diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 677b1ed184c9..4f74d94c8d97 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -22,7 +22,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
-	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+	if (__range_not_ok(from, n, TASK_SIZE))
 		return len;
 
 	do {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f85c0154b333..d7d71d6ec972 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
 	return !event->cgrp || event->cgrp == cpuctx->cgrp;
 }
 
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
 {
-	css_get(&event->cgrp->css);
+	return css_tryget(&event->cgrp->css);
 }
 
 static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	event->cgrp = cgrp;
 
 	/* must be done before we fput() the file */
-	perf_get_cgroup(event);
+	if (!perf_tryget_cgroup(event)) {
+		event->cgrp = NULL;
+		ret = -ENOENT;
+		goto out;
+	}
 
 	/*
 	 * all events in a group must monitor
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68032c6177db..49249c28690d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
 void tracing_off(void)
 {
 	if (global_trace.buffer)
-		ring_buffer_record_on(global_trace.buffer);
+		ring_buffer_record_off(global_trace.buffer);
 	/*
 	 * This flag is only looked at when buffers haven't been
 	 * allocated yet. We don't really care about the race
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index e5e1d85b8c7c..4b1dfba70f7c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -372,6 +372,13 @@ static int watchdog(void *unused)
 
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
 static int watchdog_nmi_enable(int cpu)
 {
 	struct perf_event_attr *wd_attr;
@@ -390,11 +397,21 @@ static int watchdog_nmi_enable(int cpu)
 
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+	/* save cpu0 error for future comparision */
+	if (cpu == 0 && IS_ERR(event))
+		cpu0_err = PTR_ERR(event);
+
 	if (!IS_ERR(event)) {
-		pr_info("enabled, takes one hw-pmu counter.\n");
+		/* only print for cpu0 or different than cpu0 */
+		if (cpu == 0 || cpu0_err)
+			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
 		goto out_save;
 	}
 
+	/* skip displaying the same error again */
+	if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+		return PTR_ERR(event);
 
 	/* vary the KERN level based on the returned errno */
 	if (PTR_ERR(event) == -EOPNOTSUPP)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 262589991ea4..07b5c7703dd1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1179,6 +1179,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
 		usage_with_options(stat_usage, options);
 	}
+
+	if (output_fd < 0) {
+		fprintf(stderr, "argument to --log-fd must be a > 0\n");
+		usage_with_options(stat_usage, options);
+	}
+
 	if (!output) {
 		struct timespec tm;
 		mode = append_file ? "a" : "w";
@@ -1190,7 +1196,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		}
 		clock_gettime(CLOCK_REALTIME, &tm);
 		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
-	} else if (output_fd != 2) {
+	} else if (output_fd > 0) {
 		mode = append_file ? "a" : "w";
 		output = fdopen(output_fd, mode);
 		if (!output) {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 2dd5edf161b7..e909d43cf542 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header,
 		else
 			return -1;
 	} else if (ph->needs_swap) {
-		unsigned int i;
 		/*
 		 * feature bitmap is declared as an array of unsigned longs --
 		 * not good since its size can differ between the host that
@@ -1958,14 +1957,17 @@ int perf_file_header__read(struct perf_file_header *header,
 		 * file), punt and fallback to the original behavior --
 		 * clearing all feature bits and setting buildid.
 		 */
-		for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i)
-			header->adds_features[i] = bswap_64(header->adds_features[i]);
+		mem_bswap_64(&header->adds_features,
+			    BITS_TO_U64(HEADER_FEAT_BITS));
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
-			for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) {
-				header->adds_features[i] = bswap_64(header->adds_features[i]);
-				header->adds_features[i] = bswap_32(header->adds_features[i]);
-			}
+			/* unswap as u64 */
+			mem_bswap_64(&header->adds_features,
+				    BITS_TO_U64(HEADER_FEAT_BITS));
+
+			/* unswap as u32 */
+			mem_bswap_32(&header->adds_features,
+				    BITS_TO_U32(HEADER_FEAT_BITS));
 		}
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
@@ -2091,6 +2093,35 @@ static int read_attr(int fd, struct perf_header *ph,
 	return ret <= 0 ? -1 : 0;
 }
 
+static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
+{
+	struct event_format *event = trace_find_event(evsel->attr.config);
+	char bf[128];
+
+	if (event == NULL)
+		return -1;
+
+	snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
+	evsel->name = strdup(bf);
+	if (event->name == NULL)
+		return -1;
+
+	return 0;
+}
+
+static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
+		    perf_evsel__set_tracepoint_name(pos))
+			return -1;
+	}
+
+	return 0;
+}
+
 int perf_session__read_header(struct perf_session *session, int fd)
 {
 	struct perf_header *header = &session->header;
@@ -2172,6 +2203,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
 	lseek(fd, header->data_offset, SEEK_SET);
 
+	if (perf_evlist__set_tracepoint_names(session->evlist))
+		goto out_delete_evlist;
+
 	header->frozen = 1;
 	return 0;
 out_errno:
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index f1584833bd22..587a230d2075 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -8,6 +8,8 @@
 #define BITS_PER_LONG __WORDSIZE
 #define BITS_PER_BYTE           8
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2600916efa83..c3e399bcf18d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 }
+ 
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
 
 void mem_bswap_64(void *src, int byte_size)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7a5434c00565..0c702e3f0a36 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -80,6 +80,7 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *self);