 1
> tools/perf/util/probe-file.c | 9 ++++
> 4 files changed, 69 insertions(+), 22 deletions(-)
>
> diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
> index 7a258e9..43523be 100644
> --- a/tools/perf/Documentation/perf-probe.txt
> +++ b/tools/perf/Documentation/perf-probe.txt
> @@ -151,6 +151,8 @@ Probe points are defined by following syntax.
> 3) Define event based on source file with lazy pattern
> [[GROUP:]EVENT=]SRC;PTN [ARG ...]
>
> + 4) Pre-defined SDT events
> + %[PROVIDER:]SDTEVENT
>
> 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
> Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
> @@ -158,6 +160,7 @@ modules.
> 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function.
> It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
> 'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
> +'SDTEVENT' and 'PROVIDER' is the pre-defined event name which is defined by user SDT (Statically Defined Tracing) or the pre-cached probes with event name.
>
> PROBE ARGUMENT
> --------------
> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
> index b2c6a4a..1a9ea2b 100644
> --- a/tools/perf/util/probe-event.c
> +++ b/tools/perf/util/probe-event.c
> @@ -1199,6 +1199,34 @@ err:
> return err;
> }
>
> +static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> +{
> + char *ptr;
> +
> + ptr = strchr(*arg, ':');
> + if (ptr) {
> + *ptr = '\0';
> + if (!is_c_func_name(*arg))
> + goto ng_name;
> + pev->group = strdup(*arg);
> + if (!pev->group)
> + return -ENOMEM;
> + *arg = ptr + 1;
> + } else
> + pev->group = NULL;
> + if (!is_c_func_name(*arg)) {
> +ng_name:
> + semantic_error("%s is bad for event name -it must "
> + "follow C symbol-naming rule.\n", *arg);
> + return -EINVAL;
> + }
> + pev->event = strdup(*arg);
> + if (pev->event == NULL)
> + return -ENOMEM;
> +
> + return 0;
> +}
> +
> /* Parse probepoint definition. */
> static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
> {
> @@ -1206,38 +1234,43 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
> char *ptr, *tmp;
> char c, nc = 0;
> bool file_spec = false;
> + int ret;
> +
> /*
> * <Syntax>
> * perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
> * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
> + * perf probe %[GRP:]SDT_EVENT
> */
> if (!arg)
> return -EINVAL;
>
> + if (arg[0] == '%') {
> + pev->sdt = true;
> + arg++;
> + }
> +
> ptr = strpbrk(arg, ";=@+%");
> - if (ptr && *ptr == '=') { /* Event name */
> - *ptr = '\0';
> - tmp = ptr + 1;
> - ptr = strchr(arg, ':');
> + if (pev->sdt) {
> if (ptr) {
> - *ptr = '\0';
> - if (!is_c_func_name(arg))
> - goto not_fname;
> - pev->group = strdup(arg);
> - if (!pev->group)
> - return -ENOMEM;
> - arg = ptr + 1;
> - } else
> - pev->group = NULL;
> - if (!is_c_func_name(arg)) {
> -not_fname:
> - semantic_error("%s is bad for event name -it must "
> - "follow C symbol-naming rule.\n", arg);
> + semantic_error("%s must contain only an SDT event name.\n", arg);
> return -EINVAL;
> }
> - pev->event = strdup(arg);
> - if (pev->event == NULL)
> - return -ENOMEM;
> + ret = parse_perf_probe_event_name(&arg, pev);
> + if (ret == 0) {
> + if (asprintf(&pev->point.function, "%%%s", pev->event) < 0)
> + ret = -errno;
> + }
> + return ret;
> + }
> +
> + if (ptr && *ptr == '=') { /* Event name */
> + *ptr = '\0';
> + tmp = ptr + 1;
> + ret = parse_perf_probe_event_name(&arg, pev);
> + if (ret < 0)
> + return ret;
> +
> arg = tmp;
> }
>
> @@ -2849,7 +2882,8 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> pev->point.function);
> }
> if (!entry) {
> - ret = 0;
> + /* SDT must be in the cache */
> + ret = pev->sdt ? -ENOENT : 0;
> goto out;
> }
>
> @@ -2888,7 +2922,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
> {
> int ret;
>
> - if (!pev->group) {
> + if (!pev->group && !pev->sdt) {
> /* Set group name if not given */
> if (!pev->uprobes) {
> pev->group = strdup(PERFPROBE_GROUP);
> diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
> index c451223..2a23efe 100644
> --- a/tools/perf/util/probe-event.h
> +++ b/tools/perf/util/probe-event.h
> @@ -85,6 +85,7 @@ struct perf_probe_event {
> char *group; /* Group name */
> struct perf_probe_point point; /* Probe point */
> int nargs; /* Number of arguments */
> + bool sdt; /* SDT/cached event flag */
> bool uprobes; /* Uprobe event flag */
> char *target; /* Target binary */
> struct perf_probe_arg *args; /* Arguments */
> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> index c10a647..ee560dd 100644
> --- a/tools/perf/util/probe-file.c
> +++ b/tools/perf/util/probe-file.c
> @@ -529,6 +529,15 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
> return NULL;
>
> list_for_each_entry(entry, &pcache->list, list) {
> + if (pev->sdt) {
> + if (entry->pev.event &&
> + streql(entry->pev.event, pev->event) &&
> + (!pev->group ||
> + streql(entry->pev.group, pev->group)))
> + goto found;
> +
> + continue;
> + }
> /* Hit if same event name or same command-string */
> if ((pev->event &&
> (streql(entry->pev.group, pev->group) &&
>

--
Thanks,
Hemant Kumar

2016-04-27 21:12:38

by Arnaldo Carvalho de Melo

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

Em Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu escreveu:
> From: Masami Hiramatsu <[email protected]>
>
> Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> to store corresponding elf binary.
> This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
>
> Note that the existing caches are not updated until user adds
> or updates the cache. Anyway, if there is the old style build-id
> cache it falls back to use it. (IOW, it is backward compatible)

I reworded this to:

"If there is old style build-id cache content, i.e. links to
path/to/bin/buildid/aa/bbccdd, it will still be accessible, IOW, this is
backard compatible."

This part "existing caches are not updated until the user updates de
cache" sounds confusing.

Anyway, applied.

- Arnaldo

2016-04-27 21:23:57

by Arnaldo Carvalho de Melo

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

Em Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu escreveu:
> From: Masami Hiramatsu <[email protected]>
>
> Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> to store corresponding elf binary.
> This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
>
> Note that the existing caches are not updated until user adds
> or updates the cache. Anyway, if there is the old style build-id
> cache it falls back to use it. (IOW, it is backward compatible)
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v5:
> - Support old style buildid caches.

> + /* Remove old style build-id cache */
> + if (__is_regular_file(dir_name))
> + if (unlink(dir_name))
> + goto out_free;

Shouldn't this just fail and require the user to use --force/-f or purge
first?

- Arnaldo

> if (mkdir_p(dir_name, 0755))
> goto out_free;
>
> - if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
> + /* Save the allocated buildid dirname */
> + if (asprintf(&filename, "%s/%s", dir_name,
> + build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
> filename = NULL;
> goto out_free;
> }
> @@ -437,7 +479,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
> }
>
> - if (!build_id__filename(sbuild_id, linkname, size))
> + if (!build_id_cache__linkname(sbuild_id, linkname, size))
> goto out_free;
> tmp = strrchr(linkname, '/');
> *tmp = '\0';
> @@ -446,10 +488,10 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
>
> *tmp = '/';
> - targetname = filename + strlen(buildid_dir) - 5;
> - memcpy(targetname, "../..", 5);
> + tmp = dir_name + strlen(buildid_dir) - 5;
> + memcpy(tmp, "../..", 5);
>
> - if (symlink(targetname, linkname) == 0)
> + if (symlink(tmp, linkname) == 0)
> err = 0;
> out_free:
> if (!is_kallsyms)
> @@ -474,7 +516,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
> bool build_id_cache__cached(const char *sbuild_id)
> {
> bool ret = false;
> - char *filename = build_id__filename(sbuild_id, NULL, 0);
> + char *filename = build_id_cache__linkname(sbuild_id, NULL, 0);
>
> if (filename && !access(filename, F_OK))
> ret = true;
> @@ -493,7 +535,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
> if (filename == NULL || linkname == NULL)
> goto out_free;
>
> - if (!build_id__filename(sbuild_id, linkname, size))
> + if (!build_id_cache__linkname(sbuild_id, linkname, size))
> goto out_free;
>
> if (access(linkname, F_OK))
> @@ -511,7 +553,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
> tmp = strrchr(linkname, '/') + 1;
> snprintf(tmp, size - (tmp - linkname), "%s", filename);
>
> - if (unlink(linkname))
> + if (rm_rf(linkname))
> goto out_free;
>
> err = 0;
> @@ -523,7 +565,7 @@ out_free:
>
> static int dso__cache_build_id(struct dso *dso, struct machine *machine)
> {
> - bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
> + bool is_kallsyms = dso__is_kallsyms(dso);
> bool is_vdso = dso__is_vdso(dso);
> const char *name = dso->long_name;
> char nm[PATH_MAX];
> diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
> index 0953280..76d79d0 100644
> --- a/tools/perf/util/dso.h
> +++ b/tools/perf/util/dso.h
> @@ -349,6 +349,11 @@ static inline bool dso__is_kcore(struct dso *dso)
> dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
> }
>
> +static inline bool dso__is_kallsyms(struct dso *dso)
> +{
> + return dso->kernel && dso->long_name[0] != '/';
> +}
> +
> void dso__free_a2l(struct dso *dso);
>
> enum dso_type dso__type(struct dso *dso, struct machine *machine);
> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> index 415c4f6..9463c7d 100644
> --- a/tools/perf/util/symbol.c
> +++ b/tools/perf/util/symbol.c
> @@ -1685,13 +1685,18 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
> if (!find_matching_kcore(map, path, sizeof(path)))
> return strdup(path);
>
> - scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
> + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s/kallsyms",
> buildid_dir, sbuild_id);
> -
> + /* Try old style kallsyms cache */
> if (access(path, F_OK)) {
> - pr_err("No kallsyms or vmlinux with build-id %s was found\n",
> - sbuild_id);
> - return NULL;
> + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
> + buildid_dir, sbuild_id);
> +
> + if (access(path, F_OK)) {
> + pr_err("No kallsyms or vmlinux with build-id %s was found\n",
> + sbuild_id);
> + return NULL;
> + }
> }
>
> return strdup(path);

2016-04-28 01:22:30

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

Hi Masami,

On Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> to store corresponding elf binary.
> This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
>
> Note that the existing caches are not updated until user adds
> or updates the cache. Anyway, if there is the old style build-id
> cache it falls back to use it. (IOW, it is backward compatible)
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v5:
> - Support old style buildid caches.
> ---
> tools/perf/util/build-id.c | 80 ++++++++++++++++++++++++++++++++++----------
> tools/perf/util/dso.h | 5 +++
> tools/perf/util/symbol.c | 15 ++++++--
> 3 files changed, 76 insertions(+), 24 deletions(-)
>
> diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
> index b6ecf87..b035483 100644
> --- a/tools/perf/util/build-id.c
> +++ b/tools/perf/util/build-id.c
> @@ -144,7 +144,8 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
> return ret;
> }
>
> -static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
> +static char *build_id_cache__linkname(const char *sbuild_id, char *bf,
> + size_t size)
> {
> char *tmp = bf;
> int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
> @@ -154,15 +155,45 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
> return bf;
> }
>
> +static bool __is_regular_file(const char *pathname)
> +{
> + struct stat sb;
> + return stat(pathname, &sb) == 0 && S_ISREG(sb.st_mode);
> +}

It looks like that the is_regular_file() is already in the
util/util.c

Thanks,
Namhyung


> +
> +static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
> +{
> + return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
> +}
> +
> char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
> {
> - char build_id_hex[SBUILD_ID_SIZE];
> + bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
> + bool is_vdso = dso__is_vdso((struct dso *)dso);
> + char sbuild_id[SBUILD_ID_SIZE];
> + char *linkname;
> + bool alloc = (bf == NULL);
> + int ret;
>
> if (!dso->has_build_id)
> return NULL;
>
> - build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
> - return build_id__filename(build_id_hex, bf, size);
> + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
> + linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
> + if (!linkname)
> + return NULL;
> +
> + /* Check if old style build_id cache */
> + if (__is_regular_file(linkname))
> + ret = asnprintf(&bf, size, "%s", linkname);
> + else
> + ret = asnprintf(&bf, size, "%s/%s", linkname,
> + build_id_cache__basename(is_kallsyms, is_vdso));
> + if (ret < 0 || (!alloc && size < (unsigned int)ret))
> + bf = NULL;
> + free(linkname);
> +
> + return bf;
> }
>
> bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
> @@ -341,7 +372,8 @@ void disable_buildid_cache(void)
> }
>
> static char *build_id_cache__dirname_from_path(const char *name,
> - bool is_kallsyms, bool is_vdso)
> + bool is_kallsyms, bool is_vdso,
> + const char *sbuild_id)
> {
> char *realname = (char *)name, *filename;
> bool slash = is_kallsyms || is_vdso;
> @@ -352,8 +384,9 @@ static char *build_id_cache__dirname_from_path(const char *name,
> return NULL;
> }
>
> - if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "",
> - is_vdso ? DSO__NAME_VDSO : realname) < 0)
> + if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "",
> + is_vdso ? DSO__NAME_VDSO : realname,
> + sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
> filename = NULL;
>
> if (!slash)
> @@ -372,7 +405,8 @@ int build_id_cache__list_build_ids(const char *pathname,
> int ret = 0;
>
> list = strlist__new(NULL, NULL);
> - dir_name = build_id_cache__dirname_from_path(pathname, false, false);
> + dir_name = build_id_cache__dirname_from_path(pathname, false, false,
> + NULL);
> if (!list || !dir_name) {
> ret = -ENOMEM;
> goto out;
> @@ -407,7 +441,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> {
> const size_t size = PATH_MAX;
> char *realname = NULL, *filename = NULL, *dir_name = NULL,
> - *linkname = zalloc(size), *targetname, *tmp;
> + *linkname = zalloc(size), *tmp;
> int err = -1;
>
> if (!is_kallsyms) {
> @@ -416,14 +450,22 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
> }
>
> - dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso);
> + dir_name = build_id_cache__dirname_from_path(name, is_kallsyms,
> + is_vdso, sbuild_id);
> if (!dir_name)
> goto out_free;
>
> + /* Remove old style build-id cache */
> + if (__is_regular_file(dir_name))
> + if (unlink(dir_name))
> + goto out_free;
> +
> if (mkdir_p(dir_name, 0755))
> goto out_free;
>
> - if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
> + /* Save the allocated buildid dirname */
> + if (asprintf(&filename, "%s/%s", dir_name,
> + build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
> filename = NULL;
> goto out_free;
> }
> @@ -437,7 +479,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
> }
>
> - if (!build_id__filename(sbuild_id, linkname, size))
> + if (!build_id_cache__linkname(sbuild_id, linkname, size))
> goto out_free;
> tmp = strrchr(linkname, '/');
> *tmp = '\0';
> @@ -446,10 +488,10 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
> goto out_free;
>
> *tmp = '/';
> - targetname = filename + strlen(buildid_dir) - 5;
> - memcpy(targetname, "../..", 5);
> + tmp = dir_name + strlen(buildid_dir) - 5;
> + memcpy(tmp, "../..", 5);
>
> - if (symlink(targetname, linkname) == 0)
> + if (symlink(tmp, linkname) == 0)
> err = 0;
> out_free:
> if (!is_kallsyms)
> @@ -474,7 +516,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
> bool build_id_cache__cached(const char *sbuild_id)
> {
> bool ret = false;
> - char *filename = build_id__filename(sbuild_id, NULL, 0);
> + char *filename = build_id_cache__linkname(sbuild_id, NULL, 0);
>
> if (filename && !access(filename, F_OK))
> ret = true;
> @@ -493,7 +535,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
> if (filename == NULL || linkname == NULL)
> goto out_free;
>
> - if (!build_id__filename(sbuild_id, linkname, size))
> + if (!build_id_cache__linkname(sbuild_id, linkname, size))
> goto out_free;
>
> if (access(linkname, F_OK))
> @@ -511,7 +553,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
> tmp = strrchr(linkname, '/') + 1;
> snprintf(tmp, size - (tmp - linkname), "%s", filename);
>
> - if (unlink(linkname))
> + if (rm_rf(linkname))
> goto out_free;
>
> err = 0;
> @@ -523,7 +565,7 @@ out_free:
>
> static int dso__cache_build_id(struct dso *dso, struct machine *machine)
> {
> - bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
> + bool is_kallsyms = dso__is_kallsyms(dso);
> bool is_vdso = dso__is_vdso(dso);
> const char *name = dso->long_name;
> char nm[PATH_MAX];
> diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
> index 0953280..76d79d0 100644
> --- a/tools/perf/util/dso.h
> +++ b/tools/perf/util/dso.h
> @@ -349,6 +349,11 @@ static inline bool dso__is_kcore(struct dso *dso)
> dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
> }
>
> +static inline bool dso__is_kallsyms(struct dso *dso)
> +{
> + return dso->kernel && dso->long_name[0] != '/';
> +}
> +
> void dso__free_a2l(struct dso *dso);
>
> enum dso_type dso__type(struct dso *dso, struct machine *machine);
> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> index 415c4f6..9463c7d 100644
> --- a/tools/perf/util/symbol.c
> +++ b/tools/perf/util/symbol.c
> @@ -1685,13 +1685,18 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
> if (!find_matching_kcore(map, path, sizeof(path)))
> return strdup(path);
>
> - scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
> + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s/kallsyms",
> buildid_dir, sbuild_id);
> -
> + /* Try old style kallsyms cache */
> if (access(path, F_OK)) {
> - pr_err("No kallsyms or vmlinux with build-id %s was found\n",
> - sbuild_id);
> - return NULL;
> + scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
> + buildid_dir, sbuild_id);
> +
> + if (access(path, F_OK)) {
> + pr_err("No kallsyms or vmlinux with build-id %s was found\n",
> + sbuild_id);
> + return NULL;
> + }
> }
>
> return strdup(path);
>

2016-04-28 01:51:56

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

On Wed, 27 Apr 2016 18:23:50 -0300
Arnaldo Carvalho de Melo <[email protected]> wrote:

> Em Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu escreveu:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> > to store corresponding elf binary.
> > This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
> >
> > Note that the existing caches are not updated until user adds
> > or updates the cache. Anyway, if there is the old style build-id
> > cache it falls back to use it. (IOW, it is backward compatible)
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
> > Changes in v5:
> > - Support old style buildid caches.
>
> > + /* Remove old style build-id cache */
> > + if (__is_regular_file(dir_name))
> > + if (unlink(dir_name))
> > + goto out_free;
>
> Shouldn't this just fail and require the user to use --force/-f or purge
> first?

No, I don't think so, because the old style build-id is useless for
probe-cache in anyway, and after applying this patch, perf can use
new one seemlessly. So let just renew it :)

Thank you,

--
Masami Hiramatsu <[email protected]>

2016-04-28 01:52:56

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

On Wed, 27 Apr 2016 18:12:32 -0300
Arnaldo Carvalho de Melo <[email protected]> wrote:

> Em Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu escreveu:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> > to store corresponding elf binary.
> > This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
> >
> > Note that the existing caches are not updated until user adds
> > or updates the cache. Anyway, if there is the old style build-id
> > cache it falls back to use it. (IOW, it is backward compatible)
>
> I reworded this to:
>
> "If there is old style build-id cache content, i.e. links to
> path/to/bin/buildid/aa/bbccdd, it will still be accessible, IOW, this is
> backard compatible."
>
> This part "existing caches are not updated until the user updates de
> cache" sounds confusing.

Ah, I see. Thank you!

>
> Anyway, applied.
>
> - Arnaldo


--
Masami Hiramatsu <[email protected]>

2016-04-28 02:12:43

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 04/15] perf probe: Add --cache option to cache the probe definitions

On Thu, Apr 28, 2016 at 03:37:42AM +0900, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> Add --cache option to cache the probe definitions. This
> just saves the result of the dwarf analysis to probe cache.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v5:
> - Move probe_cache* definitions. (code cleanup)
>
> Changes in v4:
> - Remove cache saving failure message.
> ---

[snip]
> +static int probe_cache__load(struct probe_cache *pcache)
> +{
> + struct probe_cache_entry *entry = NULL;
> + char buf[MAX_CMDLEN], *p;
> + int ret = 0;
> + FILE *fp;
> +
> + fp = fdopen(dup(pcache->fd), "r");
> + while (!feof(fp)) {
> + if (!fgets(buf, MAX_CMDLEN, fp))
> + break;
> + p = strchr(buf, '\n');
> + if (p)
> + *p = '\0';
> + if (buf[0] == '#') { /* #perf_probe_event */
> + entry = probe_cache_entry__new(NULL);

The probe_cache_entry__new() can fail.

Thanks,
Namhyung


> + entry->spev = strdup(buf + 1);
> + ret = parse_perf_probe_command(buf + 1, &entry->pev);
> + if (!entry->spev || ret < 0) {
> + probe_cache_entry__delete(entry);
> + goto out;
> + }
> + list_add_tail(&entry->list, &pcache->list);
> + } else { /* trace_probe_event */
> + if (!entry) {
> + ret = -EINVAL;
> + goto out;
> + }
> + strlist__add(entry->tevlist, buf);
> + }
> + }
> +out:
> + fclose(fp);
> + return ret;
> +}

2016-04-28 02:32:23

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 04/15] perf probe: Add --cache option to cache the probe definitions

On Thu, Apr 28, 2016 at 03:37:42AM +0900, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> Add --cache option to cache the probe definitions. This
> just saves the result of the dwarf analysis to probe cache.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> Changes in v5:
> - Move probe_cache* definitions. (code cleanup)
>
> Changes in v4:
> - Remove cache saving failure message.
> ---

[SNIP]
> +/* For the kernel probe caches, pass target = NULL */
> +static int probe_cache__open(struct probe_cache *pcache, const char *target)
> +{
> + char cpath[PATH_MAX];
> + char sbuildid[SBUILD_ID_SIZE];
> + char *dir_name;
> + bool is_kallsyms = !target;
> + int ret, fd;
> +
> + if (target)
> + ret = filename__sprintf_build_id(target, sbuildid);
> + else {
> + target = "[kernel.kallsyms]";
> + ret = sysfs__sprintf_build_id("/", sbuildid);
> + }
> + if (ret < 0) {
> + pr_debug("Failed to get build-id from %s.\n", target ?: "kernel");
> + return ret;
> + }
> +
> + /* If we have no buildid cache, make it */
> + if (!build_id_cache__cached(sbuildid)) {
> + ret = build_id_cache__add_s(sbuildid, target,
> + is_kallsyms, NULL);
> + if (ret < 0) {
> + pr_debug("Failed to add build-id cache: %s\n", target);
> + return ret;
> + }
> + }
> +
> + dir_name = build_id_cache__dirname_from_path(sbuildid, target,
> + is_kallsyms, false);
> + if (!dir_name)
> + return -ENOMEM;
> +
> + snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
> + fd = open(cpath, O_CREAT | O_RDWR | O_APPEND, 0644);
> + if (fd < 0)
> + pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
> + free(dir_name);
> + pcache->fd = fd;
> +
> + return fd;
> +}

[SNIP]
> +
> +int probe_cache__commit(struct probe_cache *pcache)
> +{
> + struct probe_cache_entry *entry;
> + int ret = 0;
> +
> + /* TBD: if we do not update existing entries, skip it */
> + ret = lseek(pcache->fd, 0, SEEK_SET);
> + if (ret < 0)
> + goto out;
> +
> + ret = ftruncate(pcache->fd, 0);
> + if (ret < 0)
> + goto out;

What is this doing? Does it truncate old contents on write? Opening
with O_APPEND looks strange to me..

Thanks,
Namhyung


> +
> + list_for_each_entry(entry, &pcache->list, list) {
> + ret = probe_cache_entry__write(entry, pcache->fd);
> + pr_debug("Cache committed: %d\n", ret);
> + if (ret < 0)
> + break;
> + }
> +out:
> + return ret;
> +}
> diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
> index 18ac9cf..d2b8791d 100644
> --- a/tools/perf/util/probe-file.h
> +++ b/tools/perf/util/probe-file.h
> @@ -5,6 +5,19 @@
> #include "strfilter.h"
> #include "probe-event.h"
>
> +/* Cache of probe definitions */
> +struct probe_cache_entry {
> + struct list_head list;
> + struct perf_probe_event pev;
> + char *spev;
> + struct strlist *tevlist;
> +};
> +
> +struct probe_cache {
> + int fd;
> + struct list_head list;
> +};
> +
> #define PF_FL_UPROBE 1
> #define PF_FL_RW 2
>
> @@ -18,5 +31,11 @@ int probe_file__get_events(int fd, struct strfilter *filter,
> struct strlist *plist);
> int probe_file__del_strlist(int fd, struct strlist *namelist);
>
> +struct probe_cache *probe_cache__new(const char *target);
> +int probe_cache__add_entry(struct probe_cache *pcache,
> + struct perf_probe_event *pev,
> + struct probe_trace_event *tevs, int ntevs);
> +int probe_cache__commit(struct probe_cache *pcache);
> +void probe_cache__delete(struct probe_cache *pcache);
>
> #endif
>

2016-04-28 02:48:05

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 05/15] perf probe: Use cache entry if possible

On Thu, Apr 28, 2016 at 03:37:52AM +0900, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> Before analyzing debuginfo, try to find a corresponding entry
> from probe cache always. This does not depend on --cache,
> the --cache enables to store/update cache, but looking up
> the cache is always enabled.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---

[SNIP]
> +static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> + struct probe_trace_event **tevs)
> +{
> + struct probe_cache *cache;
> + struct probe_cache_entry *entry;
> + struct probe_trace_event *tev;
> + struct str_node *node;
> + int ret, i;
> +
> + cache = probe_cache__new(pev->target);
> + if (!cache)
> + return 0;
> +
> + entry = probe_cache__find(cache, pev);
> +
> + if (!entry && !pev->event &&
> + (!pev->point.file && pev->point.function && !pev->point.retprobe &&
> + !pev->point.line && !pev->point.offset && !pev->point.lazy_line)) {
> + entry = probe_cache__find_by_name(cache, pev->group,
> + pev->point.function);
> + }

What about arguments? It seems that it only checks group and event
names of the given pev and use the cached entry's tev if found. What
if they have different argument spec?

Thanks,
Namhyung


> + if (!entry) {
> + ret = 0;
> + goto out;
> + }
> +
> + ret = strlist__nr_entries(entry->tevlist);
> + if (ret > probe_conf.max_probes) {
> + pr_debug("Too many entries matched in the cache of %s\n",
> + pev->target ? : "kernel");
> + ret = -E2BIG;
> + goto out;
> + }
> +
> + *tevs = zalloc(ret * sizeof(*tev));
> + if (!*tevs) {
> + ret = -ENOMEM;
> + goto out;
> + }
> +
> + i = 0;
> + strlist__for_each(node, entry->tevlist) {
> + tev = &(*tevs)[i++];
> + ret = parse_probe_trace_command(node->s, tev);
> + if (ret < 0)
> + goto out;
> + /* Set the uprobes attribute as same as original */
> + tev->uprobes = pev->uprobes;
> + }
> + ret = i;
> +
> +out:
> + probe_cache__delete(cache);
> + return ret;
> +}

2016-04-28 05:26:23

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 11/15] perf probe: Accept %sdt and %cached event name

On Thu, Apr 28, 2016 at 03:38:49AM +0900, Masami Hiramatsu wrote:
> From: Masami Hiramatsu <[email protected]>
>
> To improbe usability, support %[PROVIDER:]SDTEVENT format to
> add new probes on SDT and cached events.
>
> e.g.
> ----
> # perf probe -x /lib/libc-2.17.so %lll_lock_wait_private
> Added new event:
> sdt_libc:lll_lock_wait_private (on %lll_lock_wait_private in
> /usr/lib/libc-2.17.so)
>
> You can now use it in all perf tools, such as:
>
> perf record -e sdt_libc:lll_lock_wait_private -aR sleep 1
>
> # perf probe -l | more
> sdt_libc:lll_lock_wait_private (on __lll_lock_wait_private+21
> in /usr/lib/libc-2.17.so)
> ----
>
> Note that this is not only for SDT events, but also normal
> events with event-name.
>
> e.g. define "myevent" on cache (-n doesn't add the real probe)
> ----
> # perf probe -x ./perf --cache -n --add 'myevent=dso__load $params'
> ----
> Reuse the "myevent" from cache as below.
> ----
> # perf probe -x ./perf %myevent
> ----
>
> TODO:
> Wildcard is not supported yet.
>
> Signed-off-by: Masami Hiramatsu <[email protected]>
> ---
> tools/perf/Documentation/perf-probe.txt | 3 +
> tools/perf/util/probe-event.c | 78 ++++++++++++++++++++++---------
> tools/perf/util/probe-event.h | 1
> tools/perf/util/probe-file.c | 9 ++++
> 4 files changed, 69 insertions(+), 22 deletions(-)
>
> diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
> index 7a258e9..43523be 100644
> --- a/tools/perf/Documentation/perf-probe.txt
> +++ b/tools/perf/Documentation/perf-probe.txt
> @@ -151,6 +151,8 @@ Probe points are defined by following syntax.
> 3) Define event based on source file with lazy pattern
> [[GROUP:]EVENT=]SRC;PTN [ARG ...]
>
> + 4) Pre-defined SDT events
> + %[PROVIDER:]SDTEVENT

How about changing it to:

4) Pre-defined (SDT) or cached events
%EVENTNAME

?

Btw, is it possible to use group name here? The SDT will use
sdt_<libname> for group name and <provider>_<event> for event name,
right? So is it for cached events and does it support defining group
name when added like below?

# perf probe -x ./perf --cache --add 'mygroup:myevent=main'


Thanks,
Namhyung



>
> 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
> Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
> @@ -158,6 +160,7 @@ modules.
> 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function.
> It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
> 'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
> +'SDTEVENT' and 'PROVIDER' is the pre-defined event name which is defined by user SDT (Statically Defined Tracing) or the pre-cached probes with event name.
>
> PROBE ARGUMENT
> --------------
> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
> index b2c6a4a..1a9ea2b 100644
> --- a/tools/perf/util/probe-event.c
> +++ b/tools/perf/util/probe-event.c
> @@ -1199,6 +1199,34 @@ err:
> return err;
> }
>
> +static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
> +{
> + char *ptr;
> +
> + ptr = strchr(*arg, ':');
> + if (ptr) {
> + *ptr = '\0';
> + if (!is_c_func_name(*arg))
> + goto ng_name;
> + pev->group = strdup(*arg);
> + if (!pev->group)
> + return -ENOMEM;
> + *arg = ptr + 1;
> + } else
> + pev->group = NULL;
> + if (!is_c_func_name(*arg)) {
> +ng_name:
> + semantic_error("%s is bad for event name -it must "
> + "follow C symbol-naming rule.\n", *arg);
> + return -EINVAL;
> + }
> + pev->event = strdup(*arg);
> + if (pev->event == NULL)
> + return -ENOMEM;
> +
> + return 0;
> +}
> +
> /* Parse probepoint definition. */
> static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
> {
> @@ -1206,38 +1234,43 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
> char *ptr, *tmp;
> char c, nc = 0;
> bool file_spec = false;
> + int ret;
> +
> /*
> * <Syntax>
> * perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
> * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
> + * perf probe %[GRP:]SDT_EVENT
> */
> if (!arg)
> return -EINVAL;
>
> + if (arg[0] == '%') {
> + pev->sdt = true;
> + arg++;
> + }
> +
> ptr = strpbrk(arg, ";=@+%");
> - if (ptr && *ptr == '=') { /* Event name */
> - *ptr = '\0';
> - tmp = ptr + 1;
> - ptr = strchr(arg, ':');
> + if (pev->sdt) {
> if (ptr) {
> - *ptr = '\0';
> - if (!is_c_func_name(arg))
> - goto not_fname;
> - pev->group = strdup(arg);
> - if (!pev->group)
> - return -ENOMEM;
> - arg = ptr + 1;
> - } else
> - pev->group = NULL;
> - if (!is_c_func_name(arg)) {
> -not_fname:
> - semantic_error("%s is bad for event name -it must "
> - "follow C symbol-naming rule.\n", arg);
> + semantic_error("%s must contain only an SDT event name.\n", arg);
> return -EINVAL;
> }
> - pev->event = strdup(arg);
> - if (pev->event == NULL)
> - return -ENOMEM;
> + ret = parse_perf_probe_event_name(&arg, pev);
> + if (ret == 0) {
> + if (asprintf(&pev->point.function, "%%%s", pev->event) < 0)
> + ret = -errno;
> + }
> + return ret;
> + }
> +
> + if (ptr && *ptr == '=') { /* Event name */
> + *ptr = '\0';
> + tmp = ptr + 1;
> + ret = parse_perf_probe_event_name(&arg, pev);
> + if (ret < 0)
> + return ret;
> +
> arg = tmp;
> }
>
> @@ -2849,7 +2882,8 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> pev->point.function);
> }
> if (!entry) {
> - ret = 0;
> + /* SDT must be in the cache */
> + ret = pev->sdt ? -ENOENT : 0;
> goto out;
> }
>
> @@ -2888,7 +2922,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
> {
> int ret;
>
> - if (!pev->group) {
> + if (!pev->group && !pev->sdt) {
> /* Set group name if not given */
> if (!pev->uprobes) {
> pev->group = strdup(PERFPROBE_GROUP);
> diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
> index c451223..2a23efe 100644
> --- a/tools/perf/util/probe-event.h
> +++ b/tools/perf/util/probe-event.h
> @@ -85,6 +85,7 @@ struct perf_probe_event {
> char *group; /* Group name */
> struct perf_probe_point point; /* Probe point */
> int nargs; /* Number of arguments */
> + bool sdt; /* SDT/cached event flag */
> bool uprobes; /* Uprobe event flag */
> char *target; /* Target binary */
> struct perf_probe_arg *args; /* Arguments */
> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
> index c10a647..ee560dd 100644
> --- a/tools/perf/util/probe-file.c
> +++ b/tools/perf/util/probe-file.c
> @@ -529,6 +529,15 @@ probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
> return NULL;
>
> list_for_each_entry(entry, &pcache->list, list) {
> + if (pev->sdt) {
> + if (entry->pev.event &&
> + streql(entry->pev.event, pev->event) &&
> + (!pev->group ||
> + streql(entry->pev.group, pev->group)))
> + goto found;
> +
> + continue;
> + }
> /* Hit if same event name or same command-string */
> if ((pev->event &&
> (streql(entry->pev.group, pev->group) &&
>

2016-04-28 22:50:31

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 02/15] perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid

On Thu, 28 Apr 2016 10:22:23 +0900
Namhyung Kim <[email protected]> wrote:

> Hi Masami,
>
> On Thu, Apr 28, 2016 at 03:37:23AM +0900, Masami Hiramatsu wrote:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> > to store corresponding elf binary.
> > This also stores vdso in buildid/vdso, kallsyms in buildid/kallsyms.
> >
> > Note that the existing caches are not updated until user adds
> > or updates the cache. Anyway, if there is the old style build-id
> > cache it falls back to use it. (IOW, it is backward compatible)
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
> > Changes in v5:
> > - Support old style buildid caches.
> > ---
> > tools/perf/util/build-id.c | 80 ++++++++++++++++++++++++++++++++++----------
> > tools/perf/util/dso.h | 5 +++
> > tools/perf/util/symbol.c | 15 ++++++--
> > 3 files changed, 76 insertions(+), 24 deletions(-)
> >
> > diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
> > index b6ecf87..b035483 100644
> > --- a/tools/perf/util/build-id.c
> > +++ b/tools/perf/util/build-id.c
> > @@ -144,7 +144,8 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
> > return ret;
> > }
> >
> > -static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
> > +static char *build_id_cache__linkname(const char *sbuild_id, char *bf,
> > + size_t size)
> > {
> > char *tmp = bf;
> > int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
> > @@ -154,15 +155,45 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
> > return bf;
> > }
> >
> > +static bool __is_regular_file(const char *pathname)
> > +{
> > + struct stat sb;
> > + return stat(pathname, &sb) == 0 && S_ISREG(sb.st_mode);
> > +}
>
> It looks like that the is_regular_file() is already in the
> util/util.c

Nice catch!!
OK, it should be used.

Thanks!

--
Masami Hiramatsu <[email protected]>

2016-04-28 23:06:24

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 04/15] perf probe: Add --cache option to cache the probe definitions

On Thu, 28 Apr 2016 11:32:18 +0900
Namhyung Kim <[email protected]> wrote:

> On Thu, Apr 28, 2016 at 03:37:42AM +0900, Masami Hiramatsu wrote:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Add --cache option to cache the probe definitions. This
> > just saves the result of the dwarf analysis to probe cache.
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
> > Changes in v5:
> > - Move probe_cache* definitions. (code cleanup)
> >
> > Changes in v4:
> > - Remove cache saving failure message.
> > ---
>
> [SNIP]
> > +/* For the kernel probe caches, pass target = NULL */
> > +static int probe_cache__open(struct probe_cache *pcache, const char *target)
> > +{
> > + char cpath[PATH_MAX];
> > + char sbuildid[SBUILD_ID_SIZE];
> > + char *dir_name;
> > + bool is_kallsyms = !target;
> > + int ret, fd;
> > +
> > + if (target)
> > + ret = filename__sprintf_build_id(target, sbuildid);
> > + else {
> > + target = "[kernel.kallsyms]";
> > + ret = sysfs__sprintf_build_id("/", sbuildid);
> > + }
> > + if (ret < 0) {
> > + pr_debug("Failed to get build-id from %s.\n", target ?: "kernel");
> > + return ret;
> > + }
> > +
> > + /* If we have no buildid cache, make it */
> > + if (!build_id_cache__cached(sbuildid)) {
> > + ret = build_id_cache__add_s(sbuildid, target,
> > + is_kallsyms, NULL);
> > + if (ret < 0) {
> > + pr_debug("Failed to add build-id cache: %s\n", target);
> > + return ret;
> > + }
> > + }
> > +
> > + dir_name = build_id_cache__dirname_from_path(sbuildid, target,
> > + is_kallsyms, false);
> > + if (!dir_name)
> > + return -ENOMEM;
> > +
> > + snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
> > + fd = open(cpath, O_CREAT | O_RDWR | O_APPEND, 0644);
> > + if (fd < 0)
> > + pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
> > + free(dir_name);
> > + pcache->fd = fd;
> > +
> > + return fd;
> > +}
>
> [SNIP]
> > +
> > +int probe_cache__commit(struct probe_cache *pcache)
> > +{
> > + struct probe_cache_entry *entry;
> > + int ret = 0;
> > +
> > + /* TBD: if we do not update existing entries, skip it */
> > + ret = lseek(pcache->fd, 0, SEEK_SET);
> > + if (ret < 0)
> > + goto out;
> > +
> > + ret = ftruncate(pcache->fd, 0);
> > + if (ret < 0)
> > + goto out;
>
> What is this doing? Does it truncate old contents on write? Opening
> with O_APPEND looks strange to me..

Ah, right. I forget the reason why :(, but I guess it maybe because just
changing the design while coding.
I'll remove O_APPEND flag then.

Thank you!

--
Masami Hiramatsu <[email protected]>

2016-04-28 23:14:41

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 04/15] perf probe: Add --cache option to cache the probe definitions

On Thu, 28 Apr 2016 11:12:19 +0900
Namhyung Kim <[email protected]> wrote:

> On Thu, Apr 28, 2016 at 03:37:42AM +0900, Masami Hiramatsu wrote:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Add --cache option to cache the probe definitions. This
> > just saves the result of the dwarf analysis to probe cache.
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
> > Changes in v5:
> > - Move probe_cache* definitions. (code cleanup)
> >
> > Changes in v4:
> > - Remove cache saving failure message.
> > ---
>
> [snip]
> > +static int probe_cache__load(struct probe_cache *pcache)
> > +{
> > + struct probe_cache_entry *entry = NULL;
> > + char buf[MAX_CMDLEN], *p;
> > + int ret = 0;
> > + FILE *fp;
> > +
> > + fp = fdopen(dup(pcache->fd), "r");
> > + while (!feof(fp)) {
> > + if (!fgets(buf, MAX_CMDLEN, fp))
> > + break;
> > + p = strchr(buf, '\n');
> > + if (p)
> > + *p = '\0';
> > + if (buf[0] == '#') { /* #perf_probe_event */
> > + entry = probe_cache_entry__new(NULL);
>
> The probe_cache_entry__new() can fail.

Good catch!

>
> Thanks,
> Namhyung
>
>
> > + entry->spev = strdup(buf + 1);

Moreover, if this strdup fail, this goes to return but retvalue is 0...

I'll fix this too.

Thank you!

--
Masami Hiramatsu <[email protected]>

2016-04-28 23:52:36

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 05/15] perf probe: Use cache entry if possible

On Thu, 28 Apr 2016 11:47:53 +0900
Namhyung Kim <[email protected]> wrote:

> On Thu, Apr 28, 2016 at 03:37:52AM +0900, Masami Hiramatsu wrote:
> > From: Masami Hiramatsu <[email protected]>
> >
> > Before analyzing debuginfo, try to find a corresponding entry
> > from probe cache always. This does not depend on --cache,
> > the --cache enables to store/update cache, but looking up
> > the cache is always enabled.
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
>
> [SNIP]
> > +static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> > + struct probe_trace_event **tevs)
> > +{
> > + struct probe_cache *cache;
> > + struct probe_cache_entry *entry;
> > + struct probe_trace_event *tev;
> > + struct str_node *node;
> > + int ret, i;
> > +
> > + cache = probe_cache__new(pev->target);
> > + if (!cache)
> > + return 0;
> > +
> > + entry = probe_cache__find(cache, pev);
> > +
> > + if (!entry && !pev->event &&
> > + (!pev->point.file && pev->point.function && !pev->point.retprobe &&
> > + !pev->point.line && !pev->point.offset && !pev->point.lazy_line)) {
> > + entry = probe_cache__find_by_name(cache, pev->group,
> > + pev->point.function);
> > + }
>
> What about arguments? It seems that it only checks group and event
> names of the given pev and use the cached entry's tev if found. What
> if they have different argument spec?

Indeed. I think this is for reusing cached event by using event name.
however, with 11/15 ("perf probe: Accept %sdt and %cached event name"),
we don't need this anymore.

So, I'll remove this fallback code.

Thank you!

>
> Thanks,
> Namhyung
>
>
> > + if (!entry) {
> > + ret = 0;
> > + goto out;
> > + }
> > +
> > + ret = strlist__nr_entries(entry->tevlist);
> > + if (ret > probe_conf.max_probes) {
> > + pr_debug("Too many entries matched in the cache of %s\n",
> > + pev->target ? : "kernel");
> > + ret = -E2BIG;
> > + goto out;
> > + }
> > +
> > + *tevs = zalloc(ret * sizeof(*tev));
> > + if (!*tevs) {
> > + ret = -ENOMEM;
> > + goto out;
> > + }
> > +
> > + i = 0;
> > + strlist__for_each(node, entry->tevlist) {
> > + tev = &(*tevs)[i++];
> > + ret = parse_probe_trace_command(node->s, tev);
> > + if (ret < 0)
> > + goto out;
> > + /* Set the uprobes attribute as same as original */
> > + tev->uprobes = pev->uprobes;
> > + }
> > + ret = i;
> > +
> > +out:
> > + probe_cache__delete(cache);
> > + return ret;
> > +}


--
Masami Hiramatsu <[email protected]>

2016-04-29 00:13:39

by Masami Hiramatsu

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 11/15] perf probe: Accept %sdt and %cached event name

On Thu, 28 Apr 2016 14:26:05 +0900
Namhyung Kim <[email protected]> wrote:

> On Thu, Apr 28, 2016 at 03:38:49AM +0900, Masami Hiramatsu wrote:
> > From: Masami Hiramatsu <[email protected]>
> >
> > To improbe usability, support %[PROVIDER:]SDTEVENT format to
> > add new probes on SDT and cached events.
> >
> > e.g.
> > ----
> > # perf probe -x /lib/libc-2.17.so %lll_lock_wait_private
> > Added new event:
> > sdt_libc:lll_lock_wait_private (on %lll_lock_wait_private in
> > /usr/lib/libc-2.17.so)
> >
> > You can now use it in all perf tools, such as:
> >
> > perf record -e sdt_libc:lll_lock_wait_private -aR sleep 1
> >
> > # perf probe -l | more
> > sdt_libc:lll_lock_wait_private (on __lll_lock_wait_private+21
> > in /usr/lib/libc-2.17.so)
> > ----
> >
> > Note that this is not only for SDT events, but also normal
> > events with event-name.
> >
> > e.g. define "myevent" on cache (-n doesn't add the real probe)
> > ----
> > # perf probe -x ./perf --cache -n --add 'myevent=dso__load $params'
> > ----
> > Reuse the "myevent" from cache as below.
> > ----
> > # perf probe -x ./perf %myevent
> > ----
> >
> > TODO:
> > Wildcard is not supported yet.
> >
> > Signed-off-by: Masami Hiramatsu <[email protected]>
> > ---
> > tools/perf/Documentation/perf-probe.txt | 3 +
> > tools/perf/util/probe-event.c | 78 ++++++++++++++++++++++---------
> > tools/perf/util/probe-event.h | 1
> > tools/perf/util/probe-file.c | 9 ++++
> > 4 files changed, 69 insertions(+), 22 deletions(-)
> >
> > diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
> > index 7a258e9..43523be 100644
> > --- a/tools/perf/Documentation/perf-probe.txt
> > +++ b/tools/perf/Documentation/perf-probe.txt
> > @@ -151,6 +151,8 @@ Probe points are defined by following syntax.
> > 3) Define event based on source file with lazy pattern
> > [[GROUP:]EVENT=]SRC;PTN [ARG ...]
> >
> > + 4) Pre-defined SDT events
> > + %[PROVIDER:]SDTEVENT
>
> How about changing it to:
>
> 4) Pre-defined (SDT) or cached events
> %EVENTNAME
>
> ?

Agreed, because cached events can be used for that too.
I think %[GROUP:]EVENT is more accurate.

> Btw, is it possible to use group name here?

Yes :)

> The SDT will use
> sdt_<libname> for group name and <provider>_<event> for event name,
> right?

No, the provider name is used for the group name as "sdt_<provider>".

> So is it for cached events and does it support defining group
> name when added like below?
>
> # perf probe -x ./perf --cache --add 'mygroup:myevent=main'

Yes, it is done by 9/15 ("perf probe: Add group name support") :)

Thank you,



--
Masami Hiramatsu <[email protected]>

2016-04-29 02:33:29

by Namhyung Kim

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 05/15] perf probe: Use cache entry if possible

Hi Masami,

On Fri, Apr 29, 2016 at 08:52:29AM +0900, Masami Hiramatsu wrote:
> On Thu, 28 Apr 2016 11:47:53 +0900
> Namhyung Kim <[email protected]> wrote:
>
> > On Thu, Apr 28, 2016 at 03:37:52AM +0900, Masami Hiramatsu wrote:
> > > From: Masami Hiramatsu <[email protected]>
> > >
> > > Before analyzing debuginfo, try to find a corresponding entry
> > > from probe cache always. This does not depend on --cache,
> > > the --cache enables to store/update cache, but looking up
> > > the cache is always enabled.
> > >
> > > Signed-off-by: Masami Hiramatsu <[email protected]>
> > > Signed-off-by: Masami Hiramatsu <[email protected]>
> > > ---
> >
> > [SNIP]
> > > +static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
> > > + struct probe_trace_event **tevs)
> > > +{
> > > + struct probe_cache *cache;
> > > + struct probe_cache_entry *entry;
> > > + struct probe_trace_event *tev;
> > > + struct str_node *node;
> > > + int ret, i;
> > > +
> > > + cache = probe_cache__new(pev->target);
> > > + if (!cache)
> > > + return 0;
> > > +
> > > + entry = probe_cache__find(cache, pev);
> > > +
> > > + if (!entry && !pev->event &&
> > > + (!pev->point.file && pev->point.function && !pev->point.retprobe &&
> > > + !pev->point.line && !pev->point.offset && !pev->point.lazy_line)) {
> > > + entry = probe_cache__find_by_name(cache, pev->group,
> > > + pev->point.function);
> > > + }
> >
> > What about arguments? It seems that it only checks group and event
> > names of the given pev and use the cached entry's tev if found. What
> > if they have different argument spec?
>
> Indeed. I think this is for reusing cached event by using event name.
> however, with 11/15 ("perf probe: Accept %sdt and %cached event name"),
> we don't need this anymore.
>
> So, I'll remove this fallback code.

Let's think about the following case: if user added an event to cache
with argument XXX earlier and she tries to add the same event but with
different argument YYY later. But the event is in the cache so it'll
reuse the cached event with XXX, no?

Thanks,
Namhyung

> >
> >
> > > + if (!entry) {
> > > + ret = 0;
> > > + goto out;
> > > + }
> > > +
> > > + ret = strlist__nr_entries(entry->tevlist);
> > > + if (ret > probe_conf.max_probes) {
> > > + pr_debug("Too many entries matched in the cache of %s\n",
> > > + pev->target ? : "kernel");
> > > + ret = -E2BIG;
> > > + goto out;
> > > + }
> > > +
> > > + *tevs = zalloc(ret * sizeof(*tev));
> > > + if (!*tevs) {
> > > + ret = -ENOMEM;
> > > + goto out;
> > > + }
> > > +
> > > + i = 0;
> > > + strlist__for_each(node, entry->tevlist) {
> > > + tev = &(*tevs)[i++];
> > > + ret = parse_probe_trace_command(node->s, tev);
> > > + if (ret < 0)
> > > + goto out;
> > > + /* Set the uprobes attribute as same as original */
> > > + tev->uprobes = pev->uprobes;
> > > + }
> > > + ret = i;
> > > +
> > > +out:
> > > + probe_cache__delete(cache);
> > > + return ret;
> > > +}
>
>
> --
> Masami Hiramatsu <[email protected]>

2016-04-29 13:53:51

by Hemant Kumar

[permalink] [raw]
Subject: Re: [PATCH perf/core v5 00/15] perf-probe --cache and SDT support

Hi Masami,

On 04/28/2016 12:07 AM, Masami Hiramatsu wrote:
> Hi,
>
> Here is the 5th version of the patchset for probe-cache and
> initial SDT support which are going to be perf-cache finally.
>
> The previous version is here; https://lkml.org/lkml/2016/4/26/179
>
> This version fixes a build bug on "make build-test", removed
> accepted patches, and fold buildid-cache style change and backward
> compatibility patches.
> IOW, just a cleanup version :)
>
> TODOs are here, but I think it should involve kernel-side change
> to complete.
> - (perf record) Support SDT event recording directly
> - (perf record) Support @FILE/@BUILDID suffix to record specific SDTs.
> - (perf record) Try to unregister SDT events after record.

I just sent a patch enabling direct recording on SDT events implementing
1st and 3rd TODOs of the above list. Its based on your patches. Let me
know your thoughts on the same.

--
Thanks,
Hemant Kumar


> - (ftrace) Support multiple SDTs on single event.
>
> Thank you,
>
> ---
>
> Hemant Kumar (1):
> perf/sdt: ELF support for SDT
>
> Masami Hiramatsu (14):
> perf probe: Use strbuf for making strings
> perf-buildid-cache: Use path/to/bin/buildid/elf instead of path/to/bin/buildid
> perf-buildid-cache: Use lsdir for looking up buildid caches
> perf probe: Add --cache option to cache the probe definitions
> perf probe: Use cache entry if possible
> perf probe: Show all cached probes
> perf probe: Remove caches when --cache is given
> perf probe: Add group name support
> perf buildid-cache: Scan and import user SDT events to probe cache
> perf probe: Accept %sdt and %cached event name
> perf-list: Show SDT and pre-cached events
> perf-list: Skip SDTs placed in invalid binaries
> perf probe: Allow wildcard for cached events
> perf probe: Support @BUILDID or @FILE suffix for SDT events
>
>
> tools/perf/Documentation/perf-probe.txt | 24 +
> tools/perf/builtin-list.c | 4
> tools/perf/builtin-probe.c | 30 +
> tools/perf/util/build-id.c | 278 ++++++++++---
> tools/perf/util/build-id.h | 6
> tools/perf/util/dso.h | 5
> tools/perf/util/parse-events.c | 83 ++++
> tools/perf/util/parse-events.h | 2
> tools/perf/util/probe-event.c | 684 ++++++++++++++++++++++---------
> tools/perf/util/probe-event.h | 9
> tools/perf/util/probe-file.c | 492 ++++++++++++++++++++++
> tools/perf/util/probe-file.h | 41 ++
> tools/perf/util/probe-finder.c | 14 -
> tools/perf/util/symbol-elf.c | 252 +++++++++++
> tools/perf/util/symbol.c | 15 -
> tools/perf/util/symbol.h | 22 +
> 16 files changed, 1689 insertions(+), 272 deletions(-)
>
> --
> Masami Hiramatsu
>