15 files changed, 428 insertions, 366 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a36e6e5a6f4f..ca0741c91903 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,162 +1,162 @@
-libperf-y += annotate.o
-libperf-y += block-range.o
-libperf-y += build-id.o
-libperf-y += config.o
-libperf-y += ctype.o
-libperf-y += db-export.o
-libperf-y += env.o
-libperf-y += event.o
-libperf-y += evlist.o
-libperf-y += evsel.o
-libperf-y += evsel_fprintf.o
-libperf-y += find_bit.o
-libperf-y += get_current_dir_name.o
-libperf-y += kallsyms.o
-libperf-y += levenshtein.o
-libperf-y += llvm-utils.o
-libperf-y += mmap.o
-libperf-y += memswap.o
-libperf-y += parse-events.o
-libperf-y += perf_regs.o
-libperf-y += path.o
-libperf-y += print_binary.o
-libperf-y += rbtree.o
-libperf-y += libstring.o
-libperf-y += bitmap.o
-libperf-y += hweight.o
-libperf-y += smt.o
-libperf-y += strbuf.o
-libperf-y += string.o
-libperf-y += strlist.o
-libperf-y += strfilter.o
-libperf-y += top.o
-libperf-y += usage.o
-libperf-y += dso.o
-libperf-y += symbol.o
-libperf-y += symbol_fprintf.o
-libperf-y += color.o
-libperf-y += color_config.o
-libperf-y += metricgroup.o
-libperf-y += header.o
-libperf-y += callchain.o
-libperf-y += values.o
-libperf-y += debug.o
-libperf-y += machine.o
-libperf-y += map.o
-libperf-y += pstack.o
-libperf-y += session.o
-libperf-y += sample-raw.o
-libperf-y += s390-sample-raw.o
-libperf-$(CONFIG_TRACE) += syscalltbl.o
-libperf-y += ordered-events.o
-libperf-y += namespaces.o
-libperf-y += comm.o
-libperf-y += thread.o
-libperf-y += thread_map.o
-libperf-y += trace-event-parse.o
-libperf-y += parse-events-flex.o
-libperf-y += parse-events-bison.o
-libperf-y += pmu.o
-libperf-y += pmu-flex.o
-libperf-y += pmu-bison.o
-libperf-y += trace-event-read.o
-libperf-y += trace-event-info.o
-libperf-y += trace-event-scripting.o
-libperf-y += trace-event.o
-libperf-y += svghelper.o
-libperf-y += sort.o
-libperf-y += hist.o
-libperf-y += util.o
-libperf-y += xyarray.o
-libperf-y += cpumap.o
-libperf-y += cgroup.o
-libperf-y += target.o
-libperf-y += rblist.o
-libperf-y += intlist.o
-libperf-y += vdso.o
-libperf-y += counts.o
-libperf-y += stat.o
-libperf-y += stat-shadow.o
-libperf-y += stat-display.o
-libperf-y += record.o
-libperf-y += srcline.o
-libperf-y += srccode.o
-libperf-y += data.o
-libperf-y += tsc.o
-libperf-y += cloexec.o
-libperf-y += call-path.o
-libperf-y += rwsem.o
-libperf-y += thread-stack.o
-libperf-$(CONFIG_AUXTRACE) += auxtrace.o
-libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
-libperf-$(CONFIG_AUXTRACE) += intel-pt.o
-libperf-$(CONFIG_AUXTRACE) += intel-bts.o
-libperf-$(CONFIG_AUXTRACE) += arm-spe.o
-libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
-libperf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
+perf-y += annotate.o
+perf-y += block-range.o
+perf-y += build-id.o
+perf-y += config.o
+perf-y += ctype.o
+perf-y += db-export.o
+perf-y += env.o
+perf-y += event.o
+perf-y += evlist.o
+perf-y += evsel.o
+perf-y += evsel_fprintf.o
+perf-y += find_bit.o
+perf-y += get_current_dir_name.o
+perf-y += kallsyms.o
+perf-y += levenshtein.o
+perf-y += llvm-utils.o
+perf-y += mmap.o
+perf-y += memswap.o
+perf-y += parse-events.o
+perf-y += perf_regs.o
+perf-y += path.o
+perf-y += print_binary.o
+perf-y += rbtree.o
+perf-y += libstring.o
+perf-y += bitmap.o
+perf-y += hweight.o
+perf-y += smt.o
+perf-y += strbuf.o
+perf-y += string.o
+perf-y += strlist.o
+perf-y += strfilter.o
+perf-y += top.o
+perf-y += usage.o
+perf-y += dso.o
+perf-y += symbol.o
+perf-y += symbol_fprintf.o
+perf-y += color.o
+perf-y += color_config.o
+perf-y += metricgroup.o
+perf-y += header.o
+perf-y += callchain.o
+perf-y += values.o
+perf-y += debug.o
+perf-y += machine.o
+perf-y += map.o
+perf-y += pstack.o
+perf-y += session.o
+perf-y += sample-raw.o
+perf-y += s390-sample-raw.o
+perf-$(CONFIG_TRACE) += syscalltbl.o
+perf-y += ordered-events.o
+perf-y += namespaces.o
+perf-y += comm.o
+perf-y += thread.o
+perf-y += thread_map.o
+perf-y += trace-event-parse.o
+perf-y += parse-events-flex.o
+perf-y += parse-events-bison.o
+perf-y += pmu.o
+perf-y += pmu-flex.o
+perf-y += pmu-bison.o
+perf-y += trace-event-read.o
+perf-y += trace-event-info.o
+perf-y += trace-event-scripting.o
+perf-y += trace-event.o
+perf-y += svghelper.o
+perf-y += sort.o
+perf-y += hist.o
+perf-y += util.o
+perf-y += xyarray.o
+perf-y += cpumap.o
+perf-y += cgroup.o
+perf-y += target.o
+perf-y += rblist.o
+perf-y += intlist.o
+perf-y += vdso.o
+perf-y += counts.o
+perf-y += stat.o
+perf-y += stat-shadow.o
+perf-y += stat-display.o
+perf-y += record.o
+perf-y += srcline.o
+perf-y += srccode.o
+perf-y += data.o
+perf-y += tsc.o
+perf-y += cloexec.o
+perf-y += call-path.o
+perf-y += rwsem.o
+perf-y += thread-stack.o
+perf-$(CONFIG_AUXTRACE) += auxtrace.o
+perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
+perf-$(CONFIG_AUXTRACE) += intel-pt.o
+perf-$(CONFIG_AUXTRACE) += intel-bts.o
+perf-$(CONFIG_AUXTRACE) += arm-spe.o
+perf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
+perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
 
 ifdef CONFIG_LIBOPENCSD
-libperf-$(CONFIG_AUXTRACE) += cs-etm.o
-libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder/
+perf-$(CONFIG_AUXTRACE) += cs-etm.o
+perf-$(CONFIG_AUXTRACE) += cs-etm-decoder/
 endif
 
-libperf-y += parse-branch-options.o
-libperf-y += dump-insn.o
-libperf-y += parse-regs-options.o
-libperf-y += term.o
-libperf-y += help-unknown-cmd.o
-libperf-y += mem-events.o
-libperf-y += vsprintf.o
-libperf-y += units.o
-libperf-y += time-utils.o
-libperf-y += expr-bison.o
-libperf-y += branch.o
-libperf-y += mem2node.o
-
-libperf-$(CONFIG_LIBBPF) += bpf-loader.o
-libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
-libperf-$(CONFIG_LIBELF) += symbol-elf.o
-libperf-$(CONFIG_LIBELF) += probe-file.o
-libperf-$(CONFIG_LIBELF) += probe-event.o
+perf-y += parse-branch-options.o
+perf-y += dump-insn.o
+perf-y += parse-regs-options.o
+perf-y += term.o
+perf-y += help-unknown-cmd.o
+perf-y += mem-events.o
+perf-y += vsprintf.o
+perf-y += units.o
+perf-y += time-utils.o
+perf-y += expr-bison.o
+perf-y += branch.o
+perf-y += mem2node.o
+
+perf-$(CONFIG_LIBBPF) += bpf-loader.o
+perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
+perf-$(CONFIG_LIBELF) += symbol-elf.o
+perf-$(CONFIG_LIBELF) += probe-file.o
+perf-$(CONFIG_LIBELF) += probe-event.o
 
 ifndef CONFIG_LIBELF
-libperf-y += symbol-minimal.o
+perf-y += symbol-minimal.o
 endif
 
 ifndef CONFIG_SETNS
-libperf-y += setns.o
+perf-y += setns.o
 endif
 
-libperf-$(CONFIG_DWARF) += probe-finder.o
-libperf-$(CONFIG_DWARF) += dwarf-aux.o
-libperf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_DWARF) += probe-finder.o
+perf-$(CONFIG_DWARF) += dwarf-aux.o
+perf-$(CONFIG_DWARF) += dwarf-regs.o
 
-libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
-libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
-libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
-libperf-$(CONFIG_LIBUNWIND_X86)      += libunwind/x86_32.o
-libperf-$(CONFIG_LIBUNWIND_AARCH64)  += libunwind/arm64.o
+perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
+perf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+perf-$(CONFIG_LIBUNWIND_X86)      += libunwind/x86_32.o
+perf-$(CONFIG_LIBUNWIND_AARCH64)  += libunwind/arm64.o
 
-libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
+perf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
 
-libperf-y += scripting-engines/
+perf-y += scripting-engines/
 
-libperf-$(CONFIG_ZLIB) += zlib.o
-libperf-$(CONFIG_LZMA) += lzma.o
-libperf-y += demangle-java.o
-libperf-y += demangle-rust.o
+perf-$(CONFIG_ZLIB) += zlib.o
+perf-$(CONFIG_LZMA) += lzma.o
+perf-y += demangle-java.o
+perf-y += demangle-rust.o
 
 ifdef CONFIG_JITDUMP
-libperf-$(CONFIG_LIBELF) += jitdump.o
-libperf-$(CONFIG_LIBELF) += genelf.o
-libperf-$(CONFIG_DWARF) += genelf_debug.o
+perf-$(CONFIG_LIBELF) += jitdump.o
+perf-$(CONFIG_LIBELF) += genelf.o
+perf-$(CONFIG_DWARF) += genelf_debug.o
 endif
 
-libperf-y += perf-hooks.o
+perf-y += perf-hooks.o
 
-libperf-$(CONFIG_LIBBPF) += bpf-event.o
+perf-$(CONFIG_LIBBPF) += bpf-event.o
 
-libperf-$(CONFIG_CXX) += c++/
+perf-$(CONFIG_CXX) += c++/
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 796ef793f4ce..62dda96b0096 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -236,8 +236,8 @@ int perf_event__synthesize_bpf_events(struct perf_tool *tool,
 			pr_debug("%s: can't get next program: %s%s",
 				 __func__, strerror(errno),
 				 errno == EINVAL ? " -- kernel too old?" : "");
-			/* don't report error on old kernel */
-			err = (errno == EINVAL) ? 0 : -1;
+			/* don't report error on old kernel or EPERM  */
+			err = (errno == EINVAL || errno == EPERM) ? 0 : -1;
 			break;
 		}
 		fd = bpf_prog_get_fd_by_id(id);
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
index 988fef1b11d7..613ecfd76527 100644
--- a/tools/perf/util/c++/Build
+++ b/tools/perf/util/c++/Build
@@ -1,2 +1,2 @@
-libperf-$(CONFIG_CLANGLLVM) += clang.o
-libperf-$(CONFIG_CLANGLLVM) += clang-test.o
+perf-$(CONFIG_CLANGLLVM) += clang.o
+perf-$(CONFIG_CLANGLLVM) += clang-test.o
diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build
index bc22c39c727f..216cb17a3322 100644
--- a/tools/perf/util/cs-etm-decoder/Build
+++ b/tools/perf/util/cs-etm-decoder/Build
@@ -1 +1 @@
-libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
+perf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
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 7e6a8850be4a..3ab11dfa92ae 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -15,13 +15,6 @@
 
 struct cs_etm_decoder;
 
-struct cs_etm_buffer {
-	const unsigned char *buf;
-	size_t len;
-	u64 offset;
-	u64 ref_timestamp;
-};
-
 enum cs_etm_sample_type {
 	CS_ETM_EMPTY,
 	CS_ETM_RANGE,
@@ -105,9 +98,10 @@ enum {
 	CS_ETM_PROTO_PTM,
 };
 
-enum {
+enum cs_etm_decoder_operation {
 	CS_ETM_OPERATION_PRINT = 1,
 	CS_ETM_OPERATION_DECODE,
+	CS_ETM_OPERATION_MAX,
 };
 
 int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8b3f882d6e2f..110804936fc3 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -25,6 +25,7 @@
 #include "machine.h"
 #include "map.h"
 #include "perf.h"
+#include "symbol.h"
 #include "thread.h"
 #include "thread_map.h"
 #include "thread-stack.h"
@@ -64,13 +65,10 @@ struct cs_etm_queue {
 	struct thread *thread;
 	struct cs_etm_decoder *decoder;
 	struct auxtrace_buffer *buffer;
-	const struct cs_etm_state *state;
 	union perf_event *event_buf;
 	unsigned int queue_nr;
 	pid_t pid, tid;
 	int cpu;
-	u64 time;
-	u64 timestamp;
 	u64 offset;
 	u64 period_instructions;
 	struct branch_stack *last_branch;
@@ -78,11 +76,13 @@ struct cs_etm_queue {
 	size_t last_branch_pos;
 	struct cs_etm_packet *prev_packet;
 	struct cs_etm_packet *packet;
+	const unsigned char *buf;
+	size_t buf_len, buf_used;
 };
 
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
 static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
-					   pid_t tid, u64 time_);
+					   pid_t tid);
 
 /* PTMs ETMIDR [11:8] set to b0011 */
 #define ETMIDR_PTM_VERSION 0x00000300
@@ -138,10 +138,83 @@ static void cs_etm__packet_dump(const char *pkt_string)
 	fflush(stdout);
 }
 
+static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
+					  struct cs_etm_auxtrace *etm, int idx,
+					  u32 etmidr)
+{
+	u64 **metadata = etm->metadata;
+
+	t_params[idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
+	t_params[idx].etmv3.reg_ctrl = metadata[idx][CS_ETM_ETMCR];
+	t_params[idx].etmv3.reg_trc_id = metadata[idx][CS_ETM_ETMTRACEIDR];
+}
+
+static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params,
+					  struct cs_etm_auxtrace *etm, int idx)
+{
+	u64 **metadata = etm->metadata;
+
+	t_params[idx].protocol = CS_ETM_PROTO_ETMV4i;
+	t_params[idx].etmv4.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0];
+	t_params[idx].etmv4.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1];
+	t_params[idx].etmv4.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2];
+	t_params[idx].etmv4.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8];
+	t_params[idx].etmv4.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR];
+	t_params[idx].etmv4.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR];
+}
+
+static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
+				     struct cs_etm_auxtrace *etm)
+{
+	int i;
+	u32 etmidr;
+	u64 architecture;
+
+	for (i = 0; i < etm->num_cpu; i++) {
+		architecture = etm->metadata[i][CS_ETM_MAGIC];
+
+		switch (architecture) {
+		case __perf_cs_etmv3_magic:
+			etmidr = etm->metadata[i][CS_ETM_ETMIDR];
+			cs_etm__set_trace_param_etmv3(t_params, etm, i, etmidr);
+			break;
+		case __perf_cs_etmv4_magic:
+			cs_etm__set_trace_param_etmv4(t_params, etm, i);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params,
+				       struct cs_etm_queue *etmq,
+				       enum cs_etm_decoder_operation mode)
+{
+	int ret = -EINVAL;
+
+	if (!(mode < CS_ETM_OPERATION_MAX))
+		goto out;
+
+	d_params->packet_printer = cs_etm__packet_dump;
+	d_params->operation = mode;
+	d_params->data = etmq;
+	d_params->formatted = true;
+	d_params->fsyncs = false;
+	d_params->hsyncs = false;
+	d_params->frame_aligned = true;
+
+	ret = 0;
+out:
+	return ret;
+}
+
 static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_buffer *buffer)
 {
-	int i, ret;
+	int ret;
 	const char *color = PERF_COLOR_BLUE;
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params *t_params;
@@ -155,48 +228,22 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 
 	/* Use metadata to fill in trace parameters for trace decoder */
 	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
-	for (i = 0; i < etm->num_cpu; i++) {
-		if (etm->metadata[i][CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
-			u32 etmidr = etm->metadata[i][CS_ETM_ETMIDR];
-
-			t_params[i].protocol =
-					cs_etm__get_v7_protocol_version(etmidr);
-			t_params[i].etmv3.reg_ctrl =
-					etm->metadata[i][CS_ETM_ETMCR];
-			t_params[i].etmv3.reg_trc_id =
-					etm->metadata[i][CS_ETM_ETMTRACEIDR];
-		} else if (etm->metadata[i][CS_ETM_MAGIC] ==
-						      __perf_cs_etmv4_magic) {
-			t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
-			t_params[i].etmv4.reg_idr0 =
-					etm->metadata[i][CS_ETMV4_TRCIDR0];
-			t_params[i].etmv4.reg_idr1 =
-					etm->metadata[i][CS_ETMV4_TRCIDR1];
-			t_params[i].etmv4.reg_idr2 =
-					etm->metadata[i][CS_ETMV4_TRCIDR2];
-			t_params[i].etmv4.reg_idr8 =
-					etm->metadata[i][CS_ETMV4_TRCIDR8];
-			t_params[i].etmv4.reg_configr =
-					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
-			t_params[i].etmv4.reg_traceidr =
-					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
-		}
-	}
+
+	if (!t_params)
+		return;
+
+	if (cs_etm__init_trace_params(t_params, etm))
+		goto out_free;
 
 	/* Set decoder parameters to simply print the trace packets */
-	d_params.packet_printer = cs_etm__packet_dump;
-	d_params.operation = CS_ETM_OPERATION_PRINT;
-	d_params.formatted = true;
-	d_params.fsyncs = false;
-	d_params.hsyncs = false;
-	d_params.frame_aligned = true;
+	if (cs_etm__init_decoder_params(&d_params, NULL,
+					CS_ETM_OPERATION_PRINT))
+		goto out_free;
 
 	decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
 
-	zfree(&t_params);
-
 	if (!decoder)
-		return;
+		goto out_free;
 	do {
 		size_t consumed;
 
@@ -211,6 +258,9 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 	} while (buffer_used < buffer->size);
 
 	cs_etm_decoder__free(decoder);
+
+out_free:
+	zfree(&t_params);
 }
 
 static int cs_etm__flush_events(struct perf_session *session,
@@ -234,7 +284,7 @@ static int cs_etm__flush_events(struct perf_session *session,
 	if (ret < 0)
 		return ret;
 
-	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
+	return cs_etm__process_timeless_queues(etm, -1);
 }
 
 static void cs_etm__free_queue(void *priv)
@@ -326,7 +376,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	struct	 addr_location al;
 
 	if (!etmq)
-		return -1;
+		return 0;
 
 	machine = etmq->etm->machine;
 	cpumode = cs_etm__cpu_mode(etmq, address);
@@ -334,7 +384,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	thread = etmq->thread;
 	if (!thread) {
 		if (cpumode != PERF_RECORD_MISC_KERNEL)
-			return -EINVAL;
+			return 0;
 		thread = etmq->etm->unknown_thread;
 	}
 
@@ -357,12 +407,10 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	return len;
 }
 
-static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
-						unsigned int queue_nr)
+static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 {
-	int i;
 	struct cs_etm_decoder_params d_params;
-	struct cs_etm_trace_params  *t_params;
+	struct cs_etm_trace_params  *t_params = NULL;
 	struct cs_etm_queue *etmq;
 	size_t szp = sizeof(struct cs_etm_packet);
 
@@ -397,59 +445,22 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	if (!etmq->event_buf)
 		goto out_free;
 
-	etmq->etm = etm;
-	etmq->queue_nr = queue_nr;
-	etmq->pid = -1;
-	etmq->tid = -1;
-	etmq->cpu = -1;
-
 	/* Use metadata to fill in trace parameters for trace decoder */
 	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
 
 	if (!t_params)
 		goto out_free;
 
-	for (i = 0; i < etm->num_cpu; i++) {
-		if (etm->metadata[i][CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
-			u32 etmidr = etm->metadata[i][CS_ETM_ETMIDR];
-
-			t_params[i].protocol =
-					cs_etm__get_v7_protocol_version(etmidr);
-			t_params[i].etmv3.reg_ctrl =
-					etm->metadata[i][CS_ETM_ETMCR];
-			t_params[i].etmv3.reg_trc_id =
-					etm->metadata[i][CS_ETM_ETMTRACEIDR];
-		} else if (etm->metadata[i][CS_ETM_MAGIC] ==
-							__perf_cs_etmv4_magic) {
-			t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
-			t_params[i].etmv4.reg_idr0 =
-					etm->metadata[i][CS_ETMV4_TRCIDR0];
-			t_params[i].etmv4.reg_idr1 =
-					etm->metadata[i][CS_ETMV4_TRCIDR1];
-			t_params[i].etmv4.reg_idr2 =
-					etm->metadata[i][CS_ETMV4_TRCIDR2];
-			t_params[i].etmv4.reg_idr8 =
-					etm->metadata[i][CS_ETMV4_TRCIDR8];
-			t_params[i].etmv4.reg_configr =
-					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
-			t_params[i].etmv4.reg_traceidr =
-					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
-		}
-	}
+	if (cs_etm__init_trace_params(t_params, etm))
+		goto out_free;
 
-	/* Set decoder parameters to simply print the trace packets */
-	d_params.packet_printer = cs_etm__packet_dump;
-	d_params.operation = CS_ETM_OPERATION_DECODE;
-	d_params.formatted = true;
-	d_params.fsyncs = false;
-	d_params.hsyncs = false;
-	d_params.frame_aligned = true;
-	d_params.data = etmq;
+	/* Set decoder parameters to decode trace packets */
+	if (cs_etm__init_decoder_params(&d_params, etmq,
+					CS_ETM_OPERATION_DECODE))
+		goto out_free;
 
 	etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
 
-	zfree(&t_params);
-
 	if (!etmq->decoder)
 		goto out_free;
 
@@ -462,14 +473,13 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 					      cs_etm__mem_access))
 		goto out_free_decoder;
 
-	etmq->offset = 0;
-	etmq->period_instructions = 0;
-
+	zfree(&t_params);
 	return etmq;
 
 out_free_decoder:
 	cs_etm_decoder__free(etmq->decoder);
 out_free:
+	zfree(&t_params);
 	zfree(&etmq->event_buf);
 	zfree(&etmq->last_branch);
 	zfree(&etmq->last_branch_rb);
@@ -484,24 +494,30 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_queue *queue,
 			       unsigned int queue_nr)
 {
+	int ret = 0;
 	struct cs_etm_queue *etmq = queue->priv;
 
 	if (list_empty(&queue->head) || etmq)
-		return 0;
+		goto out;
 
-	etmq = cs_etm__alloc_queue(etm, queue_nr);
+	etmq = cs_etm__alloc_queue(etm);
 
-	if (!etmq)
-		return -ENOMEM;
+	if (!etmq) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	queue->priv = etmq;
-
-	if (queue->cpu != -1)
-		etmq->cpu = queue->cpu;
-
+	etmq->etm = etm;
+	etmq->queue_nr = queue_nr;
+	etmq->cpu = queue->cpu;
 	etmq->tid = queue->tid;
+	etmq->pid = -1;
+	etmq->offset = 0;
+	etmq->period_instructions = 0;
 
-	return 0;
+out:
+	return ret;
 }
 
 static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
@@ -509,6 +525,9 @@ static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
 	unsigned int i;
 	int ret;
 
+	if (!etm->kernel_start)
+		etm->kernel_start = machine__kernel_start(etm->machine);
+
 	for (i = 0; i < etm->queues.nr_queues; i++) {
 		ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i);
 		if (ret)
@@ -666,7 +685,7 @@ static int cs_etm__inject_event(union perf_event *event,
 
 
 static int
-cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
+cs_etm__get_trace(struct cs_etm_queue *etmq)
 {
 	struct auxtrace_buffer *aux_buffer = etmq->buffer;
 	struct auxtrace_buffer *old_buffer = aux_buffer;
@@ -680,7 +699,7 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	if (!aux_buffer) {
 		if (old_buffer)
 			auxtrace_buffer__drop_data(old_buffer);
-		buff->len = 0;
+		etmq->buf_len = 0;
 		return 0;
 	}
 
@@ -700,13 +719,11 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	if (old_buffer)
 		auxtrace_buffer__drop_data(old_buffer);
 
-	buff->offset = aux_buffer->offset;
-	buff->len = aux_buffer->size;
-	buff->buf = aux_buffer->data;
+	etmq->buf_used = 0;
+	etmq->buf_len = aux_buffer->size;
+	etmq->buf = aux_buffer->data;
 
-	buff->ref_timestamp = aux_buffer->reference;
-
-	return buff->len;
+	return etmq->buf_len;
 }
 
 static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
@@ -1135,6 +1152,32 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq)
 
 	return 0;
 }
+/*
+ * cs_etm__get_data_block: Fetch a block from the auxtrace_buffer queue
+ *			   if need be.
+ * Returns:	< 0	if error
+ *		= 0	if no more auxtrace_buffer to read
+ *		> 0	if the current buffer isn't empty yet
+ */
+static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
+{
+	int ret;
+
+	if (!etmq->buf_len) {
+		ret = cs_etm__get_trace(etmq);
+		if (ret <= 0)
+			return ret;
+		/*
+		 * We cannot assume consecutive blocks in the data file
+		 * are contiguous, reset the decoder to force re-sync.
+		 */
+		ret = cs_etm_decoder__reset(etmq->decoder);
+		if (ret)
+			return ret;
+	}
+
+	return etmq->buf_len;
+}
 
 static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq,
 				 struct cs_etm_packet *packet,
@@ -1474,105 +1517,124 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq)
 	return 0;
 }
 
+static int cs_etm__decode_data_block(struct cs_etm_queue *etmq)
+{
+	int ret = 0;
+	size_t processed = 0;
+
+	/*
+	 * Packets are decoded and added to the decoder's packet queue
+	 * until the decoder packet processing callback has requested that
+	 * processing stops or there is nothing left in the buffer.  Normal
+	 * operations that stop processing are a timestamp packet or a full
+	 * decoder buffer queue.
+	 */
+	ret = cs_etm_decoder__process_data_block(etmq->decoder,
+						 etmq->offset,
+						 &etmq->buf[etmq->buf_used],
+						 etmq->buf_len,
+						 &processed);
+	if (ret)
+		goto out;
+
+	etmq->offset += processed;
+	etmq->buf_used += processed;
+	etmq->buf_len -= processed;
+
+out:
+	return ret;
+}
+
+static int cs_etm__process_decoder_queue(struct cs_etm_queue *etmq)
+{
+	int ret;
+
+		/* Process each packet in this chunk */
+		while (1) {
+			ret = cs_etm_decoder__get_packet(etmq->decoder,
+							 etmq->packet);
+			if (ret <= 0)
+				/*
+				 * Stop processing this chunk on
+				 * end of data or error
+				 */
+				break;
+
+			/*
+			 * Since packet addresses are swapped in packet
+			 * handling within below switch() statements,
+			 * thus setting sample flags must be called
+			 * prior to switch() statement to use address
+			 * information before packets swapping.
+			 */
+			ret = cs_etm__set_sample_flags(etmq);
+			if (ret < 0)
+				break;
+
+			switch (etmq->packet->sample_type) {
+			case CS_ETM_RANGE:
+				/*
+				 * If the packet contains an instruction
+				 * range, generate instruction sequence
+				 * events.
+				 */
+				cs_etm__sample(etmq);
+				break;
+			case CS_ETM_EXCEPTION:
+			case CS_ETM_EXCEPTION_RET:
+				/*
+				 * If the exception packet is coming,
+				 * make sure the previous instruction
+				 * range packet to be handled properly.
+				 */
+				cs_etm__exception(etmq);
+				break;
+			case CS_ETM_DISCONTINUITY:
+				/*
+				 * Discontinuity in trace, flush
+				 * previous branch stack
+				 */
+				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;
+			}
+		}
+
+	return ret;
+}
+
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
-	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_buffer buffer;
-	size_t buffer_used, processed;
 	int err = 0;
 
-	if (!etm->kernel_start)
-		etm->kernel_start = machine__kernel_start(etm->machine);
-
 	/* Go through each buffer in the queue and decode them one by one */
 	while (1) {
-		buffer_used = 0;
-		memset(&buffer, 0, sizeof(buffer));
-		err = cs_etm__get_trace(&buffer, etmq);
+		err = cs_etm__get_data_block(etmq);
 		if (err <= 0)
 			return err;
-		/*
-		 * We cannot assume consecutive blocks in the data file are
-		 * contiguous, reset the decoder to force re-sync.
-		 */
-		err = cs_etm_decoder__reset(etmq->decoder);
-		if (err != 0)
-			return err;
 
 		/* Run trace decoder until buffer consumed or end of trace */
 		do {
-			processed = 0;
-			err = cs_etm_decoder__process_data_block(
-				etmq->decoder,
-				etmq->offset,
-				&buffer.buf[buffer_used],
-				buffer.len - buffer_used,
-				&processed);
+			err = cs_etm__decode_data_block(etmq);
 			if (err)
 				return err;
 
-			etmq->offset += processed;
-			buffer_used += processed;
+			/*
+			 * Process each packet in this chunk, nothing to do if
+			 * an error occurs other than hoping the next one will
+			 * be better.
+			 */
+			err = cs_etm__process_decoder_queue(etmq);
 
-			/* Process each packet in this chunk */
-			while (1) {
-				err = cs_etm_decoder__get_packet(etmq->decoder,
-								 etmq->packet);
-				if (err <= 0)
-					/*
-					 * Stop processing this chunk on
-					 * end of data or error
-					 */
-					break;
-
-				/*
-				 * Since packet addresses are swapped in packet
-				 * handling within below switch() statements,
-				 * thus setting sample flags must be called
-				 * prior to switch() statement to use address
-				 * information before packets swapping.
-				 */
-				err = cs_etm__set_sample_flags(etmq);
-				if (err < 0)
-					break;
-
-				switch (etmq->packet->sample_type) {
-				case CS_ETM_RANGE:
-					/*
-					 * If the packet contains an instruction
-					 * range, generate instruction sequence
-					 * events.
-					 */
-					cs_etm__sample(etmq);
-					break;
-				case CS_ETM_EXCEPTION:
-				case CS_ETM_EXCEPTION_RET:
-					/*
-					 * If the exception packet is coming,
-					 * make sure the previous instruction
-					 * range packet to be handled properly.
-					 */
-					cs_etm__exception(etmq);
-					break;
-				case CS_ETM_DISCONTINUITY:
-					/*
-					 * Discontinuity in trace, flush
-					 * previous branch stack
-					 */
-					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;
-				}
-			}
-		} while (buffer.len > buffer_used);
+		} while (etmq->buf_len);
 
 		if (err == 0)
 			/* Flush any remaining branch stack entries */
@@ -1583,7 +1645,7 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 }
 
 static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
-					   pid_t tid, u64 time_)
+					   pid_t tid)
 {
 	unsigned int i;
 	struct auxtrace_queues *queues = &etm->queues;
@@ -1593,7 +1655,6 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
 		struct cs_etm_queue *etmq = queue->priv;
 
 		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
-			etmq->time = time_;
 			cs_etm__set_pid_tid_cpu(etm, queue);
 			cs_etm__run_decoder(etmq);
 		}
@@ -1637,8 +1698,7 @@ static int cs_etm__process_event(struct perf_session *session,
 
 	if (event->header.type == PERF_RECORD_EXIT)
 		return cs_etm__process_timeless_queues(etm,
-						       event->fork.tid,
-						       sample->time);
+						       event->fork.tid);
 
 	return 0;
 }
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index d76126e0e3d0..0e97c196147a 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -105,8 +105,8 @@ struct intlist *traceid_list;
 
 #define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64))
 
-static const u64 __perf_cs_etmv3_magic   = 0x3030303030303030ULL;
-static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
+#define __perf_cs_etmv3_magic 0x3030303030303030ULL
+#define __perf_cs_etmv4_magic 0x4040404040404040ULL
 #define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64))
 #define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64))
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index dec6d218c31c..61ce197c5362 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -563,7 +563,6 @@ static int write_cmdline(struct feat_fd *ff,
 	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 
 struct cpu_topo {
-	u32 cpu_nr;
 	u32 core_sib;
 	u32 thread_sib;
 	char **core_siblings;
@@ -679,7 +678,6 @@ static struct cpu_topo *build_cpu_topology(void)
 		goto out_free;
 
 	tp = addr;
-	tp->cpu_nr = nr;
 	addr += sizeof(*tp);
 	tp->core_siblings = addr;
 	addr += sz;
@@ -1042,11 +1040,9 @@ static int write_cpuid(struct feat_fd *ff,
 	int ret;
 
 	ret = get_cpuid(buffer, sizeof(buffer));
-	if (!ret)
-		goto write_it;
+	if (ret)
+		return -1;
 
-	return -1;
-write_it:
 	return do_write_string(ff, buffer);
 }
 
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 1b704fbea9de..23bf788f84b9 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
+perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
 
 inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
 inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8529cbd3955b..b8d864ed4afe 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -270,7 +270,7 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
 }
 
 void metricgroup__print(bool metrics, bool metricgroups, char *filter,
-			bool raw)
+			bool raw, bool details)
 {
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
@@ -329,6 +329,12 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 					if (asprintf(&s, "%s\n%*s%s]",
 						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
+
+					if (details) {
+						if (asprintf(&s, "%s\n%*s%s]",
+							     s, 8, "[", pe->metric_expr) < 0)
+							return;
+					}
 				}
 
 				if (!s)
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 8a155dba0581..5c52097a5c63 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -27,6 +27,7 @@ int metricgroup__parse_groups(const struct option *opt,
 			const char *str,
 			struct rblist *metric_events);
 
-void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+void metricgroup__print(bool metrics, bool groups, char *filter,
+			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 920e1e6551dd..4dcc01b2532c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2540,7 +2540,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_sdt_events(NULL, NULL, name_only);
 
-	metricgroup__print(true, true, NULL, name_only);
+	metricgroup__print(true, true, NULL, name_only, details_flag);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index da8fe57691b8..44819bdb037d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -311,7 +311,7 @@ value_sym '/' event_config '/'
 	$$ = list;
 }
 |
-value_sym sep_slash_dc
+value_sym sep_slash_slash_dc
 {
 	struct list_head *list;
 	int type = $1 >> 16;
@@ -702,7 +702,7 @@ PE_VALUE PE_ARRAY_RANGE PE_VALUE
 
 sep_dc: ':' |
 
-sep_slash_dc: '/' | ':' |
+sep_slash_slash_dc: '/' '/' | ':' |
 
 %%
 
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d9525d220db1..c215704931dc 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -352,6 +352,11 @@ static bool s390_cpumsf_validate(int machine_type,
 			*dsdes = 85;
 			*bsdes = 32;
 			break;
+		case 2964:
+		case 2965:
+			*dsdes = 112;
+			*bsdes = 32;
+			break;
 		default:
 			/* Illegal trailer entry */
 			return false;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 82d28c67e0f3..7b342ce38d99 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,5 +1,5 @@
-libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
-libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
+perf-$(CONFIG_LIBPERL)   += trace-event-perl.o
+perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
 CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default