[PATCH v6 2/3] perf tool: add PERF_RECORD_NAMESPACES to include namespaces related info

From: Hari Bathini
Date: Wed Feb 08 2017 - 03:32:57 EST

This patch updates perf tool to examine PERF_RECORD_NAMESPACES events
emitted by the kernel when fork, clone, setns or unshare are invoked.
Also, it synthesizes PERF_RECORD_NAMESPACES events for processes that
were running prior to invocation of perf record, the data for which
is taken from /proc/$PID/ns. These changes make way for analyzing
events with regard to namespaces.

Signed-off-by: Hari Bathini <hbathini@xxxxxxxxxxxxxxxxxx>
---
tools/include/uapi/linux/perf_event.h | 38 +++++++++
tools/perf/builtin-annotate.c | 1
tools/perf/builtin-diff.c | 1
tools/perf/builtin-inject.c | 14 +++
tools/perf/builtin-kmem.c | 1
tools/perf/builtin-kvm.c | 2
tools/perf/builtin-lock.c | 1
tools/perf/builtin-mem.c | 1
tools/perf/builtin-record.c | 33 +++++++-
tools/perf/builtin-report.c | 1
tools/perf/builtin-sched.c | 1
tools/perf/builtin-script.c | 41 +++++++++
tools/perf/builtin-trace.c | 3 -
tools/perf/perf.h | 1
tools/perf/util/Build | 1
tools/perf/util/data-convert-bt.c | 2
tools/perf/util/event.c | 143 ++++++++++++++++++++++++++++++++-
tools/perf/util/event.h | 19 ++++
tools/perf/util/evsel.c | 3 +
tools/perf/util/machine.c | 34 ++++++++
tools/perf/util/machine.h | 3 +
tools/perf/util/namespaces.c | 35 ++++++++
tools/perf/util/namespaces.h | 26 ++++++
tools/perf/util/session.c | 7 ++
tools/perf/util/thread.c | 44 ++++++++++
tools/perf/util/thread.h | 6 +
tools/perf/util/tool.h | 2
27 files changed, 450 insertions(+), 14 deletions(-)
create mode 100644 tools/perf/util/namespaces.c
create mode 100644 tools/perf/util/namespaces.h

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index c66a485..ee60f54 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -344,7 +344,8 @@ struct perf_event_attr {
use_clockid : 1, /* use @clockid for time fields */
context_switch : 1, /* context switch data */
write_backward : 1, /* Write ring buffer from end to beginning */
- __reserved_1 : 36;
+ namespaces : 1, /* include namespaces data */
+ __reserved_1 : 35;

union {
__u32 wakeup_events; /* wakeup every n events */
@@ -610,6 +611,29 @@ struct perf_event_header {
__u16 size;
};

+/*
+ * The maximum size of the name of each namespace
+ */
+#define NS_NAME_SIZE 8
+
+struct perf_ns_link_info {
+ char name[NS_NAME_SIZE];
+ __u64 dev;
+ __u64 ino;
+};
+
+enum {
+ NET_NS_INDEX = 0,
+ UTS_NS_INDEX = 1,
+ IPC_NS_INDEX = 2,
+ PID_NS_INDEX = 3,
+ USER_NS_INDEX = 4,
+ MNT_NS_INDEX = 5,
+ CGROUP_NS_INDEX = 6,
+
+ NAMESPACES_MAX, /* maximum available namespaces */
+};
+
enum perf_event_type {

/*
@@ -862,6 +886,18 @@ enum perf_event_type {
*/
PERF_RECORD_SWITCH_CPU_WIDE = 15,

+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * u32 nr_namespaces;
+ * struct namespace_link_info link_info[NAMESPACES_MAX];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_NAMESPACES = 16,
+
PERF_RECORD_MAX, /* non-ABI */
};

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ebb6283..1b63dc4 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -393,6 +393,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 933aeec..37cfbaa 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -354,6 +354,7 @@ static struct perf_tool tool = {
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
.ordering_requires_timestamps = true,
};
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b9bc7e3..c5ddc73 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -333,6 +333,19 @@ static int perf_event__repipe_comm(struct perf_tool *tool,
return err;
}

+static int perf_event__repipe_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err;
+
+ err = perf_event__process_namespaces(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_exit(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -660,6 +673,7 @@ static int __cmd_inject(struct perf_inject *inject)
session->itrace_synth_opts = &inject->itrace_synth_opts;
inject->itrace_synth_opts.inject = true;
inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.namespaces = perf_event__repipe_namespaces;
inject->tool.exit = perf_event__repipe_exit;
inject->tool.id_index = perf_event__repipe_id_index;
inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 29f4751..1b53852 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -964,6 +964,7 @@ static struct perf_tool perf_kmem = {
.comm = perf_event__process_comm,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 08fa88f..18e6c38 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1044,6 +1044,7 @@ static int read_events(struct perf_kvm_stat *kvm)
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
struct perf_data_file file = {
@@ -1348,6 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
kvm->tool.exit = perf_event__process_exit;
kvm->tool.fork = perf_event__process_fork;
kvm->tool.lost = process_lost_event;
+ kvm->tool.namespaces = perf_event__process_namespaces;
kvm->tool.ordered_events = true;
perf_tool__fill_defaults(&kvm->tool);

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ce3bfb4..d750cca 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -858,6 +858,7 @@ static int __cmd_report(bool display_info)
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
struct perf_data_file file = {
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index cd7bc4d..430656c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -342,6 +342,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
.lost = perf_event__process_lost,
.fork = perf_event__process_fork,
.build_id = perf_event__process_build_id,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
},
.input_name = "perf.data",
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ffac8ca..1946a17 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -875,6 +875,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGTERM, sig_handler);
signal(SIGSEGV, sigsegv_handler);

+ if (rec->opts.record_namespaces)
+ tool->namespace_events = true;
+
if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
@@ -982,6 +985,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
*/
if (forks) {
union perf_event *event;
+ pid_t tgid;

event = malloc(sizeof(event->comm) + machine->id_hdr_size);
if (event == NULL) {
@@ -995,10 +999,28 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
* cannot see a correct process name for those events.
* Synthesize COMM event to prevent it.
*/
- perf_event__synthesize_comm(tool, event,
- rec->evlist->workload.pid,
- process_synthesized_event,
- machine);
+ tgid = perf_event__synthesize_comm(tool, event,
+ rec->evlist->workload.pid,
+ process_synthesized_event,
+ machine);
+ free(event);
+
+ if (tgid == -1)
+ goto out_child;
+
+ event = malloc(sizeof(event->namespaces) + machine->id_hdr_size);
+ if (event == NULL) {
+ err = -ENOMEM;
+ goto out_child;
+ }
+
+ /*
+ * Synthesize NAMESPACES event for the command specified.
+ */
+ perf_event__synthesize_namespaces(tool, event,
+ rec->evlist->workload.pid,
+ tgid, process_synthesized_event,
+ machine);
free(event);

perf_evlist__start_workload(rec->evlist);
@@ -1496,6 +1518,7 @@ static struct record record = {
.fork = perf_event__process_fork,
.exit = perf_event__process_exit,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.ordered_events = true,
@@ -1610,6 +1633,8 @@ static struct option __record_options[] = {
"opts", "AUX area tracing Snapshot Mode", ""),
OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
+ OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
+ "Record namespaces events"),
OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
"Record context switch events"),
OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dbd7fa0..5c92c75 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -694,6 +694,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index daceb32..109baf6 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3272,6 +3272,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
.tool = {
.sample = perf_sched__process_tracepoint_sample,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.lost = perf_event__process_lost,
.fork = perf_sched__process_fork_event,
.ordered_events = true,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c0783b4..b0672cc 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -830,6 +830,7 @@ struct perf_script {
bool show_task_events;
bool show_mmap_events;
bool show_switch_events;
+ bool show_namespaces_events;
bool allocated;
struct cpu_map *cpus;
struct thread_map *threads;
@@ -1118,6 +1119,41 @@ static int process_comm_event(struct perf_tool *tool,
return ret;
}

+static int process_namespaces_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct thread *thread;
+ struct perf_script *script = container_of(tool, struct perf_script, tool);
+ struct perf_session *session = script->session;
+ struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+ int ret = -1;
+
+ thread = machine__findnew_thread(machine, event->namespaces.pid,
+ event->namespaces.tid);
+ if (thread == NULL) {
+ pr_debug("problem processing NAMESPACES event, skipping it.\n");
+ return -1;
+ }
+
+ if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
+ goto out;
+
+ if (!evsel->attr.sample_id_all) {
+ sample->cpu = 0;
+ sample->time = 0;
+ sample->tid = event->namespaces.tid;
+ sample->pid = event->namespaces.pid;
+ }
+ print_sample_start(sample, thread, evsel);
+ perf_event__fprintf(event, stdout);
+ ret = 0;
+out:
+ thread__put(thread);
+ return ret;
+}
+
static int process_fork_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -1293,6 +1329,8 @@ static int __cmd_script(struct perf_script *script)
}
if (script->show_switch_events)
script->tool.context_switch = process_switch_event;
+ if (script->show_namespaces_events)
+ script->tool.namespaces = process_namespaces_event;

ret = perf_session__process_events(script->session);

@@ -2097,6 +2135,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.attr = process_attr,
@@ -2180,6 +2219,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"Show the mmap events"),
OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
"Show context switch events (if recorded)"),
+ OPT_BOOLEAN('\0', "show-namespaces-events", &script.show_namespaces_events,
+ "Show namespaces events (if recorded)"),
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
OPT_BOOLEAN(0, "ns", &nanosecs,
"Use 9 decimal places when displaying time"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 40ef9b2..0bcd32f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2415,8 +2415,9 @@ static int trace__replay(struct trace *trace)
trace->tool.exit = perf_event__process_exit;
trace->tool.fork = perf_event__process_fork;
trace->tool.attr = perf_event__process_attr;
- trace->tool.tracing_data = perf_event__process_tracing_data;
+ trace->tool.tracing_data = perf_event__process_tracing_data;
trace->tool.build_id = perf_event__process_build_id;
+ trace->tool.namespaces = perf_event__process_namespaces;

trace->tool.ordered_events = true;
trace->tool.ordering_requires_timestamps = true;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 1c27d94..806c216 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -50,6 +50,7 @@ struct record_opts {
bool running_time;
bool full_auxtrace;
bool auxtrace_snapshot_mode;
+ bool record_namespaces;
bool record_switch_events;
bool all_kernel;
bool all_user;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5da376b..2ea5ee1 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -42,6 +42,7 @@ libperf-y += pstack.o
libperf-y += session.o
libperf-$(CONFIG_AUDIT) += syscalltbl.o
libperf-y += ordered-events.o
+libperf-y += namespaces.o
libperf-y += comm.o
libperf-y += thread.o
libperf-y += thread_map.o
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 4e6cbc9..3b408f7 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1468,6 +1468,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
.lost = perf_event__process_lost,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
@@ -1479,6 +1480,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
c.tool.comm = process_comm_event;
c.tool.exit = process_exit_event;
c.tool.fork = process_fork_event;
+ c.tool.namespaces = process_namespaces_event;
}

err = perf_config(convert__config, &c);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8ab0d7d..0ac1a8d 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -31,6 +31,7 @@ static const char *perf_event__names[] = {
[PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES",
[PERF_RECORD_SWITCH] = "SWITCH",
[PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE",
+ [PERF_RECORD_NAMESPACES] = "NAMESPACES",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
@@ -203,6 +204,74 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
return tgid;
}

+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+ struct perf_ns_link_info *ns_link_info)
+{
+ struct stat64 st;
+ char proc_ns[128];
+
+ snprintf(ns_link_info->name, NS_NAME_SIZE, "%s", ns);
+
+ sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+ if (stat64(proc_ns, &st) == 0) {
+ ns_link_info->dev = st.st_dev;
+ ns_link_info->ino = st.st_ino;
+ }
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ pid_t pid, pid_t tgid,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ struct perf_ns_link_info *ns_link_info;
+
+ if (!tool->namespace_events)
+ return 0;
+
+ memset(&event->namespaces, 0,
+ sizeof(event->namespaces) + machine->id_hdr_size);
+
+ event->namespaces.pid = tgid;
+ event->namespaces.tid = pid;
+
+ event->namespaces.nr_namespaces = NAMESPACES_MAX;
+
+ ns_link_info = event->namespaces.link_info;
+
+ perf_event__get_ns_link_info(pid, "mnt",
+ &ns_link_info[MNT_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "net",
+ &ns_link_info[NET_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "uts",
+ &ns_link_info[UTS_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "ipc",
+ &ns_link_info[IPC_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "pid",
+ &ns_link_info[PID_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "user",
+ &ns_link_info[USER_NS_INDEX]);
+
+ perf_event__get_ns_link_info(pid, "cgroup",
+ &ns_link_info[CGROUP_NS_INDEX]);
+
+ event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+ event->namespaces.header.size = (sizeof(event->namespaces) +
+ machine->id_hdr_size);
+
+ if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+ return -1;
+
+ return 0;
+}
+
static int perf_event__synthesize_fork(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid, pid_t ppid,
@@ -434,8 +503,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
static int __event__synthesize_thread(union perf_event *comm_event,
union perf_event *mmap_event,
union perf_event *fork_event,
+ union perf_event *namespaces_event,
pid_t pid, int full,
- perf_event__handler_t process,
+ perf_event__handler_t process,
struct perf_tool *tool,
struct machine *machine,
bool mmap_data,
@@ -455,6 +525,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
if (tgid == -1)
return -1;

+ if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+ tgid, process, machine) < 0)
+ return -1;
+
+
return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
process, machine, mmap_data,
proc_map_timeout);
@@ -488,6 +563,11 @@ static int __event__synthesize_thread(union perf_event *comm_event,
if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
ppid, process, machine) < 0)
break;
+
+ if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+ tgid, process, machine) < 0)
+ break;
+
/*
* Send the prepared comm event
*/
@@ -516,6 +596,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
unsigned int proc_map_timeout)
{
union perf_event *comm_event, *mmap_event, *fork_event;
+ union perf_event *namespaces_event;
int err = -1, thread, j;

comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -530,10 +611,15 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
if (fork_event == NULL)
goto out_free_mmap;

+ namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+ machine->id_hdr_size);
+ if (namespaces_event == NULL)
+ goto out_free_fork;
+
err = 0;
for (thread = 0; thread < threads->nr; ++thread) {
if (__event__synthesize_thread(comm_event, mmap_event,
- fork_event,
+ fork_event, namespaces_event,
thread_map__pid(threads, thread), 0,
process, tool, machine,
mmap_data, proc_map_timeout)) {
@@ -559,7 +645,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
/* if not, generate events for it */
if (need_leader &&
__event__synthesize_thread(comm_event, mmap_event,
- fork_event,
+ fork_event, namespaces_event,
comm_event->comm.pid, 0,
process, tool, machine,
mmap_data, proc_map_timeout)) {
@@ -568,6 +654,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
}
}
}
+ free(namespaces_event);
+out_free_fork:
free(fork_event);
out_free_mmap:
free(mmap_event);
@@ -587,6 +675,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
char proc_path[PATH_MAX];
struct dirent *dirent;
union perf_event *comm_event, *mmap_event, *fork_event;
+ union perf_event *namespaces_event;
int err = -1;

if (machine__is_default_guest(machine))
@@ -604,11 +693,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
if (fork_event == NULL)
goto out_free_mmap;

+ namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+ machine->id_hdr_size);
+ if (namespaces_event == NULL)
+ goto out_free_fork;
+
snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
proc = opendir(proc_path);

if (proc == NULL)
- goto out_free_fork;
+ goto out_free_namespaces;

while ((dirent = readdir(proc)) != NULL) {
char *end;
@@ -620,13 +714,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
* We may race with exiting thread, so don't stop just because
* one thread couldn't be synthesized.
*/
- __event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
- 1, process, tool, machine, mmap_data,
+ __event__synthesize_thread(comm_event, mmap_event, fork_event,
+ namespaces_event, pid, 1, process,
+ tool, machine, mmap_data,
proc_map_timeout);
}

err = 0;
closedir(proc);
+out_free_namespaces:
+ free(namespaces_event);
out_free_fork:
free(fork_event);
out_free_mmap:
@@ -1008,6 +1105,29 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
}

+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+ size_t ret = 0;
+ struct perf_ns_link_info *ns_link_info;
+ u32 nr_namespaces, idx;
+
+ ns_link_info = event->namespaces.link_info;
+ nr_namespaces = event->namespaces.nr_namespaces;
+
+ ret += fprintf(fp, " %d/%d - nr_namespaces: %u [",
+ event->namespaces.pid,
+ event->namespaces.tid,
+ nr_namespaces);
+
+ for (idx = 0; idx < nr_namespaces; idx++)
+ ret += fprintf(fp, "%s: %lu/0x%lx%s", ns_link_info[idx].name,
+ (u64)ns_link_info[idx].dev,
+ (u64)ns_link_info[idx].ino,
+ ((idx + 1) != nr_namespaces) ? ", " : "]\n\n");
+
+ return ret;
+}
+
int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
@@ -1016,6 +1136,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
return machine__process_comm_event(machine, event, sample);
}

+int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ return machine__process_namespaces_event(machine, event, sample);
+}
+
int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
@@ -1196,6 +1324,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
case PERF_RECORD_MMAP:
ret += perf_event__fprintf_mmap(event, fp);
break;
+ case PERF_RECORD_NAMESPACES:
+ ret += perf_event__fprintf_namespaces(event, fp);
+ break;
case PERF_RECORD_MMAP2:
ret += perf_event__fprintf_mmap2(event, fp);
break;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c735c53..09fde83 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -39,6 +39,13 @@ struct comm_event {
char comm[16];
};

+struct namespaces_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+ u32 nr_namespaces;
+ struct perf_ns_link_info link_info[NAMESPACES_MAX];
+};
+
struct fork_event {
struct perf_event_header header;
u32 pid, ppid;
@@ -485,6 +492,7 @@ union perf_event {
struct mmap_event mmap;
struct mmap2_event mmap2;
struct comm_event comm;
+ struct namespaces_event namespaces;
struct fork_event fork;
struct lost_event lost;
struct lost_samples_event lost_samples;
@@ -587,6 +595,10 @@ int perf_event__process_switch(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
@@ -636,6 +648,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
perf_event__handler_t process,
struct machine *machine);

+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ pid_t pid, pid_t tgid,
+ perf_event__handler_t process,
+ struct machine *machine);
+
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
@@ -653,6 +671,7 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);

u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 04e536a..e94f807 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -932,6 +932,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;

+ if (opts->record_namespaces)
+ attr->namespaces = track;
+
if (opts->record_switch_events)
attr->context_switch = track;

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 747a034..ecdf1f0 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -13,6 +13,7 @@
#include <symbol/kallsyms.h>
#include "unwind.h"
#include "linux/hash.h"
+#include "asm/bug.h"

static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);

@@ -501,6 +502,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
return err;
}

+int machine__process_namespaces_event(struct machine *machine __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused)
+{
+ struct thread *thread = machine__findnew_thread(machine,
+ event->namespaces.pid,
+ event->namespaces.tid);
+ int err = 0;
+
+ WARN_ONCE(event->namespaces.nr_namespaces > NAMESPACES_MAX,
+ "\nWARNING: kernel seems to support more namespaces than perf"
+ " tool.\nTry updating the perf tool..\n\n");
+
+ WARN_ONCE(event->namespaces.nr_namespaces < NAMESPACES_MAX,
+ "\nWARNING: perf tool seems to support more namespaces than"
+ " the kernel.\nTry updating the kernel..\n\n");
+
+ if (dump_trace)
+ perf_event__fprintf_namespaces(event, stdout);
+
+ if (thread == NULL ||
+ thread__set_namespaces(thread, sample->time, &event->namespaces)) {
+ dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n");
+ err = -1;
+ }
+
+ thread__put(thread);
+
+ return err;
+}
+
int machine__process_lost_event(struct machine *machine __maybe_unused,
union perf_event *event, struct perf_sample *sample __maybe_unused)
{
@@ -1538,6 +1570,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
ret = machine__process_comm_event(machine, event, sample); break;
case PERF_RECORD_MMAP:
ret = machine__process_mmap_event(machine, event, sample); break;
+ case PERF_RECORD_NAMESPACES:
+ ret = machine__process_namespaces_event(machine, event, sample); break;
case PERF_RECORD_MMAP2:
ret = machine__process_mmap2_event(machine, event, sample); break;
case PERF_RECORD_FORK:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a283050..3cdb134 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine,
union perf_event *event);
int machine__process_switch_event(struct machine *machine,
union perf_event *event);
+int machine__process_namespaces_event(struct machine *machine,
+ union perf_event *event,
+ struct perf_sample *sample);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
new file mode 100644
index 0000000..3134c00
--- /dev/null
+++ b/tools/perf/util/namespaces.c
@@ -0,0 +1,35 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#include "namespaces.h"
+#include "util.h"
+#include "event.h"
+#include <stdlib.h>
+#include <stdio.h>
+
+struct namespaces *namespaces__new(struct namespaces_event *event)
+{
+ struct namespaces *namespaces = zalloc(sizeof(*namespaces));
+
+ if (!namespaces)
+ return NULL;
+
+ namespaces->end_time = -1;
+
+ if (event) {
+ memcpy(namespaces->link_info, event->link_info,
+ sizeof(namespaces->link_info));
+ }
+
+ return namespaces;
+}
+
+void namespaces__free(struct namespaces *namespaces)
+{
+ free(namespaces);
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
new file mode 100644
index 0000000..e42487e
--- /dev/null
+++ b/tools/perf/util/namespaces.h
@@ -0,0 +1,26 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include "../perf.h"
+#include <linux/list.h>
+
+struct namespaces_event;
+
+struct namespaces {
+ struct list_head list;
+ u64 end_time;
+ struct perf_ns_link_info link_info[NAMESPACES_MAX];
+};
+
+struct namespaces *namespaces__new(struct namespaces_event *event);
+void namespaces__free(struct namespaces *namespaces);
+
+#endif /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 349c681..d868661 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1239,6 +1239,8 @@ static int machines__deliver_event(struct machines *machines,
return tool->mmap2(tool, event, sample, machine);
case PERF_RECORD_COMM:
return tool->comm(tool, event, sample, machine);
+ case PERF_RECORD_NAMESPACES:
+ return tool->namespaces(tool, event, sample, machine);
case PERF_RECORD_FORK:
return tool->fork(tool, event, sample, machine);
case PERF_RECORD_EXIT:
@@ -1494,6 +1496,11 @@ int perf_session__register_idle_thread(struct perf_session *session)
err = -1;
}

+ if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) {
+ pr_err("problem inserting idle task.\n");
+ err = -1;
+ }
+
/* machine__findnew_thread() got the thread, so put it */
thread__put(thread);
return err;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index f5af87f..b9fe432 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,7 @@
#include "thread-stack.h"
#include "util.h"
#include "debug.h"
+#include "namespaces.h"
#include "comm.h"
#include "unwind.h"

@@ -40,6 +41,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
thread->tid = tid;
thread->ppid = -1;
thread->cpu = -1;
+ INIT_LIST_HEAD(&thread->namespaces_list);
INIT_LIST_HEAD(&thread->comm_list);

comm_str = malloc(32);
@@ -66,7 +68,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)

void thread__delete(struct thread *thread)
{
- struct comm *comm, *tmp;
+ struct namespaces *namespaces, *tmp_namespaces;
+ struct comm *comm, *tmp_comm;

BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));

@@ -76,7 +79,12 @@ void thread__delete(struct thread *thread)
map_groups__put(thread->mg);
thread->mg = NULL;
}
- list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+ list_for_each_entry_safe(namespaces, tmp_namespaces,
+ &thread->namespaces_list, list) {
+ list_del(&namespaces->list);
+ namespaces__free(namespaces);
+ }
+ list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
list_del(&comm->list);
comm__free(comm);
}
@@ -104,6 +112,38 @@ void thread__put(struct thread *thread)
}
}

+struct namespaces *thread__namespaces(const struct thread *thread)
+{
+ if (list_empty(&thread->namespaces_list))
+ return NULL;
+
+ return list_first_entry(&thread->namespaces_list, struct namespaces, list);
+}
+
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+ struct namespaces_event *event)
+{
+ struct namespaces *new, *curr = thread__namespaces(thread);
+
+ new = namespaces__new(event);
+ if (!new)
+ return -ENOMEM;
+
+ list_add(&new->list, &thread->namespaces_list);
+
+ if (timestamp && curr) {
+ /*
+ * setns syscall must have changed few or all the namespaces
+ * of this thread. Update end time for the namespaces
+ * previously used.
+ */
+ curr = list_next_entry(new, list);
+ curr->end_time = timestamp;
+ }
+
+ return 0;
+}
+
struct comm *thread__comm(const struct thread *thread)
{
if (list_empty(&thread->comm_list))
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 99263cb..b18b5a2 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -28,6 +28,7 @@ struct thread {
bool comm_set;
int comm_len;
bool dead; /* if set thread has exited */
+ struct list_head namespaces_list;
struct list_head comm_list;
u64 db_id;

@@ -40,6 +41,7 @@ struct thread {
};

struct machine;
+struct namespaces;
struct comm;

struct thread *thread__new(pid_t pid, pid_t tid);
@@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread)
thread->dead = true;
}

+struct namespaces *thread__namespaces(const struct thread *thread);
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+ struct namespaces_event *event);
+
int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
bool exec);
static inline int thread__set_comm(struct thread *thread, const char *comm,
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index ac2590a..829471a 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,6 +40,7 @@ struct perf_tool {
event_op mmap,
mmap2,
comm,
+ namespaces,
fork,
exit,
lost,
@@ -66,6 +67,7 @@ struct perf_tool {
event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
+ bool namespace_events;
};

#endif /* __PERF_TOOL_H */