Merge branch 'perf-fixes-for-linus-2' of...

Merge branch 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  perf: Fix crash in swevents
  perf buildid-list: Fix --with-hits event processing
  perf scripts python: Give field dict to unhandled callback
  perf hist: fix objdump output parsing
  perf-record: Check correct pid when forking
  perf: Do the comm inheritance per thread in event__process_task
  perf: Use event__process_task from perf sched
  perf: Process comm events by tid
  blktrace: Fix new kernel-doc warnings
  perf_events: Fix unincremented buffer base on partial copy
  perf_events: Fix event scheduling issues introduced by transactional API
  perf_events, trace: Fix perf_trace_destroy(), mutex went missing
  perf_events, trace: Fix probe unregister race
  perf_events: Fix races in group composition
  perf_events: Fix races and clean up perf_event and perf_mmap_data interaction

arch/x86/kernel/cpu/perf_event.c

@@ -106,6 +106,7 @@ struct cpu_hw_events {
 
 	int			n_events;
 	int			n_added;
+	int			n_txn;
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
@@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event)
 out:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
+	cpuc->n_txn += n - n0;
 
 	return 0;
 }
@@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;
 
+	/*
+	 * If we're called during a txn, we don't need to do anything.
+	 * The events never got scheduled and ->cancel_txn will truncate
+	 * the event_list.
+	 */
+	if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+		return;
+
 	x86_pmu_stop(event);
 
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+	cpuc->n_txn = 0;
 }
 
 /*
@@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+	/*
+	 * Truncate the collected events.
+	 */
+	cpuc->n_added -= cpuc->n_txn;
+	cpuc->n_events -= cpuc->n_txn;
 }
 
 /*
@@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
+	/*
+	 * Clear out the txn count so that ->cancel_txn() which gets
+	 * run after ->commit_txn() doesn't undo things.
+	 */
+	cpuc->n_txn = 0;
+
 	return 0;
 }
 

include/linux/perf_event.h

@@ -585,6 +585,7 @@ enum perf_event_active_state {
 struct file;
 
 struct perf_mmap_data {
+	atomic_t			refcount;
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
@@ -592,7 +593,6 @@ struct perf_mmap_data {
 #endif
 	int				nr_pages;	/* nr of data pages  */
 	int				writable;	/* are we writable   */
-	int				nr_locked;	/* nr pages mlocked  */
 
 	atomic_t			poll;		/* POLL_ for wakeups */
 
@@ -631,6 +631,9 @@ struct swevent_hlist {
 	struct rcu_head		rcu_head;
 };
 
+#define PERF_ATTACH_CONTEXT	0x01
+#define PERF_ATTACH_GROUP	0x02
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -643,10 +646,10 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	struct perf_event		*output;
 	const struct pmu		*pmu;
 
 	enum perf_event_active_state	state;
+	unsigned int			attach_state;
 	atomic64_t			count;
 
 	/*
@@ -704,6 +707,8 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
+	int				mmap_locked;
+	struct user_struct		*mmap_user;
 	struct perf_mmap_data		*data;
 
 	/* poll related */

include/trace/ftrace.h

@@ -725,7 +725,7 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	{ assign; }							\
 									\
-	head = per_cpu_ptr(event_call->perf_events, smp_processor_id());\
+	head = this_cpu_ptr(event_call->perf_events);			\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 		__count, &__regs, head);				\
 }

kernel/trace/blktrace.c

@@ -842,6 +842,7 @@ static void blk_add_trace_split(void *ignore,
 
 /**
  * blk_add_trace_remap - Add a trace for a remap operation
+ * @ignore:	trace callback data parameter (not used)
  * @q:		queue the io is for
  * @bio:	the source bio
  * @dev:	target device
@@ -873,6 +874,7 @@ static void blk_add_trace_remap(void *ignore,
 
 /**
  * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @ignore:	trace callback data parameter (not used)
  * @q:		queue the io is for
  * @rq:		the source request
  * @dev:	target device

kernel/trace/trace_event_perf.c

@@ -116,7 +116,7 @@ int perf_trace_enable(struct perf_event *p_event)
 	if (WARN_ON_ONCE(!list))
 		return -EINVAL;
 
-	list = per_cpu_ptr(list, smp_processor_id());
+	list = this_cpu_ptr(list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
@@ -132,8 +132,9 @@ void perf_trace_destroy(struct perf_event *p_event)
 	struct ftrace_event_call *tp_event = p_event->tp_event;
 	int i;
 
+	mutex_lock(&event_mutex);
 	if (--tp_event->perf_refcount > 0)
-		return;
+		goto out;
 
 	if (tp_event->class->reg)
 		tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
@@ -142,6 +143,12 @@ void perf_trace_destroy(struct perf_event *p_event)
 					    tp_event->class->perf_probe,
 					    tp_event);
 
+	/*
+	 * Ensure our callback won't be called anymore. See
+	 * tracepoint_probe_unregister() and __DO_TRACE().
+	 */
+	synchronize_sched();
+
 	free_percpu(tp_event->perf_events);
 	tp_event->perf_events = NULL;
 
@@ -151,6 +158,8 @@ void perf_trace_destroy(struct perf_event *p_event)
 			perf_trace_buf[i] = NULL;
 		}
 	}
+out:
+	mutex_unlock(&event_mutex);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@@ -169,7 +178,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	if (*rctxp < 0)
 		return NULL;
 
-	raw_data = per_cpu_ptr(perf_trace_buf[*rctxp], smp_processor_id());
+	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 
 	/* zero the dead bytes from align to not leak stack to user */
 	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));

kernel/trace/trace_kprobe.c

@@ -1359,7 +1359,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
 }
 
@@ -1392,7 +1392,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	for (i = 0; i < tp->nr_args; i++)
 		call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-	head = per_cpu_ptr(call->perf_events, smp_processor_id());
+	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
 

kernel/trace/trace_syscalls.c

@@ -519,7 +519,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
 
-	head = per_cpu_ptr(sys_data->enter_event->perf_events, smp_processor_id());
+	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
 }
 
@@ -595,7 +595,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	head = per_cpu_ptr(sys_data->exit_event->perf_events, smp_processor_id());
+	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
 }
 

tools/perf/builtin-buildid-list.c

@@ -43,8 +43,10 @@ static int __cmd_buildid_list(void)
 	if (session == NULL)
 		return -1;
 
-	if (with_hits)
+	if (with_hits) {
+		symbol_conf.full_paths = true;
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+	}
 
 	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 

tools/perf/builtin-record.c

@@ -503,7 +503,6 @@ static int __cmd_record(int argc, const char **argv)
 {
 	int i, counter;
 	struct stat st;
-	pid_t pid = 0;
 	int flags;
 	int err;
 	unsigned long waking = 0;
@@ -572,7 +571,7 @@ static int __cmd_record(int argc, const char **argv)
 
 	if (forks) {
 		child_pid = fork();
-		if (pid < 0) {
+		if (child_pid < 0) {
 			perror("failed to fork");
 			exit(-1);
 		}

tools/perf/builtin-sched.c

@@ -1645,6 +1645,7 @@ static struct perf_event_ops event_ops = {
 	.sample			= process_sample_event,
 	.comm			= event__process_comm,
 	.lost			= event__process_lost,
+	.fork			= event__process_task,
 	.ordered_samples	= true,
 };
 

tools/perf/scripts/python/check-perf-trace.py

@@ -51,8 +51,7 @@ def kmem__kmalloc(event_name, context, common_cpu,
 
 		flag_str("kmem__kmalloc", "gfp_flags", gfp_flags)),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     try:
         unhandled[event_name] += 1
     except TypeError:

tools/perf/util/event.c

@@ -370,9 +370,9 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm)
 
 int event__process_comm(event_t *self, struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->comm.pid);
+	struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
-	dump_printf(": %s:%d\n", self->comm.comm, self->comm.pid);
+	dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
 
 	if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
@@ -532,16 +532,11 @@ int event__process_mmap(event_t *self, struct perf_session *session)
 
 int event__process_task(event_t *self, struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, self->fork.pid);
-	struct thread *parent = perf_session__findnew(session, self->fork.ppid);
+	struct thread *thread = perf_session__findnew(session, self->fork.tid);
+	struct thread *parent = perf_session__findnew(session, self->fork.ptid);
 
 	dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
 		    self->fork.ppid, self->fork.ptid);
-	/*
-	 * A thread clone will have the same PID for both parent and child.
-	 */
-	if (thread == parent)
-		return 0;
 
 	if (self->header.type == PERF_RECORD_EXIT)
 		return 0;

tools/perf/util/hist.c

@@ -965,7 +965,7 @@ static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
 		 * Parse hexa addresses followed by ':'
 		 */
 		line_ip = strtoull(tmp, &tmp2, 16);
-		if (*tmp2 != ':')
+		if (*tmp2 != ':' || tmp == tmp2)
 			line_ip = -1;
 	}
 

tools/perf/util/scripting-engines/trace-event-python.c

@@ -208,7 +208,7 @@ static void python_process_event(int cpu, void *data,
 				 int size __unused,
 				 unsigned long long nsecs, char *comm)
 {
-	PyObject *handler, *retval, *context, *t, *obj;
+	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long long val;
@@ -232,6 +232,14 @@ static void python_process_event(int cpu, void *data,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		handler = NULL;
+	if (!handler) {
+		dict = PyDict_New();
+		if (!dict)
+			Py_FatalError("couldn't create Python dict");
+	}
 	s = nsecs / NSECS_PER_SEC;
 	ns = nsecs - s * NSECS_PER_SEC;
 
@@ -242,12 +250,20 @@ static void python_process_event(int cpu, void *data,
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
 	PyTuple_SetItem(t, n++,
 			PyCObject_FromVoidPtr(scripting_context, NULL));
+
+	if (handler) {
 		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(s));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
-
+	} else {
+		PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
+		PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
+		PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
+		PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
+		PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
 			int offset;
@@ -272,27 +288,31 @@ static void python_process_event(int cpu, void *data,
 					obj = PyLong_FromUnsignedLongLong(val);
 			}
 		}
+		if (handler)
 			PyTuple_SetItem(t, n++, obj);
+		else
+			PyDict_SetItemString(dict, field->name, obj);
+
 	}
+	if (!handler)
+		PyTuple_SetItem(t, n++, dict);
 
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
+	if (handler) {
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
 	} else {
 		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
 		if (handler && PyCallable_Check(handler)) {
-			if (_PyTuple_Resize(&t, N_COMMON_FIELDS) == -1)
-				Py_FatalError("error resizing Python tuple");
 
 			retval = PyObject_CallObject(handler, t);
 			if (retval == NULL)
 				handler_call_die("trace_unhandled");
 		}
+		Py_DECREF(dict);
 	}
 
 	Py_DECREF(t);
@@ -548,12 +568,10 @@ static int python_generate_script(const char *outfile)
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
-		"common_cpu, common_secs, common_nsecs,\n\t\t"
-		"common_pid, common_comm):\n");
+		"event_fields_dict):\n");
 
-	fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
-		"common_secs, common_nsecs,\n\t\tcommon_pid, "
-		"common_comm)\n\n");
+	fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))"
+		"for k,v in sorted(event_fields_dict.items())])\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"