1 files changed, 136 insertions, 41 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 555247568e7a..b97b41c7655c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -54,6 +54,7 @@
 #define COMM_LEN		20
 #define SYM_LEN			129
 #define MAX_PID			1024000
+#define PID_MAX_LIMIT		4194304 /* kernel limit on 64-bit */
 #define MAX_PRIO		140
 #define SEP_LEN			100
 
@@ -273,6 +274,7 @@ struct thread_runtime {
 	u64 migrations;
 
 	int prio;
+	bool color;
 };
 
 /* per event run time data */
@@ -364,14 +366,25 @@ get_new_event(struct task_desc *task, u64 timestamp)
 	struct sched_atom *event = zalloc(sizeof(*event));
 	unsigned long idx = task->nr_events;
 	size_t size;
+	struct sched_atom **atoms_p;
+
+	if (event == NULL) {
+		pr_err("ERROR: sched: failed to allocate event\n");
+		return NULL;
+	}
 
 	event->timestamp = timestamp;
 	event->nr = idx;
 
+	size = sizeof(struct sched_atom *) * (task->nr_events + 1);
+	atoms_p = realloc(task->atoms, size);
+	if (!atoms_p) {
+		pr_err("ERROR: sched: failed to grow atoms array\n");
+		free(event);
+		return NULL;
+	}
+	task->atoms = atoms_p;
 	task->nr_events++;
-	size = sizeof(struct sched_atom *) * task->nr_events;
-	task->atoms = realloc(task->atoms, size);
-	BUG_ON(!task->atoms);
 
 	task->atoms[idx] = event;
 
@@ -402,6 +415,8 @@ static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task
 	}
 
 	event = get_new_event(task, timestamp);
+	if (event == NULL)
+		return;
 
 	event->type = SCHED_EVENT_RUN;
 	event->duration = duration;
@@ -415,6 +430,8 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 	struct sched_atom *event, *wakee_event;
 
 	event = get_new_event(task, timestamp);
+	if (event == NULL)
+		return;
 	event->type = SCHED_EVENT_WAKEUP;
 	event->wakee = wakee;
 
@@ -429,6 +446,10 @@ static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *t
 	}
 
 	wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem));
+	if (!wakee_event->wait_sem) {
+		pr_err("ERROR: sched: failed to allocate semaphore\n");
+		return;
+	}
 	sem_init(wakee_event->wait_sem, 0, 0);
 	event->wait_sem = wakee_event->wait_sem;
 
@@ -440,6 +461,9 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *ta
 {
 	struct sched_atom *event = get_new_event(task, timestamp);
 
+	if (event == NULL)
+		return;
+
 	event->type = SCHED_EVENT_SLEEP;
 
 	sched->nr_sleep_events++;
@@ -448,17 +472,28 @@ static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *ta
 static struct task_desc *register_pid(struct perf_sched *sched,
 				      unsigned long pid, const char *comm)
 {
-	struct task_desc *task;
+	struct task_desc *task, **tasks_p;
 	static int pid_max;
 
+	/* perf.data is untrusted — cap pid to prevent overflow in size calculations */
+	if (pid >= PID_MAX_LIMIT) {
+		pr_err("pid %lu exceeds limit %d, skipping\n", pid, PID_MAX_LIMIT);
+		return NULL;
+	}
+
 	if (sched->pid_to_task == NULL) {
 		if (sysctl__read_int("kernel/pid_max", &pid_max) < 0)
 			pid_max = MAX_PID;
-		BUG_ON((sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *))) == NULL);
+		sched->pid_to_task = calloc(pid_max, sizeof(struct task_desc *));
+		if (sched->pid_to_task == NULL)
+			return NULL;
 	}
 	if (pid >= (unsigned long)pid_max) {
-		BUG_ON((sched->pid_to_task = realloc(sched->pid_to_task, (pid + 1) *
-			sizeof(struct task_desc *))) == NULL);
+		void *p = realloc(sched->pid_to_task, (pid + 1) * sizeof(struct task_desc *));
+
+		if (p == NULL)
+			return NULL;
+		sched->pid_to_task = p;
 		while (pid >= (unsigned long)pid_max)
 			sched->pid_to_task[pid_max++] = NULL;
 	}
@@ -469,9 +504,11 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 		return task;
 
 	task = zalloc(sizeof(*task));
+	if (task == NULL)
+		return NULL;
 	task->pid = pid;
-	task->nr = sched->nr_tasks;
-	strcpy(task->comm, comm);
+	if (comm)
+		strlcpy(task->comm, comm, sizeof(task->comm));
 	/*
 	 * every task starts in sleeping state - this gets ignored
 	 * if there's no wakeup pointing to this sleep state:
@@ -479,10 +516,12 @@ static struct task_desc *register_pid(struct perf_sched *sched,
 	add_sched_event_sleep(sched, task, 0);
 
 	sched->pid_to_task[pid] = task;
-	sched->nr_tasks++;
-	sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_desc *));
-	BUG_ON(!sched->tasks);
-	sched->tasks[task->nr] = task;
+	tasks_p = realloc(sched->tasks, (sched->nr_tasks + 1) * sizeof(struct task_desc *));
+	if (!tasks_p)
+		return NULL;
+	sched->tasks = tasks_p;
+	sched->tasks[sched->nr_tasks] = task;
+	task->nr = sched->nr_tasks++;
 
 	if (verbose > 0)
 		printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
@@ -841,6 +880,8 @@ replay_wakeup_event(struct perf_sched *sched,
 
 	waker = register_pid(sched, sample->tid, "<unknown>");
 	wakee = register_pid(sched, pid, comm);
+	if (waker == NULL || wakee == NULL)
+		return -1;
 
 	add_sched_event_wakeup(sched, waker, sample->time, wakee);
 	return 0;
@@ -882,6 +923,8 @@ static int replay_switch_event(struct perf_sched *sched,
 
 	prev = register_pid(sched, prev_pid, prev_comm);
 	next = register_pid(sched, next_pid, next_comm);
+	if (prev == NULL || next == NULL)
+		return -1;
 
 	sched->cpu_last_switched[cpu] = timestamp;
 
@@ -1147,7 +1190,12 @@ static int latency_switch_event(struct perf_sched *sched,
 	int cpu = sample->cpu, err = -1;
 	s64 delta;
 
-	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (cpu >= MAX_CPUS || cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, cpu);
+		return 0;
+	}
 
 	timestamp0 = sched->cpu_last_switched[cpu];
 	sched->cpu_last_switched[cpu] = timestamp;
@@ -1177,7 +1225,7 @@ static int latency_switch_event(struct perf_sched *sched,
 		}
 	}
 	if (add_sched_out_event(out_events, prev_state, timestamp))
-		return -1;
+		goto out_put;
 
 	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
@@ -1211,14 +1259,22 @@ static int latency_runtime_event(struct perf_sched *sched,
 	const u32 pid	   = evsel__intval(evsel, sample, "pid");
 	const u64 runtime  = evsel__intval(evsel, sample, "runtime");
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
-	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+	struct work_atoms *atoms;
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu, err = -1;
 
 	if (thread == NULL)
 		return -1;
 
-	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
+	atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
+
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (cpu >= MAX_CPUS || cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, cpu);
+		err = 0;
+		goto out_put;
+	}
 	if (!atoms) {
 		if (thread_atoms_insert(sched, thread))
 			goto out_put;
@@ -1541,22 +1597,32 @@ static int process_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unus
 
 static bool thread__has_color(struct thread *thread)
 {
-	return thread__priv(thread) != NULL;
+	struct thread_runtime *tr = thread__priv(thread);
+
+	return tr != NULL && tr->color;
 }
 
 static struct thread*
 map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid)
 {
 	struct thread *thread = machine__findnew_thread(machine, pid, tid);
-	bool color = false;
 
-	if (!sched->map.color_pids || !thread || thread__priv(thread))
+	if (!sched->map.color_pids || !thread)
 		return thread;
 
-	if (thread_map__has(sched->map.color_pids, tid))
-		color = true;
+	/*
+	 * Always check the color-pids map, even if thread__priv() is
+	 * already set.  COMM events processed before the first sched_switch
+	 * allocate a thread_runtime via thread__get_runtime(), so priv is
+	 * non-NULL before we ever get here.  Skipping the check on non-NULL
+	 * priv would prevent those threads from being colored.
+	 */
+	if (thread_map__has(sched->map.color_pids, tid)) {
+		struct thread_runtime *tr = thread__get_runtime(thread);
 
-	thread__set_priv(thread, color ? ((void*)1) : NULL);
+		if (tr)
+			tr->color = true;
+	}
 	return thread;
 }
 
@@ -1647,7 +1713,12 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	const char *str;
 	int ret = -1;
 
-	BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
+	/* perf.data is untrusted input — CPU may be absent or corrupted */
+	if (this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0) {
+		pr_warning("WARNING: at offset %#" PRIx64 ": out-of-bound sample CPU %d, skipping sample\n",
+			   sample->file_offset, this_cpu.cpu);
+		return 0;
+	}
 
 	if (this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
@@ -1659,7 +1730,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			new_cpu = true;
 		}
 	} else
-		cpus_nr = sched->max_cpu.cpu;
+		cpus_nr = sched->max_cpu.cpu + 1;
 
 	timestamp0 = sched->cpu_last_switched[this_cpu.cpu];
 	sched->cpu_last_switched[this_cpu.cpu] = timestamp;
@@ -2175,7 +2246,8 @@ static void timehist_print_sample(struct perf_sched *sched,
 	char nstr[30];
 	u64 wait_time;
 
-	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+	if (cpu_list && (sample->cpu >= MAX_NR_CPUS ||
+			!test_bit(sample->cpu, cpu_bitmap)))
 		return;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
@@ -2439,10 +2511,13 @@ static void free_idle_threads(void)
 			struct idle_thread_runtime *itr;
 
 			itr = thread__priv(idle);
-			if (itr)
+			if (itr) {
 				thread__put(itr->last_thread);
+				free_callchain(&itr->callchain);
+				callchain_cursor_cleanup(&itr->cursor);
+			}
 
-			thread__delete(idle);
+			thread__put(idle);
 		}
 	}
 
@@ -2475,8 +2550,11 @@ static struct thread *get_idle_thread(int cpu)
 		idle_threads[cpu] = thread__new(0, 0);
 
 		if (idle_threads[cpu]) {
-			if (init_idle_thread(idle_threads[cpu]) < 0)
+			if (init_idle_thread(idle_threads[cpu]) < 0) {
+				/* clean up so next call doesn't find a half-initialized thread */
+				thread__zput(idle_threads[cpu]);
 				return NULL;
+			}
 		}
 	}
 
@@ -2528,12 +2606,16 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			idle = get_idle_thread(sample->cpu);
 			if (idle == NULL) {
 				pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+				thread__put(thread);
 				return NULL;
 			}
 
 			itr = thread__priv(idle);
-			if (itr == NULL)
+			if (itr == NULL) {
+				thread__put(idle);
+				thread__put(thread);
 				return NULL;
+			}
 
 			thread__put(itr->last_thread);
 			itr->last_thread = thread__get(thread);
@@ -2541,6 +2623,8 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			/* copy task callchain when entering to idle */
 			if (evsel__intval(evsel, sample, "next_pid") == 0)
 				save_idle_callchain(sched, itr, sample);
+
+			thread__put(idle);
 		}
 	}
 
@@ -2574,7 +2658,9 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 		else if (evsel__name_is(evsel, "sched:sched_switch"))
 			prio = evsel__intval(evsel, sample, "prev_prio");
 
-		if (prio != -1 && !test_bit(prio, sched->prio_bitmap)) {
+		/* negative prio means no info; out-of-range prio can't match the filter */
+		if (prio >= 0 &&
+		    (prio >= MAX_PRIO || !test_bit(prio, sched->prio_bitmap))) {
 			rc = true;
 			sched->skipped_samples++;
 		}
@@ -2856,8 +2942,15 @@ static int timehist_sched_change_event(const struct perf_tool *tool,
 			t = ptime->end;
 	}
 
-	if (!sched->idle_hist || thread__tid(thread) == 0) {
-		if (!cpu_list || test_bit(sample->cpu, cpu_bitmap))
+	/*
+	 * Use is_idle_sample() not thread__tid() == 0: a crafted perf.data
+	 * can set common_pid=0 with prev_pid!=0, giving us a machine thread
+	 * whose priv is thread_runtime, not idle_thread_runtime — the cast
+	 * below would read past the allocation.
+	 */
+	if (!sched->idle_hist || is_idle_sample(sample, evsel)) {
+		if (!cpu_list || (sample->cpu < MAX_NR_CPUS &&
+				 test_bit(sample->cpu, cpu_bitmap)))
 			timehist_update_runtime_stats(tr, t, tprev);
 
 		if (sched->idle_hist) {
@@ -2887,7 +2980,7 @@ static int timehist_sched_change_event(const struct perf_tool *tool,
 			if (itr->cursor.nr)
 				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
 
-			itr->last_thread = NULL;
+			thread__zput(itr->last_thread);
 		}
 
 		if (!sched->summary_only)
@@ -3051,7 +3144,8 @@ static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root)
 	size_t ret = 0;
 	FILE *fp = stdout;
 	struct callchain_node *chain;
-	struct rb_node *rb_node = rb_first_cached(root);
+	/* sort() uses rb_insert_color() on rb_root, not rb_root_cached */
+	struct rb_node *rb_node = rb_first(&root->rb_root);
 
 	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
 	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
@@ -3193,7 +3287,9 @@ static int perf_timehist__process_sample(const struct perf_tool *tool,
 		.cpu = sample->cpu,
 	};
 
-	if (this_cpu.cpu > sched->max_cpu.cpu)
+	/* max_cpu indexes arrays allocated with MAX_CPUS entries */
+	if (this_cpu.cpu >= 0 && this_cpu.cpu < MAX_CPUS &&
+	    this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
 
 	if (evsel->handler != NULL) {
@@ -3299,6 +3395,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	 */
 	sched->tool.sample	 = perf_timehist__process_sample;
 	sched->tool.mmap	 = perf_event__process_mmap;
+	sched->tool.mmap2	 = perf_event__process_mmap2;
 	sched->tool.comm	 = perf_event__process_comm;
 	sched->tool.exit	 = perf_event__process_exit;
 	sched->tool.fork	 = perf_event__process_fork;
@@ -3362,8 +3459,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		perf_session__set_tracepoints_handlers(session, migrate_handlers))
 		goto out;
 
-	/* pre-allocate struct for per-CPU idle stats */
-	sched->max_cpu.cpu = env->nr_cpus_online;
+	/* pre-allocate struct for per-CPU idle stats; cap to array bounds */
+	sched->max_cpu.cpu = min(env->nr_cpus_online, MAX_CPUS);
 	if (sched->max_cpu.cpu == 0)
 		sched->max_cpu.cpu = 4;
 	if (init_idle_threads(sched->max_cpu.cpu))
@@ -3556,10 +3653,8 @@ out_free_cpus_switch_event:
 
 static int setup_map_cpus(struct perf_sched *sched)
 {
-	sched->max_cpu.cpu  = sysconf(_SC_NPROCESSORS_CONF);
-
 	if (sched->map.comp) {
-		sched->map.comp_cpus = calloc(sched->max_cpu.cpu, sizeof(int));
+		sched->map.comp_cpus = calloc(MAX_CPUS, sizeof(*sched->map.comp_cpus));
 		if (!sched->map.comp_cpus)
 			return -1;
 	}