Merge tag 'perf-core-for-mingo-4.19-20180801' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf trace: (Arnaldo Carvalho de Melo)

- Do not require --no-syscalls to suppress strace like output, i.e.

     # perf trace -e sched:*switch

  will show just sched:sched_switch events, not strace-like formatted
  syscall events, use --syscalls to get the previous behaviour.

  If instead:

     # perf trace

  is used, i.e. no events specified, then --syscalls is implied and
  system wide strace like formatting will be applied to all syscalls.

  The behaviour when just a syscall subset is used with '-e' is unchanged:

     # perf trace -e *sleep,sched:*switch

  will work as before: just the 'nanosleep' syscall will be strace-like
  formatted plus the sched:sched_switch tracepoint event, system wide.

- Allow string table generators to use a default header dir, allowing
  use of them without parameters to see the table it generates on
  stdout, e.g.:

    $ tools/perf/trace/beauty/kvm_ioctl.sh
    static const char *kvm_ioctl_cmds[] = {
        [0x00] = "GET_API_VERSION",
        [0x01] = "CREATE_VM",
        [0x02] = "GET_MSR_INDEX_LIST",
        [0x03] = "CHECK_EXTENSION",
<BIG SNIP>
        [0xe0] = "CREATE_DEVICE",
        [0xe1] = "SET_DEVICE_ATTR",
        [0xe2] = "GET_DEVICE_ATTR",
        [0xe3] = "HAS_DEVICE_ATTR",
    };
    $

  See 'ls tools/perf/trace/beauty/*.sh' to see the available string
  table generators.

- Add a generator for IPPROTO_ socket's protocol constants.

perf record: (Kan Liang)

- Fix error out while applying initial delay and using LBR, due to
  the use of a PERF_TYPE_SOFTWARE/PERF_COUNT_SW_DUMMY event to track
  PERF_RECORD_MMAP events while waiting for the initial delay. Such
  events fail when configured asking PERF_SAMPLE_BRANCH_STACK in
  perf_event_attr.sample_type.

perf c2c: (Jiri Olsa)

- Fix report crash for empty browser, when processing a perf.data file
  without events of interest, either because not asked for in
  'perf record' or because the workload didn't triggered such events.

perf list: (Michael Petlan)

- Align metric group description format with PMU event description.

perf tests: (Sandipan Das)

- Fix indexing when invoking subtests, which caused BPF tests to
  get results for the next test in the list, with the last one
  reporting a failure.

eBPF:

- Fix installation directory for header files included from eBPF proggies,
  avoiding clashing with relative paths used to build other software projects
  such as glibc. (Thomas Richter)

- Show better message when failing to load an object. (Arnaldo Carvalho de Melo)

General: (Christophe Leroy)

- Allow overriding MAX_NR_CPUS at compile time, to make the tooling
  usable in systems with less memory, in time this has to be changed
  to properly allocate based on _NPROCESSORS_ONLN.

Architecture specific:

- Update arm64's ThunderX2 implementation defined pmu core events (Ganapatrao Kulkarni)

- Fix complex event name parsing in 'perf test' for PowerPC, where the 'umask' event
  modifier isn't present. (Sandipan Das)

CoreSight ARM hardware tracing: (Leo Yan)

- Fix start tracing packet handling.

- Support dummy address value for CS_ETM_TRACE_ON packet.

- Generate branch sample when receiving a CS_ETM_TRACE_ON packet.

- Generate branch sample for CS_ETM_TRACE_ON packet.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

29 files changed, 556 insertions, 49 deletions

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions of the Internet Protocol.
+ *
+ * Version:	@(#)in.h	1.0.1	04/21/93
+ *
+ * Authors:	Original taken from the GNU Project <netinet/in.h> file.
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
+#define IPPROTO_IP		IPPROTO_IP
+  IPPROTO_ICMP = 1,		/* Internet Control Message Protocol	*/
+#define IPPROTO_ICMP		IPPROTO_ICMP
+  IPPROTO_IGMP = 2,		/* Internet Group Management Protocol	*/
+#define IPPROTO_IGMP		IPPROTO_IGMP
+  IPPROTO_IPIP = 4,		/* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP		IPPROTO_IPIP
+  IPPROTO_TCP = 6,		/* Transmission Control Protocol	*/
+#define IPPROTO_TCP		IPPROTO_TCP
+  IPPROTO_EGP = 8,		/* Exterior Gateway Protocol		*/
+#define IPPROTO_EGP		IPPROTO_EGP
+  IPPROTO_PUP = 12,		/* PUP protocol				*/
+#define IPPROTO_PUP		IPPROTO_PUP
+  IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
+#define IPPROTO_UDP		IPPROTO_UDP
+  IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+#define IPPROTO_IDP		IPPROTO_IDP
+  IPPROTO_TP = 29,		/* SO Transport Protocol Class 4	*/
+#define IPPROTO_TP		IPPROTO_TP
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP		IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,		/* IPv6-in-IPv4 tunnelling		*/
+#define IPPROTO_IPV6		IPPROTO_IPV6
+  IPPROTO_RSVP = 46,		/* RSVP Protocol			*/
+#define IPPROTO_RSVP		IPPROTO_RSVP
+  IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
+#define IPPROTO_GRE		IPPROTO_GRE
+  IPPROTO_ESP = 50,		/* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP		IPPROTO_ESP
+  IPPROTO_AH = 51,		/* Authentication Header protocol	*/
+#define IPPROTO_AH		IPPROTO_AH
+  IPPROTO_MTP = 92,		/* Multicast Transport Protocol		*/
+#define IPPROTO_MTP		IPPROTO_MTP
+  IPPROTO_BEETPH = 94,		/* IP option pseudo header for BEET	*/
+#define IPPROTO_BEETPH		IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,		/* Encapsulation Header			*/
+#define IPPROTO_ENCAP		IPPROTO_ENCAP
+  IPPROTO_PIM = 103,		/* Protocol Independent Multicast	*/
+#define IPPROTO_PIM		IPPROTO_PIM
+  IPPROTO_COMP = 108,		/* Compression Header Protocol		*/
+#define IPPROTO_COMP		IPPROTO_COMP
+  IPPROTO_SCTP = 132,		/* Stream Control Transport Protocol	*/
+#define IPPROTO_SCTP		IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,	/* UDP-Lite (RFC 3828)			*/
+#define IPPROTO_UDPLITE		IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
+#define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_RAW = 255,		/* Raw IP packets			*/
+#define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+	__be32	s_addr;
+};
+#endif
+
+#define IP_TOS		1
+#define IP_TTL		2
+#define IP_HDRINCL	3
+#define IP_OPTIONS	4
+#define IP_ROUTER_ALERT	5
+#define IP_RECVOPTS	6
+#define IP_RETOPTS	7
+#define IP_PKTINFO	8
+#define IP_PKTOPTIONS	9
+#define IP_MTU_DISCOVER	10
+#define IP_RECVERR	11
+#define IP_RECVTTL	12
+#define	IP_RECVTOS	13
+#define IP_MTU		14
+#define IP_FREEBIND	15
+#define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
+#define IP_PASSSEC	18
+#define IP_TRANSPARENT	19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS	IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
+#define IP_BIND_ADDRESS_NO_PORT	24
+#define IP_RECVFRAGSIZE	25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT		0	/* Never send DF frames */
+#define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
+#define IP_PMTUDISC_DO			2	/* Always DF		*/
+#define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT		5
+
+#define IP_MULTICAST_IF			32
+#define IP_MULTICAST_TTL 		33
+#define IP_MULTICAST_LOOP 		34
+#define IP_ADD_MEMBERSHIP		35
+#define IP_DROP_MEMBERSHIP		36
+#define IP_UNBLOCK_SOURCE		37
+#define IP_BLOCK_SOURCE			38
+#define IP_ADD_SOURCE_MEMBERSHIP	39
+#define IP_DROP_SOURCE_MEMBERSHIP	40
+#define IP_MSFILTER			41
+#define MCAST_JOIN_GROUP		42
+#define MCAST_BLOCK_SOURCE		43
+#define MCAST_UNBLOCK_SOURCE		44
+#define MCAST_LEAVE_GROUP		45
+#define MCAST_JOIN_SOURCE_GROUP		46
+#define MCAST_LEAVE_SOURCE_GROUP	47
+#define MCAST_MSFILTER			48
+#define IP_MULTICAST_ALL		49
+#define IP_UNICAST_IF			50
+
+#define MCAST_EXCLUDE	0
+#define MCAST_INCLUDE	1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+	struct in_addr imr_multiaddr;	/* IP multicast address of group */
+	struct in_addr imr_interface;	/* local IP address of interface */
+};
+
+struct ip_mreqn {
+	struct in_addr	imr_multiaddr;		/* IP multicast address of group */
+	struct in_addr	imr_address;		/* local IP address of interface */
+	int		imr_ifindex;		/* Interface index */
+};
+
+struct ip_mreq_source {
+	__be32		imr_multiaddr;
+	__be32		imr_interface;
+	__be32		imr_sourceaddr;
+};
+
+struct ip_msfilter {
+	__be32		imsf_multiaddr;
+	__be32		imsf_interface;
+	__u32		imsf_fmode;
+	__u32		imsf_numsrc;
+	__be32		imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+	(sizeof(struct ip_msfilter) - sizeof(__u32) \
+	+ (numsrc) * sizeof(__u32))
+
+struct group_req {
+	__u32				 gr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gr_group;	/* group address */
+};
+
+struct group_source_req {
+	__u32				 gsr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gsr_group;	/* group address */
+	struct __kernel_sockaddr_storage gsr_source;	/* source address */
+};
+
+struct group_filter {
+	__u32				 gf_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+	__u32				 gf_fmode;	/* filter mode */
+	__u32				 gf_numsrc;	/* number of sources */
+	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+	int		ipi_ifindex;
+	struct in_addr	ipi_spec_dst;
+	struct in_addr	ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
+struct sockaddr_in {
+  __kernel_sa_family_t	sin_family;	/* Address family		*/
+  __be16		sin_port;	/* Port number			*/
+  struct in_addr	sin_addr;	/* Internet address		*/
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char		__pad[__SOCK_SIZE__ - sizeof(short int) -
+			sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define	IN_CLASSA(a)		((((long int) (a)) & 0x80000000) == 0)
+#define	IN_CLASSA_NET		0xff000000
+#define	IN_CLASSA_NSHIFT	24
+#define	IN_CLASSA_HOST		(0xffffffff & ~IN_CLASSA_NET)
+#define	IN_CLASSA_MAX		128
+
+#define	IN_CLASSB(a)		((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define	IN_CLASSB_NET		0xffff0000
+#define	IN_CLASSB_NSHIFT	16
+#define	IN_CLASSB_HOST		(0xffffffff & ~IN_CLASSB_NET)
+#define	IN_CLASSB_MAX		65536
+
+#define	IN_CLASSC(a)		((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define	IN_CLASSC_NET		0xffffff00
+#define	IN_CLASSC_NSHIFT	8
+#define	IN_CLASSC_HOST		(0xffffffff & ~IN_CLASSC_NET)
+
+#define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define	IN_MULTICAST(a)		IN_CLASSD(a)
+#define IN_MULTICAST_NET	0xF0000000
+
+#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define	INADDR_ANY		((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define	INADDR_BROADCAST	((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define	INADDR_NONE		((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define	IN_LOOPBACKNET		127
+
+/* Address to loopback in software to local host.  */
+#define	INADDR_LOOPBACK		0x7f000001	/* 127.0.0.1   */
+#define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index d3318f99006c..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -907,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f2ea85ee573f..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +761,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
@@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 814aaf269949..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f5de8245b32..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
@@ -599,7 +599,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			for (subi = 0; subi < subn; subi++) {
 				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
 					t->subtest.get_desc(subi));
-				err = test_and_print(t, skip, subi + 1);
+				err = test_and_print(t, skip, subi);
 				if (err != TEST_OK && t->subtest.skip_if_fail)
 					skip = true;
 			}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index a36313daec4e..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1690,7 +1690,7 @@ static struct evlist_test test__events_pmu[] = {
 		.id    = 2,
 	},
 	{
-		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp",
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
 		.check = test__checkevent_complex_name,
 		.id    = 3,
 	}
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8b2c099e750a..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch) {
-		ret = cs_etm__synth_branch_sample(etmq);
-		if (ret)
-			return ret;
+	if (etm->sample_branches && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
@@ -944,6 +974,17 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 
 		etmq->period_instructions = 0;
 
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1023,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5285da0417c5..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -859,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1097,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 96eab4ec34ff..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}