Merge tag 'perf-core-for-mingo-4.20-20180924' 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:

Hardware tracing changes:

 intel-pt:

 - Previously, the decoder would indicate begin / end by a branch from / to zero.
   That hides useful information, in particular when a trace ends with a call.
   Remove that limitation. (Adrian Hunter)

 - Better "callindent" output in 'perf script', improving intel-PT output (Andi Kleen)

Arch specific changes:

 - Split the PMU events into meaningful functional groups for the ARM eMAG arch (Sean V Kelley)

Fixes:

 perf help:

 - Add missing subcommand `version` (Sangwon Hong)

Miscellaneous:

 - More patches renaming of structs, enums, functions to make libbtraceevent
   more generally available (Tzvetomir Stoyanov (VMware))

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

35 files changed, 832 insertions, 255 deletions

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index b4a29f435b06..eda41673c4f3 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -798,7 +798,8 @@ int cmd_inject(int argc, const char **argv)
 			   "kallsyms pathname"),
 		OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
 		OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
-				    NULL, "opts", "Instruction Tracing options",
+				    NULL, "opts", "Instruction Tracing options\n"
+				    ITRACE_HELP,
 				    itrace_parse_synth_opts),
 		OPT_BOOLEAN(0, "strip", &inject.strip,
 			    "strip non-synthesized events (use with --itrace)"),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 7507e4d6dce1..c0703979c51d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1104,7 +1104,7 @@ int cmd_report(int argc, const char **argv)
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 765391b6c88c..4da5e32b9e03 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_WEIGHT))
 		return -EINVAL;
 
-	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+	if (PRINT_FIELD(SYM) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
 		pr_err("Display of symbols requested but neither sample IP nor "
-			   "sample address\nis selected. Hence, no addresses to convert "
+			   "sample address\navailable. Hence, no addresses to convert "
 		       "to symbols.\n");
 		return -EINVAL;
 	}
@@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "selected.\n");
 		return -EINVAL;
 	}
-	if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-	    !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
-		pr_err("Display of DSO requested but no address to convert.  Select\n"
-		       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
+	if (PRINT_FIELD(DSO) &&
+		!(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+		pr_err("Display of DSO requested but no address to convert.\n");
 		return -EINVAL;
 	}
 	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
+	int dlen = 0;
 	u64 ip = 0;
 
 	/*
@@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 			ip = sample->ip;
 	}
 
+	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
+		dlen += fprintf(fp, "(");
+		dlen += map__fprintf_dsoname(al->map, fp);
+		dlen += fprintf(fp, ")\t");
+	}
+
 	if (name)
 		len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
 	else if (ip)
@@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (len < spacing)
 		len += fprintf(fp, "%*s", spacing - len, "");
 
-	return len;
+	return len + dlen;
 }
 
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
@@ -1255,6 +1262,18 @@ static struct {
 	{0, NULL}
 };
 
+static const char *sample_flags_to_name(u32 flags)
+{
+	int i;
+
+	for (i = 0; sample_flags[i].name ; i++) {
+		if (sample_flags[i].flags == flags)
+			return sample_flags[i].name;
+	}
+
+	return NULL;
+}
+
 static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
 	const char *chars = PERF_IP_FLAG_CHARS;
@@ -1264,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	char str[33];
 	int i, pos = 0;
 
-	for (i = 0; sample_flags[i].name ; i++) {
-		if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
-			name = sample_flags[i].name;
-			break;
-		}
+	name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX);
+	if (name)
+		return fprintf(fp, "  %-15s%4s ", name, in_tx ? "(x)" : "");
+
+	if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN));
+		if (name)
+			return fprintf(fp, "  tr strt %-7s%4s ", name, in_tx ? "(x)" : "");
+	}
+
+	if (flags & PERF_IP_FLAG_TRACE_END) {
+		name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END));
+		if (name)
+			return fprintf(fp, "  tr end  %-7s%4s ", name, in_tx ? "(x)" : "");
 	}
 
 	for (i = 0; i < n; i++, flags >>= 1) {
@@ -1281,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 	}
 	str[pos] = 0;
 
-	if (name)
-		return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
-
-	return fprintf(fp, "  %-11s ", str);
+	return fprintf(fp, "  %-19s ", str);
 }
 
 struct printer_data {
@@ -2491,6 +2516,8 @@ parse:
 						output[j].fields &= ~all_output_options[i].field;
 					else
 						output[j].fields |= all_output_options[i].field;
+					output[j].user_set = true;
+					output[j].wildcard_set = true;
 				}
 			}
 		} else {
@@ -2501,7 +2528,8 @@ parse:
 				rc = -EINVAL;
 				goto out;
 			}
-			output[type].fields |= all_output_options[i].field;
+			output[type].user_set = true;
+			output[type].wildcard_set = true;
 		}
 	}
 
@@ -3193,7 +3221,7 @@ int cmd_script(int argc, const char **argv)
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-			    "Instruction Tracing options",
+			    "Instruction Tracing options\n" ITRACE_HELP,
 			    itrace_parse_synth_opts),
 	OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
 			"Show full source file name path for source lines"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7ce277d22a91..90289f31dd87 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -181,7 +181,7 @@ static int __tp_field__init_uint(struct tp_field *field, int size, int offset, b
 	return 0;
 }
 
-static int tp_field__init_uint(struct tp_field *field, struct format_field *format_field, bool needs_swap)
+static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap)
 {
 	return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
 }
@@ -198,7 +198,7 @@ static int __tp_field__init_ptr(struct tp_field *field, int offset)
 	return 0;
 }
 
-static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
+static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field)
 {
 	return __tp_field__init_ptr(field, format_field->offset);
 }
@@ -214,7 +214,7 @@ static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
 					  struct tp_field *field,
 					  const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -230,7 +230,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
 					 struct tp_field *field,
 					 const char *name)
 {
-	struct format_field *format_field = perf_evsel__field(evsel, name);
+	struct tep_format_field *format_field = perf_evsel__field(evsel, name);
 
 	if (format_field == NULL)
 		return -1;
@@ -862,12 +862,12 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
  * args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
  */
 struct syscall {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	int		    nr_args;
 	int		    args_size;
 	bool		    is_exit;
 	bool		    is_open;
-	struct format_field *args;
+	struct tep_format_field *args;
 	const char	    *name;
 	struct syscall_fmt  *fmt;
 	struct syscall_arg_fmt *arg_fmt;
@@ -1279,7 +1279,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
 
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
-	struct format_field *field, *last_field = NULL;
+	struct tep_format_field *field, *last_field = NULL;
 	int idx = 0, len;
 
 	for (field = sc->args; field; field = field->next, ++idx) {
@@ -1293,7 +1293,7 @@ static int syscall__set_arg_fmts(struct syscall *sc)
 			  strcmp(field->name, "path") == 0 ||
 			  strcmp(field->name, "pathname") == 0))
 			sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
-		else if (field->flags & FIELD_IS_POINTER)
+		else if (field->flags & TEP_FIELD_IS_POINTER)
 			sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
 		else if (strcmp(field->type, "pid_t") == 0)
 			sc->arg_fmt[idx].scnprintf = SCA_PID;
@@ -1525,7 +1525,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 	ttrace->ret_scnprintf = NULL;
 
 	if (sc->args != NULL) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		for (field = sc->args; field;
 		     field = field->next, ++arg.idx, bit <<= 1) {
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 2d0caf20ff3a..bc6c585f74fc 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -30,3 +30,4 @@ perf-test			mainporcelain common
 perf-timechart			mainporcelain common
 perf-top			mainporcelain common
 perf-trace			mainporcelain audit
+perf-version			mainporcelain common
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
new file mode 100644
index 000000000000..abc98b018446
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/branch.json
@@ -0,0 +1,23 @@
+[
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC",
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC",
+    },
+    {
+        "PublicDescription": "Mispredicted or not predicted branch speculatively executed",
+        "EventCode": "0x10",
+        "EventName": "BR_MIS_PRED",
+        "BriefDescription": "Branch mispredicted"
+    },
+    {
+        "PublicDescription": "Predictable branch speculatively executed",
+        "EventCode": "0x12",
+        "EventName": "BR_PRED",
+        "BriefDescription": "Predictable branch"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
new file mode 100644
index 000000000000..687b2629e1d1
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/bus.json
@@ -0,0 +1,26 @@
+[
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NOT_SHARED",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_NORMAL",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_PERIPH",
+    },
+    {
+        "PublicDescription": "Bus access",
+        "EventCode": "0x19",
+        "EventName": "BUS_ACCESS",
+        "BriefDescription": "Bus access"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
new file mode 100644
index 000000000000..df9201434cb6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/cache.json
@@ -0,0 +1,191 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache refill",
+        "EventCode": "0x01",
+        "EventName": "L1I_CACHE_REFILL",
+        "BriefDescription": "L1I cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB refill",
+        "EventCode": "0x02",
+        "EventName": "L1I_TLB_REFILL",
+        "BriefDescription": "L1I TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache refill",
+        "EventCode": "0x03",
+        "EventName": "L1D_CACHE_REFILL",
+        "BriefDescription": "L1D cache refill"
+    },
+    {
+        "PublicDescription": "Level 1 data cache access",
+        "EventCode": "0x04",
+        "EventName": "L1D_CACHE_ACCESS",
+        "BriefDescription": "L1D cache access"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB refill",
+        "EventCode": "0x05",
+        "EventName": "L1D_TLB_REFILL",
+        "BriefDescription": "L1D TLB refill"
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache access",
+        "EventCode": "0x14",
+        "EventName": "L1I_CACHE_ACCESS",
+        "BriefDescription": "L1I cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data cache access",
+        "EventCode": "0x16",
+        "EventName": "L2D_CACHE_ACCESS",
+        "BriefDescription": "L2D cache access"
+    },
+    {
+        "PublicDescription": "Level 2 data refill",
+        "EventCode": "0x17",
+        "EventName": "L2D_CACHE_REFILL",
+        "BriefDescription": "L2D cache refill"
+    },
+    {
+        "PublicDescription": "Level 2 data cache, Write-Back",
+        "EventCode": "0x18",
+        "EventName": "L2D_CACHE_WB",
+        "BriefDescription": "L2D cache Write-Back"
+    },
+    {
+        "PublicDescription": "Level 1 data TLB access. This event counts any load or store operation which accesses the data L1 TLB",
+        "EventCode": "0x25",
+        "EventName": "L1D_TLB_ACCESS",
+        "BriefDescription": "L1D TLB access"
+    },
+    {
+        "PublicDescription": "Level 1 instruction TLB access. This event counts any instruction fetch which accesses the instruction L1 TLB",
+        "EventCode": "0x26",
+        "EventName": "L1I_TLB_ACCESS",
+        "BriefDescription": "L1I TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to data TLB that caused a page table walk. This event counts on any data access which causes L2D_TLB_REFILL to count",
+        "EventCode": "0x34",
+        "EventName": "L2D_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Level 2 access to instruciton TLB that caused a page table walk. This event counts on any instruciton access which causes L2I_TLB_REFILL to count",
+        "EventCode": "0x35",
+        "EventName": "L2I_TLB_ACCESS",
+        "BriefDescription": "L2D TLB access"
+    },
+    {
+        "PublicDescription": "Branch target buffer misprediction",
+        "EventCode": "0x102",
+        "EventName": "BTB_MIS_PRED",
+        "BriefDescription": "BTB misprediction"
+    },
+    {
+        "PublicDescription": "ITB miss",
+        "EventCode": "0x103",
+        "EventName": "ITB_MISS",
+        "BriefDescription": "ITB miss"
+    },
+    {
+        "PublicDescription": "DTB miss",
+        "EventCode": "0x104",
+        "EventName": "DTB_MISS",
+        "BriefDescription": "DTB miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache late miss",
+        "EventCode": "0x105",
+        "EventName": "L1D_CACHE_LATE_MISS",
+        "BriefDescription": "L1D cache late miss"
+    },
+    {
+        "PublicDescription": "Level 1 data cache prefetch request",
+        "EventCode": "0x106",
+        "EventName": "L1D_CACHE_PREFETCH",
+        "BriefDescription": "L1D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 2 data cache prefetch request",
+        "EventCode": "0x107",
+        "EventName": "L2D_CACHE_PREFETCH",
+        "BriefDescription": "L2D cache prefetch"
+    },
+    {
+        "PublicDescription": "Level 1 stage 2 TLB refill",
+        "EventCode": "0x111",
+        "EventName": "L1_STAGE2_TLB_REFILL",
+        "BriefDescription": "L1 stage 2 TLB refill"
+    },
+    {
+        "PublicDescription": "Page walk cache level-0 stage-1 hit",
+        "EventCode": "0x112",
+        "EventName": "PAGE_WALK_L0_STAGE1_HIT",
+        "BriefDescription": "Page walk, L0 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-1 hit",
+        "EventCode": "0x113",
+        "EventName": "PAGE_WALK_L1_STAGE1_HIT",
+        "BriefDescription": "Page walk, L1 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-1 hit",
+        "EventCode": "0x114",
+        "EventName": "PAGE_WALK_L2_STAGE1_HIT",
+        "BriefDescription": "Page walk, L2 stage-1 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-1 stage-2 hit",
+        "EventCode": "0x115",
+        "EventName": "PAGE_WALK_L1_STAGE2_HIT",
+        "BriefDescription": "Page walk, L1 stage-2 hit"
+    },
+    {
+        "PublicDescription": "Page walk cache level-2 stage-2 hit",
+        "EventCode": "0x116",
+        "EventName": "PAGE_WALK_L2_STAGE2_HIT",
+        "BriefDescription": "Page walk, L2 stage-2 hit"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
new file mode 100644
index 000000000000..38cd1f1a70dc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/clock.json
@@ -0,0 +1,20 @@
+[
+    {
+        "PublicDescription": "The number of core clock cycles",
+        "EventCode": "0x11",
+        "EventName": "CPU_CYCLES",
+        "BriefDescription": "Clock cycles"
+    },
+    {
+        "PublicDescription": "FSU clocking gated off cycle",
+        "EventCode": "0x101",
+        "EventName": "FSU_CLOCK_OFF_CYCLES",
+        "BriefDescription": "FSU clocking gated off cycle"
+    },
+    {
+        "PublicDescription": "Wait state cycle",
+        "EventCode": "0x110",
+        "EventName": "Wait_CYCLES",
+        "BriefDescription": "Wait state cycle"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
deleted file mode 100644
index bc03c06c3918..000000000000
--- a/tools/perf/pmu-events/arch/arm64/ampere/emag/core-imp-def.json
+++ /dev/null
@@ -1,32 +0,0 @@
-[
-    {
-        "ArchStdEvent": "L1D_CACHE_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_REFILL_WR",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_RD",
-    },
-    {
-        "ArchStdEvent": "L1D_TLB_WR",
-    },
-    {
-        "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
-        "ArchStdEvent": "BUS_ACCESS_WR",
-   }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
new file mode 100644
index 000000000000..3720dc28a15f
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/exception.json
@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    },
+    {
+        "PublicDescription": "Exception taken",
+        "EventCode": "0x09",
+        "EventName": "EXC_TAKEN",
+        "BriefDescription": "Exception taken"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition check pass, exception return",
+        "EventCode": "0x0a",
+        "EventName": "EXC_RETURN",
+        "BriefDescription": "Exception return"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
new file mode 100644
index 000000000000..82cf753e6472
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/instruction.json
@@ -0,0 +1,89 @@
+[
+    {
+        "ArchStdEvent": "LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "DP_SPEC",
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC",
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC",
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC",
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC",
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC",
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC",
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, software increment",
+        "EventCode": "0x00",
+        "EventName": "SW_INCR",
+        "BriefDescription": "Software increment"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed",
+        "EventCode": "0x08",
+        "EventName": "INST_RETIRED",
+        "BriefDescription": "Instruction retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, condition code check pass, write to CONTEXTIDR",
+        "EventCode": "0x0b",
+        "EventName": "CID_WRITE_RETIRED",
+        "BriefDescription": "Write to CONTEXTIDR"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed",
+        "EventCode": "0x1b",
+        "EventName": "INST_SPEC",
+        "BriefDescription": "Speculatively executed"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed (condition check pass), write to TTBR",
+        "EventCode": "0x1c",
+        "EventName": "TTBR_WRITE_RETIRED",
+        "BriefDescription": "Instruction executed, TTBR write"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, branch. This event counts all branches, taken or not. This excludes exception entries, debug entries and CCFAIL branches",
+        "EventCode": "0x21",
+        "EventName": "BR_RETIRED",
+        "BriefDescription": "Branch retired"
+    },
+    {
+        "PublicDescription": "Instruction architecturally executed, mispredicted branch. This event counts any branch counted by BR_RETIRED which is not correctly predicted and causes a pipeline flush",
+        "EventCode": "0x22",
+        "EventName": "BR_MISPRED_RETIRED",
+        "BriefDescription": "Mispredicted branch retired"
+    },
+    {
+        "PublicDescription": "Operation speculatively executed, NOP",
+        "EventCode": "0x100",
+        "EventName": "NOP_SPEC",
+        "BriefDescription": "Speculatively executed, NOP"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
new file mode 100644
index 000000000000..2aecc5c2347d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/intrinsic.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "LDREX_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC",
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC",
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
new file mode 100644
index 000000000000..08508697b318
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/memory.json
@@ -0,0 +1,29 @@
+[
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "PublicDescription": "Data memory access",
+        "EventCode": "0x13",
+        "EventName": "MEM_ACCESS",
+        "BriefDescription": "Memory access"
+    },
+    {
+        "PublicDescription": "Local memory error. This event counts any correctable or uncorrectable memory error (ECC or parity) in the protected core RAMs",
+        "EventCode": "0x1a",
+        "EventName": "MEM_ERROR",
+        "BriefDescription": "Memory error"
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
new file mode 100644
index 000000000000..e2087de586bf
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/ampere/emag/pipeline.json
@@ -0,0 +1,50 @@
+[
+    {
+        "PublicDescription": "Decode starved for instruction cycle",
+        "EventCode": "0x108",
+        "EventName": "DECODE_STALL",
+        "BriefDescription": "Decode starved"
+    },
+    {
+        "PublicDescription": "Op dispatch stalled cycle",
+        "EventCode": "0x109",
+        "EventName": "DISPATCH_STALL",
+        "BriefDescription": "Dispatch stalled"
+    },
+    {
+        "PublicDescription": "IXA Op non-issue",
+        "EventCode": "0x10a",
+        "EventName": "IXA_STALL",
+        "BriefDescription": "IXA stalled"
+    },
+    {
+        "PublicDescription": "IXB Op non-issue",
+        "EventCode": "0x10b",
+        "EventName": "IXB_STALL",
+        "BriefDescription": "IXB stalled"
+    },
+    {
+        "PublicDescription": "BX Op non-issue",
+        "EventCode": "0x10c",
+        "EventName": "BX_STALL",
+        "BriefDescription": "BX stalled"
+    },
+    {
+        "PublicDescription": "LX Op non-issue",
+        "EventCode": "0x10d",
+        "EventName": "LX_STALL",
+        "BriefDescription": "LX stalled"
+    },
+    {
+        "PublicDescription": "SX Op non-issue",
+        "EventCode": "0x10e",
+        "EventName": "SX_STALL",
+        "BriefDescription": "SX stalled"
+    },
+    {
+        "PublicDescription": "FX Op non-issue",
+        "EventCode": "0x10f",
+        "EventName": "FX_STALL",
+        "BriefDescription": "FX stalled"
+    },
+]
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 699561fa512c..5f8501c68da4 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -8,7 +8,7 @@
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int is_signed;
 	int ret = 0;
 
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | FIELD_IS_SIGNED);
+	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index a86b7eab6673..0a6ce9c4fc11 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -576,6 +576,23 @@ static inline void auxtrace__free(struct perf_session *session)
 	return session->auxtrace->free(session);
 }
 
+#define ITRACE_HELP \
+"				i:	    		synthesize instructions events\n"		\
+"				b:	    		synthesize branches events\n"		\
+"				c:	    		synthesize branches events (calls only)\n"	\
+"				r:	    		synthesize branches events (returns only)\n" \
+"				x:	    		synthesize transactions events\n"		\
+"				w:	    		synthesize ptwrite events\n"		\
+"				p:	    		synthesize power events\n"			\
+"				e:	    		synthesize error events\n"			\
+"				d:	    		create a debug log\n"			\
+"				g[len]:     		synthesize a call chain (use with i or x)\n" \
+"				l[len]:     		synthesize last branch entries (use with i or x)\n" \
+"				sNUMBER:    		skip initial number of events\n"		\
+"				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
+"				concatenate multiple options. Default is ibxwpe or cewp\n"
+
+
 #else
 
 static inline struct auxtrace_record *
@@ -716,6 +733,8 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct perf_evlist *evlist, int idx,
 				   bool per_cpu);
 
+#define ITRACE_HELP ""
+
 #endif
 
 #endif
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index f75d4aa612c5..2a36fab76994 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -182,20 +182,20 @@ err_put_field:
 }
 
 static struct bt_ctf_field_type*
-get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
+get_tracepoint_field_type(struct ctf_writer *cw, struct tep_format_field *field)
 {
 	unsigned long flags = field->flags;
 
-	if (flags & FIELD_IS_STRING)
+	if (flags & TEP_FIELD_IS_STRING)
 		return cw->data.string;
 
-	if (!(flags & FIELD_IS_SIGNED)) {
+	if (!(flags & TEP_FIELD_IS_SIGNED)) {
 		/* unsigned long are mostly pointers */
-		if (flags & FIELD_IS_LONG || flags & FIELD_IS_POINTER)
+		if (flags & TEP_FIELD_IS_LONG || flags & TEP_FIELD_IS_POINTER)
 			return cw->data.u64_hex;
 	}
 
-	if (flags & FIELD_IS_SIGNED) {
+	if (flags & TEP_FIELD_IS_SIGNED) {
 		if (field->size == 8)
 			return cw->data.s64;
 		else
@@ -287,7 +287,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
 				      struct perf_sample *sample,
-				      struct format_field *fmtf)
+				      struct tep_format_field *fmtf)
 {
 	struct bt_ctf_field_type *type;
 	struct bt_ctf_field *array_field;
@@ -304,10 +304,10 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
-	if (flags & FIELD_IS_STRING)
-		flags &= ~FIELD_IS_ARRAY;
+	if (flags & TEP_FIELD_IS_STRING)
+		flags &= ~TEP_FIELD_IS_ARRAY;
 
-	if (flags & FIELD_IS_DYNAMIC) {
+	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
 		tmp_val = tep_read_number(fmtf->event->pevent,
@@ -317,7 +317,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		offset &= 0xffff;
 	}
 
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 
 		type = bt_ctf_event_class_get_field_by_name(
 				event_class, name);
@@ -338,7 +338,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
 			field = bt_ctf_field_create(type);
@@ -348,7 +348,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			return -1;
 		}
 
-		if (flags & FIELD_IS_STRING)
+		if (flags & TEP_FIELD_IS_STRING)
 			ret = string_set_value(field, data + offset + i * len);
 		else {
 			unsigned long long value_int;
@@ -357,7 +357,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 					fmtf->event->pevent,
 					data + offset + i * len, len);
 
-			if (!(flags & FIELD_IS_SIGNED))
+			if (!(flags & TEP_FIELD_IS_SIGNED))
 				ret = bt_ctf_field_unsigned_integer_set_value(
 						field, value_int);
 			else
@@ -369,7 +369,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
 		}
-		if (!(flags & FIELD_IS_ARRAY)) {
+		if (!(flags & TEP_FIELD_IS_ARRAY)) {
 			ret = bt_ctf_event_set_payload(event, name, field);
 			if (ret) {
 				pr_err("failed to set payload %s\n", name);
@@ -378,7 +378,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		}
 		bt_ctf_field_put(field);
 	}
-	if (flags & FIELD_IS_ARRAY) {
+	if (flags & TEP_FIELD_IS_ARRAY) {
 		ret = bt_ctf_event_set_payload(event, name, array_field);
 		if (ret) {
 			pr_err("Failed add payload array %s\n", name);
@@ -396,10 +396,10 @@ err_put_field:
 static int add_tracepoint_fields_values(struct ctf_writer *cw,
 					struct bt_ctf_event_class *event_class,
 					struct bt_ctf_event *event,
-					struct format_field *fields,
+					struct tep_format_field *fields,
 					struct perf_sample *sample)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -417,8 +417,8 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 				 struct perf_evsel *evsel,
 				 struct perf_sample *sample)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_values(cw, event_class, event,
@@ -970,7 +970,7 @@ out:
 
 static int event_class_add_field(struct bt_ctf_event_class *event_class,
 		struct bt_ctf_field_type *type,
-		struct format_field *field)
+		struct tep_format_field *field)
 {
 	struct bt_ctf_field_type *t = NULL;
 	char *name;
@@ -1009,10 +1009,10 @@ static int event_class_add_field(struct bt_ctf_event_class *event_class,
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
-				       struct format_field *fields,
+				       struct tep_format_field *fields,
 				       struct bt_ctf_event_class *event_class)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	int ret;
 
 	for (field = fields; field; field = field->next) {
@@ -1030,15 +1030,15 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		 * type and don't care that it is an array. What we don't
 		 * support is an array of strings.
 		 */
-		if (flags & FIELD_IS_STRING)
-			flags &= ~FIELD_IS_ARRAY;
+		if (flags & TEP_FIELD_IS_STRING)
+			flags &= ~TEP_FIELD_IS_ARRAY;
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
 		ret = event_class_add_field(event_class, type, field);
 
-		if (flags & FIELD_IS_ARRAY)
+		if (flags & TEP_FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
@@ -1055,8 +1055,8 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 				struct perf_evsel *evsel,
 				struct bt_ctf_event_class *class)
 {
-	struct format_field *common_fields = evsel->tp_format->format.common_fields;
-	struct format_field *fields        = evsel->tp_format->format.fields;
+	struct tep_format_field *common_fields = evsel->tp_format->format.common_fields;
+	struct tep_format_field *fields        = evsel->tp_format->format.fields;
 	int ret;
 
 	ret = add_tracepoint_fields_types(cw, common_fields, class);
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 7123746edcf4..69fbb0a72d0c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -463,6 +463,28 @@ int db_export__branch_types(struct db_export *dbe)
 		if (err)
 			break;
 	}
+
+	/* Add trace begin / end variants */
+	for (i = 0; branch_types[i].name ; i++) {
+		const char *name = branch_types[i].name;
+		u32 type = branch_types[i].branch_type;
+		char buf[64];
+
+		if (type == PERF_IP_FLAG_BRANCH ||
+		    (type & (PERF_IP_FLAG_TRACE_BEGIN | PERF_IP_FLAG_TRACE_END)))
+			continue;
+
+		snprintf(buf, sizeof(buf), "trace begin / %s", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_BEGIN, buf);
+		if (err)
+			break;
+
+		snprintf(buf, sizeof(buf), "%s / trace end", name);
+		err = db_export__branch_type(dbe, type | PERF_IP_FLAG_TRACE_END, buf);
+		if (err)
+			break;
+	}
+
 	return err;
 }
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4ec909d57e9c..cb7f01059940 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2682,7 +2682,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	return 0;
 }
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
@@ -2690,7 +2690,7 @@ struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *nam
 void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 			 const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 	int offset;
 
 	if (!field)
@@ -2698,7 +2698,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 
 	offset = field->offset;
 
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		offset = *(int *)(sample->raw_data + field->offset);
 		offset &= 0xffff;
 	}
@@ -2706,7 +2706,7 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
 	return sample->raw_data + offset;
 }
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
 			 bool needs_swap)
 {
 	u64 value;
@@ -2748,7 +2748,7 @@ u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
 u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
 		       const char *name)
 {
-	struct format_field *field = perf_evsel__field(evsel, name);
+	struct tep_format_field *field = perf_evsel__field(evsel, name);
 
 	if (!field)
 		return 0;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4f8430a85531..4107c39f4a54 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,7 +102,7 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	struct event_format	*tp_format;
+	struct tep_event_format	*tp_format;
 	off_t			id_offset;
 	struct perf_stat_evsel  *stats;
 	void			*priv;
@@ -211,7 +211,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
 
 struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
-struct event_format *event_format__new(const char *sys, const char *name);
+struct tep_event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx);
@@ -296,11 +296,11 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 	return perf_evsel__rawptr(evsel, sample, name);
 }
 
-struct format_field;
+struct tep_format_field;
 
-u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
+struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
 	(evsel->attr.type == PERF_TYPE_##t &&	\
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 06dfb027879d..0d0a4c6f368b 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -73,7 +73,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 	}
 
 	if (details->trace_fields) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
 			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c78051ad1fcc..1ec1d9bc2d63 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3206,7 +3206,7 @@ static int read_attr(int fd, struct perf_header *ph,
 static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 						struct tep_handle *pevent)
 {
-	struct event_format *event;
+	struct tep_event_format *event;
 	char bf[128];
 
 	/* already prepared */
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index d404bed7003a..58f6a9ceb590 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1165,7 +1165,7 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 		decoder->pge = false;
 		decoder->continuous_period = false;
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_TRACE_END;
 		return 0;
 	}
 	if (err == INTEL_PT_RETURN)
@@ -1179,9 +1179,13 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->continuous_period = false;
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0)
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
+				decoder->state.to_ip = decoder->last_ip;
 				decoder->ip = decoder->last_ip;
+			}
+			decoder->state.type |= INTEL_PT_TRACE_END;
 		} else {
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->state.from_ip = decoder->ip;
@@ -1208,7 +1212,8 @@ static int intel_pt_walk_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->ip = to_ip;
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
+			decoder->state.to_ip = to_ip;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 		}
 		intel_pt_log_at("ERROR: Conditional branch when expecting indirect branch",
@@ -1640,14 +1645,15 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_TIP_PGD:
 			decoder->state.from_ip = decoder->ip;
-			decoder->state.to_ip = 0;
-			if (decoder->packet.count != 0) {
+			if (decoder->packet.count == 0) {
+				decoder->state.to_ip = 0;
+			} else {
 				intel_pt_set_ip(decoder);
-				intel_pt_log("Omitting PGD ip " x64_fmt "\n",
-					     decoder->ip);
+				decoder->state.to_ip = decoder->ip;
 			}
 			decoder->pge = false;
 			decoder->continuous_period = false;
+			decoder->state.type |= INTEL_PT_TRACE_END;
 			return 0;
 
 		case INTEL_PT_TIP_PGE:
@@ -1661,6 +1667,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 				intel_pt_set_ip(decoder);
 				decoder->state.to_ip = decoder->ip;
 			}
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 
 		case INTEL_PT_TIP:
@@ -1739,6 +1746,7 @@ next:
 			intel_pt_set_ip(decoder);
 			decoder->state.from_ip = 0;
 			decoder->state.to_ip = decoder->ip;
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
 			return 0;
 		}
 
@@ -2077,9 +2085,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
 			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
-			if (decoder->ip)
-				return 0;
-			break;
+			if (!decoder->ip)
+				break;
+			if (decoder->packet.type == INTEL_PT_TIP_PGE)
+				decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			if (decoder->packet.type == INTEL_PT_TIP_PGD)
+				decoder->state.type |= INTEL_PT_TRACE_END;
+			return 0;
 
 		case INTEL_PT_FUP:
 			if (intel_pt_have_ip(decoder))
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 51c18d67f4ca..ed088d4726ba 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -37,6 +37,8 @@ enum intel_pt_sample_type {
 	INTEL_PT_EX_STOP	= 1 << 6,
 	INTEL_PT_PWR_EXIT	= 1 << 7,
 	INTEL_PT_CBR_CHG	= 1 << 8,
+	INTEL_PT_TRACE_BEGIN	= 1 << 9,
+	INTEL_PT_TRACE_END	= 1 << 10,
 };
 
 enum intel_pt_period_type {
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index aec68908d604..48c1d415c6b0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -908,6 +908,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 		ptq->insn_len = ptq->state->insn_len;
 		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
 	}
+
+	if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
+		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
+	if (ptq->state->type & INTEL_PT_TRACE_END)
+		ptq->flags |= PERF_IP_FLAG_TRACE_END;
 }
 
 static int intel_pt_setup_queue(struct intel_pt *pt,
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ce501ba14b08..50150dfc0cdf 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -340,7 +340,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 }
 
 static PyObject*
-tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
 	struct tep_handle *pevent = field->event->pevent;
 	void *data = pe->sample.raw_data;
@@ -348,28 +348,28 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 	unsigned long long val;
 	unsigned int offset, len;
 
-	if (field->flags & FIELD_IS_ARRAY) {
+	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len    = field->size;
-		if (field->flags & FIELD_IS_DYNAMIC) {
+		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 			val     = tep_read_number(pevent, data + offset, len);
 			offset  = val;
 			len     = offset >> 16;
 			offset &= 0xffff;
 		}
-		if (field->flags & FIELD_IS_STRING &&
+		if (field->flags & TEP_FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
 			ret = _PyUnicode_FromString((char *)data + offset);
 		} else {
 			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-			field->flags &= ~FIELD_IS_STRING;
+			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
 		val = tep_read_number(pevent, data + field->offset,
 				      field->size);
-		if (field->flags & FIELD_IS_POINTER)
+		if (field->flags & TEP_FIELD_IS_POINTER)
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
-		else if (field->flags & FIELD_IS_SIGNED)
+		else if (field->flags & TEP_FIELD_IS_SIGNED)
 			ret = PyLong_FromLong((long) val);
 		else
 			ret = PyLong_FromUnsignedLong((unsigned long) val);
@@ -383,10 +383,10 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 {
 	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
 	struct perf_evsel *evsel = pevent->evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	if (!evsel->tp_format) {
-		struct event_format *tp_format;
+		struct tep_event_format *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->attr.config);
 		if (!tp_format)
@@ -1240,7 +1240,7 @@ static struct {
 static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct event_format *tp_format;
+	struct tep_event_format *tp_format;
 	static char *kwlist[] = { "sys", "name", NULL };
 	char *sys  = NULL;
 	char *name = NULL;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 45484f0f7292..89cb887648f9 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -99,7 +99,7 @@ static void define_symbolic_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_symbolic_values(struct print_flag_sym *field,
+static void define_symbolic_values(struct tep_print_flag_sym *field,
 				   const char *ev_name,
 				   const char *field_name)
 {
@@ -157,7 +157,7 @@ static void define_flag_value(const char *ev_name,
 	LEAVE;
 }
 
-static void define_flag_values(struct print_flag_sym *field,
+static void define_flag_values(struct tep_print_flag_sym *field,
 			       const char *ev_name,
 			       const char *field_name)
 {
@@ -189,62 +189,62 @@ static void define_flag_field(const char *ev_name,
 	LEAVE;
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
+	case TEP_PRINT_ATOM:
 		define_flag_value(ev_name, cur_field_name, "0",
 				  args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
 		define_flag_field(ev_name, cur_field_name, args->flags.delim);
 		define_flag_values(args->flags.flags, ev_name, cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
 		define_symbolic_field(ev_name, cur_field_name);
 		define_symbolic_values(args->symbol.symbols, ev_name,
 				       cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_STRING:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_STRING:
+	case TEP_PRINT_BITMASK:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
 		define_event_symbols(event, ev_name, args->op.right);
 		break;
-	case PRINT_FUNC:
+	case TEP_PRINT_FUNC:
 	default:
 		pr_err("Unsupported print arg type\n");
 		/* we should warn... */
@@ -338,8 +338,8 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct addr_location *al)
 {
 	struct thread *thread = al->thread;
-	struct event_format *event = evsel->tp_format;
-	struct format_field *field;
+	struct tep_event_format *event = evsel->tp_format;
+	struct tep_format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
@@ -388,9 +388,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	/* common fields other than pid can be accessed via xsub fns */
 
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
+		if (field->flags & TEP_FIELD_IS_STRING) {
 			int offset;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				offset = *(int *)(data + field->offset);
 				offset &= 0xffff;
 			} else
@@ -399,7 +399,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 		} else { /* FIELD_IS_NUMERIC */
 			val = read_size(event, data + field->offset,
 					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
+			if (field->flags & TEP_FIELD_IS_SIGNED) {
 				XPUSHs(sv_2mortal(newSViv(val)));
 			} else {
 				XPUSHs(sv_2mortal(newSVuv(val)));
@@ -537,8 +537,8 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -646,11 +646,11 @@ sub print_backtrace\n\
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -668,7 +668,7 @@ sub print_backtrace\n\
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t       ");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
@@ -678,7 +678,7 @@ sub print_backtrace\n\
 					event->name);
 				fprintf(ofp, "\"%s\", $%s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t       ");
 					count = 4;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index dfc6093f118c..69aa93d4ee99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -193,7 +193,7 @@ static void try_call_object(const char *handler_name, PyObject *args)
 		call_object(handler, args, handler_name);
 }
 
-static void define_value(enum print_arg_type field_type,
+static void define_value(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *field_value,
@@ -204,7 +204,7 @@ static void define_value(enum print_arg_type field_type,
 	unsigned long long value;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_value";
 
 	t = PyTuple_New(4);
@@ -223,8 +223,8 @@ static void define_value(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_values(enum print_arg_type field_type,
-			  struct print_flag_sym *field,
+static void define_values(enum tep_print_arg_type field_type,
+			  struct tep_print_flag_sym *field,
 			  const char *ev_name,
 			  const char *field_name)
 {
@@ -235,7 +235,7 @@ static void define_values(enum print_arg_type field_type,
 		define_values(field_type, field->next, ev_name, field_name);
 }
 
-static void define_field(enum print_arg_type field_type,
+static void define_field(enum tep_print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
 			 const char *delim)
@@ -244,10 +244,10 @@ static void define_field(enum print_arg_type field_type,
 	PyObject *t;
 	unsigned n = 0;
 
-	if (field_type == PRINT_SYMBOL)
+	if (field_type == TEP_PRINT_SYMBOL)
 		handler_name = "define_symbolic_field";
 
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		t = PyTuple_New(3);
 	else
 		t = PyTuple_New(2);
@@ -256,7 +256,7 @@ static void define_field(enum print_arg_type field_type,
 
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
 	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
-	if (field_type == PRINT_FLAGS)
+	if (field_type == TEP_PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
 
 	try_call_object(handler_name, t);
@@ -264,54 +264,54 @@ static void define_field(enum print_arg_type field_type,
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event_format *event,
 				 const char *ev_name,
-				 struct print_arg *args)
+				 struct tep_print_arg *args)
 {
 	if (args == NULL)
 		return;
 
 	switch (args->type) {
-	case PRINT_NULL:
+	case TEP_PRINT_NULL:
 		break;
-	case PRINT_ATOM:
-		define_value(PRINT_FLAGS, ev_name, cur_field_name, "0",
+	case TEP_PRINT_ATOM:
+		define_value(TEP_PRINT_FLAGS, ev_name, cur_field_name, "0",
 			     args->atom.atom);
 		zero_flag_atom = 0;
 		break;
-	case PRINT_FIELD:
+	case TEP_PRINT_FIELD:
 		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
-	case PRINT_FLAGS:
+	case TEP_PRINT_FLAGS:
 		define_event_symbols(event, ev_name, args->flags.field);
-		define_field(PRINT_FLAGS, ev_name, cur_field_name,
+		define_field(TEP_PRINT_FLAGS, ev_name, cur_field_name,
 			     args->flags.delim);
-		define_values(PRINT_FLAGS, args->flags.flags, ev_name,
+		define_values(TEP_PRINT_FLAGS, args->flags.flags, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_SYMBOL:
+	case TEP_PRINT_SYMBOL:
 		define_event_symbols(event, ev_name, args->symbol.field);
-		define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL);
-		define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
+		define_field(TEP_PRINT_SYMBOL, ev_name, cur_field_name, NULL);
+		define_values(TEP_PRINT_SYMBOL, args->symbol.symbols, ev_name,
 			      cur_field_name);
 		break;
-	case PRINT_HEX:
-	case PRINT_HEX_STR:
+	case TEP_PRINT_HEX:
+	case TEP_PRINT_HEX_STR:
 		define_event_symbols(event, ev_name, args->hex.field);
 		define_event_symbols(event, ev_name, args->hex.size);
 		break;
-	case PRINT_INT_ARRAY:
+	case TEP_PRINT_INT_ARRAY:
 		define_event_symbols(event, ev_name, args->int_array.field);
 		define_event_symbols(event, ev_name, args->int_array.count);
 		define_event_symbols(event, ev_name, args->int_array.el_size);
 		break;
-	case PRINT_STRING:
+	case TEP_PRINT_STRING:
 		break;
-	case PRINT_TYPE:
+	case TEP_PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
 		break;
-	case PRINT_OP:
+	case TEP_PRINT_OP:
 		if (strcmp(args->op.op, ":") == 0)
 			zero_flag_atom = 1;
 		define_event_symbols(event, ev_name, args->op.left);
@@ -319,11 +319,11 @@ static void define_event_symbols(struct event_format *event,
 		break;
 	default:
 		/* gcc warns for these? */
-	case PRINT_BSTRING:
-	case PRINT_DYNAMIC_ARRAY:
-	case PRINT_DYNAMIC_ARRAY_LEN:
-	case PRINT_FUNC:
-	case PRINT_BITMASK:
+	case TEP_PRINT_BSTRING:
+	case TEP_PRINT_DYNAMIC_ARRAY:
+	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
+	case TEP_PRINT_FUNC:
+	case TEP_PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -332,10 +332,10 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static PyObject *get_field_numeric_entry(struct event_format *event,
-		struct format_field *field, void *data)
+static PyObject *get_field_numeric_entry(struct tep_event_format *event,
+		struct tep_format_field *field, void *data)
 {
-	bool is_array = field->flags & FIELD_IS_ARRAY;
+	bool is_array = field->flags & TEP_FIELD_IS_ARRAY;
 	PyObject *obj = NULL, *list = NULL;
 	unsigned long long val;
 	unsigned int item_size, n_items, i;
@@ -353,7 +353,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 
 		val = read_size(event, data + field->offset + i * item_size,
 				item_size);
-		if (field->flags & FIELD_IS_SIGNED) {
+		if (field->flags & TEP_FIELD_IS_SIGNED) {
 			if ((long long)val >= LONG_MIN &&
 					(long long)val <= LONG_MAX)
 				obj = _PyLong_FromLong(val);
@@ -790,11 +790,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
 {
-	struct event_format *event = evsel->tp_format;
+	struct tep_event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj = NULL, *callchain;
 	PyObject *dict = NULL, *all_entries_dict = NULL;
 	static char handler_name[256];
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long s, ns;
 	unsigned n = 0;
 	int pid;
@@ -867,22 +867,22 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		unsigned int offset, len;
 		unsigned long long val;
 
-		if (field->flags & FIELD_IS_ARRAY) {
+		if (field->flags & TEP_FIELD_IS_ARRAY) {
 			offset = field->offset;
 			len    = field->size;
-			if (field->flags & FIELD_IS_DYNAMIC) {
+			if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 				val     = tep_read_number(scripting_context->pevent,
 							  data + offset, len);
 				offset  = val;
 				len     = offset >> 16;
 				offset &= 0xffff;
 			}
-			if (field->flags & FIELD_IS_STRING &&
+			if (field->flags & TEP_FIELD_IS_STRING &&
 			    is_printable_array(data + offset, len)) {
 				obj = _PyUnicode_FromString((char *) data + offset);
 			} else {
 				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
-				field->flags &= ~FIELD_IS_STRING;
+				field->flags &= ~TEP_FIELD_IS_STRING;
 			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
@@ -1590,8 +1590,8 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	struct tep_event_format *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
 	int not_first, count;
 	FILE *ofp;
@@ -1686,12 +1686,12 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			count++;
 
 			fprintf(ofp, "%s=", f->name);
-			if (f->flags & FIELD_IS_STRING ||
-			    f->flags & FIELD_IS_FLAG ||
-			    f->flags & FIELD_IS_ARRAY ||
-			    f->flags & FIELD_IS_SYMBOLIC)
+			if (f->flags & TEP_FIELD_IS_STRING ||
+			    f->flags & TEP_FIELD_IS_FLAG ||
+			    f->flags & TEP_FIELD_IS_ARRAY ||
+			    f->flags & TEP_FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
-			else if (f->flags & FIELD_IS_SIGNED)
+			else if (f->flags & TEP_FIELD_IS_SIGNED)
 				fprintf(ofp, "%%d");
 			else
 				fprintf(ofp, "%%u");
@@ -1709,7 +1709,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 			if (++count % 5 == 0)
 				fprintf(ofp, "\n\t\t");
 
-			if (f->flags & FIELD_IS_FLAG) {
+			if (f->flags & TEP_FIELD_IS_FLAG) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
@@ -1719,7 +1719,7 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 					event->name);
 				fprintf(ofp, "\"%s\", %s)", f->name,
 					f->name);
-			} else if (f->flags & FIELD_IS_SYMBOLIC) {
+			} else if (f->flags & TEP_FIELD_IS_SYMBOLIC) {
 				if ((count - 1) % 5 != 0) {
 					fprintf(ofp, "\n\t\t");
 					count = 4;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b284276ec963..f96c005b3c41 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1884,7 +1884,7 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
 struct hpp_dynamic_entry {
 	struct perf_hpp_fmt hpp;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned dynamic_len;
 	bool raw_trace;
 };
@@ -1899,7 +1899,7 @@ static int hde_width(struct hpp_dynamic_entry *hde)
 		if (namelen > len)
 			len = namelen;
 
-		if (!(hde->field->flags & FIELD_IS_STRING)) {
+		if (!(hde->field->flags & TEP_FIELD_IS_STRING)) {
 			/* length for print hex numbers */
 			fieldlen = hde->field->size * 2 + 2;
 		}
@@ -1915,7 +1915,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 			       struct hist_entry *he)
 {
 	char *str, *pos;
-	struct format_field *field = hde->field;
+	struct tep_format_field *field = hde->field;
 	size_t namelen;
 	bool last = false;
 
@@ -2000,7 +2000,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	struct hpp_dynamic_entry *hde;
 	size_t len = fmt->user_len;
 	char *str, *pos;
-	struct format_field *field;
+	struct tep_format_field *field;
 	size_t namelen;
 	bool last = false;
 	int ret;
@@ -2060,7 +2060,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 			       struct hist_entry *a, struct hist_entry *b)
 {
 	struct hpp_dynamic_entry *hde;
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned offset, size;
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
@@ -2071,7 +2071,7 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	}
 
 	field = hde->field;
-	if (field->flags & FIELD_IS_DYNAMIC) {
+	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
 
 		tep_read_number_field(field, a->raw_data, &dyn);
@@ -2117,7 +2117,7 @@ static void hde_free(struct perf_hpp_fmt *fmt)
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct tep_format_field *field,
 		      int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2252,7 +2252,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 }
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
-				    struct format_field *field,
+				    struct tep_format_field *field,
 				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2270,7 +2270,7 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
@@ -2305,7 +2305,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
@@ -2327,7 +2327,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct tep_format_field *field;
 	bool raw_trace = symbol_conf.raw_trace;
 	int ret = 0;
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index dd17d6a38d3a..c091635bf7dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -36,6 +36,7 @@
  * @branch_count: the branch count when the entry was created
  * @cp: call path
  * @no_call: a 'call' was not seen
+ * @trace_end: a 'call' but trace ended
  */
 struct thread_stack_entry {
 	u64 ret_addr;
@@ -44,6 +45,7 @@ struct thread_stack_entry {
 	u64 branch_count;
 	struct call_path *cp;
 	bool no_call;
+	bool trace_end;
 };
 
 /**
@@ -112,7 +114,8 @@ static struct thread_stack *thread_stack__new(struct thread *thread,
 	return ts;
 }
 
-static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr,
+			      bool trace_end)
 {
 	int err = 0;
 
@@ -124,6 +127,7 @@ static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
 		}
 	}
 
+	ts->stack[ts->cnt].trace_end = trace_end;
 	ts->stack[ts->cnt++].ret_addr = ret_addr;
 
 	return err;
@@ -150,6 +154,18 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
 	}
 }
 
+static void thread_stack__pop_trace_end(struct thread_stack *ts)
+{
+	size_t i;
+
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].trace_end)
+			ts->cnt = i;
+		else
+			return;
+	}
+}
+
 static bool thread_stack__in_kernel(struct thread_stack *ts)
 {
 	if (!ts->cnt)
@@ -254,10 +270,19 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 		ret_addr = from_ip + insn_len;
 		if (ret_addr == to_ip)
 			return 0; /* Zero-length calls are excluded */
-		return thread_stack__push(thread->ts, ret_addr);
-	} else if (flags & PERF_IP_FLAG_RETURN) {
-		if (!from_ip)
-			return 0;
+		return thread_stack__push(thread->ts, ret_addr,
+					  flags & PERF_IP_FLAG_TRACE_END);
+	} else if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		/*
+		 * If the caller did not change the trace number (which would
+		 * have flushed the stack) then try to make sense of the stack.
+		 * Possibly, tracing began after returning to the current
+		 * address, so try to pop that. Also, do not expect a call made
+		 * when the trace ended, to return, so pop that.
+		 */
+		thread_stack__pop(thread->ts, to_ip);
+		thread_stack__pop_trace_end(thread->ts);
+	} else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) {
 		thread_stack__pop(thread->ts, to_ip);
 	}
 
@@ -332,7 +357,7 @@ void call_return_processor__free(struct call_return_processor *crp)
 
 static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 				 u64 timestamp, u64 ref, struct call_path *cp,
-				 bool no_call)
+				 bool no_call, bool trace_end)
 {
 	struct thread_stack_entry *tse;
 	int err;
@@ -350,6 +375,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->branch_count = ts->branch_count;
 	tse->cp = cp;
 	tse->no_call = no_call;
+	tse->trace_end = trace_end;
 
 	return 0;
 }
@@ -423,7 +449,7 @@ static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
 		return -ENOMEM;
 
 	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
-				     true);
+				     true, false);
 }
 
 static int thread_stack__no_call_return(struct thread *thread,
@@ -455,7 +481,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 			if (!cp)
 				return -ENOMEM;
 			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true);
+						     cp, true, false);
 		}
 	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
@@ -480,7 +506,7 @@ static int thread_stack__no_call_return(struct thread *thread,
 		return -ENOMEM;
 
 	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true);
+				    true, false);
 	if (err)
 		return err;
 
@@ -500,7 +526,7 @@ static int thread_stack__trace_begin(struct thread *thread,
 
 	/* Pop trace end */
 	tse = &ts->stack[ts->cnt - 1];
-	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+	if (tse->trace_end) {
 		err = thread_stack__call_return(thread, ts, --ts->cnt,
 						timestamp, ref, false);
 		if (err)
@@ -529,7 +555,7 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 	ret_addr = sample->ip + sample->insn_len;
 
 	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
-				     false);
+				     false, true);
 }
 
 int thread_stack__process(struct thread *thread, struct comm *comm,
@@ -579,6 +605,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 	ts->last_time = sample->time;
 
 	if (sample->flags & PERF_IP_FLAG_CALL) {
+		bool trace_end = sample->flags & PERF_IP_FLAG_TRACE_END;
 		struct call_path_root *cpr = ts->crp->cpr;
 		struct call_path *cp;
 		u64 ret_addr;
@@ -596,7 +623,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		if (!cp)
 			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
-					    cp, false);
+					    cp, false, trace_end);
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
 		if (!sample->ip || !sample->addr)
 			return 0;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e76214f8d596..a4d7de1c96d1 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -33,8 +33,8 @@ static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
 	struct tep_handle *pevent = context->pevent;
-	struct event_format *event;
-	struct format_field *field;
+	struct tep_event_format *event;
+	struct tep_format_field *field;
 
 	if (!*size) {
 		if (!pevent->events)
@@ -94,9 +94,9 @@ int common_pc(struct scripting_context *context)
 }
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data)
+raw_field_value(struct tep_event_format *event, const char *name, void *data)
 {
-	struct format_field *field;
+	struct tep_format_field *field;
 	unsigned long long val;
 
 	field = tep_find_any_field(event, name);
@@ -108,12 +108,12 @@ raw_field_value(struct event_format *event, const char *name, void *data)
 	return val;
 }
 
-unsigned long long read_size(struct event_format *event, void *ptr, int size)
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size)
 {
 	return tep_read_number(event->pevent, ptr, size);
 }
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
 	struct tep_record record;
@@ -130,7 +130,7 @@ void event_format__fprintf(struct event_format *event,
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size)
 {
 	return event_format__fprintf(event, cpu, data, size, stdout);
@@ -188,8 +188,8 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event)
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event)
 {
 	static int idx;
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 3dfc1db6b25b..b98ee2a2eb44 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -102,7 +102,7 @@ static unsigned int read4(struct tep_handle *pevent)
 
 	if (do_read(&data, 4) < 0)
 		return 0;
-	return __data2host4(pevent, data);
+	return __tep_data2host4(pevent, data);
 }
 
 static unsigned long long read8(struct tep_handle *pevent)
@@ -111,7 +111,7 @@ static unsigned long long read8(struct tep_handle *pevent)
 
 	if (do_read(&data, 8) < 0)
 		return 0;
-	return __data2host8(pevent, data);
+	return __tep_data2host8(pevent, data);
 }
 
 static char *read_string(void)
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 58bb72f266f3..95664b2f771e 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -72,12 +72,12 @@ void trace_event__cleanup(struct trace_event *t)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static struct event_format*
+static struct tep_event_format*
 tp_format(const char *sys, const char *name)
 {
 	char *tp_dir = get_events_file(sys);
 	struct tep_handle *pevent = tevent.pevent;
-	struct event_format *event = NULL;
+	struct tep_event_format *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
@@ -102,7 +102,7 @@ tp_format(const char *sys, const char *name)
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
@@ -111,7 +111,7 @@ trace_event__tp_format(const char *sys, const char *name)
 	return tp_format(sys, name);
 }
 
-struct event_format *trace_event__tp_format_id(int id)
+struct tep_event_format *trace_event__tp_format_id(int id)
 {
 	if (!tevent_initialized && trace_event__init2())
 		return ERR_PTR(-ENOMEM);
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index c69d77d7cf55..f024d73bfc40 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -11,28 +11,28 @@ struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
-struct plugin_list;
+struct tep_plugin_list;
 
 struct trace_event {
 	struct tep_handle	*pevent;
-	struct plugin_list	*plugin_list;
+	struct tep_plugin_list	*plugin_list;
 };
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
 int trace_event__register_resolver(struct machine *machine,
 				   tep_func_resolver_t *func);
-struct event_format*
+struct tep_event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
-struct event_format *trace_event__tp_format_id(int id);
+struct tep_event_format *trace_event__tp_format_id(int id);
 
 int bigendian(void);
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event_format *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event_format *event,
 			 int cpu, void *data, int size);
 
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
@@ -40,7 +40,7 @@ int parse_event_file(struct tep_handle *pevent,
 		     char *buf, unsigned long size, char *sys);
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data);
+raw_field_value(struct tep_event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
@@ -48,9 +48,9 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event);
-unsigned long long read_size(struct event_format *event, void *ptr, int size);
+struct tep_event_format *trace_find_next_event(struct tep_handle *pevent,
+					       struct tep_event_format *event);
+unsigned long long read_size(struct tep_event_format *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);