perf tools: some fixes and tweaks

index 42ea4e9..2b77b33 100644
@@ -14,6 +14,7 @@
 #include "target.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "debug.h"
 #include <unistd.h>
 
 #include "parse-events.h"

@@ -454,6 +455,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
 
+	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 

@@ -492,6 +494,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	int thread;
 	int nr_threads = thread_map__nr(evlist->threads);
 
+	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 

82 lines not on this page · raw message

index 925e0c3..381f4fd 100644
@@ -8,6 +8,26 @@
 #include "cpumap.h"
 #include "thread_map.h"
 
+/*
+ * Support debug printing even though util/debug.c is not linked.  That means
+ * implementing 'verbose' and 'eprintf'.
+ */
+int verbose;
+
+int eprintf(int level, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (verbose >= level) {
+		va_start(args, fmt);
+		ret = vfprintf(stderr, fmt, args);
+		va_end(args);
+	}
+
+	return ret;
+}
+
 /* Define PyVarObject_HEAD_INIT for python 2.5 */
 #ifndef PyVarObject_HEAD_INIT
 # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,

index a34c587..7b6a2bb 100644
@@ -367,7 +367,7 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
-	u64 sample_type = perf_evlist__sample_type(self->evlist);
+	u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
 
 	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {

index 1ebb8fb..e60585e 100644
@@ -65,6 +65,20 @@ struct read_event {
 	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
 	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
 
+/*
+ * Events have compatible sample types if the following bits all have the same
+ * value.  This is because the order of sample members is fixed.  For sample
+ * events the order is: PERF_SAMPLE_IP, PERF_SAMPLE_TID, PERF_SAMPLE_TIME,
+ * PERF_SAMPLE_ADDR, PERF_SAMPLE_ID.  For non-sample events the sample members
+ * are accessed in reverse order.  The order is: PERF_SAMPLE_ID,
+ * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.
+ */
+#define PERF_COMPAT_MASK				\
+	(PERF_SAMPLE_IP   | PERF_SAMPLE_TID       |	\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR      |	\
+	 PERF_SAMPLE_ID   | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];

187 lines not on this page · raw message

index 0583d36..b1be475 100644
@@ -32,11 +32,15 @@ struct perf_evlist {
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
+	int		 id_pos;
+	int		 is_pos;
+	u64		 combined_sample_type;
 	struct {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
 	bool		 overwrite;
+	bool		 matching_sample_types;
 	struct perf_mmap *mmap;
 	struct pollfd	 *pollfd;
 	struct thread_map *threads;

@@ -83,6 +87,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist);
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 

@@ -118,7 +123,8 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist);
 void __perf_evlist__set_leader(struct list_head *list);
 void perf_evlist__set_leader(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 

94 lines not on this page · raw message

index 3f156cc..c6d616c 100644
@@ -45,6 +45,11 @@ struct perf_sample_id {
  * @name - Can be set to retain the original event name passed by the user,
  *         so that when showing results in tools such as 'perf stat', we
  *         show the name used, not some alias.
+ * @id_pos: the position of the event id (PERF_SAMPLE_ID) in a sample event
+ *          i.e. in the array of struct sample_event
+ * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID)
+ *          in a non-sample event i.e. if sample_id_all is used there is an id
+ *          sample appended to non-sample events
  */
 struct perf_evsel {
 	struct list_head	node;

@@ -71,6 +76,8 @@ struct perf_evsel {
 	} handler;
 	struct cpu_map		*cpus;
 	unsigned int		sample_size;
+	int			id_pos;
+	int			is_pos;
 	bool 			supported;
 	bool 			needs_swap;
 	/* parse modifier helper */

@@ -100,6 +107,9 @@ void perf_evsel__delete(struct perf_evsel *evsel);
 void perf_evsel__config(struct perf_evsel *evsel,
 			struct perf_record_opts *opts);
 
+int __perf_evsel__sample_size(u64 sample_type);
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
 #define PERF_EVSEL__MAX_ALIASES 8

index d0d9f94..d4c9a26 100644
@@ -734,7 +734,7 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 sample_type = perf_evlist__sample_type(session->evlist);
+	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
 
 	if (event->header.type != PERF_RECORD_SAMPLE &&
 	    !perf_evlist__sample_id_all(session->evlist)) {

@@ -893,7 +893,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
+	    !sample->callchain)
 		return 0;
 
 	if (!ip_callchain__valid(sample->callchain, event)) {

@@ -1293,7 +1293,9 @@ int perf_session__process_events(struct perf_session *self,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
+	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
+
+	if (!(sample_type & PERF_SAMPLE_RAW)) {
 		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
 		return false;
 	}

index f9f9d63..67ba572 100644
@@ -233,7 +233,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t tid,
+static struct thread *__machine__findnew_thread(struct machine *machine,
+						pid_t pid, pid_t tid,
 						bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;

@@ -245,8 +246,11 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->tid == tid)
+	if (machine->last_match && machine->last_match->tid == tid) {
+		if (pid && pid != machine->last_match->pid_)
+			machine->last_match->pid_ = pid;
 		return machine->last_match;
+	}
 
 	while (*p != NULL) {
 		parent = *p;

@@ -254,6 +258,8 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 
 		if (th->tid == tid) {
 			machine->last_match = th;
+			if (pid && pid != th->pid_)
+				th->pid_ = pid;
 			return th;
 		}
 

@@ -266,7 +272,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 	if (!create)
 		return NULL;
 
-	th = thread__new(tid);
+	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);

@@ -278,12 +284,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, tid, true);
+	return __machine__findnew_thread(machine, 0, tid, true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, tid, false);
+	return __machine__findnew_thread(machine, 0, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)

index 6feeb88..e3d4a55 100644
@@ -7,12 +7,13 @@
 #include "util.h"
 #include "debug.h"
 
-struct thread *thread__new(pid_t tid)
+struct thread *thread__new(pid_t pid, pid_t tid)
 {
 	struct thread *self = zalloc(sizeof(*self));
 
 	if (self != NULL) {
 		map_groups__init(&self->mg);
+		self->pid_ = pid;
 		self->tid = tid;
 		self->ppid = -1;
 		self->comm = malloc(32);

index 0fe1f9c..fc464bc 100644
@@ -12,6 +12,7 @@ struct thread {
 		struct list_head node;
 	};
 	struct map_groups	mg;
+	pid_t			pid_; /* Not all tools update this */
 	pid_t			tid;
 	pid_t			ppid;
 	char			shortname[3];

@@ -24,7 +25,7 @@ struct thread {
 
 struct machine;
 
-struct thread *thread__new(pid_t tid);
+struct thread *thread__new(pid_t pid, pid_t tid);
 void thread__delete(struct thread *self);
 
 int thread__set_comm(struct thread *self, const char *comm);

index 1d8de2e..0d4ae1d 100644
@@ -198,7 +198,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread = machine__findnew_thread(machine, event->ip.pid);
+	thread = machine__findnew_thread(machine, event->ip.pid, event->ip.pid);
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);

index b49f5c5..c324778 100644
@@ -305,7 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
+							event->ip.pid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",

index 24b78ae..ecbbec8 100644
@@ -691,7 +691,8 @@ static int process_sample_event(struct perf_tool *tool,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, sample->tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
 						 tool);
 

index 76543a4..ee33ba2 100644
@@ -805,7 +805,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, sample->tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",

index 948183a..49593a0 100644
@@ -934,8 +934,8 @@ static int latency_switch_event(struct perf_sched *sched,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, prev_pid);
-	sched_in = machine__findnew_thread(machine, next_pid);
+	sched_out = machine__findnew_thread(machine, 0, prev_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
 	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {

@@ -978,7 +978,7 @@ static int latency_runtime_event(struct perf_sched *sched,
 {
 	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
 	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
-	struct thread *thread = machine__findnew_thread(machine, pid);
+	struct thread *thread = machine__findnew_thread(machine, 0, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu;

@@ -1016,7 +1016,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	if (!success)
 		return 0;
 
-	wakee = machine__findnew_thread(machine, pid);
+	wakee = machine__findnew_thread(machine, 0, pid);
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, wakee))

@@ -1070,7 +1070,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (sched->profile_cpu == -1)
 		return 0;
 
-	migrant = machine__findnew_thread(machine, pid);
+	migrant = machine__findnew_thread(machine, 0, pid);
 	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))

@@ -1289,8 +1289,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, prev_pid);
-	sched_in = machine__findnew_thread(machine, next_pid);
+	sched_out = machine__findnew_thread(machine, 0, prev_pid);
+	sched_in = machine__findnew_thread(machine, 0, next_pid);
 
 	sched->curr_thread[this_cpu] = sched_in;
 

@@ -1425,7 +1425,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 						 struct perf_evsel *evsel,
 						 struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, sample->tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 	int err = 0;
 
 	if (thread == NULL) {

index ecb6979..b094b33 100644
@@ -480,7 +480,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct machine *machine)
 {
 	struct addr_location al;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
+	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
+							event->ip.tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",

index 0e4b67f..f8bc748 100644
@@ -301,7 +301,9 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	char *msg;
 	void *args;
 	size_t printed = 0;
-	struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+	struct thread *thread = machine__findnew_thread(&trace->host,
+							sample->pid,
+							sample->tid);
 	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
 	struct thread_trace *ttrace = thread__trace(thread);
 

@@ -344,7 +346,9 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 {
 	int ret;
 	u64 duration = 0;
-	struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+	struct thread *thread = machine__findnew_thread(&trace->host,
+							sample->pid,
+							sample->tid);
 	struct thread_trace *ttrace = thread__trace(thread);
 	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
 

@@ -397,7 +401,9 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 {
         u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
 	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
-	struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+	struct thread *thread = machine__findnew_thread(&trace->host,
+							sample->pid,
+							sample->tid);
 	struct thread_trace *ttrace = thread__trace(thread);
 
 	if (ttrace == NULL)

index 89085a9..5a178d5 100644
@@ -88,7 +88,8 @@ static struct machine *setup_fake_machine(struct machines *machines)
 	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
 		struct thread *thread;
 
-		thread = machine__findnew_thread(machine, fake_threads[i].pid);
+		thread = machine__findnew_thread(machine, fake_threads[i].pid,
+						 fake_threads[i].pid);
 		if (thread == NULL)
 			goto out;
 

index 5295625..0f9d27a 100644
@@ -24,7 +24,8 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
+							event->ip.pid);
 
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",

@@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 				       __maybe_unused,
 				       struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+	struct thread *thread = machine__findnew_thread(machine,
+							event->fork.pid,
+							event->fork.tid);
 
 	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
 		    event->fork.ppid, event->fork.ptid);

index 9541270..ec494a3 100644
@@ -677,7 +677,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  symbol_filter_t filter)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
+							event->ip.pid);
 
 	if (thread == NULL)
 		return -1;

index 67ba572..16b84ac 100644
@@ -30,7 +30,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		return -ENOMEM;
 
 	if (pid != HOST_KERNEL_ID) {
-		struct thread *thread = machine__findnew_thread(machine, pid);
+		struct thread *thread = machine__findnew_thread(machine, 0,
+								pid);
 		char comm[64];
 
 		if (thread == NULL)

@@ -282,9 +283,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid)
 {
-	return __machine__findnew_thread(machine, 0, tid, true);
+	return __machine__findnew_thread(machine, pid, tid, true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t tid)

@@ -294,7 +296,9 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+	struct thread *thread = machine__findnew_thread(machine,
+							event->comm.pid,
+							event->comm.tid);
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);

@@ -975,7 +979,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 		return 0;
 	}
 
-	thread = machine__findnew_thread(machine, event->mmap.pid);
+	thread = machine__findnew_thread(machine, event->mmap.pid,
+					 event->mmap.pid);
 	if (thread == NULL)
 		goto out_problem;
 

@@ -1002,8 +1007,12 @@ out_problem:
 
 int machine__process_fork_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
-	struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+	struct thread *thread = machine__findnew_thread(machine,
+							event->fork.pid,
+							event->fork.tid);
+	struct thread *parent = machine__findnew_thread(machine,
+							event->fork.ppid,
+							event->fork.ptid);
 
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);

index 5bb6244..604be6b 100644
@@ -101,7 +101,8 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+				       pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 

index d4c9a26..708c72b 100644
@@ -991,7 +991,7 @@ void perf_event_header__bswap(struct perf_event_header *self)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-	return machine__findnew_thread(&session->machines.host, pid);
+	return machine__findnew_thread(&session->machines.host, 0, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)

index 724b75a..20e2ed9 100644
@@ -1114,24 +1114,38 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
 	return 0;
 }
 
-static bool sample_overlap(const union perf_event *event,
-			   const void *offset, u64 size)
+static inline bool overflow_one(const void *endp, const void *offset)
 {
-	const void *base = event;
-
-	if (offset + size > base + event->header.size)
-		return true;
+	return offset + sizeof(u64) > endp;
+}
 
-	return false;
+static inline bool overflow(const void *endp, u16 max_size, const void *offset,
+			    u64 size)
+{
+	return size > max_size || offset + size > endp;
 }
 
+#define OVERFLOW_CHECK_ONE(offset)				\
+	do {							\
+		if (overflow_one(endp, (offset)))		\
+			return -EFAULT;				\
+	} while (0)
+
+#define OVERFLOW_CHECK(offset, size)				\
+	do {							\
+		if (overflow(endp, max_size, (offset), (size)))	\
+			return -EFAULT;				\
+	} while (0)
+
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
 	u64 type = evsel->attr.sample_type;
-	u64 regs_user = evsel->attr.sample_regs_user;
 	bool swapped = evsel->needs_swap;
 	const u64 *array;
+	u16 max_size = event->header.size;
+	const void *endp = (void *)event + max_size;
+	u64 sz;
 
 	/*
 	 * used for cross-endian analysis. See git commit 65014ab3

@@ -1153,6 +1167,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	array = event->sample.array;
 
+	/*
+	 * sample_size is based on PERF_SAMPLE_MASK which includes up to
+	 * PERF_SAMPLE_PERIOD.  After that overflow_one() or overflow() must be
+	 * used to check the format does not go past the end of the event.
+	 */
 	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 

@@ -1221,20 +1240,19 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
-		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
-			return -EFAULT;
-
-		data->callchain = (struct ip_callchain *)array;
+		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
-		if (sample_overlap(event, array, data->callchain->nr))
+		OVERFLOW_CHECK_ONE(array);
+		data->callchain = (struct ip_callchain *)array++;
+		if (data->callchain->nr > max_callchain_nr)
 			return -EFAULT;
-
-		array += 1 + data->callchain->nr;
+		sz = data->callchain->nr * sizeof(u64);
+		OVERFLOW_CHECK(array, sz);
+		array = (void *)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		const u64 *pdata;
-
+		OVERFLOW_CHECK_ONE(array);
 		u.val64 = *array;
 		if (WARN_ONCE(swapped,
 			      "Endianness of raw data not corrected!\n")) {

@@ -1243,65 +1261,73 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
 		}
-
-		if (sample_overlap(event, array, sizeof(u32)))
-			return -EFAULT;
-
 		data->raw_size = u.val32[0];
-		pdata = (void *) array + sizeof(u32);
+		array = (void *)array + sizeof(u32);
 
-		if (sample_overlap(event, pdata, data->raw_size))
-			return -EFAULT;
-
-		data->raw_data = (void *) pdata;
-
-		array = (void *)array + data->raw_size + sizeof(u32);
+		OVERFLOW_CHECK(array, data->raw_size);
+		data->raw_data = (void *)array;
+		array = (void *)array + data->raw_size;
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		u64 sz;
+		const u64 max_branch_nr = UINT64_MAX /
+					  sizeof(struct branch_entry);
 
-		data->branch_stack = (struct branch_stack *)array;
-		array++; /* nr */
+		OVERFLOW_CHECK_ONE(array);
+		data->branch_stack = (struct branch_stack *)array++;
 
+		if (data->branch_stack->nr > max_branch_nr)
+			return -EFAULT;
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
-		sz /= sizeof(u64);
-		array += sz;
+		OVERFLOW_CHECK(array, sz);
+		array = (void *)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
+		u64 avail;
+
 		/* First u64 tells us if we have any regs in sample. */
-		u64 avail = *array++;
+		OVERFLOW_CHECK_ONE(array);
+		avail = *array++;
 
 		if (avail) {
+			u64 regs_user = evsel->attr.sample_regs_user;
+
+			sz = hweight_long(regs_user) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz);
 			data->user_regs.regs = (u64 *)array;
-			array += hweight_long(regs_user);
+			array = (void *)array + sz;
 		}
 	}
 
 	if (type & PERF_SAMPLE_STACK_USER) {
-		u64 size = *array++;
+		OVERFLOW_CHECK_ONE(array);
+		sz = *array++;
 
 		data->user_stack.offset = ((char *)(array - 1)
 					  - (char *) event);
 
-		if (!size) {
+		if (!sz) {
 			data->user_stack.size = 0;
 		} else {
+			OVERFLOW_CHECK(array, sz);
 			data->user_stack.data = (char *)array;
-			array += size / sizeof(*array);
+			array = (void *)array + sz;
+			OVERFLOW_CHECK_ONE(array);
 			data->user_stack.size = *array++;
 		}
 	}
 
 	data->weight = 0;
 	if (type & PERF_SAMPLE_WEIGHT) {
+		OVERFLOW_CHECK_ONE(array);
 		data->weight = *array;
 		array++;
 	}
 
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	if (type & PERF_SAMPLE_DATA_SRC) {
+		OVERFLOW_CHECK_ONE(array);
 		data->data_src = *array;
 		array++;
 	}

index 42b6a63..024162a 100644
@@ -20,14 +20,6 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event)
-{
-	unsigned int chain_size = event->header.size;
-	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-	return chain->nr * sizeof(u64) <= chain_size;
-}
-
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, siblings)
 

index 3ee9f67..988c1aa 100644
@@ -103,11 +103,6 @@ int callchain_append(struct callchain_root *root,
 int callchain_merge(struct callchain_cursor *cursor,
 		    struct callchain_root *dst, struct callchain_root *src);
 
-struct ip_callchain;
-union perf_event;
-
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event);
 /*
  * Initialize a cursor before adding entries inside, but keep
  * the previously allocated entries as a cache.

index 708c72b..1b07d7a 100644
@@ -889,22 +889,6 @@ static int perf_session_deliver_event(struct perf_session *session,
 	}
 }
 
-static int perf_session__preprocess_sample(struct perf_session *session,
-					   union perf_event *event, struct perf_sample *sample)
-{
-	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !sample->callchain)
-		return 0;
-
-	if (!ip_callchain__valid(sample->callchain, event)) {
-		pr_debug("call-chain problem with event, skipping it.\n");
-		++session->stats.nr_invalid_chains;
-		session->stats.total_invalid_chains += sample->period;
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
 					    struct perf_tool *tool, u64 file_offset)
 {

@@ -967,10 +951,6 @@ static int perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	/* Preprocess sample records - precheck callchains */
-	if (perf_session__preprocess_sample(session, event, &sample))
-		return 0;
-
 	if (tool->ordered_samples) {
 		ret = perf_session_queue_event(session, event, &sample,
 					       file_offset);

index 0d4ae1d..ffacd46 100644
@@ -198,7 +198,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread = machine__findnew_thread(machine, event->ip.pid, event->ip.pid);
+	thread = machine__findnew_thread(machine, sample->pid, sample->pid);
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);

@@ -206,7 +206,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {

index c324778..c2dff9c 100644
@@ -305,8 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
-							event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",

index a8ff6d2..4274680 100644
@@ -96,7 +96,7 @@ dump_raw_samples(struct perf_tool *tool,
 		symbol_conf.field_sep,
 		sample->tid,
 		symbol_conf.field_sep,
-		event->ip.ip,
+		sample->ip,
 		symbol_conf.field_sep,
 		sample->addr,
 		symbol_conf.field_sep,

index b094b33..05e1db2 100644
@@ -480,8 +480,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct machine *machine)
 {
 	struct addr_location al;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
-							event->ip.tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",

index bbf4635..0ecec5f 100644
@@ -690,7 +690,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
 	struct symbol *parent = NULL;
-	u64 ip = event->ip.ip;
+	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 

@@ -700,10 +700,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		if (!seen)
 			seen = intlist__new(NULL);
 
-		if (!intlist__has_entry(seen, event->ip.pid)) {
+		if (!intlist__has_entry(seen, sample->pid)) {
 			pr_err("Can't find guest [%d]'s kernel information\n",
-				event->ip.pid);
-			intlist__add(seen, event->ip.pid);
+				sample->pid);
+			intlist__add(seen, sample->pid);
 		}
 		return;
 	}

@@ -838,7 +838,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
 			++top->guest_kernel_samples;
-			machine = perf_session__find_machine(session, event->ip.pid);
+			machine = perf_session__find_machine(session,
+							     sample.pid);
 			break;
 		case PERF_RECORD_MISC_GUEST_USER:
 			++top->guest_us_samples;

index 5a178d5..7e0ca15 100644
@@ -220,6 +220,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				},
 			};
 
+			sample.pid = ip_event.ip.pid;
+			sample.ip = ip_event.ip.ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;

@@ -244,6 +246,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				},
 			};
 
+			sample.pid = ip_event.ip.pid;
+			sample.ip = ip_event.ip.ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;

index 0f9d27a..fb58409 100644
@@ -18,14 +18,14 @@
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
-			   struct perf_sample *sample __maybe_unused,
+			   struct perf_sample *sample,
 			   struct perf_evsel *evsel __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
-							event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",

@@ -34,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;

index ec494a3..6861d19 100644
@@ -677,8 +677,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  symbol_filter_t filter)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid,
-							event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid,
+							sample->pid);
 
 	if (thread == NULL)
 		return -1;

@@ -700,7 +700,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 		machine__create_kernel_maps(machine);
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, al);
+			      sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");

156 lines not on this page · raw message

index 1b07d7a..eea5eef 100644
@@ -802,7 +802,8 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 static struct machine *
 	perf_session__find_machine_for_cpumode(struct perf_session *session,
-					       union perf_event *event)
+					       union perf_event *event,
+					       struct perf_sample *sample)
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 

@@ -814,7 +815,7 @@ static struct machine *
 		if (event->header.type == PERF_RECORD_MMAP)
 			pid = event->mmap.pid;
 		else
-			pid = event->ip.pid;
+			pid = sample->pid;
 
 		return perf_session__findnew_machine(session, pid);
 	}

@@ -851,7 +852,8 @@ static int perf_session_deliver_event(struct perf_session *session,
 		hists__inc_nr_events(&evsel->hists, event->header.type);
 	}
 
-	machine = perf_session__find_machine_for_cpumode(session, event);
+	machine = perf_session__find_machine_for_cpumode(session, event,
+							 sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:

index 7e0ca15..cfdbfd9 100644
@@ -195,6 +195,19 @@ static struct sample fake_samples[][5] = {
 	},
 };
 
+/* PERF_SAMPLE_IP | PERF_SAMPLE_TID | * but not PERF_SAMPLE_IDENTIFIER */
+struct ip_event {
+	struct perf_event_header header;
+	u64 ip;
+	u32 pid, tid;
+	unsigned char __more_data[];
+};
+
+union perf_ip_event {
+	struct ip_event ip;
+	union perf_event event;
+};
+
 static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 {
 	struct perf_evsel *evsel;

@@ -210,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 */
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
-			const union perf_event event = {
+			const union perf_ip_event ip_event = {
 				.ip = {
 					.header = {
 						.misc = PERF_RECORD_MISC_USER,

@@ -219,10 +232,11 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.ip  = fake_common_samples[k].ip,
 				},
 			};
+			const union perf_event *event = &ip_event.event;
 
 			sample.pid = ip_event.ip.pid;
 			sample.ip = ip_event.ip.ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
+			if (perf_event__preprocess_sample(event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
 

@@ -236,7 +250,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 		}
 
 		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
-			const union perf_event event = {
+			const union perf_ip_event ip_event = {
 				.ip = {
 					.header = {
 						.misc = PERF_RECORD_MISC_USER,

@@ -245,10 +259,11 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.ip  = fake_samples[i][k].ip,
 				},
 			};
+			const union perf_event *event = &ip_event.event;
 
 			sample.pid = ip_event.ip.pid;
 			sample.ip = ip_event.ip.ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
+			if (perf_event__preprocess_sample(event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
 

index e60585e..94f4503 100644
@@ -8,16 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 
-/*
- * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
- */
-struct ip_event {
-	struct perf_event_header header;
-	u64 ip;
-	u32 pid, tid;
-	unsigned char __more_data[];
-};
-
 struct mmap_event {
 	struct perf_event_header header;
 	u32 pid, tid;

@@ -162,7 +152,6 @@ struct tracing_data_event {
 
 union perf_event {
 	struct perf_event_header	header;
-	struct ip_event			ip;
 	struct mmap_event		mmap;
 	struct comm_event		comm;
 	struct fork_event		fork;

index 0b1df41..876a18c 100644
@@ -478,6 +478,16 @@ enum perf_event_type {
 	 * file will be supported by older perf tools, with these new optional
 	 * fields being ignored.
 	 *
+	 * struct sample_id {
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			id;       } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 * } && perf_event_attr.sample_id_all
+	 */
+
+	/*
 	 * The MMAP events record the PROT_EXEC mappings so that we can
 	 * correlate userspace IPs to code. They have the following structure:
 	 *

@@ -489,6 +499,7 @@ enum perf_event_type {
 	 *	u64				len;
 	 *	u64				pgoff;
 	 *	char				filename[];
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_MMAP			= 1,

@@ -498,6 +509,7 @@ enum perf_event_type {
 	 *	struct perf_event_header	header;
 	 *	u64				id;
 	 *	u64				lost;
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_LOST			= 2,

@@ -508,6 +520,7 @@ enum perf_event_type {
 	 *
 	 *	u32				pid, tid;
 	 *	char				comm[];
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_COMM			= 3,

@@ -518,6 +531,7 @@ enum perf_event_type {
 	 *	u32				pid, ppid;
 	 *	u32				tid, ptid;
 	 *	u64				time;
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_EXIT			= 4,

@@ -528,6 +542,7 @@ enum perf_event_type {
 	 *	u64				time;
 	 *	u64				id;
 	 *	u64				stream_id;
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_THROTTLE			= 5,

@@ -539,6 +554,7 @@ enum perf_event_type {
 	 *	u32				pid, ppid;
 	 *	u32				tid, ptid;
 	 *	u64				time;
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_FORK			= 7,

@@ -549,6 +565,7 @@ enum perf_event_type {
 	 *	u32				pid, tid;
 	 *
 	 *	struct read_format		values;
+	 *	struct sample_id		sample_id;
 	 * };
 	 */
 	PERF_RECORD_READ			= 8,

@@ -596,7 +613,7 @@ enum perf_event_type {
 	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
 	 *
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
-	 *	{ u64			data_src;     } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

index 708ab70..c9ef899 100644
@@ -4462,20 +4462,6 @@ void perf_output_sample(struct perf_output_handle *handle,
 		}
 	}
 
-	if (!event->attr.watermark) {
-		int wakeup_events = event->attr.wakeup_events;
-
-		if (wakeup_events) {
-			struct ring_buffer *rb = handle->rb;
-			int events = local_inc_return(&rb->events);
-
-			if (events >= wakeup_events) {
-				local_sub(wakeup_events, &rb->events);
-				local_inc(&rb->wakeup);
-			}
-		}
-	}
-
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
 		if (data->br_stack) {
 			size_t size;

@@ -4511,16 +4497,31 @@ void perf_output_sample(struct perf_output_handle *handle,
 		}
 	}
 
-	if (sample_type & PERF_SAMPLE_STACK_USER)
+	if (sample_type & PERF_SAMPLE_STACK_USER) {
 		perf_output_sample_ustack(handle,
 					  data->stack_user_size,
 					  data->regs_user.regs);
+	}
 
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		perf_output_put(handle, data->weight);
 
 	if (sample_type & PERF_SAMPLE_DATA_SRC)
 		perf_output_put(handle, data->data_src.val);
+
+	if (!event->attr.watermark) {
+		int wakeup_events = event->attr.wakeup_events;
+
+		if (wakeup_events) {
+			struct ring_buffer *rb = handle->rb;
+			int events = local_inc_return(&rb->events);
+
+			if (events >= wakeup_events) {
+				local_sub(wakeup_events, &rb->events);
+				local_inc(&rb->wakeup);
+			}
+		}
+	}
 }
 
 void perf_prepare_sample(struct perf_event_header *header,

index 876a18c..71f1ad3 100644
@@ -134,8 +134,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 
-	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
 };
 
 /*

@@ -471,12 +472,12 @@ enum perf_event_type {
 	/*
 	 * If perf_event_attr.sample_id_all is set then all event types will
 	 * have the sample_type selected fields related to where/when
-	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
-	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
-	 * the perf_event_header and the fields already present for the existing
-	 * fields, i.e. at the end of the payload. That way a newer perf.data
-	 * file will be supported by older perf tools, with these new optional
-	 * fields being ignored.
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
 	 *
 	 * struct sample_id {
 	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID

@@ -484,7 +485,12 @@ enum perf_event_type {
 	 *	{ u64			id;       } && PERF_SAMPLE_ID
 	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
 	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 * } && perf_event_attr.sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
 	 */
 
 	/*

@@ -574,6 +580,13 @@ enum perf_event_type {
 	 * struct {
 	 *	struct perf_event_header	header;
 	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
 	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
 	 *	{ u64			time;     } && PERF_SAMPLE_TIME

index c9ef899..91c241d 100644
@@ -1216,6 +1216,9 @@ static void perf_event__id_header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_TIME)
 		size += sizeof(data->time);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
+
 	if (sample_type & PERF_SAMPLE_ID)
 		size += sizeof(data->id);
 

@@ -4251,7 +4254,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_TIME)
 		data->time = perf_clock();
 
-	if (sample_type & PERF_SAMPLE_ID)
+	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
 		data->id = primary_event_id(event);
 
 	if (sample_type & PERF_SAMPLE_STREAM_ID)

@@ -4290,6 +4293,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		perf_output_put(handle, data->cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
 }
 
 void perf_event__output_id_sample(struct perf_event *event,

@@ -4402,6 +4408,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	perf_output_put(handle, *header);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
+
 	if (sample_type & PERF_SAMPLE_IP)
 		perf_output_put(handle, data->ip);
 

index b8a5a75..ee6a8f1 100644
@@ -89,30 +89,6 @@ void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist)
 	perf_evlist__set_id_pos(evlist);
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-			struct perf_record_opts *opts)
-{
-	struct perf_evsel *evsel;
-	/*
-	 * Set the evsel leader links before we configure attributes,
-	 * since some might depend on this info.
-	 */
-	if (opts->group)
-		perf_evlist__set_leader(evlist);
-
-	if (evlist->cpus->map[0] < 0)
-		opts->no_inherit = true;
-
-	list_for_each_entry(evsel, &evlist->entries, node) {
-		perf_evsel__config(evsel, opts);
-
-		if (evlist->nr_entries > 1)
-			perf_evsel__set_sample_id(evsel);
-	}
-
-	perf_evlist__make_sample_types_compatible(evlist);
-}
-
 static void perf_evlist__purge(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos, *n;

new file mode 100644
index 0000000..67291e4
@@ -0,0 +1,27 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "cpumap.h"
+
+void perf_evlist__config(struct perf_evlist *evlist,
+			 struct perf_record_opts *opts)
+{
+	struct perf_evsel *evsel;
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
+	if (opts->group)
+		perf_evlist__set_leader(evlist);
+
+	if (evlist->cpus->map[0] < 0)
+		opts->no_inherit = true;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		perf_evsel__config(evsel, opts);
+
+		if (evlist->nr_entries > 1)
+			perf_evsel__set_sample_id(evsel);
+	}
+
+	perf_evlist__make_sample_types_compatible(evlist);
+}

index 5b1b5ab..c4185b9 100644
@@ -72,7 +72,7 @@ int test__basic_mmap(void)
 		}
 
 		evsels[i]->attr.wakeup_events = 1;
-		perf_evsel__set_sample_id(evsels[i]);
+		perf_evsel__set_sample_id(evsels[i], false);
 
 		perf_evlist__add(evlist, evsels[i]);
 

index 94f4503..82bad0d 100644
@@ -53,7 +53,8 @@ struct read_event {
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
 	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
-	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
+	 PERF_SAMPLE_IDENTIFIER)
 
 /*
  * Events have compatible sample types if the following bits all have the same

@@ -61,13 +62,15 @@ struct read_event {
  * events the order is: PERF_SAMPLE_IP, PERF_SAMPLE_TID, PERF_SAMPLE_TIME,
  * PERF_SAMPLE_ADDR, PERF_SAMPLE_ID.  For non-sample events the sample members
  * are accessed in reverse order.  The order is: PERF_SAMPLE_ID,
- * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.
+ * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.  PERF_SAMPLE_IDENTIFIER is added for
+ * completeness but it should not be used with PERF_SAMPLE_ID.  Sample types
+ * that include PERF_SAMPLE_IDENTIFIER are always compatible.
  */
 #define PERF_COMPAT_MASK				\
 	(PERF_SAMPLE_IP   | PERF_SAMPLE_TID       |	\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR      |	\
 	 PERF_SAMPLE_ID   | PERF_SAMPLE_STREAM_ID |	\
-	 PERF_SAMPLE_CPU)
+	 PERF_SAMPLE_CPU  | PERF_SAMPLE_IDENTIFIER)
 
 struct sample_event {
 	struct perf_event_header        header;

index ee6a8f1..49ea13c 100644
@@ -56,7 +56,7 @@ struct perf_evlist *perf_evlist__new(void)
  * Events with compatible sample types all have the same id_pos
  * and is_pos.  For convenience, put a copy on evlist.
  */
-static void perf_evlist__set_id_pos(struct perf_evlist *evlist)
+void perf_evlist__set_id_pos(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist);
 

@@ -790,6 +790,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		size += sizeof(data->cpu) * 2;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
 out:
 	return size;
 }

index b1be475..18b968c3 100644
@@ -87,7 +87,9 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist);
+bool perf_can_sample_identifier(void);
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 

100 lines not on this page · raw message

index c6d616c..bca8e5f 100644
@@ -148,7 +148,8 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 #define perf_evsel__reset_sample_bit(evsel, bit) \
 	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool use_sample_identifier);
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			   const char *filter);

112 lines not on this page · raw message

index ffacd46..eb33da6 100644
@@ -301,7 +301,8 @@ found:
 	sample_sw.period = sample->period;
 	sample_sw.time	 = sample->time;
 	perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-				      &sample_sw, false);
+				      evsel->attr.sample_regs_user, &sample_sw,
+				      false);
 	build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
 	return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }

index 82bad0d..7f5c36b 100644
@@ -228,6 +228,7 @@ int perf_event__preprocess_sample(const union perf_event *self,
 const char *perf_event__name(unsigned int id);
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
+				  u64 sample_regs_user,
 				  const struct perf_sample *sample,
 				  bool swapped);
 

86 lines not on this page · raw message

index 7f5c36b..c49cb4c 100644
@@ -227,6 +227,8 @@ int perf_event__preprocess_sample(const union perf_event *self,
 
 const char *perf_event__name(unsigned int id);
 
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+				     u64 sample_regs_user);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  u64 sample_regs_user,
 				  const struct perf_sample *sample,

87 lines not on this page · raw message

index 35b45f1466..5ee3933 100644
@@ -94,6 +94,10 @@ static struct test {
 		.func = test__sw_clock_freq,
 	},
 	{
+		.desc = "Test sample parsing",
+		.func = test__sample_parsing,
+	},
+	{
 		.func = NULL,
 	},
 };

263 lines not on this page · raw message

index 07a92f9..90e3056 100644
@@ -35,5 +35,6 @@ int test__bp_signal(void);
 int test__bp_signal_overflow(void);
 int test__task_exit(void);
 int test__sw_clock_freq(void);
+int test__sample_parsing(void);
 
 #endif /* TESTS_H */