diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 280533ebf9df43b933e517750c29c141dd3feddc..6fdf78625c51cdcd08048dec45adad287a3e452e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -152,12 +152,16 @@ OPTIONS
 
 -d::
 --data::
-	Sample addresses.
+	Record the sample addresses.
 
 -T::
 --timestamp::
-	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
-	for instance.
+	Record the sample timestamps. Use it with 'perf report -D' to see the
+	timestamps, for instance.
+
+-P::
+--period::
+	Record the sample period.
 
 -n::
 --no-samples::
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a0bdd6124583d0c8d02bcb29d852124a8d7bea69..fe50a1b34aa0035dec38a07a752ae33df9ad0e5d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -50,24 +50,20 @@ include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
-include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/find_next_bit.c
 lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
-arch/*/include/asm/perf_regs.h
 arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
 include/linux/poison.h
-include/linux/magic.h
 include/linux/hw_breakpoint.h
 include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d3731cce7c1cc5d498977f31427895487ed723b9..4d6cdeb94fe1e34876391098fb5302a1ae76bf33 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1027,10 +1027,9 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
 	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
-	OPT_BOOLEAN('d', "data", &record.opts.sample_address,
-		    "Sample addresses"),
-	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
-	OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Record the sample timestamps"),
+	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 628090b478ab38e48fee8c6c3fddca4f60bace35..32626ea3e2276b11279db88207e42c29eeed391a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -320,7 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	fprintf(stdout, "#\n# Total Lost Samples: %lu\n#\n", evlist->stats.total_lost_samples);
+	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
 	evlist__for_each(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ff3d25803400af60a00714b0e37d171cb15dca8d..b24ecee95fec1683d9d812e51e9392c260196c67 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -549,7 +549,10 @@ static int __run_perf_stat(int argc, const char **argv)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    perf_evsel__name(counter));
 				counter->supported = false;
-				continue;
+
+				if ((counter->leader != counter) ||
+				    !(counter->leader->nr_members > 1))
+					continue;
 			}
 
 			perf_evsel__open_strerror(counter, &target,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a05490d06374d30a6488781adf0e2f812b48fcb7..4bf805b2fbf66fe77725cd4fa722a8dcb6e0699d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -68,6 +68,23 @@
 # define MSG_CMSG_CLOEXEC	0x40000000
 #endif
 
+#ifndef PERF_FLAG_FD_NO_GROUP
+# define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
+#endif
+
+#ifndef PERF_FLAG_FD_OUTPUT
+# define PERF_FLAG_FD_OUTPUT		(1UL << 1)
+#endif
+
+#ifndef PERF_FLAG_PID_CGROUP
+# define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#endif
+
+#ifndef PERF_FLAG_FD_CLOEXEC
+# define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
+#endif
+
+
 struct tp_field {
 	int offset;
 	union {
@@ -358,6 +375,14 @@ static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 
 #define SCA_HEX syscall_arg__scnprintf_hex
 
+static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
+					 struct syscall_arg *arg)
+{
+	return scnprintf(bf, size, "%d", arg->val);
+}
+
+#define SCA_INT syscall_arg__scnprintf_int
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {
@@ -810,6 +835,34 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 
 #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 
+static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
+						struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return 0;
+
+#define	P_FLAG(n) \
+	if (flags & PERF_FLAG_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~PERF_FLAG_##n; \
+	}
+
+	P_FLAG(FD_NO_GROUP);
+	P_FLAG(FD_OUTPUT);
+	P_FLAG(PID_CGROUP);
+	P_FLAG(FD_CLOEXEC);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
+
 static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
 						   struct syscall_arg *arg)
 {
@@ -1077,6 +1130,11 @@ static struct syscall_fmt {
 	{ .name	    = "openat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "perf_event_open", .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_INT, /* pid */
+			     [2] = SCA_INT, /* cpu */
+			     [3] = SCA_FD,  /* group_fd */
+			     [4] = SCA_PERF_FLAGS,  /* flags */ }, },
 	{ .name	    = "pipe2",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a3e36fc634dc40005e77f7b228ec8ffb5ad001af..d4f9994ae47fc6f594980ea828c31fb2e9ad4f11 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1058,7 +1058,7 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 
 #define BUF_SIZE		1024
 
-#define p_hex(val)		snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val))
+#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
 #define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
 #define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88d87bf3049f6b43e235fb7a9075f62a6be4e47f..f31e024ddf7dd683b7073fc858bdeb530748e6a0 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1299,7 +1299,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		drop_rate = (double)stats->total_lost_samples /
 			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
 		if (drop_rate > 0.05) {
-			ui__warning("Processed %lu samples and lost %3.2f%% samples!\n\n",
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
 				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
 				    drop_rate * 100.0);
 		}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 0c264bc685aceb94c544358c38caa8158d441b68..edc2d633b33224530e9dcb7780877bf7d1be08b3 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -115,20 +115,17 @@ int rm_rf(char *path)
 	return rmdir(path);
 }
 
-static int slow_copyfile(const char *from, const char *to, mode_t mode)
+static int slow_copyfile(const char *from, const char *to)
 {
 	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
-	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
-	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
-	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -178,29 +175,48 @@ int copyfile_mode(const char *from, const char *to, mode_t mode)
 	int fromfd, tofd;
 	struct stat st;
 	int err = -1;
+	char *tmp = NULL, *ptr = NULL;
 
 	if (stat(from, &st))
 		goto out;
 
-	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to, mode);
-
-	fromfd = open(from, O_RDONLY);
-	if (fromfd < 0)
+	/* extra 'x' at the end is to reserve space for '.' */
+	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+		tmp = NULL;
 		goto out;
+	}
+	ptr = strrchr(tmp, '/');
+	if (!ptr)
+		goto out;
+	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+	*ptr = '.';
 
-	tofd = creat(to, mode);
+	tofd = mkstemp(tmp);
 	if (tofd < 0)
-		goto out_close_from;
+		goto out;
+
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
+	if (st.st_size == 0) { /* /proc? do it slowly... */
+		err = slow_copyfile(from, tmp);
+		goto out_close_to;
+	}
+
+	fromfd = open(from, O_RDONLY);
+	if (fromfd < 0)
+		goto out_close_to;
 
 	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
 
-	close(tofd);
-	if (err)
-		unlink(to);
-out_close_from:
 	close(fromfd);
+out_close_to:
+	close(tofd);
+	if (!err)
+		err = link(tmp, to);
+	unlink(tmp);
 out:
+	free(tmp);
 	return err;
 }