Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 7efe15b..8dcfca1 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,155 +1,175 @@
-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 += 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 += 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-$(CONFIG_TRACE) += syscalltbl.o
-libperf-y += ordered-events.o
-libperf-y += namespaces.o
-libperf-y += comm.o
-libperf-y += thread.o
-libperf-y += thread_map.o
-libperf-y += trace-event-parse.o
-libperf-y += parse-events-flex.o
-libperf-y += parse-events-bison.o
-libperf-y += pmu.o
-libperf-y += pmu-flex.o
-libperf-y += pmu-bison.o
-libperf-y += trace-event-read.o
-libperf-y += trace-event-info.o
-libperf-y += trace-event-scripting.o
-libperf-y += trace-event.o
-libperf-y += svghelper.o
-libperf-y += sort.o
-libperf-y += hist.o
-libperf-y += util.o
-libperf-y += xyarray.o
-libperf-y += cpumap.o
-libperf-y += cgroup.o
-libperf-y += target.o
-libperf-y += rblist.o
-libperf-y += intlist.o
-libperf-y += vdso.o
-libperf-y += counts.o
-libperf-y += stat.o
-libperf-y += stat-shadow.o
-libperf-y += record.o
-libperf-y += srcline.o
-libperf-y += data.o
-libperf-y += tsc.o
-libperf-y += cloexec.o
-libperf-y += call-path.o
-libperf-y += rwsem.o
-libperf-y += thread-stack.o
-libperf-$(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 += cacheline.o
+perf-y += config.o
+perf-y += copyfile.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 += perf_event_attr_fprintf.o
+perf-y += evswitch.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 += rlimit.o
+perf-y += argv_split.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 += dsos.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-$(CONFIG_TRACE) += syscalltbl.o
+perf-y += ordered-events.o
+perf-y += namespaces.o
+perf-y += comm.o
+perf-y += thread.o
+perf-y += thread_map.o
+perf-y += trace-event-parse.o
+perf-y += parse-events-flex.o
+perf-y += parse-events-bison.o
+perf-y += pmu.o
+perf-y += pmu-flex.o
+perf-y += pmu-bison.o
+perf-y += trace-event-read.o
+perf-y += trace-event-info.o
+perf-y += trace-event-scripting.o
+perf-y += trace-event.o
+perf-y += svghelper.o
+perf-y += sort.o
+perf-y += hist.o
+perf-y += util.o
+perf-y += cpumap.o
+perf-y += cputopo.o
+perf-y += cgroup.o
+perf-y += target.o
+perf-y += rblist.o
+perf-y += intlist.o
+perf-y += vdso.o
+perf-y += counts.o
+perf-y += stat.o
+perf-y += stat-shadow.o
+perf-y += stat-display.o
+perf-y += record.o
+perf-y += srcline.o
+perf-y += srccode.o
+perf-y += synthetic-events.o
+perf-y += data.o
+perf-y += tsc.o
+perf-y += cloexec.o
+perf-y += call-path.o
+perf-y += rwsem.o
+perf-y += thread-stack.o
+perf-$(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 += drv_configs.o
-libperf-y += units.o
-libperf-y += time-utils.o
-libperf-y += expr-bison.o
-libperf-y += branch.o
-libperf-y += mem2node.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
 
-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-$(CONFIG_LIBELF) += probe-event.o
+perf-$(CONFIG_LIBBPF) += bpf-loader.o
+perf-$(CONFIG_LIBBPF) += bpf_map.o
+perf-$(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-$(CONFIG_ZSTD) += zstd.o
+
+perf-$(CONFIG_LIBCAP) += cap.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-$(CONFIG_CXX) += c++/
+perf-$(CONFIG_LIBBPF) += bpf-event.o
+
+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))"
@@ -198,10 +218,18 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/ctype.o: ../lib/ctype.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 3802cee..59241ff 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -19,7 +19,7 @@
 if test -d ../../.git -o -f ../../.git
 then
 	TAG=$(git describe --abbrev=0 --match "v[0-9].[0-9]*" 2>/dev/null )
-	CID=$(git log -1 --abbrev=4 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+	CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
 elif test -f ../../PERF-VERSION-FILE
 then
 	TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a1..e42bf57 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1,34 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Parts came from builtin-annotate.c, see those files for further
  * copyright notes.
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include <errno.h>
 #include <inttypes.h>
-#include "util.h"
+#include <libgen.h>
+#include <stdlib.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include "util.h" // hex_width()
 #include "ui/ui.h"
 #include "sort.h"
 #include "build-id.h"
 #include "color.h"
 #include "config.h"
-#include "cache.h"
+#include "dso.h"
+#include "env.h"
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "bpf-event.h"
 #include "block-range.h"
 #include "string2.h"
+#include "util/event.h"
 #include "arch/common.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <bpf/libbpf.h>
+#include <subcmd/parse-options.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -42,7 +56,7 @@
 #define DARROW_CHAR	((unsigned char)'.')
 #define UARROW_CHAR	((unsigned char)'-')
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 struct annotation_options annotation__default_options = {
 	.use_offset     = true,
@@ -134,14 +148,21 @@
 	return 0;
 }
 
+#include "arch/arc/annotate/instructions.c"
 #include "arch/arm/annotate/instructions.c"
 #include "arch/arm64/annotate/instructions.c"
+#include "arch/csky/annotate/instructions.c"
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
+		.name = "arc",
+		.init = arc__annotate_init,
+	},
+	{
 		.name = "arm",
 		.init = arm__annotate_init,
 	},
@@ -150,6 +171,10 @@
 		.init = arm64__annotate_init,
 	},
 	{
+		.name = "csky",
+		.init = csky__annotate_init,
+	},
+	{
 		.name = "x86",
 		.init = x86__annotate_init,
 		.instructions = x86__instructions,
@@ -170,6 +195,13 @@
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
@@ -183,18 +215,18 @@
 }
 
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
-			      struct ins_operands *ops)
+			      struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
-		  struct ins_operands *ops)
+		   struct ins_operands *ops, int max_ins_name)
 {
 	if (ins->ops->scnprintf)
-		return ins->ops->scnprintf(ins, bf, size, ops);
+		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
 
-	return ins__raw_scnprintf(ins, bf, size, ops);
+	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 }
 
 bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
@@ -258,18 +290,18 @@
 }
 
 static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	if (ops->target.sym)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
 
 	if (ops->target.addr == 0)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
 
-	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -373,15 +405,15 @@
 }
 
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	const char *c;
 
 	if (!ops->target.addr || ops->target.offset < 0)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
 	if (ops->target.outside && ops->target.sym != NULL)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
 
 	c = strchr(ops->raw, ',');
 	c = validate_comma(c, ops);
@@ -400,7 +432,7 @@
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -468,16 +500,16 @@
 }
 
 static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
 	int printed;
 
 	if (ops->locked.ins.ops == NULL)
-		return ins__raw_scnprintf(ins, bf, size, ops);
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
 
-	printed = scnprintf(bf, size, "%-6s ", ins->name);
+	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
-					size - printed, ops->locked.ops);
+					size - printed, ops->locked.ops, max_ins_name);
 }
 
 static void lock__delete(struct ins_operands *ops)
@@ -537,7 +569,7 @@
 	if (comment == NULL)
 		return 0;
 
-	comment = ltrim(comment);
+	comment = skip_spaces(comment);
 	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
 	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
@@ -549,9 +581,9 @@
 }
 
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -582,16 +614,16 @@
 	if (comment == NULL)
 		return 0;
 
-	comment = ltrim(comment);
+	comment = skip_spaces(comment);
 	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
 
 	return 0;
 }
 
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops)
+			   struct ins_operands *ops, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s %s", ins->name,
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -601,9 +633,9 @@
 };
 
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
-			  struct ins_operands *ops __maybe_unused)
+			  struct ins_operands *ops __maybe_unused, int max_ins_name)
 {
-	return scnprintf(bf, size, "%-6s", "nop");
+	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -903,17 +935,16 @@
 }
 
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-				    struct perf_evsel *evsel, u64 addr,
+				    struct evsel *evsel, u64 addr,
 				    struct perf_sample *sample)
 {
 	struct annotated_source *src;
 
 	if (sym == NULL)
 		return 0;
-	src = symbol__hists(sym, evsel->evlist->nr_entries);
-	if (src == NULL)
-		return -ENOMEM;
-	return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample);
+	src = symbol__hists(sym, evsel->evlist->core.nr_entries);
+	return (src) ?  __symbol__inc_addr_samples(sym, map, src, evsel->idx,
+						   addr, sample) : 0;
 }
 
 static int symbol__account_cycles(u64 addr, u64 start,
@@ -992,6 +1023,7 @@
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
+	unsigned int cover_insn = 0;
 	u64 offset;
 
 	n_insn = annotation__count_insn(notes, start, end);
@@ -999,27 +1031,40 @@
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
 		/* Hide data when there are too many overlaps. */
-		if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2)
+		if (ch->reset >= 0x7fff)
 			return;
 
 		for (offset = start; offset <= end; offset++) {
 			struct annotation_line *al = notes->offsets[offset];
 
-			if (al)
+			if (al && al->ipc == 0.0) {
 				al->ipc = ipc;
+				cover_insn++;
+			}
+		}
+
+		if (cover_insn) {
+			notes->hit_cycles += ch->cycles;
+			notes->hit_insn += n_insn * ch->num;
+			notes->cover_insn += cover_insn;
 		}
 	}
 }
 
 void annotation__compute_ipc(struct annotation *notes, size_t size)
 {
-	u64 offset;
+	s64 offset;
 
 	if (!notes->src || !notes->src->cycles_hist)
 		return;
 
+	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->hit_cycles = 0;
+	notes->hit_insn = 0;
+	notes->cover_insn = 0;
+
 	pthread_mutex_lock(&notes->lock);
-	for (offset = 0; offset < size; ++offset) {
+	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
 		ch = &notes->src->cycles_hist[offset];
@@ -1041,13 +1086,13 @@
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
-				 struct perf_evsel *evsel)
+				 struct evsel *evsel)
 {
 	return symbol__inc_addr_samples(ams->sym, ams->map, evsel, ams->al_addr, sample);
 }
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
-				 struct perf_evsel *evsel, u64 ip)
+				 struct evsel *evsel, u64 ip)
 {
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evsel, ip, sample);
 }
@@ -1065,7 +1110,7 @@
 
 static int disasm_line__parse(char *line, const char **namep, char **rawp)
 {
-	char tmp, *name = ltrim(line);
+	char tmp, *name = skip_spaces(line);
 
 	if (name[0] == '\0')
 		return -1;
@@ -1080,16 +1125,14 @@
 	*namep = strdup(name);
 
 	if (*namep == NULL)
-		goto out_free_name;
+		goto out;
 
 	(*rawp)[0] = tmp;
-	*rawp = ltrim(*rawp);
+	*rawp = strim(*rawp);
 
 	return 0;
 
-out_free_name:
-	free((void *)namep);
-	*namep = NULL;
+out:
 	return -1;
 }
 
@@ -1097,7 +1140,7 @@
 	size_t			 privsize;
 	struct arch		*arch;
 	struct map_symbol	 ms;
-	struct perf_evsel	*evsel;
+	struct evsel	*evsel;
 	struct annotation_options *options;
 	s64			 offset;
 	char			*line;
@@ -1128,12 +1171,12 @@
 annotation_line__new(struct annotate_args *args, size_t privsize)
 {
 	struct annotation_line *al;
-	struct perf_evsel *evsel = args->evsel;
+	struct evsel *evsel = args->evsel;
 	size_t size = privsize + sizeof(*al);
 	int nr = 1;
 
 	if (perf_evsel__is_group_event(evsel))
-		nr = evsel->nr_members;
+		nr = evsel->core.nr_members;
 
 	size += sizeof(al->data[0]) * nr;
 
@@ -1198,17 +1241,16 @@
 		dl->ins.ops->free(&dl->ops);
 	else
 		ins__delete(&dl->ops);
-	free((void *)dl->ins.name);
-	dl->ins.name = NULL;
+	zfree(&dl->ins.name);
 	annotation_line__delete(&dl->al);
 }
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
 
-	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
+	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
 }
 
 static void annotation_line__add(struct annotation_line *al, struct list_head *head)
@@ -1323,7 +1365,7 @@
 
 static int
 annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start,
-		       struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
+		       struct evsel *evsel, u64 len, int min_pcnt, int printed,
 		       int max_lines, struct annotation_line *queue, int addr_fmt_width,
 		       int percent_type)
 {
@@ -1412,7 +1454,7 @@
 			return -1;
 
 		if (perf_evsel__is_group_event(evsel))
-			width *= evsel->nr_members;
+			width *= evsel->core.nr_members;
 
 		if (!*al->line)
 			printf(" %*s:\n", width, " ");
@@ -1462,7 +1504,7 @@
 		return -1;
 
 	line_ip = -1;
-	parsed_line = rtrim(line);
+	parsed_line = strim(line);
 
 	/* /filename:linenr ? Save line number and ignore. */
 	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
@@ -1470,7 +1512,7 @@
 		return 0;
 	}
 
-	tmp = ltrim(parsed_line);
+	tmp = skip_spaces(parsed_line);
 	if (*tmp) {
 		/*
 		 * Parse hexa addresses followed by ':'
@@ -1550,7 +1592,7 @@
 				return;
 		}
 
-		list_del(&dl->al.node);
+		list_del_init(&dl->al.node);
 		disasm_line__free(dl);
 	}
 }
@@ -1586,6 +1628,22 @@
 			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
 	}
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso->long_name);
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
@@ -1617,7 +1675,7 @@
 
 	build_id_path = strdup(filename);
 	if (!build_id_path)
-		return -1;
+		return ENOMEM;
 
 	/*
 	 * old style build-id cache has name of XX/XXXXXXX.. while
@@ -1645,6 +1703,160 @@
 	return 0;
 }
 
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+
+static int symbol__disassemble_bpf(struct symbol *sym,
+				   struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotation_options *opts = args->options;
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_linfo *prog_linfo = NULL;
+	struct bpf_prog_info_node *info_node;
+	int len = sym->end - sym->start;
+	disassembler_ftype disassemble;
+	struct map *map = args->ms.map;
+	struct disassemble_info info;
+	struct dso *dso = map->dso;
+	int pc = 0, count, sub_id;
+	struct btf *btf = NULL;
+	char tpath[PATH_MAX];
+	size_t buf_size;
+	int nr_skip = 0;
+	char *buf;
+	bfd *bfdf;
+	int ret;
+	FILE *s;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
+
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
+
+	memset(tpath, 0, sizeof(tpath));
+	perf_exe(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	assert(bfdf);
+	assert(bfd_check_format(bfdf, bfd_object));
+
+	s = open_memstream(&buf, &buf_size);
+	if (!s) {
+		ret = errno;
+		goto out;
+	}
+	init_disassemble_info(&info, s,
+			      (fprintf_ftype) fprintf);
+
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+
+	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+						 dso->bpf_prog.id);
+	if (!info_node) {
+		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+		goto out;
+	}
+	info_linear = info_node->info_linear;
+	sub_id = dso->bpf_prog.sub_id;
+
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
+	info.buffer_length = info_linear->info.jited_prog_len;
+
+	if (info_linear->info.nr_line_info)
+		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+
+	if (info_linear->info.btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(dso->bpf_prog.env,
+					  info_linear->info.btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	disassemble_init_for_target(&info);
+
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+	disassemble = disassembler(info.arch,
+				   bfd_big_endian(bfdf),
+				   info.mach,
+				   bfdf);
+#else
+	disassemble = disassembler(bfdf);
+#endif
+	assert(disassemble);
+
+	fflush(s);
+	do {
+		const struct bpf_line_info *linfo = NULL;
+		struct disasm_line *dl;
+		size_t prev_buf_size;
+		const char *srcline;
+		u64 addr;
+
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
+		count = disassemble(pc, &info);
+
+		if (prog_linfo)
+			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+								addr, sub_id,
+								nr_skip);
+
+		if (linfo && btf) {
+			srcline = btf__name_by_offset(btf, linfo->line_off);
+			nr_skip++;
+		} else
+			srcline = NULL;
+
+		fprintf(s, "\n");
+		prev_buf_size = buf_size;
+		fflush(s);
+
+		if (!opts->hide_src_code && srcline) {
+			args->offset = -1;
+			args->line = strdup(srcline);
+			args->line_nr = 0;
+			args->ms.sym  = sym;
+			dl = disasm_line__new(args);
+			if (dl) {
+				annotation_line__add(&dl->al,
+						     &notes->src->source);
+			}
+		}
+
+		args->offset = pc;
+		args->line = buf + prev_buf_size;
+		args->line_nr = 0;
+		args->ms.sym  = sym;
+		dl = disasm_line__new(args);
+		if (dl)
+			annotation_line__add(&dl->al, &notes->src->source);
+
+		pc += count;
+	} while (count > 0 && pc < len);
+
+	ret = 0;
+out:
+	free(prog_linfo);
+	free(btf);
+	fclose(s);
+	bfd_close(bfdf);
+	return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+				   struct annotate_args *args __maybe_unused)
+{
+	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct annotation_options *opts = args->options;
@@ -1672,7 +1884,9 @@
 	pr_debug("annotating [%p] %30s : [%p] %30s\n",
 		 dso, dso->long_name, sym, sym->name);
 
-	if (dso__is_kcore(dso)) {
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+		return symbol__disassemble_bpf(sym, args);
+	} else if (dso__is_kcore(dso)) {
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);
 		kce.offs = sym->start;
@@ -1696,15 +1910,14 @@
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw",
-		 opts->annotate_src ? "-S" : "",
-		 symfs_filename, symfs_filename);
+		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -1729,7 +1942,8 @@
 		close(stdout_fd[0]);
 		dup2(stdout_fd[1], 1);
 		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, NULL);
+		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+		      NULL);
 		perror(command);
 		exit(-1);
 	}
@@ -1750,7 +1964,7 @@
 	while (!feof(file)) {
 		/*
 		 * The source code line number (lineno) needs to be kept in
-		 * accross calls to symbol__parse_objdump_line(), so that it
+		 * across calls to symbol__parse_objdump_line(), so that it
 		 * can associate it with the instructions till the next one.
 		 * See disasm_line__new() and struct disasm_line::line_nr.
 		 */
@@ -1820,10 +2034,10 @@
 }
 
 static void annotation__calc_percent(struct annotation *notes,
-				     struct perf_evsel *leader, s64 len)
+				     struct evsel *leader, s64 len)
 {
 	struct annotation_line *al, *next;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		s64 end;
@@ -1850,7 +2064,7 @@
 	}
 }
 
-void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel)
+void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 {
 	struct annotation *notes = symbol__annotation(sym);
 
@@ -1858,10 +2072,11 @@
 }
 
 int symbol__annotate(struct symbol *sym, struct map *map,
-		     struct perf_evsel *evsel, size_t privsize,
+		     struct evsel *evsel, size_t privsize,
 		     struct annotation_options *options,
 		     struct arch **parch)
 {
+	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
 		.privsize	= privsize,
 		.evsel		= evsel,
@@ -1873,11 +2088,11 @@
 	int err;
 
 	if (!arch_name)
-		return -1;
+		return errno;
 
 	args.arch = arch = arch__find(arch_name);
 	if (arch == NULL)
-		return -ENOTSUP;
+		return ENOTSUP;
 
 	if (parch)
 		*parch = arch;
@@ -1892,6 +2107,7 @@
 
 	args.ms.map = map;
 	args.ms.sym = sym;
+	notes->start = map__rip_2objdump(map, sym->start);
 
 	return symbol__disassemble(sym, &args);
 }
@@ -2021,7 +2237,7 @@
 	}
 }
 
-static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
+static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->idx);
@@ -2048,7 +2264,7 @@
 }
 
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
-			    struct perf_evsel *evsel,
+			    struct evsel *evsel,
 			    struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
@@ -2079,7 +2295,7 @@
 	len = symbol__size(sym);
 
 	if (perf_evsel__is_group_event(evsel)) {
-		width *= evsel->nr_members;
+		width *= evsel->core.nr_members;
 		perf_evsel__group_desc(evsel, buf, sizeof(buf));
 		evsel_name = buf;
 	}
@@ -2212,7 +2428,7 @@
 	return 0;
 }
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel,
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 				struct annotation_options *opts)
 {
 	const char *ev_name = perf_evsel__name(evsel);
@@ -2270,7 +2486,7 @@
 	struct annotation_line *al, *n;
 
 	list_for_each_entry_safe(al, n, &as->source, node) {
-		list_del(&al->node);
+		list_del_init(&al->node);
 		disasm_line__free(disasm_line(al));
 	}
 }
@@ -2383,12 +2599,30 @@
 	return 1;
 }
 
+static int annotation__max_ins_name(struct annotation *notes)
+{
+	int max_name = 0, len;
+	struct annotation_line *al;
+
+        list_for_each_entry(al, &notes->src->source, node) {
+		if (al->offset == -1)
+			continue;
+
+		len = strlen(disasm_line(al)->ins.name);
+		if (max_name < len)
+			max_name = len;
+	}
+
+	return max_name;
+}
+
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
 {
 	notes->widths.addr = notes->widths.target =
 		notes->widths.min_addr = hex_width(symbol__size(sym));
 	notes->widths.max_addr = hex_width(sym->end);
 	notes->widths.jumps = width_jumps(notes->max_jump_sources);
+	notes->widths.max_ins_name = annotation__max_ins_name(notes);
 }
 
 void annotation__update_column_widths(struct annotation *notes)
@@ -2446,7 +2680,7 @@
 }
 
 int symbol__tty_annotate2(struct symbol *sym, struct map *map,
-			  struct perf_evsel *evsel,
+			  struct evsel *evsel,
 			  struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
@@ -2474,7 +2708,7 @@
 }
 
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
-			 struct perf_evsel *evsel,
+			 struct evsel *evsel,
 			 struct annotation_options *opts)
 {
 	struct dso *dso = map->dso;
@@ -2552,7 +2786,23 @@
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
+	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name);
+}
+
+static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
+{
+	double ipc = 0.0, coverage = 0.0;
+
+	if (notes->hit_cycles)
+		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+
+	if (notes->total_insn) {
+		coverage = notes->cover_insn * 100.0 /
+			((double)notes->total_insn);
+	}
+
+	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
+		  ipc, coverage);
 }
 
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
@@ -2650,6 +2900,11 @@
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
 					    "Cycle(min/max)");
 		}
+
+		if (show_title && !*al->line) {
+			ipc_coverage_string(bf, sizeof(bf), notes);
+			obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
+		}
 	}
 
 	obj__printf(obj, " ");
@@ -2724,7 +2979,7 @@
 				 wops->write_graph);
 }
 
-int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel,
+int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 		      struct annotation_options *options, struct arch **parch)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -2733,10 +2988,10 @@
 
 	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
 	if (notes->offsets == NULL)
-		return -1;
+		return ENOMEM;
 
 	if (perf_evsel__is_group_event(evsel))
-		nr_pcnt = evsel->nr_members;
+		nr_pcnt = evsel->core.nr_members;
 
 	err = symbol__annotate(sym, map, evsel, 0, options, parch);
 	if (err)
@@ -2746,8 +3001,6 @@
 
 	symbol__calc_percent(sym, evsel);
 
-	notes->start = map__rip_2objdump(map, sym->start);
-
 	annotation__set_offsets(notes, size);
 	annotation__mark_jump_targets(notes, sym);
 	annotation__compute_ipc(notes, size);
@@ -2755,12 +3008,13 @@
 	notes->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
+	sym->annotate2 = true;
 
 	return 0;
 
 out_free_offsets:
 	zfree(&notes->offsets);
-	return -1;
+	return err;
 }
 
 #define ANNOTATION__CFG(n) \
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 5399ba2..d76fd0e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -4,16 +4,24 @@
 
 #include <stdbool.h>
 #include <stdint.h>
+#include <stdio.h>
 #include <linux/types.h>
-#include "symbol.h"
-#include "hist.h"
-#include "sort.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <asm/bug.h>
+#include "symbol_conf.h"
 
+struct hist_browser_timer;
+struct hist_entry;
 struct ins_ops;
+struct map;
+struct map_symbol;
+struct addr_map_symbol;
+struct option;
+struct perf_sample;
+struct evsel;
+struct symbol;
 
 struct ins {
 	const char     *name;
@@ -51,19 +59,20 @@
 	void (*free)(struct ins_operands *ops);
 	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
-			 struct ins_operands *ops);
+			 struct ins_operands *ops, int max_ins_name);
 };
 
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
 bool ins__is_lock(const struct ins *ins);
-int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name);
 bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
+#define ANNOTATION__AVG_IPC_WIDTH 36
 
 struct annotation_options {
 	bool hide_src_code,
@@ -207,12 +216,12 @@
 
 int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   char *bf, size_t size,
-					   struct perf_evsel *evsel,
+					   struct evsel *evsel,
 					   bool show_freq);
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
-void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
+void symbol__calc_percent(struct symbol *sym, struct evsel *evsel);
 
 struct sym_hist {
 	u64		      nr_samples;
@@ -236,7 +245,7 @@
 /** struct annotated_source - symbols with hits have this attached as in sannotation
  *
  * @histograms: Array of addr hit histograms per event being monitored
- * nr_histograms: This may not be the same as evsel->evlist->nr_entries if
+ * nr_histograms: This may not be the same as evsel->evlist->core.nr_entries if
  * 		  we have more than a group in a evlist, where we will want
  * 		  to see each group separately, that is why symbol__annotate2()
  * 		  sets src->nr_histograms to evsel->nr_members.
@@ -262,6 +271,10 @@
 	pthread_mutex_t		lock;
 	u64			max_coverage;
 	u64			start;
+	u64			hit_cycles;
+	u64			hit_insn;
+	unsigned int		total_insn;
+	unsigned int		cover_insn;
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;
@@ -276,6 +289,7 @@
 		u8		target;
 		u8		min_addr;
 		u8		max_addr;
+		u8		max_ins_name;
 	} widths;
 	bool			have_cycles;
 	struct annotated_source *src;
@@ -321,24 +335,24 @@
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
-				 struct perf_evsel *evsel);
+				 struct evsel *evsel);
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
 				    unsigned cycles);
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
-				 struct perf_evsel *evsel, u64 addr);
+				 struct evsel *evsel, u64 addr);
 
 struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map,
-		     struct perf_evsel *evsel, size_t privsize,
+		     struct evsel *evsel, size_t privsize,
 		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct symbol *sym, struct map *map,
-		      struct perf_evsel *evsel,
+		      struct evsel *evsel,
 		      struct annotation_options *options,
 		      struct arch **parch);
 
@@ -355,6 +369,11 @@
 	__SYMBOL_ANNOTATE_ERRNO__START		= -10000,
 
 	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
+	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP,
+	SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE,
+	SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
@@ -363,32 +382,32 @@
 				 int errnum, char *buf, size_t buflen);
 
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
-			    struct perf_evsel *evsel,
+			    struct evsel *evsel,
 			    struct annotation_options *options);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel,
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 				struct annotation_options *opts);
 
 bool ui__has_annotation(void);
 
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
-			 struct perf_evsel *evsel, struct annotation_options *opts);
+			 struct evsel *evsel, struct annotation_options *opts);
 
 int symbol__tty_annotate2(struct symbol *sym, struct map *map,
-			  struct perf_evsel *evsel, struct annotation_options *opts);
+			  struct evsel *evsel, struct annotation_options *opts);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
-			 struct perf_evsel *evsel,
+			 struct evsel *evsel,
 			 struct hist_browser_timer *hbt,
 			 struct annotation_options *opts);
 #else
 static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
 				struct map *map __maybe_unused,
-				struct perf_evsel *evsel  __maybe_unused,
+				struct evsel *evsel  __maybe_unused,
 				struct hist_browser_timer *hbt __maybe_unused,
 				struct annotation_options *opts __maybe_unused)
 {
diff --git a/tools/perf/util/archinsn.h b/tools/perf/util/archinsn.h
new file mode 100644
index 0000000..448cbb6
--- /dev/null
+++ b/tools/perf/util/archinsn.h
@@ -0,0 +1,12 @@
+#ifndef INSN_H
+#define INSN_H 1
+
+struct perf_sample;
+struct machine;
+struct thread;
+
+void arch_fetch_insn(struct perf_sample *sample,
+		     struct thread *thread,
+		     struct machine *machine);
+
+#endif
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 6067267..53be12b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -8,19 +8,18 @@
 #include <errno.h>
 #include <byteswap.h>
 #include <inttypes.h>
+#include <unistd.h>
+#include <stdlib.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
-#include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
-#include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "util.h"
-#include "thread.h"
 #include "debug.h"
 #include "auxtrace.h"
 #include "arm-spe.h"
@@ -181,7 +180,7 @@
 	[ARM_SPE_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
 };
 
-static void arm_spe_print_info(u64 *arr)
+static void arm_spe_print_info(__u64 *arr)
 {
 	if (!dump_trace)
 		return;
@@ -192,12 +191,12 @@
 int arm_spe_process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
-	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	size_t min_sz = sizeof(u64) * ARM_SPE_PMU_TYPE;
 	struct arm_spe *spe;
 	int err;
 
-	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
 					min_sz)
 		return -EINVAL;
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index db15113..8470dfe 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * auxtrace.c: AUX area trace support
  * Copyright (c) 2013-2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <inttypes.h>
@@ -27,20 +18,21 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/string.h>
+#include <linux/time64.h>
 
 #include <sys/param.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 
-#include "../perf.h"
-#include "util.h"
 #include "evlist.h"
 #include "dso.h"
 #include "map.h"
 #include "pmu.h"
 #include "evsel.h"
-#include "cpumap.h"
+#include "symbol.h"
+#include "util/synthetic-events.h"
 #include "thread_map.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
@@ -48,6 +40,7 @@
 #include <linux/hash.h>
 
 #include "event.h"
+#include "record.h"
 #include "session.h"
 #include "debug.h"
 #include <subcmd/parse-options.h>
@@ -57,9 +50,12 @@
 #include "intel-bts.h"
 #include "arm-spe.h"
 #include "s390-cpumsf.h"
+#include "util/mmap.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/kernel.h>
 #include "symbol/kallsyms.h"
+#include <internal/lib.h>
 
 static bool auxtrace__dont_decode(struct perf_session *session)
 {
@@ -131,20 +127,20 @@
 }
 
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct perf_evlist *evlist, int idx,
+				   struct evlist *evlist, int idx,
 				   bool per_cpu)
 {
 	mp->idx = idx;
 
 	if (per_cpu) {
-		mp->cpu = evlist->cpus->map[idx];
-		if (evlist->threads)
-			mp->tid = thread_map__pid(evlist->threads, 0);
+		mp->cpu = evlist->core.cpus->map[idx];
+		if (evlist->core.threads)
+			mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
 		else
 			mp->tid = -1;
 	} else {
 		mp->cpu = -1;
-		mp->tid = thread_map__pid(evlist->threads, idx);
+		mp->tid = perf_thread_map__pid(evlist->core.threads, idx);
 	}
 }
 
@@ -392,7 +388,7 @@
 		return err;
 
 	if (event->header.type == PERF_RECORD_AUXTRACE) {
-		if (event->header.size < sizeof(struct auxtrace_event) ||
+		if (event->header.size < sizeof(struct perf_record_auxtrace) ||
 		    event->header.size != sz) {
 			err = -EINVAL;
 			goto out;
@@ -415,7 +411,7 @@
 
 			buffer = list_entry(queues->queue_array[i].head.next,
 					    struct auxtrace_buffer, list);
-			list_del(&buffer->list);
+			list_del_init(&buffer->list);
 			auxtrace_buffer__free(buffer);
 		}
 	}
@@ -510,7 +506,7 @@
 }
 
 size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
-				       struct perf_evlist *evlist)
+				       struct evlist *evlist)
 {
 	if (itr)
 		return itr->info_priv_size(itr, evlist);
@@ -525,7 +521,7 @@
 
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
-			       struct auxtrace_info_event *auxtrace_info,
+			       struct perf_record_auxtrace_info *auxtrace_info,
 			       size_t priv_size)
 {
 	if (itr)
@@ -546,9 +542,9 @@
 	return 0;
 }
 
-int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit)
 {
-	if (itr && itr->snapshot_finish)
+	if (!on_exit && itr && itr->snapshot_finish)
 		return itr->snapshot_finish(itr);
 	return 0;
 }
@@ -563,7 +559,7 @@
 }
 
 int auxtrace_record__options(struct auxtrace_record *itr,
-			     struct perf_evlist *evlist,
+			     struct evlist *evlist,
 			     struct record_opts *opts)
 {
 	if (itr)
@@ -584,6 +580,16 @@
 	if (!str)
 		return 0;
 
+	/* PMU-agnostic options */
+	switch (*str) {
+	case 'e':
+		opts->auxtrace_snapshot_on_exit = true;
+		str++;
+		break;
+	default:
+		break;
+	}
+
 	if (itr)
 		return itr->parse_snapshot_options(itr, opts, str);
 
@@ -592,7 +598,7 @@
 }
 
 struct auxtrace_record *__weak
-auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+auxtrace_record__init(struct evlist *evlist __maybe_unused, int *err)
 {
 	*err = 0;
 	return NULL;
@@ -619,7 +625,7 @@
 	struct auxtrace_index *auxtrace_index, *n;
 
 	list_for_each_entry_safe(auxtrace_index, n, head, list) {
-		list_del(&auxtrace_index->list);
+		list_del_init(&auxtrace_index->list);
 		free(auxtrace_index);
 	}
 }
@@ -855,13 +861,13 @@
 	free(buffer);
 }
 
-void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
-			  const char *msg)
+			  const char *msg, u64 timestamp)
 {
 	size_t size;
 
-	memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+	memset(auxtrace_error, 0, sizeof(struct perf_record_auxtrace_error));
 
 	auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
 	auxtrace_error->type = type;
@@ -869,7 +875,9 @@
 	auxtrace_error->cpu = cpu;
 	auxtrace_error->pid = pid;
 	auxtrace_error->tid = tid;
+	auxtrace_error->fmt = 1;
 	auxtrace_error->ip = ip;
+	auxtrace_error->time = timestamp;
 	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
 
 	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
@@ -888,12 +896,12 @@
 
 	pr_debug2("Synthesizing auxtrace information\n");
 	priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
-	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+	ev = zalloc(sizeof(struct perf_record_auxtrace_info) + priv_size);
 	if (!ev)
 		return -ENOMEM;
 
 	ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
-	ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+	ev->auxtrace_info.header.size = sizeof(struct perf_record_auxtrace_info) +
 					priv_size;
 	err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
 					 priv_size);
@@ -906,9 +914,8 @@
 	return err;
 }
 
-int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event,
-				      struct perf_session *session)
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 
@@ -932,14 +939,13 @@
 	}
 }
 
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session)
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event)
 {
 	s64 err;
 
 	if (dump_trace)
-		fprintf(stdout, " size: %#"PRIx64"  offset: %#"PRIx64"  ref: %#"PRIx64"  idx: %u  tid: %d  cpu: %d\n",
+		fprintf(stdout, " size: %#"PRI_lx64"  offset: %#"PRI_lx64"  ref: %#"PRI_lx64"  idx: %u  tid: %d  cpu: %d\n",
 			event->auxtrace.size, event->auxtrace.offset,
 			event->auxtrace.reference, event->auxtrace.idx,
 			event->auxtrace.tid, event->auxtrace.cpu);
@@ -950,7 +956,7 @@
 	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
 		return -EINVAL;
 
-	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	err = session->auxtrace->process_auxtrace_event(session, event, session->tool);
 	if (err < 0)
 		return err;
 
@@ -964,16 +970,24 @@
 #define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
 #define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample)
 {
-	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
+	synth_opts->other_events = true;
 	synth_opts->errors = true;
-	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	if (no_sample) {
+		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+		synth_opts->period = 1;
+		synth_opts->calls = true;
+	} else {
+		synth_opts->instructions = true;
+		synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 	synth_opts->initial_skip = 0;
@@ -1001,7 +1015,8 @@
 	}
 
 	if (!str) {
-		itrace_synth_opts__set_default(synth_opts);
+		itrace_synth_opts__set_default(synth_opts,
+					       synth_opts->default_no_sample);
 		return 0;
 	}
 
@@ -1060,6 +1075,9 @@
 		case 'p':
 			synth_opts->pwr_events = true;
 			break;
+		case 'o':
+			synth_opts->other_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;
@@ -1153,20 +1171,35 @@
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 {
-	struct auxtrace_error_event *e = &event->auxtrace_error;
+	struct perf_record_auxtrace_error *e = &event->auxtrace_error;
+	unsigned long long nsecs = e->time;
+	const char *msg = e->msg;
 	int ret;
 
 	ret = fprintf(fp, " %s error type %u",
 		      auxtrace_error_name(e->type), e->type);
-	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
-		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+
+	if (e->fmt && nsecs) {
+		unsigned long secs = nsecs / NSEC_PER_SEC;
+
+		nsecs -= secs * NSEC_PER_SEC;
+		ret += fprintf(fp, " time %lu.%09llu", secs, nsecs);
+	} else {
+		ret += fprintf(fp, " time 0");
+	}
+
+	if (!e->fmt)
+		msg = (const char *)&e->time;
+
+	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRI_lx64" code %u: %s\n",
+		       e->cpu, e->pid, e->tid, e->ip, e->code, msg);
 	return ret;
 }
 
 void perf_session__auxtrace_error_inc(struct perf_session *session,
 				      union perf_event *event)
 {
-	struct auxtrace_error_event *e = &event->auxtrace_error;
+	struct perf_record_auxtrace_error *e = &event->auxtrace_error;
 
 	if (e->type < PERF_AUXTRACE_ERROR_MAX)
 		session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
@@ -1185,9 +1218,8 @@
 	}
 }
 
-int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session)
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event)
 {
 	if (auxtrace__dont_decode(session))
 		return 0;
@@ -1196,11 +1228,12 @@
 	return 0;
 }
 
-static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+static int __auxtrace_mmap__read(struct mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 bool snapshot, size_t snapshot_size)
 {
+	struct auxtrace_mmap *mm = &map->auxtrace_mmap;
 	u64 head, old = mm->prev, offset, ref;
 	unsigned char *data = mm->base;
 	size_t size, head_off, old_off, len1, len2, padding;
@@ -1273,9 +1306,9 @@
 	}
 
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
-	padding = size & 7;
+	padding = size & (PERF_AUXTRACE_RECORD_ALIGNMENT - 1);
 	if (padding)
-		padding = 8 - padding;
+		padding = PERF_AUXTRACE_RECORD_ALIGNMENT - padding;
 
 	memset(&ev, 0, sizeof(ev));
 	ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
@@ -1287,7 +1320,7 @@
 	ev.auxtrace.tid = mm->tid;
 	ev.auxtrace.cpu = mm->cpu;
 
-	if (fn(tool, &ev, data1, len1, data2, len2))
+	if (fn(tool, map, &ev, data1, len1, data2, len2))
 		return -1;
 
 	mm->prev = head;
@@ -1306,18 +1339,18 @@
 	return 1;
 }
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+	return __auxtrace_mmap__read(map, itr, tool, fn, false, 0);
 }
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size)
 {
-	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+	return __auxtrace_mmap__read(map, itr, tool, fn, true, snapshot_size);
 }
 
 /**
@@ -1397,7 +1430,7 @@
 		return;
 
 	auxtrace_cache__drop(c);
-	free(c->hashtable);
+	zfree(&c->hashtable);
 	free(c);
 }
 
@@ -1443,12 +1476,11 @@
 
 static void addr_filter__free_str(struct addr_filter *filt)
 {
-	free(filt->str);
+	zfree(&filt->str);
 	filt->action   = NULL;
 	filt->sym_from = NULL;
 	filt->sym_to   = NULL;
 	filt->filename = NULL;
-	filt->str      = NULL;
 }
 
 static struct addr_filter *addr_filter__new(void)
@@ -1894,7 +1926,8 @@
 	if (!map)
 		return NULL;
 
-	map__load(map);
+	if (map__load(map) < 0)
+		pr_err("File '%s' not found or has no symbols.\n", name);
 
 	dso = dso__get(map->dso);
 
@@ -1978,17 +2011,14 @@
 
 static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
 {
-	struct symbol *first_sym = dso__first_symbol(dso);
-	struct symbol *last_sym = dso__last_symbol(dso);
-
-	if (!first_sym || !last_sym) {
-		pr_err("Failed to determine filter for %s\nNo symbols found.\n",
+	if (dso__data_file_size(dso, NULL)) {
+		pr_err("Failed to determine filter for %s\nCannot determine file size.\n",
 		       filt->filename);
 		return -EINVAL;
 	}
 
-	filt->addr = first_sym->start;
-	filt->size = last_sym->end - first_sym->start;
+	filt->addr = 0;
+	filt->size = dso->data.file_size;
 
 	return 0;
 }
@@ -2071,7 +2101,7 @@
 	return err < 0 ? NULL : filter;
 }
 
-static int parse_addr_filter(struct perf_evsel *evsel, const char *filter,
+static int parse_addr_filter(struct evsel *evsel, const char *filter,
 			     int max_nr)
 {
 	struct addr_filters filts;
@@ -2122,19 +2152,19 @@
 	return err;
 }
 
-static struct perf_pmu *perf_evsel__find_pmu(struct perf_evsel *evsel)
+static struct perf_pmu *perf_evsel__find_pmu(struct evsel *evsel)
 {
 	struct perf_pmu *pmu = NULL;
 
 	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-		if (pmu->type == evsel->attr.type)
+		if (pmu->type == evsel->core.attr.type)
 			break;
 	}
 
 	return pmu;
 }
 
-static int perf_evsel__nr_addr_filter(struct perf_evsel *evsel)
+static int perf_evsel__nr_addr_filter(struct evsel *evsel)
 {
 	struct perf_pmu *pmu = perf_evsel__find_pmu(evsel);
 	int nr_addr_filters = 0;
@@ -2147,9 +2177,9 @@
 	return nr_addr_filters;
 }
 
-int auxtrace_parse_filters(struct perf_evlist *evlist)
+int auxtrace_parse_filters(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	char *filter;
 	int err, max_nr;
 
@@ -2168,3 +2198,36 @@
 
 	return 0;
 }
+
+int auxtrace__process_event(struct perf_session *session, union perf_event *event,
+			    struct perf_sample *sample, struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->flush_events(session, tool);
+}
+
+void auxtrace__free_events(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free_events(session);
+}
+
+void auxtrace__free(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free(session);
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 71fc3bd..f201f36 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * auxtrace.h: AUX area trace support
  * Copyright (c) 2013-2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef __PERF_AUXTRACE_H
@@ -20,24 +11,33 @@
 #include <errno.h>
 #include <stdbool.h>
 #include <stddef.h>
+#include <stdio.h> // FILE
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
-
-#include "../perf.h"
-#include "event.h"
-#include "session.h"
-#include "debug.h"
+#include <asm/bitsperlong.h>
+#include <asm/barrier.h>
 
 union perf_event;
 struct perf_session;
-struct perf_evlist;
+struct evlist;
 struct perf_tool;
+struct mmap;
+struct perf_sample;
 struct option;
 struct record_opts;
-struct auxtrace_info_event;
+struct perf_record_auxtrace_error;
+struct perf_record_auxtrace_info;
 struct events_stats;
 
+enum auxtrace_error_type {
+       PERF_AUXTRACE_ERROR_ITRACE  = 1,
+       PERF_AUXTRACE_ERROR_MAX
+};
+
+/* Auxtrace records must have the same alignment as perf event records */
+#define PERF_AUXTRACE_RECORD_ALIGNMENT 8
+
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
 	PERF_AUXTRACE_INTEL_PT,
@@ -56,6 +56,7 @@
 /**
  * struct itrace_synth_opts - AUX area tracing synthesis options.
  * @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
  * @inject: indicates the event (not just the sample) must be fully synthesized
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
@@ -63,6 +64,8 @@
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
+ * @other_events: whether to synthesize other events recorded due to the use of
+ *                aux_output
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -77,15 +80,19 @@
  * @period_type: 'instructions' events period type
  * @initial_skip: skip N events at the beginning.
  * @cpu_bitmap: CPUs for which to synthesize events, or NULL for all
+ * @ptime_range: time intervals to trace or NULL
+ * @range_num: number of time intervals to trace
  */
 struct itrace_synth_opts {
 	bool			set;
+	bool			default_no_sample;
 	bool			inject;
 	bool			instructions;
 	bool			branches;
 	bool			transactions;
 	bool			ptwrites;
 	bool			pwr_events;
+	bool			other_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;
@@ -100,6 +107,8 @@
 	enum itrace_period_type	period_type;
 	unsigned long		initial_skip;
 	unsigned long		*cpu_bitmap;
+	struct perf_time_interval *ptime_range;
+	int			range_num;
 };
 
 /**
@@ -307,13 +316,13 @@
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
-				 struct perf_evlist *evlist,
+				 struct evlist *evlist,
 				 struct record_opts *opts);
 	size_t (*info_priv_size)(struct auxtrace_record *itr,
-				 struct perf_evlist *evlist);
+				 struct evlist *evlist);
 	int (*info_fill)(struct auxtrace_record *itr,
 			 struct perf_session *session,
-			 struct auxtrace_info_event *auxtrace_info,
+			 struct perf_record_auxtrace_info *auxtrace_info,
 			 size_t priv_size);
 	void (*free)(struct auxtrace_record *itr);
 	int (*snapshot_start)(struct auxtrace_record *itr);
@@ -371,6 +380,8 @@
 	int			cnt;
 };
 
+struct auxtrace_cache;
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 /*
@@ -430,17 +441,18 @@
 				unsigned int auxtrace_pages,
 				bool auxtrace_overwrite);
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct perf_evlist *evlist, int idx,
+				   struct evlist *evlist, int idx,
 				   bool per_cpu);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  struct mmap *map,
 				  union perf_event *event, void *data1,
 				  size_t len1, void *data2, size_t len2);
 
-int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+int auxtrace_mmap__read(struct mmap *map, struct auxtrace_record *itr,
 			struct perf_tool *tool, process_auxtrace_t fn);
 
-int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+int auxtrace_mmap__read_snapshot(struct mmap *map,
 				 struct auxtrace_record *itr,
 				 struct perf_tool *tool, process_auxtrace_t fn,
 				 size_t snapshot_size);
@@ -479,24 +491,24 @@
 			struct auxtrace_cache_entry *entry);
 void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
 
-struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
 					      int *err);
 
 int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 				    struct record_opts *opts,
 				    const char *str);
 int auxtrace_record__options(struct auxtrace_record *itr,
-			     struct perf_evlist *evlist,
+			     struct evlist *evlist,
 			     struct record_opts *opts);
 size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
-				       struct perf_evlist *evlist);
+				       struct evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
-			       struct auxtrace_info_event *auxtrace_info,
+			       struct perf_record_auxtrace_info *auxtrace_info,
 			       size_t priv_size);
 void auxtrace_record__free(struct auxtrace_record *itr);
 int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
-int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr, bool on_exit);
 int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
 				   struct auxtrace_mmap *mm,
 				   unsigned char *data, u64 *head, u64 *old);
@@ -509,26 +521,20 @@
 			    bool needs_swap);
 void auxtrace_index__free(struct list_head *head);
 
-void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
-			  const char *msg);
+			  const char *msg, u64 timestamp);
 
-int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
-					 struct perf_tool *tool,
-					 struct perf_session *session,
-					 perf_event__handler_t process);
-int perf_event__process_auxtrace_info(struct perf_tool *tool,
-				      union perf_event *event,
-				      struct perf_session *session);
-s64 perf_event__process_auxtrace(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
-int perf_event__process_auxtrace_error(struct perf_tool *tool,
-				       union perf_event *event,
-				       struct perf_session *session);
+int perf_event__process_auxtrace_info(struct perf_session *session,
+				      union perf_event *event);
+s64 perf_event__process_auxtrace(struct perf_session *session,
+				 union perf_event *event);
+int perf_event__process_auxtrace_error(struct perf_session *session,
+				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample);
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
 void perf_session__auxtrace_error_inc(struct perf_session *session,
@@ -539,48 +545,51 @@
 void addr_filters__exit(struct addr_filters *filts);
 int addr_filters__parse_bare_filter(struct addr_filters *filts,
 				    const char *filter);
-int auxtrace_parse_filters(struct perf_evlist *evlist);
+int auxtrace_parse_filters(struct evlist *evlist);
 
-static inline int auxtrace__process_event(struct perf_session *session,
-					  union perf_event *event,
-					  struct perf_sample *sample,
-					  struct perf_tool *tool)
+int auxtrace__process_event(struct perf_session *session, union perf_event *event,
+			    struct perf_sample *sample, struct perf_tool *tool);
+int auxtrace__flush_events(struct perf_session *session, struct perf_tool *tool);
+void auxtrace__free_events(struct perf_session *session);
+void auxtrace__free(struct perf_session *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"
+
+static inline
+void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts,
+				       struct perf_time_interval *ptime_range,
+				       int range_num)
 {
-	if (!session->auxtrace)
-		return 0;
-
-	return session->auxtrace->process_event(session, event, sample, tool);
+	opts->ptime_range = ptime_range;
+	opts->range_num = range_num;
 }
 
-static inline int auxtrace__flush_events(struct perf_session *session,
-					 struct perf_tool *tool)
+static inline
+void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts)
 {
-	if (!session->auxtrace)
-		return 0;
-
-	return session->auxtrace->flush_events(session, tool);
-}
-
-static inline void auxtrace__free_events(struct perf_session *session)
-{
-	if (!session->auxtrace)
-		return;
-
-	return session->auxtrace->free_events(session);
-}
-
-static inline void auxtrace__free(struct perf_session *session)
-{
-	if (!session->auxtrace)
-		return;
-
-	return session->auxtrace->free(session);
+	opts->ptime_range = NULL;
+	opts->range_num = 0;
 }
 
 #else
+#include "debug.h"
 
 static inline struct auxtrace_record *
-auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+auxtrace_record__init(struct evlist *evlist __maybe_unused,
 		      int *err)
 {
 	*err = 0;
@@ -592,18 +601,9 @@
 {
 }
 
-static inline int
-perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
-				     struct perf_tool *tool __maybe_unused,
-				     struct perf_session *session __maybe_unused,
-				     perf_event__handler_t process __maybe_unused)
-{
-	return -EINVAL;
-}
-
 static inline
 int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
-			     struct perf_evlist *evlist __maybe_unused,
+			     struct evlist *evlist __maybe_unused,
 			     struct record_opts *opts __maybe_unused)
 {
 	return 0;
@@ -700,7 +700,7 @@
 }
 
 static inline
-int auxtrace_parse_filters(struct perf_evlist *evlist __maybe_unused)
+int auxtrace_parse_filters(struct evlist *evlist __maybe_unused)
 {
 	return 0;
 }
@@ -714,9 +714,26 @@
 				unsigned int auxtrace_pages,
 				bool auxtrace_overwrite);
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct perf_evlist *evlist, int idx,
+				   struct evlist *evlist, int idx,
 				   bool per_cpu);
 
+#define ITRACE_HELP ""
+
+static inline
+void itrace_synth_opts__set_time_range(struct itrace_synth_opts *opts
+				       __maybe_unused,
+				       struct perf_time_interval *ptime_range
+				       __maybe_unused,
+				       int range_num __maybe_unused)
+{
+}
+
+static inline
+void itrace_synth_opts__clear_time_range(struct itrace_synth_opts *opts
+					 __maybe_unused)
+{
+}
+
 #endif
 
 #endif
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index f1451c9..1be4326 100644
--- a/tools/perf/util/block-range.c
+++ b/tools/perf/util/block-range.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "block-range.h"
 #include "annotate.h"
+#include <assert.h>
+#include <stdlib.h>
 
 struct {
 	struct rb_root root;
diff --git a/tools/perf/util/block-range.h b/tools/perf/util/block-range.h
index a5ba719..ec0fb53 100644
--- a/tools/perf/util/block-range.h
+++ b/tools/perf/util/block-range.h
@@ -2,7 +2,11 @@
 #ifndef __PERF_BLOCK_RANGE_H
 #define __PERF_BLOCK_RANGE_H
 
-#include "symbol.h"
+#include <stdbool.h>
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+struct symbol;
 
 /*
  * struct block_range - non-overlapping parts of basic blocks
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
new file mode 100644
index 0000000..f7ed5d1
--- /dev/null
+++ b/tools/perf/util/bpf-event.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdlib.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include "bpf-event.h"
+#include "debug.h"
+#include "dso.h"
+#include "symbol.h"
+#include "machine.h"
+#include "env.h"
+#include "session.h"
+#include "map.h"
+#include "evlist.h"
+#include "record.h"
+#include "util/synthetic-events.h"
+
+#define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
+
+static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
+{
+	int ret = 0;
+	size_t i;
+
+	for (i = 0; i < len; i++)
+		ret += snprintf(buf + ret, size - ret, "%02x", data[i]);
+	return ret;
+}
+
+static int machine__process_bpf_event_load(struct machine *machine,
+					   union perf_event *event,
+					   struct perf_sample *sample __maybe_unused)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct perf_env *env = machine->env;
+	int id = event->bpf.id;
+	unsigned int i;
+
+	/* perf-record, no need to handle bpf-event */
+	if (env == NULL)
+		return 0;
+
+	info_node = perf_env__find_bpf_prog_info(env, id);
+	if (!info_node)
+		return 0;
+	info_linear = info_node->info_linear;
+
+	for (i = 0; i < info_linear->info.nr_jited_ksyms; i++) {
+		u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);
+		u64 addr = addrs[i];
+		struct map *map;
+
+		map = map_groups__find(&machine->kmaps, addr);
+
+		if (map) {
+			map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO;
+			map->dso->bpf_prog.id = id;
+			map->dso->bpf_prog.sub_id = i;
+			map->dso->bpf_prog.env = env;
+		}
+	}
+	return 0;
+}
+
+int machine__process_bpf(struct machine *machine, union perf_event *event,
+			 struct perf_sample *sample)
+{
+	if (dump_trace)
+		perf_event__fprintf_bpf(event, stdout);
+
+	switch (event->bpf.type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+		return machine__process_bpf_event_load(machine, event, sample);
+
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		/*
+		 * Do not free bpf_prog_info and btf of the program here,
+		 * as annotation still need them. They will be freed at
+		 * the end of the session.
+		 */
+		break;
+	default:
+		pr_debug("unexpected bpf event type of %d\n", event->bpf.type);
+		break;
+	}
+	return 0;
+}
+
+static int perf_env__fetch_btf(struct perf_env *env,
+			       u32 btf_id,
+			       struct btf *btf)
+{
+	struct btf_node *node;
+	u32 data_size;
+	const void *data;
+
+	data = btf__get_raw_data(btf, &data_size);
+
+	node = malloc(data_size + sizeof(struct btf_node));
+	if (!node)
+		return -1;
+
+	node->id = btf_id;
+	node->data_size = data_size;
+	memcpy(node->data, data, data_size);
+
+	perf_env__insert_btf(env, node);
+	return 0;
+}
+
+static int synthesize_bpf_prog_name(char *buf, int size,
+				    struct bpf_prog_info *info,
+				    struct btf *btf,
+				    u32 sub_id)
+{
+	u8 (*prog_tags)[BPF_TAG_SIZE] = (void *)(uintptr_t)(info->prog_tags);
+	void *func_infos = (void *)(uintptr_t)(info->func_info);
+	u32 sub_prog_cnt = info->nr_jited_ksyms;
+	const struct bpf_func_info *finfo;
+	const char *short_name = NULL;
+	const struct btf_type *t;
+	int name_len;
+
+	name_len = snprintf(buf, size, "bpf_prog_");
+	name_len += snprintf_hex(buf + name_len, size - name_len,
+				 prog_tags[sub_id], BPF_TAG_SIZE);
+	if (btf) {
+		finfo = func_infos + sub_id * info->func_info_rec_size;
+		t = btf__type_by_id(btf, finfo->type_id);
+		short_name = btf__name_by_offset(btf, t->name_off);
+	} else if (sub_id == 0 && sub_prog_cnt == 1) {
+		/* no subprog */
+		if (info->name[0])
+			short_name = info->name;
+	} else
+		short_name = "F";
+	if (short_name)
+		name_len += snprintf(buf + name_len, size - name_len,
+				     "_%s", short_name);
+	return name_len;
+}
+
+/*
+ * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf
+ * program. One PERF_RECORD_BPF_EVENT is generated for the program. And
+ * one PERF_RECORD_KSYMBOL is generated for each sub program.
+ *
+ * Returns:
+ *    0 for success;
+ *   -1 for failures;
+ *   -2 for lack of kernel support.
+ */
+static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
+					       perf_event__handler_t process,
+					       struct machine *machine,
+					       int fd,
+					       union perf_event *event,
+					       struct record_opts *opts)
+{
+	struct perf_record_ksymbol *ksymbol_event = &event->ksymbol;
+	struct perf_record_bpf_event *bpf_event = &event->bpf;
+	struct bpf_prog_info_linear *info_linear;
+	struct perf_tool *tool = session->tool;
+	struct bpf_prog_info_node *info_node;
+	struct bpf_prog_info *info;
+	struct btf *btf = NULL;
+	struct perf_env *env;
+	u32 sub_prog_cnt, i;
+	int err = 0;
+	u64 arrays;
+
+	/*
+	 * for perf-record and perf-report use header.env;
+	 * otherwise, use global perf_env.
+	 */
+	env = session->data ? &session->header.env : &perf_env;
+
+	arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
+
+	info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		info_linear = NULL;
+		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+		return -1;
+	}
+
+	if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		pr_debug("%s: the kernel is too old, aborting\n", __func__);
+		return -2;
+	}
+
+	info = &info_linear->info;
+
+	/* number of ksyms, func_lengths, and tags should match */
+	sub_prog_cnt = info->nr_jited_ksyms;
+	if (sub_prog_cnt != info->nr_prog_tags ||
+	    sub_prog_cnt != info->nr_jited_func_lens)
+		return -1;
+
+	/* check BTF func info support */
+	if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
+		/* btf func info number should be same as sub_prog_cnt */
+		if (sub_prog_cnt != info->nr_func_info) {
+			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
+			err = -1;
+			goto out;
+		}
+		if (btf__get_from_id(info->btf_id, &btf)) {
+			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
+			err = -1;
+			btf = NULL;
+			goto out;
+		}
+		perf_env__fetch_btf(env, info->btf_id, btf);
+	}
+
+	/* Synthesize PERF_RECORD_KSYMBOL */
+	for (i = 0; i < sub_prog_cnt; i++) {
+		__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+		__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+		int name_len;
+
+		*ksymbol_event = (struct perf_record_ksymbol) {
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = offsetof(struct perf_record_ksymbol, name),
+			},
+			.addr = prog_addrs[i],
+			.len = prog_lens[i],
+			.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+			.flags = 0,
+		};
+
+		name_len = synthesize_bpf_prog_name(ksymbol_event->name,
+						    KSYM_NAME_LEN, info, btf, i);
+		ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
+							 sizeof(u64));
+
+		memset((void *)event + event->header.size, 0, machine->id_hdr_size);
+		event->header.size += machine->id_hdr_size;
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+	if (!opts->no_bpf_event) {
+		/* Synthesize PERF_RECORD_BPF_EVENT */
+		*bpf_event = (struct perf_record_bpf_event) {
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(struct perf_record_bpf_event),
+			},
+			.type = PERF_BPF_EVENT_PROG_LOAD,
+			.flags = 0,
+			.id = info->id,
+		};
+		memcpy(bpf_event->tag, info->tag, BPF_TAG_SIZE);
+		memset((void *)event + event->header.size, 0, machine->id_hdr_size);
+		event->header.size += machine->id_hdr_size;
+
+		/* save bpf_prog_info to env */
+		info_node = malloc(sizeof(struct bpf_prog_info_node));
+		if (!info_node) {
+			err = -1;
+			goto out;
+		}
+
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+		info_linear = NULL;
+
+		/*
+		 * process after saving bpf_prog_info to env, so that
+		 * required information is ready for look up
+		 */
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+out:
+	free(info_linear);
+	free(btf);
+	return err ? -1 : 0;
+}
+
+int perf_event__synthesize_bpf_events(struct perf_session *session,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts)
+{
+	union perf_event *event;
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
+	if (!event)
+		return -1;
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT) {
+				err = 0;
+				break;
+			}
+			pr_debug("%s: can't get next program: %s%s\n",
+				 __func__, strerror(errno),
+				 errno == EINVAL ? " -- kernel too old?" : "");
+			/* 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);
+		if (fd < 0) {
+			pr_debug("%s: failed to get fd for prog_id %u\n",
+				 __func__, id);
+			continue;
+		}
+
+		err = perf_event__synthesize_one_bpf_prog(session, process,
+							  machine, fd,
+							  event, opts);
+		close(fd);
+		if (err) {
+			/* do not return error for old kernel */
+			if (err == -2)
+				err = 0;
+			break;
+		}
+	}
+	free(event);
+	return err;
+}
+
+static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct btf *btf = NULL;
+	u64 arrays;
+	u32 btf_id;
+	int fd;
+
+	fd = bpf_prog_get_fd_by_id(id);
+	if (fd < 0)
+		return;
+
+	arrays = 1UL << BPF_PROG_INFO_JITED_KSYMS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
+	arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_PROG_TAGS;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_INSNS;
+	arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
+	arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
+
+	info_linear = bpf_program__get_prog_info_linear(fd, arrays);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+		goto out;
+	}
+
+	btf_id = info_linear->info.btf_id;
+
+	info_node = malloc(sizeof(struct bpf_prog_info_node));
+	if (info_node) {
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+	} else
+		free(info_linear);
+
+	if (btf_id == 0)
+		goto out;
+
+	if (btf__get_from_id(btf_id, &btf)) {
+		pr_debug("%s: failed to get BTF of id %u, aborting\n",
+			 __func__, btf_id);
+		goto out;
+	}
+	perf_env__fetch_btf(env, btf_id, btf);
+
+out:
+	free(btf);
+	close(fd);
+}
+
+static int bpf_event__sb_cb(union perf_event *event, void *data)
+{
+	struct perf_env *env = data;
+
+	if (event->header.type != PERF_RECORD_BPF_EVENT)
+		return -1;
+
+	switch (event->bpf.type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+		perf_env__add_bpf_info(env, event->bpf.id);
+
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		/*
+		 * Do not free bpf_prog_info and btf of the program here,
+		 * as annotation still need them. They will be freed at
+		 * the end of the session.
+		 */
+		break;
+	default:
+		pr_debug("unexpected bpf event type of %d\n", event->bpf.type);
+		break;
+	}
+
+	return 0;
+}
+
+int bpf_event__add_sb_event(struct evlist **evlist,
+			    struct perf_env *env)
+{
+	struct perf_event_attr attr = {
+		.type	          = PERF_TYPE_SOFTWARE,
+		.config           = PERF_COUNT_SW_DUMMY,
+		.sample_id_all    = 1,
+		.watermark        = 1,
+		.bpf_event        = 1,
+		.size	   = sizeof(attr), /* to capture ABI version */
+	};
+
+	/*
+	 * Older gcc versions don't support designated initializers, like above,
+	 * for unnamed union members, such as the following:
+	 */
+	attr.wakeup_watermark = 1;
+
+	return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
+}
+
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				    struct perf_env *env,
+				    FILE *fp)
+{
+	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
+	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
+	char name[KSYM_NAME_LEN];
+	struct btf *btf = NULL;
+	u32 sub_prog_cnt, i;
+
+	sub_prog_cnt = info->nr_jited_ksyms;
+	if (sub_prog_cnt != info->nr_prog_tags ||
+	    sub_prog_cnt != info->nr_jited_func_lens)
+		return;
+
+	if (info->btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(env, info->btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	if (sub_prog_cnt == 1) {
+		synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, 0);
+		fprintf(fp, "# bpf_prog_info %u: %s addr 0x%llx size %u\n",
+			info->id, name, prog_addrs[0], prog_lens[0]);
+		return;
+	}
+
+	fprintf(fp, "# bpf_prog_info %u:\n", info->id);
+	for (i = 0; i < sub_prog_cnt; i++) {
+		synthesize_bpf_prog_name(name, KSYM_NAME_LEN, info, btf, i);
+
+		fprintf(fp, "# \tsub_prog %u: %s addr 0x%llx size %u\n",
+			i, name, prog_addrs[i], prog_lens[i]);
+	}
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
new file mode 100644
index 0000000..81fdc88
--- /dev/null
+++ b/tools/perf/util/bpf-event.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_BPF_EVENT_H
+#define __PERF_BPF_EVENT_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <pthread.h>
+#include <api/fd/array.h>
+#include <stdio.h>
+
+struct bpf_prog_info;
+struct machine;
+union perf_event;
+struct perf_env;
+struct perf_sample;
+struct perf_session;
+struct record_opts;
+struct evlist;
+struct target;
+
+struct bpf_prog_info_node {
+	struct bpf_prog_info_linear	*info_linear;
+	struct rb_node			rb_node;
+};
+
+struct btf_node {
+	struct rb_node	rb_node;
+	u32		id;
+	u32		data_size;
+	char		data[];
+};
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int machine__process_bpf(struct machine *machine, union perf_event *event,
+			 struct perf_sample *sample);
+int bpf_event__add_sb_event(struct evlist **evlist,
+				 struct perf_env *env);
+void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				    struct perf_env *env,
+				    FILE *fp);
+#else
+static inline int machine__process_bpf(struct machine *machine __maybe_unused,
+				       union perf_event *event __maybe_unused,
+				       struct perf_sample *sample __maybe_unused)
+{
+	return 0;
+}
+
+static inline int bpf_event__add_sb_event(struct evlist **evlist __maybe_unused,
+					  struct perf_env *env __maybe_unused)
+{
+	return 0;
+}
+
+static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						  struct perf_env *env __maybe_unused,
+						  FILE *fp __maybe_unused)
+{
+
+}
+#endif // HAVE_LIBBPF_SUPPORT
+#endif
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 47aac41..10c187b 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -12,33 +12,28 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <errno.h>
-#include "perf.h"
+#include <stdlib.h>
 #include "debug.h"
+#include "evlist.h"
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
 #include "parse-events.h"
 #include "strfilter.h"
+#include "util.h"
 #include "llvm-utils.h"
 #include "c++/clang-c.h"
 
-#define DEFINE_PRINT_FN(name, level) \
-static int libbpf_##name(const char *fmt, ...)	\
-{						\
-	va_list args;				\
-	int ret;				\
-						\
-	va_start(args, fmt);			\
-	ret = veprintf(level, verbose, pr_fmt(fmt), args);\
-	va_end(args);				\
-	return ret;				\
-}
+#include <internal/xyarray.h>
 
-DEFINE_PRINT_FN(warning, 1)
-DEFINE_PRINT_FN(info, 1)
-DEFINE_PRINT_FN(debug, 1)
+static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)),
+			      const char *fmt, va_list args)
+{
+	return veprintf(1, verbose, pr_fmt(fmt), args);
+}
 
 struct bpf_prog_priv {
 	bool is_tp;
@@ -59,9 +54,7 @@
 	struct bpf_object *obj;
 
 	if (!libbpf_initialized) {
-		libbpf_set_print(libbpf_warning,
-				 libbpf_info,
-				 libbpf_debug);
+		libbpf_set_print(libbpf_perf_print);
 		libbpf_initialized = true;
 	}
 
@@ -79,9 +72,7 @@
 	struct bpf_object *obj;
 
 	if (!libbpf_initialized) {
-		libbpf_set_print(libbpf_warning,
-				 libbpf_info,
-				 libbpf_debug);
+		libbpf_set_print(libbpf_perf_print);
 		libbpf_initialized = true;
 	}
 
@@ -99,7 +90,7 @@
 			if (err)
 				return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
 		} else
-			pr_debug("bpf: successfull builtin compilation\n");
+			pr_debug("bpf: successful builtin compilation\n");
 		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 
 		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
@@ -775,7 +766,7 @@
 
 		if (priv->is_tp) {
 			fd = bpf_program__fd(prog);
-			err = (*func)(priv->sys_name, priv->evt_name, fd, arg);
+			err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg);
 			if (err) {
 				pr_debug("bpf: tracepoint call back failed, stop iterate\n");
 				return err;
@@ -800,7 +791,7 @@
 				return fd;
 			}
 
-			err = (*func)(tev->group, tev->event, fd, arg);
+			err = (*func)(tev->group, tev->event, fd, obj, arg);
 			if (err) {
 				pr_debug("bpf: call back failed, stop iterate\n");
 				return err;
@@ -829,7 +820,7 @@
 	} k;
 	union {
 		u64 value;
-		struct perf_evsel *evsel;
+		struct evsel *evsel;
 	} v;
 };
 
@@ -841,7 +832,7 @@
 bpf_map_op__delete(struct bpf_map_op *op)
 {
 	if (!list_empty(&op->list))
-		list_del(&op->list);
+		list_del_init(&op->list);
 	if (op->key_type == BPF_MAP_KEY_RANGES)
 		parse_events__clear_array(&op->k.array);
 	free(op);
@@ -1055,7 +1046,7 @@
 static int
 bpf_map__config_value(struct bpf_map *map,
 		      struct parse_events_term *term,
-		      struct perf_evlist *evlist __maybe_unused)
+		      struct evlist *evlist __maybe_unused)
 {
 	if (!term->err_val) {
 		pr_debug("Config value not set\n");
@@ -1073,9 +1064,9 @@
 static int
 __bpf_map__config_event(struct bpf_map *map,
 			struct parse_events_term *term,
-			struct perf_evlist *evlist)
+			struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	const struct bpf_map_def *def;
 	struct bpf_map_op *op;
 	const char *map_name = bpf_map__name(map);
@@ -1115,7 +1106,7 @@
 static int
 bpf_map__config_event(struct bpf_map *map,
 		      struct parse_events_term *term,
-		      struct perf_evlist *evlist)
+		      struct evlist *evlist)
 {
 	if (!term->err_val) {
 		pr_debug("Config value not set\n");
@@ -1133,7 +1124,7 @@
 struct bpf_obj_config__map_func {
 	const char *config_opt;
 	int (*config_func)(struct bpf_map *, struct parse_events_term *,
-			   struct perf_evlist *);
+			   struct evlist *);
 };
 
 struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
@@ -1181,7 +1172,7 @@
 static int
 bpf__obj_config_map(struct bpf_object *obj,
 		    struct parse_events_term *term,
-		    struct perf_evlist *evlist,
+		    struct evlist *evlist,
 		    int *key_scan_pos)
 {
 	/* key is "map:<mapname>.<config opt>" */
@@ -1240,7 +1231,7 @@
 
 int bpf__config_obj(struct bpf_object *obj,
 		    struct parse_events_term *term,
-		    struct perf_evlist *evlist,
+		    struct evlist *evlist,
 		    int *error_pos)
 {
 	int key_scan_pos = 0;
@@ -1413,9 +1404,9 @@
 
 static int
 apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
-			   struct perf_evsel *evsel)
+			   struct evsel *evsel)
 {
-	struct xyarray *xy = evsel->fd;
+	struct xyarray *xy = evsel->core.fd;
 	struct perf_event_attr *attr;
 	unsigned int key, events;
 	bool check_pass = false;
@@ -1433,7 +1424,7 @@
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
 	}
 
-	attr = &evsel->attr;
+	attr = &evsel->core.attr;
 	if (attr->inherit) {
 		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
@@ -1503,7 +1494,7 @@
 	struct bpf_map *map;
 	int err;
 
-	bpf_map__for_each(map, obj) {
+	bpf_object__for_each_map(map, obj) {
 		err = apply_obj_config_map(map);
 		if (err)
 			return err;
@@ -1527,7 +1518,7 @@
 
 #define bpf__for_each_map(pos, obj, objtmp)	\
 	bpf_object__for_each_safe(obj, objtmp)	\
-		bpf_map__for_each(pos, obj)
+		bpf_object__for_each_map(pos, obj)
 
 #define bpf__for_each_map_named(pos, obj, objtmp, name)	\
 	bpf__for_each_map(pos, obj, objtmp) 		\
@@ -1535,11 +1526,11 @@
 			(strcmp(name, 			\
 				bpf_map__name(pos)) == 0))
 
-struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name)
+struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
 	struct bpf_object *obj, *tmp;
-	struct perf_evsel *evsel = NULL;
+	struct evsel *evsel = NULL;
 	struct bpf_map *map;
 	int err;
 	bool need_init = false;
@@ -1577,7 +1568,7 @@
 			return ERR_PTR(-err);
 		}
 
-		evsel = perf_evlist__last(evlist);
+		evsel = evlist__last(evlist);
 	}
 
 	bpf__for_each_map_named(map, obj, tmp, name) {
@@ -1603,7 +1594,7 @@
 
 			op = bpf_map__add_newop(map, NULL);
 			if (IS_ERR(op))
-				return ERR_PTR(PTR_ERR(op));
+				return ERR_CAST(op);
 			op->op_type = BPF_MAP_OP_SET_EVSEL;
 			op->v.evsel = evsel;
 		}
@@ -1612,10 +1603,10 @@
 	return evsel;
 }
 
-int bpf__setup_stdout(struct perf_evlist *evlist)
+int bpf__setup_stdout(struct evlist *evlist)
 {
-	struct perf_evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return IS_ERR(evsel) ? PTR_ERR(evsel) : 0;
+	struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
+	return PTR_ERR_OR_ZERO(evsel);
 }
 
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
@@ -1768,7 +1759,7 @@
 
 int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
 			     struct parse_events_term *term __maybe_unused,
-			     struct perf_evlist *evlist __maybe_unused,
+			     struct evlist *evlist __maybe_unused,
 			     int *error_pos __maybe_unused, int err,
 			     char *buf, size_t size)
 {
@@ -1792,7 +1783,7 @@
 	return 0;
 }
 
-int bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused,
+int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
 				     int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 62d245a..25251d6 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,11 +8,7 @@
 
 #include <linux/compiler.h>
 #include <linux/err.h>
-#include <string.h>
 #include <bpf/libbpf.h>
-#include "probe-event.h"
-#include "evlist.h"
-#include "debug.h"
 
 enum bpf_loader_errno {
 	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
@@ -43,13 +39,14 @@
 	__BPF_LOADER_ERRNO__END,
 };
 
-struct perf_evsel;
+struct evsel;
+struct evlist;
 struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event,
-					int fd, void *arg);
+					int fd, struct bpf_object *obj, void *arg);
 
 #ifdef HAVE_LIBBPF_SUPPORT
 struct bpf_object *bpf__prepare_load(const char *filename, bool source);
@@ -73,20 +70,22 @@
 		       bpf_prog_iter_callback_t func, void *arg);
 
 int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
-		    struct perf_evlist *evlist, int *error_pos);
+		    struct evlist *evlist, int *error_pos);
 int bpf__strerror_config_obj(struct bpf_object *obj,
 			     struct parse_events_term *term,
-			     struct perf_evlist *evlist,
+			     struct evlist *evlist,
 			     int *error_pos, int err, char *buf,
 			     size_t size);
 int bpf__apply_obj_config(void);
 int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 
-int bpf__setup_stdout(struct perf_evlist *evlist);
-struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const char *name);
-int bpf__strerror_setup_output_event(struct perf_evlist *evlist, int err, char *buf, size_t size);
+int bpf__setup_stdout(struct evlist *evlist);
+struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name);
+int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size);
 #else
 #include <errno.h>
+#include <string.h>
+#include "debug.h"
 
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -120,7 +119,7 @@
 static inline int
 bpf__config_obj(struct bpf_object *obj __maybe_unused,
 		struct parse_events_term *term __maybe_unused,
-		struct perf_evlist *evlist __maybe_unused,
+		struct evlist *evlist __maybe_unused,
 		int *error_pos __maybe_unused)
 {
 	return 0;
@@ -133,13 +132,13 @@
 }
 
 static inline int
-bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+bpf__setup_stdout(struct evlist *evlist __maybe_unused)
 {
 	return 0;
 }
 
-static inline struct perf_evsel *
-bpf__setup_output_event(struct perf_evlist *evlist __maybe_unused, const char *name __maybe_unused)
+static inline struct evsel *
+bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused)
 {
 	return NULL;
 }
@@ -183,7 +182,7 @@
 static inline int
 bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
 			 struct parse_events_term *term __maybe_unused,
-			 struct perf_evlist *evlist __maybe_unused,
+			 struct evlist *evlist __maybe_unused,
 			 int *error_pos __maybe_unused,
 			 int err __maybe_unused,
 			 char *buf, size_t size)
@@ -199,7 +198,7 @@
 }
 
 static inline int
-bpf__strerror_setup_output_event(struct perf_evlist *evlist __maybe_unused,
+bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
 				 int err __maybe_unused, char *buf, size_t size)
 {
 	return __bpf_strerror(buf, size);
@@ -207,7 +206,7 @@
 
 #endif
 
-static inline int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size)
+static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size)
 {
 	return bpf__strerror_setup_output_event(evlist, err, buf, size);
 }
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 77e4891..b020a86 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -8,12 +8,12 @@
  */
 
 #include <bpf/libbpf.h>
-#include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-finder.h"
 #include <errno.h>
+#include <stdlib.h>
 #include <dwarf-regs.h>
 #include <linux/filter.h>
 
diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c
new file mode 100644
index 0000000..eb853ca
--- /dev/null
+++ b/tools/perf/util/bpf_map.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include "util/bpf_map.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def)
+{
+	return def->type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+	       def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+	       def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
+}
+
+static void *bpf_map_def__alloc_value(const struct bpf_map_def *def)
+{
+	if (bpf_map_def__is_per_cpu(def))
+		return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF));
+
+	return malloc(def->value_size);
+}
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp)
+{
+	const struct bpf_map_def *def = bpf_map__def(map);
+	void *prev_key = NULL, *key, *value;
+	int fd = bpf_map__fd(map), err;
+	int printed = 0;
+
+	if (fd < 0)
+		return fd;
+
+	if (IS_ERR(def))
+		return PTR_ERR(def);
+
+	err = -ENOMEM;
+	key = malloc(def->key_size);
+	if (key == NULL)
+		goto out;
+
+	value = bpf_map_def__alloc_value(def);
+	if (value == NULL)
+		goto out_free_key;
+
+	while ((err = bpf_map_get_next_key(fd, prev_key, key) == 0)) {
+		int intkey = *(int *)key;
+
+		if (!bpf_map_lookup_elem(fd, key, value)) {
+			bool boolval = *(bool *)value;
+			if (boolval)
+				printed += fprintf(fp, "[%d] = %d,\n", intkey, boolval);
+		} else {
+			printed += fprintf(fp, "[%d] = ERROR,\n", intkey);
+		}
+
+		prev_key = key;
+	}
+
+	if (err == ENOENT)
+		err = printed;
+
+	free(value);
+out_free_key:
+	free(key);
+out:
+	return err;
+}
diff --git a/tools/perf/util/bpf_map.h b/tools/perf/util/bpf_map.h
new file mode 100644
index 0000000..d6abd5e
--- /dev/null
+++ b/tools/perf/util/bpf_map.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#ifndef __PERF_BPF_MAP_H
+#define __PERF_BPF_MAP_H 1
+
+#include <stdio.h>
+#include <linux/compiler.h>
+struct bpf_map;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+
+int bpf_map__fprintf(struct bpf_map *map, FILE *fp);
+
+#else
+
+static inline int bpf_map__fprintf(struct bpf_map *map __maybe_unused, FILE *fp __maybe_unused)
+{
+	return 0;
+}
+
+#endif // HAVE_LIBBPF_SUPPORT
+
+#endif // __PERF_BPF_MAP_H
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index a4fce27..2285b1e 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -1,7 +1,6 @@
-#include "perf.h"
-#include "util/util.h"
-#include "util/debug.h"
+#include "util/map_symbol.h"
 #include "util/branch.h"
+#include <linux/kernel.h>
 
 static bool cross_area(u64 addr1, u64 addr2, int size)
 {
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 1e3c7c5..88e00d2 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -1,8 +1,46 @@
 #ifndef _PERF_BRANCH_H
 #define _PERF_BRANCH_H 1
-
+/*
+ * The linux/stddef.h isn't need here, but is needed for __always_inline used
+ * in files included from uapi/linux/perf_event.h such as
+ * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h,
+ * detected in at least musl libc, used in Alpine Linux. -acme
+ */
+#include <stdio.h>
 #include <stdint.h>
-#include "../perf.h"
+#include <linux/compiler.h>
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+struct branch_flags {
+	u64 mispred:1;
+	u64 predicted:1;
+	u64 in_tx:1;
+	u64 abort:1;
+	u64 cycles:16;
+	u64 type:4;
+	u64 reserved:40;
+};
+
+struct branch_info {
+	struct addr_map_symbol from;
+	struct addr_map_symbol to;
+	struct branch_flags    flags;
+	char		       *srcline_from;
+	char		       *srcline_to;
+};
+
+struct branch_entry {
+	u64			from;
+	u64			to;
+	struct branch_flags	flags;
+};
+
+struct branch_stack {
+	u64			nr;
+	struct branch_entry	entries[0];
+};
 
 struct branch_type_stat {
 	bool	branch_to;
@@ -13,8 +51,6 @@
 	u64	cross_2m;
 };
 
-struct branch_flags;
-
 void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 		       u64 from, u64 to);
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 04b1d53..c076fc7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -7,14 +7,18 @@
  * Copyright (C) 2009, 2010 Red Hat Inc.
  * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
  */
-#include "util.h"
+#include "util.h" // lsdir(), mkdir_p(), rm_rf()
 #include <dirent.h>
 #include <errno.h>
 #include <stdio.h>
 #include <sys/stat.h>
 #include <sys/types.h>
+#include "util/copyfile.h"
+#include "dso.h"
 #include "build-id.h"
 #include "event.h"
+#include "namespaces.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include <linux/kernel.h>
@@ -27,14 +31,15 @@
 #include "probe-file.h"
 #include "strlist.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static bool no_buildid_cache;
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
 			   struct perf_sample *sample,
-			   struct perf_evsel *evsel __maybe_unused,
+			   struct evsel *evsel __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
@@ -183,6 +188,7 @@
 	return bf;
 }
 
+/* The caller is responsible to free the returned buffer. */
 char *build_id_cache__origname(const char *sbuild_id)
 {
 	char *linkname;
@@ -291,7 +297,7 @@
 			 pid_t pid, u16 misc, struct feat_fd *fd)
 {
 	int err;
-	struct build_id_event b;
+	struct perf_record_header_build_id b;
 	size_t len;
 
 	len = name_len + 1;
@@ -363,7 +369,8 @@
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		err = machine__write_buildid_table(pos, fd);
 		if (err)
@@ -396,7 +403,8 @@
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 
 		err = machine__hit_all_dsos(pos);
@@ -849,7 +857,8 @@
 
 	ret = machine__cache_build_ids(&session->machines.host);
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__cache_build_ids(pos);
 	}
@@ -866,7 +875,8 @@
 	struct rb_node *nd;
 	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
 
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__read_build_ids(pos, with_hits);
 	}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index f0c5651..aad419b 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -6,9 +6,10 @@
 #define SBUILD_ID_SIZE	(BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
-#include "namespaces.h"
 #include <linux/types.h>
 
+struct nsinfo;
+
 extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
 struct feat_fd;
@@ -23,7 +24,7 @@
 			     bool is_debug);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
-			   struct perf_sample *sample, struct perf_evsel *evsel,
+			   struct perf_sample *sample, struct evsel *evsel,
 			   struct machine *machine);
 
 int dsos__hit_all(struct perf_session *session);
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
index 988fef1..613ecfd 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/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
index e513366..2df8a45 100644
--- a/tools/perf/util/c++/clang-c.h
+++ b/tools/perf/util/c++/clang-c.h
@@ -3,7 +3,6 @@
 #define PERF_UTIL_CLANG_C_H
 
 #include <stddef.h>	/* for size_t */
-#include <util-cxx.h>	/* for __maybe_unused */
 
 #ifdef __cplusplus
 extern "C" {
@@ -22,6 +21,7 @@
 #else
 
 #include <errno.h>
+#include <linux/compiler.h>	/* for __maybe_unused */
 
 static inline void perf_clang__init(void) { }
 static inline void perf_clang__cleanup(void) { }
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
index 7b042a5..21b2360 100644
--- a/tools/perf/util/c++/clang-test.cpp
+++ b/tools/perf/util/c++/clang-test.cpp
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "clang.h"
 #include "clang-c.h"
+extern "C" {
+#include "../util.h"
+}
 #include "llvm/IR/Function.h"
 #include "llvm/IR/LLVMContext.h"
 
-#include <util-cxx.h>
 #include <tests/llvm.h>
 #include <string>
 
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 8951250..fc361c3 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -156,11 +156,11 @@
 #endif
 	if (NotAdded) {
 		llvm::errs() << "TargetMachine can't emit a file of this type\n";
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
+		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
 	}
 	PM.run(*Module);
 
-	return std::move(Buffer);
+	return Buffer;
 }
 
 }
diff --git a/tools/perf/util/cacheline.c b/tools/perf/util/cacheline.c
new file mode 100644
index 0000000..e98b525
--- /dev/null
+++ b/tools/perf/util/cacheline.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "cacheline.h"
+#include <unistd.h>
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+#include <api/fs/fs.h>
+#include "debug.h"
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+	static int size;
+
+	if (!size)
+		cache_line_size(&size);
+
+	return size;
+}
diff --git a/tools/perf/util/cacheline.h b/tools/perf/util/cacheline.h
new file mode 100644
index 0000000..dec8c0f
--- /dev/null
+++ b/tools/perf/util/cacheline.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CACHELINE_H
+#define PERF_CACHELINE_H
+
+#include <linux/compiler.h>
+
+int __pure cacheline_size(void);
+
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size() - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size() - 1));
+}
+
+#endif // PERF_CACHELINE_H
diff --git a/tools/perf/util/call-path.c b/tools/perf/util/call-path.c
index 904a170..5c60b8b 100644
--- a/tools/perf/util/call-path.c
+++ b/tools/perf/util/call-path.c
@@ -1,22 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * call-path.h: Manipulate a tree data structure containing function call paths
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
 
-#include "util.h"
 #include "call-path.h"
 
 static void call_path__init(struct call_path *cp, struct call_path *parent,
@@ -48,7 +40,7 @@
 	struct call_path_block *pos, *n;
 
 	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
-		list_del(&pos->node);
+		list_del_init(&pos->node);
 		free(pos);
 	}
 	free(cpr);
diff --git a/tools/perf/util/call-path.h b/tools/perf/util/call-path.h
index 477f6d0..6b32291 100644
--- a/tools/perf/util/call-path.h
+++ b/tools/perf/util/call-path.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * call-path.h: Manipulate a tree data structure containing function call paths
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef __PERF_CALL_PATH_H
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 32ef7bd..9a9b56e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -16,15 +16,22 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <math.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 
 #include "asm/bug.h"
 
+#include "debug.h"
+#include "dso.h"
+#include "event.h"
 #include "hist.h"
-#include "util.h"
 #include "sort.h"
 #include "machine.h"
+#include "map.h"
 #include "callchain.h"
 #include "branch.h"
+#include "symbol.h"
+#include "../perf.h"
 
 #define CALLCHAIN_PARAM_DEFAULT			\
 	.mode		= CHAIN_GRAPH_ABS,	\
@@ -634,7 +641,7 @@
 		struct callchain_list *call, *tmp;
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
-			list_del(&call->list);
+			list_del_init(&call->list);
 			map__zput(call->ms.map);
 			free(call);
 		}
@@ -766,6 +773,7 @@
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
+			cnode->from_count++;
 		}
 	}
 
@@ -999,7 +1007,7 @@
 		callchain_cursor_append(cursor, list->ip,
 					list->ms.map, list->ms.sym,
 					false, NULL, 0, 0, 0, list->srcline);
-		list_del(&list->list);
+		list_del_init(&list->list);
 		map__zput(list->ms.map);
 		free(list);
 	}
@@ -1074,7 +1082,7 @@
 
 int sample__resolve_callchain(struct perf_sample *sample,
 			      struct callchain_cursor *cursor, struct symbol **parent,
-			      struct perf_evsel *evsel, struct addr_location *al,
+			      struct evsel *evsel, struct addr_location *al,
 			      int max_stack)
 {
 	if (sample->callchain == NULL && !symbol_conf.show_branchflag_count)
@@ -1345,10 +1353,10 @@
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 iter_cycles)
+			   u64 iter_cycles, u64 from_count)
 {
 	int printed = 0, i = 0;
-	u64 cycles;
+	u64 cycles, v = 0;
 
 	cycles = cycles_count / branch_count;
 	if (cycles) {
@@ -1357,14 +1365,16 @@
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count) {
-		printed += count_pri64_printf(i++, "iter",
-				iter_count,
-				bf + printed, bfsize - printed);
+	if (iter_count && from_count) {
+		v = iter_count / from_count;
+		if (v) {
+			printed += count_pri64_printf(i++, "iter",
+					v, bf + printed, bfsize - printed);
 
-		printed += count_pri64_printf(i++, "avg_cycles",
-				iter_cycles / iter_count,
-				bf + printed, bfsize - printed);
+			printed += count_pri64_printf(i++, "avg_cycles",
+					iter_cycles / iter_count,
+					bf + printed, bfsize - printed);
+		}
 	}
 
 	if (i)
@@ -1377,6 +1387,7 @@
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
+			     u64 from_count,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1389,7 +1400,8 @@
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, iter_cycles);
+				cycles_count, iter_count, iter_cycles,
+				from_count);
 	}
 
 	if (!printed)
@@ -1402,13 +1414,14 @@
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
+				   u64 from_count,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, iter_cycles, brtype_stat);
+			 iter_count, iter_cycles, from_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1422,6 +1435,7 @@
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
+	u64 from_count;
 
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
@@ -1429,11 +1443,12 @@
 	cycles_count = clist->cycles_count;
 	iter_count = clist->iter_count;
 	iter_cycles = clist->iter_cycles;
+	from_count = clist->from_count;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       &clist->brtype_stat);
+				       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
@@ -1443,13 +1458,13 @@
 	struct rb_node *n;
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
-		list_del(&list->list);
+		list_del_init(&list->list);
 		map__zput(list->ms.map);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
-		list_del(&list->list);
+		list_del_init(&list->list);
 		map__zput(list->ms.map);
 		free(list);
 	}
@@ -1534,7 +1549,7 @@
 
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
-		list_del(&chain->list);
+		list_del_init(&chain->list);
 		map__zput(chain->ms.map);
 		free(chain);
 	}
@@ -1569,3 +1584,18 @@
 
 	return rc;
 }
+
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+	struct callchain_cursor_node *node;
+
+	cursor->nr = 0;
+	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 154560b..83398e5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -2,14 +2,18 @@
 #ifndef __PERF_CALLCHAIN_H
 #define __PERF_CALLCHAIN_H
 
-#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include "event.h"
-#include "map.h"
-#include "symbol.h"
+#include "map_symbol.h"
 #include "branch.h"
 
+struct addr_location;
+struct evsel;
+struct ip_callchain;
+struct map;
+struct perf_sample;
+struct thread;
+
 #define HELP_PAD "\t\t\t\t"
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
@@ -118,6 +122,7 @@
 		bool		has_children;
 	};
 	u64			branch_count;
+	u64			from_count;
 	u64			predicted_count;
 	u64			abort_count;
 	u64			cycles_count;
@@ -187,20 +192,7 @@
 int callchain_merge(struct callchain_cursor *cursor,
 		    struct callchain_root *dst, struct callchain_root *src);
 
-/*
- * Initialize a cursor before adding entries inside, but keep
- * the previously allocated entries as a cache.
- */
-static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
-{
-	struct callchain_cursor_node *node;
-
-	cursor->nr = 0;
-	cursor->last = &cursor->first;
-
-	for (node = cursor->first; node != NULL; node = node->next)
-		map__zput(node->map);
-}
+void callchain_cursor_reset(struct callchain_cursor *cursor);
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
 			    struct map *map, struct symbol *sym,
@@ -248,7 +240,7 @@
 
 int sample__resolve_callchain(struct perf_sample *sample,
 			      struct callchain_cursor *cursor, struct symbol **parent,
-			      struct perf_evsel *evsel, struct addr_location *al,
+			      struct evsel *evsel, struct addr_location *al,
 			      int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
 int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c
new file mode 100644
index 0000000..c3ba841
--- /dev/null
+++ b/tools/perf/util/cap.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Capability utilities
+ */
+
+#ifdef HAVE_LIBCAP_SUPPORT
+
+#include "cap.h"
+#include <stdbool.h>
+#include <sys/capability.h>
+
+bool perf_cap__capable(cap_value_t cap)
+{
+	cap_flag_value_t val;
+	cap_t caps = cap_get_proc();
+
+	if (!caps)
+		return false;
+
+	if (cap_get_flag(caps, cap, CAP_EFFECTIVE, &val) != 0)
+		val = CAP_CLEAR;
+
+	if (cap_free(caps) != 0)
+		return false;
+
+	return val == CAP_SET;
+}
+
+#endif  /* HAVE_LIBCAP_SUPPORT */
diff --git a/tools/perf/util/cap.h b/tools/perf/util/cap.h
new file mode 100644
index 0000000..051dc59
--- /dev/null
+++ b/tools/perf/util/cap.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_CAP_H
+#define __PERF_CAP_H
+
+#include <stdbool.h>
+#include <linux/capability.h>
+#include <linux/compiler.h>
+
+#ifdef HAVE_LIBCAP_SUPPORT
+
+#include <sys/capability.h>
+
+bool perf_cap__capable(cap_value_t cap);
+
+#else
+
+#include <unistd.h>
+#include <sys/types.h>
+
+static inline bool perf_cap__capable(int cap __maybe_unused)
+{
+	return geteuid() == 0;
+}
+
+#endif /* HAVE_LIBCAP_SUPPORT */
+
+/* For older systems */
+#ifndef CAP_SYSLOG
+#define CAP_SYSLOG	34
+#endif
+
+#endif /* __PERF_CAP_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index ccd0263..4881d4a 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,14 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
-#include "../perf.h"
 #include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
 #include <linux/stringify.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
 
 int nr_cgroups;
 
@@ -90,9 +91,9 @@
 	return fd;
 }
 
-static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str)
+static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str)
 {
-	struct perf_evsel *counter;
+	struct evsel *counter;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
@@ -124,22 +125,22 @@
 	return cgroup;
 
 out_free_name:
-	free(cgroup->name);
+	zfree(&cgroup->name);
 out_err:
 	free(cgroup);
 	return NULL;
 }
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name)
+struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name)
 {
 	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
 
 	return cgroup ?: cgroup__new(name);
 }
 
-static int add_cgroup(struct perf_evlist *evlist, const char *str)
+static int add_cgroup(struct evlist *evlist, const char *str)
 {
-	struct perf_evsel *counter;
+	struct evsel *counter;
 	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
 	int n;
 
@@ -184,15 +185,15 @@
        return cgroup;
 }
 
-static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup)
+static void evsel__set_default_cgroup(struct evsel *evsel, struct cgroup *cgroup)
 {
 	if (evsel->cgrp == NULL)
 		evsel->cgrp = cgroup__get(cgroup);
 }
 
-void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup)
+void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
 		evsel__set_default_cgroup(evsel, cgroup);
@@ -201,14 +202,14 @@
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
-	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-	struct perf_evsel *counter;
+	struct evlist *evlist = *(struct evlist **)opt->value;
+	struct evsel *counter;
 	struct cgroup *cgrp = NULL;
 	const char *p, *e, *eos = str + strlen(str);
 	char *s;
 	int ret, i;
 
-	if (list_empty(&evlist->entries)) {
+	if (list_empty(&evlist->core.entries)) {
 		fprintf(stderr, "must define events before cgroups\n");
 		return -1;
 	}
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index f033a80..2ec11f0 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -18,11 +18,11 @@
 struct cgroup *cgroup__get(struct cgroup *cgroup);
 void cgroup__put(struct cgroup *cgroup);
 
-struct perf_evlist;
+struct evlist;
 
-struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name);
+struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name);
 
-void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
+void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup);
 
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index ca0fff6..a12872f 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,14 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <sched.h>
-#include "util.h"
-#include "../perf.h"
+#include "util.h" // for sched_getcpu()
+#include "../perf-sys.h"
 #include "cloexec.h"
+#include "event.h"
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
-#include <asm/unistd.h>
 #include <sys/syscall.h>
+#include <linux/string.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 39e628b..bffbdd2 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,53 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "cache.h"
-#include "config.h"
+#include <subcmd/pager.h>
 #include <stdlib.h>
 #include <stdio.h>
+#include <string.h>
 #include "color.h"
 #include <math.h>
 #include <unistd.h>
 
 int perf_use_color_default = -1;
 
-int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
-{
-	if (value) {
-		if (!strcasecmp(value, "never"))
-			return 0;
-		if (!strcasecmp(value, "always"))
-			return 1;
-		if (!strcasecmp(value, "auto"))
-			goto auto_color;
-	}
-
-	/* Missing or explicit false to turn off colorization */
-	if (!perf_config_bool(var, value))
-		return 0;
-
-	/* any normal truth value defaults to 'auto' */
- auto_color:
-	if (stdout_is_tty < 0)
-		stdout_is_tty = isatty(1);
-	if (stdout_is_tty || pager_in_use()) {
-		char *term = getenv("TERM");
-		if (term && strcmp(term, "dumb"))
-			return 1;
-	}
-	return 0;
-}
-
-int perf_color_default_config(const char *var, const char *value,
-			      void *cb __maybe_unused)
-{
-	if (!strcmp(var, "color.ui")) {
-		perf_use_color_default = perf_config_colorbool(var, value, -1);
-		return 0;
-	}
-
-	return 0;
-}
-
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
 			     const char *fmt, va_list args, const char *trail)
 {
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 22777b1..01f7bed 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -3,6 +3,7 @@
 #define __PERF_COLOR_H
 
 #include <stdio.h>
+#include <stdarg.h>
 
 /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */
 #define COLOR_MAXLEN 24
diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c
new file mode 100644
index 0000000..dc09ba7
--- /dev/null
+++ b/tools/perf/util/color_config.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <subcmd/pager.h>
+#include <string.h>
+#include "config.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include "color.h"
+#include <math.h>
+#include <unistd.h>
+
+int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
+{
+	if (value) {
+		if (!strcasecmp(value, "never"))
+			return 0;
+		if (!strcasecmp(value, "always"))
+			return 1;
+		if (!strcasecmp(value, "auto"))
+			goto auto_color;
+	}
+
+	/* Missing or explicit false to turn off colorization */
+	if (!perf_config_bool(var, value))
+		return 0;
+
+	/* any normal truth value defaults to 'auto' */
+ auto_color:
+	if (stdout_is_tty < 0)
+		stdout_is_tty = isatty(1);
+	if (stdout_is_tty || pager_in_use()) {
+		char *term = getenv("TERM");
+		if (term && strcmp(term, "dumb"))
+			return 1;
+	}
+	return 0;
+}
+
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
+{
+	if (!strcmp(var, "color.ui")) {
+		perf_use_color_default = perf_config_colorbool(var, value, -1);
+		return 0;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 31279a7..afb8d4f 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "comm.h"
-#include "util.h"
 #include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include <linux/rbtree.h>
+#include <linux/zalloc.h>
 #include "rwsem.h"
 
 struct comm_str {
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 3e5c438..f35d8fb 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -2,9 +2,9 @@
 #ifndef __PERF_COMM_H
 #define __PERF_COMM_H
 
-#include "../perf.h"
-#include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/types.h>
+#include <stdbool.h>
 
 struct comm_str;
 
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 892e92e..0cd3369 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -2,6 +2,11 @@
 #ifndef PERF_COMPRESS_H
 #define PERF_COMPRESS_H
 
+#include <stdbool.h>
+#ifdef HAVE_ZSTD_SUPPORT
+#include <zstd.h>
+#endif
+
 #ifdef HAVE_ZLIB_SUPPORT
 int gzip_decompress_to_file(const char *input, int output_fd);
 bool gzip_is_compressed(const char *input);
@@ -12,4 +17,52 @@
 bool lzma_is_compressed(const char *input);
 #endif
 
+struct zstd_data {
+#ifdef HAVE_ZSTD_SUPPORT
+	ZSTD_CStream	*cstream;
+	ZSTD_DStream	*dstream;
+#endif
+};
+
+#ifdef HAVE_ZSTD_SUPPORT
+
+int zstd_init(struct zstd_data *data, int level);
+int zstd_fini(struct zstd_data *data);
+
+size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+				       void *src, size_t src_size, size_t max_record_size,
+				       size_t process_header(void *record, size_t increment));
+
+size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size,
+			      void *dst, size_t dst_size);
+#else /* !HAVE_ZSTD_SUPPORT */
+
+static inline int zstd_init(struct zstd_data *data __maybe_unused, int level __maybe_unused)
+{
+	return 0;
+}
+
+static inline int zstd_fini(struct zstd_data *data __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
+				       void *src __maybe_unused, size_t src_size __maybe_unused,
+				       size_t max_record_size __maybe_unused,
+				       size_t process_header(void *record, size_t increment) __maybe_unused)
+{
+	return 0;
+}
+
+static inline size_t zstd_decompress_stream(struct zstd_data *data __maybe_unused, void *src __maybe_unused,
+					    size_t src_size __maybe_unused, void *dst __maybe_unused,
+					    size_t dst_size __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 #endif /* PERF_COMPRESS_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 5ac1570..0bc9c4d 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,18 +11,23 @@
  */
 #include <errno.h>
 #include <sys/param.h>
-#include "util.h"
 #include "cache.h"
+#include "callchain.h"
 #include <subcmd/exec-cmd.h>
+#include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
+#include "build-id.h"
+#include "debug.h"
 #include "config.h"
+#include "debug.h"
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <linux/string.h>
-
-#include "sane_ctype.h"
+#include <linux/zalloc.h>
+#include <linux/ctype.h>
 
 #define MAXNAME (256)
 
@@ -419,6 +424,9 @@
 static int perf_default_core_config(const char *var __maybe_unused,
 				    const char *value __maybe_unused)
 {
+	if (!strcmp(var, "core.proc-map-timeout"))
+		proc_map_timeout = strtoul(value, NULL, 10);
+
 	/* Add other config variables here. */
 	return 0;
 }
@@ -628,11 +636,10 @@
 	}
 
 	ret = set_value(item, value);
-	return ret;
 
 out_free:
 	free(key);
-	return -1;
+	return ret;
 }
 
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
@@ -735,11 +742,15 @@
 			if (ret < 0) {
 				pr_err("Error: wrong config key-value pair %s=%s\n",
 				       key, value);
-				break;
+				/*
+				 * Can't be just a 'break', as perf_config_set__for_each_entry()
+				 * expands to two nested for() loops.
+				 */
+				goto out;
 			}
 		}
 	}
-
+out:
 	return ret;
 }
 
@@ -811,14 +822,14 @@
 void set_buildid_dir(const char *dir)
 {
 	if (dir)
-		scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
+		scnprintf(buildid_dir, MAXPATHLEN, "%s", dir);
 
 	/* default to $HOME/.debug */
 	if (buildid_dir[0] == '\0') {
 		char *home = getenv("HOME");
 
 		if (home) {
-			snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s",
+			snprintf(buildid_dir, MAXPATHLEN, "%s/%s",
 				 home, DEBUG_CACHE_DIR);
 		} else {
 			strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1);
diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c
new file mode 100644
index 0000000..47e03de
--- /dev/null
+++ b/tools/perf/util/copyfile.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/copyfile.h"
+#include "util/namespaces.h"
+#include <internal/lib.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi)
+{
+	int err = -1;
+	char *line = NULL;
+	size_t n;
+	FILE *from_fp, *to_fp;
+	struct nscookie nsc;
+
+	nsinfo__mountns_enter(nsi, &nsc);
+	from_fp = fopen(from, "r");
+	nsinfo__mountns_exit(&nsc);
+	if (from_fp == NULL)
+		goto out;
+
+	to_fp = fopen(to, "w");
+	if (to_fp == NULL)
+		goto out_fclose_from;
+
+	while (getline(&line, &n, from_fp) > 0)
+		if (fputs(line, to_fp) == EOF)
+			goto out_fclose_to;
+	err = 0;
+out_fclose_to:
+	fclose(to_fp);
+	free(line);
+out_fclose_from:
+	fclose(from_fp);
+out:
+	return err;
+}
+
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+	void *ptr;
+	loff_t pgoff;
+
+	pgoff = off_in & ~(page_size - 1);
+	off_in -= pgoff;
+
+	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+	if (ptr == MAP_FAILED)
+		return -1;
+
+	while (size) {
+		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		size -= ret;
+		off_in += ret;
+		off_out += ret;
+	}
+	munmap(ptr, off_in + size);
+
+	return size ? -1 : 0;
+}
+
+static int copyfile_mode_ns(const char *from, const char *to, mode_t mode,
+			    struct nsinfo *nsi)
+{
+	int fromfd, tofd;
+	struct stat st;
+	int err;
+	char *tmp = NULL, *ptr = NULL;
+	struct nscookie nsc;
+
+	nsinfo__mountns_enter(nsi, &nsc);
+	err = stat(from, &st);
+	nsinfo__mountns_exit(&nsc);
+	if (err)
+		goto out;
+	err = -1;
+
+	/* extra 'x' at the end is to reserve space for '.' */
+	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+		tmp = NULL;
+		goto out;
+	}
+	ptr = strrchr(tmp, '/');
+	if (!ptr)
+		goto out;
+	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+	*ptr = '.';
+
+	tofd = mkstemp(tmp);
+	if (tofd < 0)
+		goto out;
+
+	if (st.st_size == 0) { /* /proc? do it slowly... */
+		err = slow_copyfile(from, tmp, nsi);
+		if (!err && fchmod(tofd, mode))
+			err = -1;
+		goto out_close_to;
+	}
+
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
+	nsinfo__mountns_enter(nsi, &nsc);
+	fromfd = open(from, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fromfd < 0)
+		goto out_close_to;
+
+	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
+
+	close(fromfd);
+out_close_to:
+	close(tofd);
+	if (!err)
+		err = link(tmp, to);
+	unlink(tmp);
+out:
+	free(tmp);
+	return err;
+}
+
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi)
+{
+	return copyfile_mode_ns(from, to, 0755, nsi);
+}
+
+int copyfile_mode(const char *from, const char *to, mode_t mode)
+{
+	return copyfile_mode_ns(from, to, mode, NULL);
+}
+
+int copyfile(const char *from, const char *to)
+{
+	return copyfile_mode(from, to, 0755);
+}
diff --git a/tools/perf/util/copyfile.h b/tools/perf/util/copyfile.h
new file mode 100644
index 0000000..e85d2f2
--- /dev/null
+++ b/tools/perf/util/copyfile.h
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef PERF_COPYFILE_H_
+#define PERF_COPYFILE_H_
+
+#include <linux/types.h>
+#include <sys/types.h>
+#include <fcntl.h>
+
+struct nsinfo;
+
+int copyfile(const char *from, const char *to);
+int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size);
+
+#endif // PERF_COPYFILE_H_
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 03032b4..f94e1a2 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -3,7 +3,7 @@
 #include <stdlib.h>
 #include "evsel.h"
 #include "counts.h"
-#include "util.h"
+#include <linux/zalloc.h>
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
@@ -19,6 +19,15 @@
 		}
 
 		counts->values = values;
+
+		values = xyarray__new(ncpus, nthreads, sizeof(bool));
+		if (!values) {
+			xyarray__delete(counts->values);
+			free(counts);
+			return NULL;
+		}
+
+		counts->loaded = values;
 	}
 
 	return counts;
@@ -27,6 +36,7 @@
 void perf_counts__delete(struct perf_counts *counts)
 {
 	if (counts) {
+		xyarray__delete(counts->loaded);
 		xyarray__delete(counts->values);
 		free(counts);
 	}
@@ -34,21 +44,22 @@
 
 static void perf_counts__reset(struct perf_counts *counts)
 {
+	xyarray__reset(counts->loaded);
 	xyarray__reset(counts->values);
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel)
+void perf_evsel__reset_counts(struct evsel *evsel)
 {
 	perf_counts__reset(evsel->counts);
 }
 
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
+int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads)
 {
 	evsel->counts = perf_counts__new(ncpus, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_counts(struct perf_evsel *evsel)
+void perf_evsel__free_counts(struct evsel *evsel)
 {
 	perf_counts__delete(evsel->counts);
 	evsel->counts = NULL;
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 0d1050c..92196df 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -2,24 +2,18 @@
 #ifndef __PERF_COUNTS_H
 #define __PERF_COUNTS_H
 
-#include "xyarray.h"
+#include <linux/types.h>
+#include <internal/xyarray.h>
+#include <perf/evsel.h>
+#include <stdbool.h>
 
-struct perf_counts_values {
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-	bool	loaded;
-};
+struct evsel;
 
 struct perf_counts {
 	s8			  scaled;
 	struct perf_counts_values aggr;
 	struct xyarray		  *values;
+	struct xyarray		  *loaded;
 };
 
 
@@ -29,11 +23,23 @@
 	return xyarray__entry(counts->values, cpu, thread);
 }
 
+static inline bool
+perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread)
+{
+	return *((bool *) xyarray__entry(counts->loaded, cpu, thread));
+}
+
+static inline void
+perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded)
+{
+	*((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded;
+}
+
 struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
-void perf_evsel__free_counts(struct perf_evsel *evsel);
+void perf_evsel__reset_counts(struct evsel *evsel);
+int perf_evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__free_counts(struct evsel *evsel);
 
 #endif /* __PERF_COUNTS_H */
diff --git a/tools/perf/util/cpu-set-sched.h b/tools/perf/util/cpu-set-sched.h
new file mode 100644
index 0000000..8cf4e40
--- /dev/null
+++ b/tools/perf/util/cpu-set-sched.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: LGPL-2.1
+// Definitions taken from glibc for use with older systems, same licensing.
+#ifndef _CPU_SET_SCHED_PERF_H
+#define _CPU_SET_SCHED_PERF_H
+
+#include <features.h>
+#include <sched.h>
+
+#ifndef CPU_EQUAL
+#ifndef __CPU_EQUAL_S
+#if __GNUC_PREREQ (2, 91)
+# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \
+  (__builtin_memcmp (cpusetp1, cpusetp2, setsize) == 0)
+#else
+# define __CPU_EQUAL_S(setsize, cpusetp1, cpusetp2) \
+  (__extension__							      \
+   ({ const __cpu_mask *__arr1 = (cpusetp1)->__bits;			      \
+      const __cpu_mask *__arr2 = (cpusetp2)->__bits;			      \
+      size_t __imax = (setsize) / sizeof (__cpu_mask);			      \
+      size_t __i;							      \
+      for (__i = 0; __i < __imax; ++__i)				      \
+	if (__arr1[__i] != __arr2[__i])					      \
+	  break;							      \
+      __i == __imax; }))
+#endif
+#endif // __CPU_EQUAL_S
+
+#define CPU_EQUAL(cpusetp1, cpusetp2) \
+  __CPU_EQUAL_S (sizeof (cpu_set_t), cpusetp1, cpusetp2)
+#endif // CPU_EQUAL
+
+#ifndef CPU_OR
+#ifndef __CPU_OP_S
+#define __CPU_OP_S(setsize, destset, srcset1, srcset2, op) \
+  (__extension__							      \
+   ({ cpu_set_t *__dest = (destset);					      \
+      const __cpu_mask *__arr1 = (srcset1)->__bits;			      \
+      const __cpu_mask *__arr2 = (srcset2)->__bits;			      \
+      size_t __imax = (setsize) / sizeof (__cpu_mask);			      \
+      size_t __i;							      \
+      for (__i = 0; __i < __imax; ++__i)				      \
+	((__cpu_mask *) __dest->__bits)[__i] = __arr1[__i] op __arr2[__i];    \
+      __dest; }))
+#endif // __CPU_OP_S
+
+#define CPU_OR(destset, srcset1, srcset2) \
+  __CPU_OP_S (sizeof (cpu_set_t), destset, srcset1, srcset2, |)
+#endif // CPU_OR
+
+#endif // _CPU_SET_SCHED_PERF_H
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 1ccbd33..a22c111 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
 #include <api/fs/fs.h>
-#include "../perf.h"
 #include "cpumap.h"
+#include "debug.h"
+#include "event.h"
 #include <assert.h>
 #include <dirent.h>
 #include <stdio.h>
@@ -10,190 +10,19 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static int max_cpu_num;
 static int max_present_cpu_num;
 static int max_node_num;
 static int *cpunode_map;
 
-static struct cpu_map *cpu_map__default_new(void)
+static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
 {
-	struct cpu_map *cpus;
-	int nr_cpus;
+	struct perf_cpu_map *map;
 
-	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-	if (nr_cpus < 0)
-		return NULL;
-
-	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
-	if (cpus != NULL) {
-		int i;
-		for (i = 0; i < nr_cpus; ++i)
-			cpus->map[i] = i;
-
-		cpus->nr = nr_cpus;
-		refcount_set(&cpus->refcnt, 1);
-	}
-
-	return cpus;
-}
-
-static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
-{
-	size_t payload_size = nr_cpus * sizeof(int);
-	struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
-
-	if (cpus != NULL) {
-		cpus->nr = nr_cpus;
-		memcpy(cpus->map, tmp_cpus, payload_size);
-		refcount_set(&cpus->refcnt, 1);
-	}
-
-	return cpus;
-}
-
-struct cpu_map *cpu_map__read(FILE *file)
-{
-	struct cpu_map *cpus = NULL;
-	int nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
-	int max_entries = 0;
-	int n, cpu, prev;
-	char sep;
-
-	sep = 0;
-	prev = -1;
-	for (;;) {
-		n = fscanf(file, "%u%c", &cpu, &sep);
-		if (n <= 0)
-			break;
-		if (prev >= 0) {
-			int new_max = nr_cpus + cpu - prev - 1;
-
-			if (new_max >= max_entries) {
-				max_entries = new_max + MAX_NR_CPUS / 2;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
-				if (tmp == NULL)
-					goto out_free_tmp;
-				tmp_cpus = tmp;
-			}
-
-			while (++prev < cpu)
-				tmp_cpus[nr_cpus++] = prev;
-		}
-		if (nr_cpus == max_entries) {
-			max_entries += MAX_NR_CPUS;
-			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
-			if (tmp == NULL)
-				goto out_free_tmp;
-			tmp_cpus = tmp;
-		}
-
-		tmp_cpus[nr_cpus++] = cpu;
-		if (n == 2 && sep == '-')
-			prev = cpu;
-		else
-			prev = -1;
-		if (n == 1 || sep == '\n')
-			break;
-	}
-
-	if (nr_cpus > 0)
-		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
-		cpus = cpu_map__default_new();
-out_free_tmp:
-	free(tmp_cpus);
-	return cpus;
-}
-
-static struct cpu_map *cpu_map__read_all_cpu_map(void)
-{
-	struct cpu_map *cpus = NULL;
-	FILE *onlnf;
-
-	onlnf = fopen("/sys/devices/system/cpu/online", "r");
-	if (!onlnf)
-		return cpu_map__default_new();
-
-	cpus = cpu_map__read(onlnf);
-	fclose(onlnf);
-	return cpus;
-}
-
-struct cpu_map *cpu_map__new(const char *cpu_list)
-{
-	struct cpu_map *cpus = NULL;
-	unsigned long start_cpu, end_cpu = 0;
-	char *p = NULL;
-	int i, nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
-	int max_entries = 0;
-
-	if (!cpu_list)
-		return cpu_map__read_all_cpu_map();
-
-	if (!isdigit(*cpu_list))
-		goto out;
-
-	while (isdigit(*cpu_list)) {
-		p = NULL;
-		start_cpu = strtoul(cpu_list, &p, 0);
-		if (start_cpu >= INT_MAX
-		    || (*p != '\0' && *p != ',' && *p != '-'))
-			goto invalid;
-
-		if (*p == '-') {
-			cpu_list = ++p;
-			p = NULL;
-			end_cpu = strtoul(cpu_list, &p, 0);
-
-			if (end_cpu >= INT_MAX || (*p != '\0' && *p != ','))
-				goto invalid;
-
-			if (end_cpu < start_cpu)
-				goto invalid;
-		} else {
-			end_cpu = start_cpu;
-		}
-
-		for (; start_cpu <= end_cpu; start_cpu++) {
-			/* check for duplicates */
-			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i] == (int)start_cpu)
-					goto invalid;
-
-			if (nr_cpus == max_entries) {
-				max_entries += MAX_NR_CPUS;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
-				if (tmp == NULL)
-					goto invalid;
-				tmp_cpus = tmp;
-			}
-			tmp_cpus[nr_cpus++] = (int)start_cpu;
-		}
-		if (*p)
-			++p;
-
-		cpu_list = p;
-	}
-
-	if (nr_cpus > 0)
-		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
-		cpus = cpu_map__default_new();
-invalid:
-	free(tmp_cpus);
-out:
-	return cpus;
-}
-
-static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
-{
-	struct cpu_map *map;
-
-	map = cpu_map__empty_new(cpus->nr);
+	map = perf_cpu_map__empty_new(cpus->nr);
 	if (map) {
 		unsigned i;
 
@@ -213,14 +42,14 @@
 	return map;
 }
 
-static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask)
+static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask)
 {
-	struct cpu_map *map;
+	struct perf_cpu_map *map;
 	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
 
 	nr = bitmap_weight(mask->mask, nbits);
 
-	map = cpu_map__empty_new(nr);
+	map = perf_cpu_map__empty_new(nr);
 	if (map) {
 		int cpu, i = 0;
 
@@ -231,15 +60,15 @@
 
 }
 
-struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
+struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data)
 {
 	if (data->type == PERF_CPU_MAP__CPUS)
 		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
 	else
-		return cpu_map__from_mask((struct cpu_map_mask *)data->data);
+		return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data);
 }
 
-size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
+size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp)
 {
 #define BUFSIZE 1024
 	char buf[BUFSIZE];
@@ -249,22 +78,9 @@
 #undef BUFSIZE
 }
 
-struct cpu_map *cpu_map__dummy_new(void)
+struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
 {
-	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
-
-	if (cpus != NULL) {
-		cpus->nr = 1;
-		cpus->map[0] = -1;
-		refcount_set(&cpus->refcnt, 1);
-	}
-
-	return cpus;
-}
-
-struct cpu_map *cpu_map__empty_new(int nr)
-{
-	struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr);
+	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr);
 
 	if (cpus != NULL) {
 		int i;
@@ -279,28 +95,6 @@
 	return cpus;
 }
 
-static void cpu_map__delete(struct cpu_map *map)
-{
-	if (map) {
-		WARN_ONCE(refcount_read(&map->refcnt) != 0,
-			  "cpu_map refcnt unbalanced\n");
-		free(map);
-	}
-}
-
-struct cpu_map *cpu_map__get(struct cpu_map *map)
-{
-	if (map)
-		refcount_inc(&map->refcnt);
-	return map;
-}
-
-void cpu_map__put(struct cpu_map *map)
-{
-	if (map && refcount_dec_and_test(&map->refcnt))
-		cpu_map__delete(map);
-}
-
 static int cpu__get_topology_int(int cpu, const char *name, int *value)
 {
 	char path[PATH_MAX];
@@ -317,7 +111,7 @@
 	return ret ?: value;
 }
 
-int cpu_map__get_socket(struct cpu_map *map, int idx, void *data __maybe_unused)
+int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
 {
 	int cpu;
 
@@ -334,11 +128,11 @@
 	return *(int *)a - *(int *)b;
 }
 
-int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
-		       int (*f)(struct cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
+		       int (*f)(struct perf_cpu_map *map, int cpu, void *data),
 		       void *data)
 {
-	struct cpu_map *c;
+	struct perf_cpu_map *c;
 	int nr = cpus->nr;
 	int cpu, s1, s2;
 
@@ -366,15 +160,55 @@
 	return 0;
 }
 
+int cpu_map__get_die_id(int cpu)
+{
+	int value, ret = cpu__get_topology_int(cpu, "die_id", &value);
+
+	return ret ?: value;
+}
+
+int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+{
+	int cpu, die_id, s;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	die_id = cpu_map__get_die_id(cpu);
+	/* There is no die_id on legacy system. */
+	if (die_id == -1)
+		die_id = 0;
+
+	s = cpu_map__get_socket(map, idx, data);
+	if (s == -1)
+		return -1;
+
+	/*
+	 * Encode socket in bit range 15:8
+	 * die_id is relative to socket, and
+	 * we need a global id. So we combine
+	 * socket + die id
+	 */
+	if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n"))
+		return -1;
+
+	if (WARN_ONCE(s >> 8, "The socket id number is too big.\n"))
+		return -1;
+
+	return (s << 8) | (die_id & 0xff);
+}
+
 int cpu_map__get_core_id(int cpu)
 {
 	int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
 	return ret ?: value;
 }
 
-int cpu_map__get_core(struct cpu_map *map, int idx, void *data)
+int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
 {
-	int cpu, s;
+	int cpu, s_die;
 
 	if (idx > map->nr)
 		return -1;
@@ -383,25 +217,35 @@
 
 	cpu = cpu_map__get_core_id(cpu);
 
-	s = cpu_map__get_socket(map, idx, data);
-	if (s == -1)
+	/* s_die is the combination of socket + die id */
+	s_die = cpu_map__get_die(map, idx, data);
+	if (s_die == -1)
 		return -1;
 
 	/*
-	 * encode socket in upper 16 bits
-	 * core_id is relative to socket, and
+	 * encode socket in bit range 31:24
+	 * encode die id in bit range 23:16
+	 * core_id is relative to socket and die,
 	 * we need a global id. So we combine
-	 * socket+ core id
+	 * socket + die id + core id
 	 */
-	return (s << 16) | (cpu & 0xffff);
+	if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n"))
+		return -1;
+
+	return (s_die << 16) | (cpu & 0xffff);
 }
 
-int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp)
 {
 	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
 }
 
-int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep)
+{
+	return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
+}
+
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep)
 {
 	return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
 }
@@ -613,29 +457,17 @@
 	return 0;
 }
 
-bool cpu_map__has(struct cpu_map *cpus, int cpu)
+bool cpu_map__has(struct perf_cpu_map *cpus, int cpu)
 {
-	return cpu_map__idx(cpus, cpu) != -1;
+	return perf_cpu_map__idx(cpus, cpu) != -1;
 }
 
-int cpu_map__idx(struct cpu_map *cpus, int cpu)
-{
-	int i;
-
-	for (i = 0; i < cpus->nr; ++i) {
-		if (cpus->map[i] == cpu)
-			return i;
-	}
-
-	return -1;
-}
-
-int cpu_map__cpu(struct cpu_map *cpus, int idx)
+int cpu_map__cpu(struct perf_cpu_map *cpus, int idx)
 {
 	return cpus->map[idx];
 }
 
-size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
+size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
 {
 	int i, cpu, start = -1;
 	bool first = true;
@@ -674,7 +506,7 @@
 
 #undef COMMA
 
-	pr_debug("cpumask list: %s\n", buf);
+	pr_debug2("cpumask list: %s\n", buf);
 	return ret;
 }
 
@@ -687,14 +519,17 @@
 	return '?';
 }
 
-size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
+size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 {
 	int i, cpu;
 	char *ptr = buf;
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
@@ -723,3 +558,13 @@
 	buf[size - 1] = '\0';
 	return ptr - buf;
 }
+
+const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
+{
+	static const struct perf_cpu_map *online = NULL;
+
+	if (!online)
+		online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+
+	return online;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index ed8999d..2553bef 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -4,36 +4,28 @@
 
 #include <stdio.h>
 #include <stdbool.h>
-#include <linux/refcount.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
 
-#include "perf.h"
-#include "util/debug.h"
+struct perf_record_cpu_map_data;
 
-struct cpu_map {
-	refcount_t refcnt;
-	int nr;
-	int map[];
-};
-
-struct cpu_map *cpu_map__new(const char *cpu_list);
-struct cpu_map *cpu_map__empty_new(int nr);
-struct cpu_map *cpu_map__dummy_new(void);
-struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
-struct cpu_map *cpu_map__read(FILE *file);
-size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
-size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size);
-size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
+struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
+size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
+size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
+size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
-int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
+int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
+int cpu_map__get_die_id(int cpu);
+int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__get_core_id(int cpu);
-int cpu_map__get_core(struct cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
-int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
+int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp);
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep);
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep);
+const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
 
-struct cpu_map *cpu_map__get(struct cpu_map *map);
-void cpu_map__put(struct cpu_map *map);
-
-static inline int cpu_map__socket(struct cpu_map *sock, int s)
+static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
 {
 	if (!sock || s > sock->nr || s < 0)
 		return 0;
@@ -42,7 +34,12 @@
 
 static inline int cpu_map__id_to_socket(int id)
 {
-	return id >> 16;
+	return id >> 24;
+}
+
+static inline int cpu_map__id_to_die(int id)
+{
+	return (id >> 16) & 0xff;
 }
 
 static inline int cpu_map__id_to_cpu(int id)
@@ -50,16 +47,6 @@
 	return id & 0xffff;
 }
 
-static inline int cpu_map__nr(const struct cpu_map *map)
-{
-	return map ? map->nr : 1;
-}
-
-static inline bool cpu_map__empty(const struct cpu_map *map)
-{
-	return map ? map->map[0] == -1 : true;
-}
-
 int cpu__setup_cpunode_map(void);
 
 int cpu__max_node(void);
@@ -67,11 +54,10 @@
 int cpu__max_present_cpu(void);
 int cpu__get_node(int cpu);
 
-int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
-		       int (*f)(struct cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
+		       int (*f)(struct perf_cpu_map *map, int cpu, void *data),
 		       void *data);
 
-int cpu_map__cpu(struct cpu_map *cpus, int idx);
-bool cpu_map__has(struct cpu_map *cpus, int cpu);
-int cpu_map__idx(struct cpu_map *cpus, int cpu);
+int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
+bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
new file mode 100644
index 0000000..1b52402
--- /dev/null
+++ b/tools/perf/util/cputopo.c
@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/param.h>
+#include <sys/utsname.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <string.h>
+#include <api/fs/fs.h>
+#include <linux/zalloc.h>
+#include <perf/cpumap.h>
+
+#include "cputopo.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "env.h"
+
+#define CORE_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define DIE_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/die_cpus_list"
+#define THRD_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
+#define THRD_SIB_FMT_NEW \
+	"%s/devices/system/cpu/cpu%d/topology/core_cpus_list"
+#define NODE_ONLINE_FMT \
+	"%s/devices/system/node/online"
+#define NODE_MEMINFO_FMT \
+	"%s/devices/system/node/node%d/meminfo"
+#define NODE_CPULIST_FMT \
+	"%s/devices/system/node/node%d/cpulist"
+
+static int build_cpu_topology(struct cpu_topology *tp, int cpu)
+{
+	FILE *fp;
+	char filename[MAXPATHLEN];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	ssize_t sret;
+	u32 i = 0;
+	int ret = -1;
+
+	scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT,
+		  sysfs__mountpoint(), cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto try_dies;
+
+	sret = getline(&buf, &len, fp);
+	fclose(fp);
+	if (sret <= 0)
+		goto try_dies;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->core_sib; i++) {
+		if (!strcmp(buf, tp->core_siblings[i]))
+			break;
+	}
+	if (i == tp->core_sib) {
+		tp->core_siblings[i] = buf;
+		tp->core_sib++;
+		buf = NULL;
+		len = 0;
+	}
+	ret = 0;
+
+try_dies:
+	if (!tp->die_siblings)
+		goto try_threads;
+
+	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+		  sysfs__mountpoint(), cpu);
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto try_threads;
+
+	sret = getline(&buf, &len, fp);
+	fclose(fp);
+	if (sret <= 0)
+		goto try_threads;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->die_sib; i++) {
+		if (!strcmp(buf, tp->die_siblings[i]))
+			break;
+	}
+	if (i == tp->die_sib) {
+		tp->die_siblings[i] = buf;
+		tp->die_sib++;
+		buf = NULL;
+		len = 0;
+	}
+	ret = 0;
+
+try_threads:
+	scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW,
+		  sysfs__mountpoint(), cpu);
+	if (access(filename, F_OK) == -1) {
+		scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+			  sysfs__mountpoint(), cpu);
+	}
+	fp = fopen(filename, "r");
+	if (!fp)
+		goto done;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto done;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < tp->thread_sib; i++) {
+		if (!strcmp(buf, tp->thread_siblings[i]))
+			break;
+	}
+	if (i == tp->thread_sib) {
+		tp->thread_siblings[i] = buf;
+		tp->thread_sib++;
+		buf = NULL;
+	}
+	ret = 0;
+done:
+	if (fp)
+		fclose(fp);
+	free(buf);
+	return ret;
+}
+
+void cpu_topology__delete(struct cpu_topology *tp)
+{
+	u32 i;
+
+	if (!tp)
+		return;
+
+	for (i = 0 ; i < tp->core_sib; i++)
+		zfree(&tp->core_siblings[i]);
+
+	if (tp->die_sib) {
+		for (i = 0 ; i < tp->die_sib; i++)
+			zfree(&tp->die_siblings[i]);
+	}
+
+	for (i = 0 ; i < tp->thread_sib; i++)
+		zfree(&tp->thread_siblings[i]);
+
+	free(tp);
+}
+
+static bool has_die_topology(void)
+{
+	char filename[MAXPATHLEN];
+	struct utsname uts;
+
+	if (uname(&uts) < 0)
+		return false;
+
+	if (strncmp(uts.machine, "x86_64", 6))
+		return false;
+
+	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+		  sysfs__mountpoint(), 0);
+	if (access(filename, F_OK) == -1)
+		return false;
+
+	return true;
+}
+
+struct cpu_topology *cpu_topology__new(void)
+{
+	struct cpu_topology *tp = NULL;
+	void *addr;
+	u32 nr, i, nr_addr;
+	size_t sz;
+	long ncpus;
+	int ret = -1;
+	struct perf_cpu_map *map;
+	bool has_die = has_die_topology();
+
+	ncpus = cpu__max_present_cpu();
+
+	/* build online CPU map */
+	map = perf_cpu_map__new(NULL);
+	if (map == NULL) {
+		pr_debug("failed to get system cpumap\n");
+		return NULL;
+	}
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	sz = nr * sizeof(char *);
+	if (has_die)
+		nr_addr = 3;
+	else
+		nr_addr = 2;
+	addr = calloc(1, sizeof(*tp) + nr_addr * sz);
+	if (!addr)
+		goto out_free;
+
+	tp = addr;
+	addr += sizeof(*tp);
+	tp->core_siblings = addr;
+	addr += sz;
+	if (has_die) {
+		tp->die_siblings = addr;
+		addr += sz;
+	}
+	tp->thread_siblings = addr;
+
+	for (i = 0; i < nr; i++) {
+		if (!cpu_map__has(map, i))
+			continue;
+
+		ret = build_cpu_topology(tp, i);
+		if (ret < 0)
+			break;
+	}
+
+out_free:
+	perf_cpu_map__put(map);
+	if (ret) {
+		cpu_topology__delete(tp);
+		tp = NULL;
+	}
+	return tp;
+}
+
+static int load_numa_node(struct numa_topology_node *node, int nr)
+{
+	char str[MAXPATHLEN];
+	char field[32];
+	char *buf = NULL, *p;
+	size_t len = 0;
+	int ret = -1;
+	FILE *fp;
+	u64 mem;
+
+	node->node = (u32) nr;
+
+	scnprintf(str, MAXPATHLEN, NODE_MEMINFO_FMT,
+		  sysfs__mountpoint(), nr);
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
+
+	while (getline(&buf, &len, fp) > 0) {
+		/* skip over invalid lines */
+		if (!strchr(buf, ':'))
+			continue;
+		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
+			goto err;
+		if (!strcmp(field, "MemTotal:"))
+			node->mem_total = mem;
+		if (!strcmp(field, "MemFree:"))
+			node->mem_free = mem;
+		if (node->mem_total && node->mem_free)
+			break;
+	}
+
+	fclose(fp);
+	fp = NULL;
+
+	scnprintf(str, MAXPATHLEN, NODE_CPULIST_FMT,
+		  sysfs__mountpoint(), nr);
+
+	fp = fopen(str, "r");
+	if (!fp)
+		return -1;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto err;
+
+	p = strchr(buf, '\n');
+	if (p)
+		*p = '\0';
+
+	node->cpus = buf;
+	fclose(fp);
+	return 0;
+
+err:
+	free(buf);
+	if (fp)
+		fclose(fp);
+	return ret;
+}
+
+struct numa_topology *numa_topology__new(void)
+{
+	struct perf_cpu_map *node_map = NULL;
+	struct numa_topology *tp = NULL;
+	char path[MAXPATHLEN];
+	char *buf = NULL;
+	size_t len = 0;
+	u32 nr, i;
+	FILE *fp;
+	char *c;
+
+	scnprintf(path, MAXPATHLEN, NODE_ONLINE_FMT,
+		  sysfs__mountpoint());
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return NULL;
+
+	if (getline(&buf, &len, fp) <= 0)
+		goto out;
+
+	c = strchr(buf, '\n');
+	if (c)
+		*c = '\0';
+
+	node_map = perf_cpu_map__new(buf);
+	if (!node_map)
+		goto out;
+
+	nr = (u32) node_map->nr;
+
+	tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0])*nr);
+	if (!tp)
+		goto out;
+
+	tp->nr = nr;
+
+	for (i = 0; i < nr; i++) {
+		if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+			numa_topology__delete(tp);
+			tp = NULL;
+			break;
+		}
+	}
+
+out:
+	free(buf);
+	fclose(fp);
+	perf_cpu_map__put(node_map);
+	return tp;
+}
+
+void numa_topology__delete(struct numa_topology *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->nr; i++)
+		zfree(&tp->nodes[i].cpus);
+
+	free(tp);
+}
diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h
new file mode 100644
index 0000000..7bf6b81
--- /dev/null
+++ b/tools/perf/util/cputopo.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_CPUTOPO_H
+#define __PERF_CPUTOPO_H
+
+#include <linux/types.h>
+
+struct cpu_topology {
+	u32	  core_sib;
+	u32	  die_sib;
+	u32	  thread_sib;
+	char	**core_siblings;
+	char	**die_siblings;
+	char	**thread_siblings;
+};
+
+struct numa_topology_node {
+	char		*cpus;
+	u32		 node;
+	u64		 mem_total;
+	u64		 mem_free;
+};
+
+struct numa_topology {
+	u32				nr;
+	struct numa_topology_node	nodes[0];
+};
+
+struct cpu_topology *cpu_topology__new(void);
+void cpu_topology__delete(struct cpu_topology *tp);
+
+struct numa_topology *numa_topology__new(void);
+void numa_topology__delete(struct numa_topology *tp);
+
+#endif /* __PERF_CPUTOPO_H */
diff --git a/tools/perf/util/cs-etm-decoder/Build b/tools/perf/util/cs-etm-decoder/Build
index bc22c39..216cb17 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.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 938def6..cd92a99 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -8,6 +8,7 @@
 
 #include <linux/err.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #include <stdlib.h>
 #include <opencsd/c_api/opencsd_c_api.h>
 #include <opencsd/etmv4/trc_pkt_types_etmv4.h>
@@ -16,9 +17,6 @@
 #include "cs-etm.h"
 #include "cs-etm-decoder.h"
 #include "intlist.h"
-#include "util.h"
-
-#define MAX_BUFFER 1024
 
 /* use raw logging */
 #ifdef CS_DEBUG_RAW
@@ -31,34 +29,26 @@
 #endif
 #endif
 
-#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
-
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
-	bool trace_on;
 	dcd_tree_handle_t dcd_tree;
 	cs_etm_mem_cb_type mem_access;
 	ocsd_datapath_resp_t prev_return;
-	u32 packet_count;
-	u32 head;
-	u32 tail;
-	struct cs_etm_packet packet_buffer[MAX_BUFFER];
 };
 
 static u32
 cs_etm_decoder__mem_access(const void *context,
 			   const ocsd_vaddr_t address,
 			   const ocsd_mem_space_acc_t mem_space __maybe_unused,
+			   const u8 trace_chan_id,
 			   const u32 req_size,
 			   u8 *buffer)
 {
 	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
 
-	return decoder->mem_access(decoder->data,
-				   address,
-				   req_size,
-				   buffer);
+	return decoder->mem_access(decoder->data, trace_chan_id,
+				   address, req_size, buffer);
 }
 
 int cs_etm_decoder__add_mem_access_cb(struct cs_etm_decoder *decoder,
@@ -67,9 +57,10 @@
 {
 	decoder->mem_access = cb_func;
 
-	if (ocsd_dt_add_callback_mem_acc(decoder->dcd_tree, start, end,
-					 OCSD_MEM_SPACE_ANY,
-					 cs_etm_decoder__mem_access, decoder))
+	if (ocsd_dt_add_callback_trcid_mem_acc(decoder->dcd_tree, start, end,
+					       OCSD_MEM_SPACE_ANY,
+					       cs_etm_decoder__mem_access,
+					       decoder))
 		return -1;
 
 	return 0;
@@ -89,14 +80,14 @@
 	return 0;
 }
 
-int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue,
 			       struct cs_etm_packet *packet)
 {
-	if (!decoder || !packet)
+	if (!packet_queue || !packet)
 		return -EINVAL;
 
 	/* Nothing to do, might as well just return */
-	if (decoder->packet_count == 0)
+	if (packet_queue->packet_count == 0)
 		return 0;
 	/*
 	 * The queueing process in function cs_etm_decoder__buffer_packet()
@@ -107,15 +98,29 @@
 	 * value.  Otherwise the first element of the packet queue is not
 	 * used.
 	 */
-	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
+	packet_queue->head = (packet_queue->head + 1) &
+			     (CS_ETM_PACKET_MAX_BUFFER - 1);
 
-	*packet = decoder->packet_buffer[decoder->head];
+	*packet = packet_queue->packet_buffer[packet_queue->head];
 
-	decoder->packet_count--;
+	packet_queue->packet_count--;
 
 	return 1;
 }
 
+static int cs_etm_decoder__gen_etmv3_config(struct cs_etm_trace_params *params,
+					    ocsd_etmv3_cfg *config)
+{
+	config->reg_idr = params->etmv3.reg_idr;
+	config->reg_ctrl = params->etmv3.reg_ctrl;
+	config->reg_ccer = params->etmv3.reg_ccer;
+	config->reg_trc_id = params->etmv3.reg_trc_id;
+	config->arch_ver = ARCH_V7;
+	config->core_prof = profile_CortexA;
+
+	return 0;
+}
+
 static void cs_etm_decoder__gen_etmv4_config(struct cs_etm_trace_params *params,
 					     ocsd_etmv4_cfg *config)
 {
@@ -237,10 +242,19 @@
 					  struct cs_etm_decoder *decoder)
 {
 	const char *decoder_name;
+	ocsd_etmv3_cfg config_etmv3;
 	ocsd_etmv4_cfg trace_config_etmv4;
 	void *trace_config;
 
 	switch (t_params->protocol) {
+	case CS_ETM_PROTO_ETMV3:
+	case CS_ETM_PROTO_PTM:
+		cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3);
+		decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
+							OCSD_BUILTIN_DCD_ETMV3 :
+							OCSD_BUILTIN_DCD_PTM;
+		trace_config = &config_etmv3;
+		break;
 	case CS_ETM_PROTO_ETMV4i:
 		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
 		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
@@ -255,74 +269,156 @@
 						     trace_config);
 }
 
-static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
+static ocsd_datapath_resp_t
+cs_etm_decoder__do_soft_timestamp(struct cs_etm_queue *etmq,
+				  struct cs_etm_packet_queue *packet_queue,
+				  const uint8_t trace_chan_id)
 {
-	int i;
+	/* No timestamp packet has been received, nothing to do */
+	if (!packet_queue->timestamp)
+		return OCSD_RESP_CONT;
 
-	decoder->head = 0;
-	decoder->tail = 0;
-	decoder->packet_count = 0;
-	for (i = 0; i < MAX_BUFFER; i++) {
-		decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
-		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
-		decoder->packet_buffer[i].last_instr_taken_branch = false;
-		decoder->packet_buffer[i].exc = false;
-		decoder->packet_buffer[i].exc_ret = false;
-		decoder->packet_buffer[i].cpu = INT_MIN;
-	}
+	packet_queue->timestamp = packet_queue->next_timestamp;
+
+	/* Estimate the timestamp for the next range packet */
+	packet_queue->next_timestamp += packet_queue->instr_count;
+	packet_queue->instr_count = 0;
+
+	/* Tell the front end which traceid_queue needs attention */
+	cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id);
+
+	return OCSD_RESP_WAIT;
 }
 
 static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
+cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq,
+				  const ocsd_generic_trace_elem *elem,
+				  const uint8_t trace_chan_id)
+{
+	struct cs_etm_packet_queue *packet_queue;
+
+	/* First get the packet queue for this traceID */
+	packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
+	if (!packet_queue)
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	/*
+	 * We've seen a timestamp packet before - simply record the new value.
+	 * Function do_soft_timestamp() will report the value to the front end,
+	 * hence asking the decoder to keep decoding rather than stopping.
+	 */
+	if (packet_queue->timestamp) {
+		packet_queue->next_timestamp = elem->timestamp;
+		return OCSD_RESP_CONT;
+	}
+
+	/*
+	 * This is the first timestamp we've seen since the beginning of traces
+	 * or a discontinuity.  Since timestamps packets are generated *after*
+	 * range packets have been generated, we need to estimate the time at
+	 * which instructions started by substracting the number of instructions
+	 * executed to the timestamp.
+	 */
+	packet_queue->timestamp = elem->timestamp - packet_queue->instr_count;
+	packet_queue->next_timestamp = elem->timestamp;
+	packet_queue->instr_count = 0;
+
+	/* Tell the front end which traceid_queue needs attention */
+	cs_etm__etmq_set_traceid_queue_timestamp(etmq, trace_chan_id);
+
+	/* Halt processing until we are being told to proceed */
+	return OCSD_RESP_WAIT;
+}
+
+static void
+cs_etm_decoder__reset_timestamp(struct cs_etm_packet_queue *packet_queue)
+{
+	packet_queue->timestamp = 0;
+	packet_queue->next_timestamp = 0;
+	packet_queue->instr_count = 0;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_packet(struct cs_etm_packet_queue *packet_queue,
 			      const u8 trace_chan_id,
 			      enum cs_etm_sample_type sample_type)
 {
 	u32 et = 0;
-	struct int_node *inode = NULL;
+	int cpu;
 
-	if (decoder->packet_count >= MAX_BUFFER - 1)
+	if (packet_queue->packet_count >= CS_ETM_PACKET_MAX_BUFFER - 1)
 		return OCSD_RESP_FATAL_SYS_ERR;
 
-	/* Search the RB tree for the cpu associated with this traceID */
-	inode = intlist__find(traceid_list, trace_chan_id);
-	if (!inode)
+	if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
 		return OCSD_RESP_FATAL_SYS_ERR;
 
-	et = decoder->tail;
-	et = (et + 1) & (MAX_BUFFER - 1);
-	decoder->tail = et;
-	decoder->packet_count++;
+	et = packet_queue->tail;
+	et = (et + 1) & (CS_ETM_PACKET_MAX_BUFFER - 1);
+	packet_queue->tail = et;
+	packet_queue->packet_count++;
 
-	decoder->packet_buffer[et].sample_type = sample_type;
-	decoder->packet_buffer[et].exc = false;
-	decoder->packet_buffer[et].exc_ret = false;
-	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
-	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
+	packet_queue->packet_buffer[et].sample_type = sample_type;
+	packet_queue->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
+	packet_queue->packet_buffer[et].cpu = cpu;
+	packet_queue->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	packet_queue->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
+	packet_queue->packet_buffer[et].instr_count = 0;
+	packet_queue->packet_buffer[et].last_instr_taken_branch = false;
+	packet_queue->packet_buffer[et].last_instr_size = 0;
+	packet_queue->packet_buffer[et].last_instr_type = 0;
+	packet_queue->packet_buffer[et].last_instr_subtype = 0;
+	packet_queue->packet_buffer[et].last_instr_cond = 0;
+	packet_queue->packet_buffer[et].flags = 0;
+	packet_queue->packet_buffer[et].exception_number = UINT32_MAX;
+	packet_queue->packet_buffer[et].trace_chan_id = trace_chan_id;
 
-	if (decoder->packet_count == MAX_BUFFER - 1)
+	if (packet_queue->packet_count == CS_ETM_PACKET_MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
 
 	return OCSD_RESP_CONT;
 }
 
 static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
+cs_etm_decoder__buffer_range(struct cs_etm_queue *etmq,
+			     struct cs_etm_packet_queue *packet_queue,
 			     const ocsd_generic_trace_elem *elem,
 			     const uint8_t trace_chan_id)
 {
 	int ret = 0;
 	struct cs_etm_packet *packet;
 
-	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+	ret = cs_etm_decoder__buffer_packet(packet_queue, trace_chan_id,
 					    CS_ETM_RANGE);
 	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
 		return ret;
 
-	packet = &decoder->packet_buffer[decoder->tail];
+	packet = &packet_queue->packet_buffer[packet_queue->tail];
+
+	switch (elem->isa) {
+	case ocsd_isa_aarch64:
+		packet->isa = CS_ETM_ISA_A64;
+		break;
+	case ocsd_isa_arm:
+		packet->isa = CS_ETM_ISA_A32;
+		break;
+	case ocsd_isa_thumb2:
+		packet->isa = CS_ETM_ISA_T32;
+		break;
+	case ocsd_isa_tee:
+	case ocsd_isa_jazelle:
+	case ocsd_isa_custom:
+	case ocsd_isa_unknown:
+	default:
+		packet->isa = CS_ETM_ISA_UNKNOWN;
+	}
 
 	packet->start_addr = elem->st_addr;
 	packet->end_addr = elem->en_addr;
+	packet->instr_count = elem->num_instr_range;
+	packet->last_instr_type = elem->last_i_type;
+	packet->last_instr_subtype = elem->last_i_subtype;
+	packet->last_instr_cond = elem->last_instr_cond;
+
 	switch (elem->last_i_type) {
 	case OCSD_INSTR_BR:
 	case OCSD_INSTR_BR_INDIRECT:
@@ -330,21 +426,97 @@
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;
 		break;
 	}
 
+	packet->last_instr_size = elem->last_instr_sz;
+
+	/* per-thread scenario, no need to generate a timestamp */
+	if (cs_etm__etmq_is_timeless(etmq))
+		goto out;
+
+	/*
+	 * The packet queue is full and we haven't seen a timestamp (had we
+	 * seen one the packet queue wouldn't be full).  Let the front end
+	 * deal with it.
+	 */
+	if (ret == OCSD_RESP_WAIT)
+		goto out;
+
+	packet_queue->instr_count += elem->num_instr_range;
+	/* Tell the front end we have a new timestamp to process */
+	ret = cs_etm_decoder__do_soft_timestamp(etmq, packet_queue,
+						trace_chan_id);
+out:
 	return ret;
 }
 
 static ocsd_datapath_resp_t
-cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
-				const uint8_t trace_chan_id)
+cs_etm_decoder__buffer_discontinuity(struct cs_etm_packet_queue *queue,
+				     const uint8_t trace_chan_id)
 {
-	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
-					     CS_ETM_TRACE_ON);
+	/*
+	 * Something happened and who knows when we'll get new traces so
+	 * reset time statistics.
+	 */
+	cs_etm_decoder__reset_timestamp(queue);
+	return cs_etm_decoder__buffer_packet(queue, trace_chan_id,
+					     CS_ETM_DISCONTINUITY);
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_exception(struct cs_etm_packet_queue *queue,
+				 const ocsd_generic_trace_elem *elem,
+				 const uint8_t trace_chan_id)
+{	int ret = 0;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(queue, trace_chan_id,
+					    CS_ETM_EXCEPTION);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &queue->packet_buffer[queue->tail];
+	packet->exception_number = elem->exception_number;
+
+	return ret;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_exception_ret(struct cs_etm_packet_queue *queue,
+				     const uint8_t trace_chan_id)
+{
+	return cs_etm_decoder__buffer_packet(queue, trace_chan_id,
+					     CS_ETM_EXCEPTION_RET);
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
+			struct cs_etm_packet_queue *packet_queue,
+			const ocsd_generic_trace_elem *elem,
+			const uint8_t trace_chan_id)
+{
+	pid_t tid;
+
+	/* Ignore PE_CONTEXT packets that don't have a valid contextID */
+	if (!elem->context.ctxt_id_valid)
+		return OCSD_RESP_CONT;
+
+	tid =  elem->context.context_id;
+	if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id))
+		return OCSD_RESP_FATAL_SYS_ERR;
+
+	/*
+	 * A timestamp is generated after a PE_CONTEXT element so make sure
+	 * to rely on that coming one.
+	 */
+	cs_etm_decoder__reset_timestamp(packet_queue);
+
+	return OCSD_RESP_CONT;
 }
 
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
@@ -355,32 +527,44 @@
 {
 	ocsd_datapath_resp_t resp = OCSD_RESP_CONT;
 	struct cs_etm_decoder *decoder = (struct cs_etm_decoder *) context;
+	struct cs_etm_queue *etmq = decoder->data;
+	struct cs_etm_packet_queue *packet_queue;
+
+	/* First get the packet queue for this traceID */
+	packet_queue = cs_etm__etmq_get_packet_queue(etmq, trace_chan_id);
+	if (!packet_queue)
+		return OCSD_RESP_FATAL_SYS_ERR;
 
 	switch (elem->elem_type) {
 	case OCSD_GEN_TRC_ELEM_UNKNOWN:
 		break;
+	case OCSD_GEN_TRC_ELEM_EO_TRACE:
 	case OCSD_GEN_TRC_ELEM_NO_SYNC:
-		decoder->trace_on = false;
-		break;
 	case OCSD_GEN_TRC_ELEM_TRACE_ON:
-		resp = cs_etm_decoder__buffer_trace_on(decoder,
-						       trace_chan_id);
-		decoder->trace_on = true;
+		resp = cs_etm_decoder__buffer_discontinuity(packet_queue,
+							    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
-		resp = cs_etm_decoder__buffer_range(decoder, elem,
+		resp = cs_etm_decoder__buffer_range(etmq, packet_queue, elem,
 						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
-		decoder->packet_buffer[decoder->tail].exc = true;
+		resp = cs_etm_decoder__buffer_exception(packet_queue, elem,
+							trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
-		decoder->packet_buffer[decoder->tail].exc_ret = true;
+		resp = cs_etm_decoder__buffer_exception_ret(packet_queue,
+							    trace_chan_id);
+		break;
+	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
+		resp = cs_etm_decoder__do_hard_timestamp(etmq, elem,
+							 trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_PE_CONTEXT:
-	case OCSD_GEN_TRC_ELEM_EO_TRACE:
+		resp = cs_etm_decoder__set_tid(etmq, packet_queue,
+					       elem, trace_chan_id);
+		break;
 	case OCSD_GEN_TRC_ELEM_ADDR_NACC:
-	case OCSD_GEN_TRC_ELEM_TIMESTAMP:
 	case OCSD_GEN_TRC_ELEM_CYCLE_COUNT:
 	case OCSD_GEN_TRC_ELEM_ADDR_UNKNOWN:
 	case OCSD_GEN_TRC_ELEM_EVENT:
@@ -398,11 +582,20 @@
 					struct cs_etm_decoder *decoder)
 {
 	const char *decoder_name;
+	ocsd_etmv3_cfg config_etmv3;
 	ocsd_etmv4_cfg trace_config_etmv4;
 	void *trace_config;
 	u8 csid;
 
 	switch (t_params->protocol) {
+	case CS_ETM_PROTO_ETMV3:
+	case CS_ETM_PROTO_PTM:
+		cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3);
+		decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ?
+							OCSD_BUILTIN_DCD_ETMV3 :
+							OCSD_BUILTIN_DCD_PTM;
+		trace_config = &config_etmv3;
+		break;
 	case CS_ETM_PROTO_ETMV4i:
 		cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4);
 		decoder_name = OCSD_BUILTIN_DCD_ETMV4I;
@@ -460,7 +653,6 @@
 
 	decoder->data = d_params->data;
 	decoder->prev_return = OCSD_RESP_CONT;
-	cs_etm_decoder__clear_buffer(decoder);
 	format = (d_params->formatted ? OCSD_TRC_SRC_FRAME_FORMATTED :
 					 OCSD_TRC_SRC_SINGLE);
 	flags = 0;
@@ -483,7 +675,7 @@
 	/* init library print logging support */
 	ret = cs_etm_decoder__init_def_logger_printing(d_params, decoder);
 	if (ret != 0)
-		goto err_free_decoder_tree;
+		goto err_free_decoder;
 
 	/* init raw frame logging if required */
 	cs_etm_decoder__init_raw_frame_logging(d_params, decoder);
@@ -493,15 +685,13 @@
 							 &t_params[i],
 							 decoder);
 		if (ret != 0)
-			goto err_free_decoder_tree;
+			goto err_free_decoder;
 	}
 
 	return decoder;
 
-err_free_decoder_tree:
-	ocsd_destroy_dcd_tree(decoder->dcd_tree);
 err_free_decoder:
-	free(decoder);
+	cs_etm_decoder__free(decoder);
 	return NULL;
 }
 
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 612b575..11f3391 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -14,34 +14,19 @@
 #include <stdio.h>
 
 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 = 0,
-	CS_ETM_RANGE = 1 << 0,
-	CS_ETM_TRACE_ON = 1 << 1,
-};
-
-struct cs_etm_packet {
-	enum cs_etm_sample_type sample_type;
-	u64 start_addr;
-	u64 end_addr;
-	u8 last_instr_taken_branch;
-	u8 exc;
-	u8 exc_ret;
-	int cpu;
-};
+struct cs_etm_packet;
+struct cs_etm_packet_queue;
 
 struct cs_etm_queue;
 
-typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u64,
-				  size_t, u8 *);
+typedef u32 (*cs_etm_mem_cb_type)(struct cs_etm_queue *, u8, u64, size_t, u8 *);
+
+struct cs_etmv3_trace_params {
+	u32 reg_ctrl;
+	u32 reg_trc_id;
+	u32 reg_ccer;
+	u32 reg_idr;
+};
 
 struct cs_etmv4_trace_params {
 	u32 reg_idr0;
@@ -55,6 +40,7 @@
 struct cs_etm_trace_params {
 	int protocol;
 	union {
+		struct cs_etmv3_trace_params etmv3;
 		struct cs_etmv4_trace_params etmv4;
 	};
 };
@@ -78,11 +64,13 @@
 	CS_ETM_PROTO_ETMV3 = 1,
 	CS_ETM_PROTO_ETMV4i,
 	CS_ETM_PROTO_ETMV4d,
+	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,
@@ -100,7 +88,7 @@
 				      u64 start, u64 end,
 				      cs_etm_mem_cb_type cb_func);
 
-int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
+int cs_etm_decoder__get_packet(struct cs_etm_packet_queue *packet_queue,
 			       struct cs_etm_packet *packet);
 
 int cs_etm_decoder__reset(struct cs_etm_decoder *decoder);
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index ca57765..4ba0f87 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -11,7 +11,9 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 
+#include <opencsd/ocsd_if_types.h>
 #include <stdlib.h>
 
 #include "auxtrace.h"
@@ -19,26 +21,24 @@
 #include "cs-etm.h"
 #include "cs-etm-decoder/cs-etm-decoder.h"
 #include "debug.h"
+#include "dso.h"
 #include "evlist.h"
 #include "intlist.h"
 #include "machine.h"
 #include "map.h"
 #include "perf.h"
+#include "session.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "symbol.h"
+#include "tool.h"
 #include "thread.h"
-#include "thread_map.h"
 #include "thread-stack.h"
-#include "util.h"
+#include <tools/libc_compat.h>
+#include "util/synthetic-events.h"
 
 #define MAX_TIMESTAMP (~0ULL)
 
-/*
- * A64 instructions are always 4 bytes
- *
- * Only A64 is supported, so can use this constant for converting between
- * addresses and instruction counts, calculting offsets etc
- */
-#define A64_INSTR_SIZE 4
-
 struct cs_etm_auxtrace {
 	struct auxtrace auxtrace;
 	struct auxtrace_queues queues;
@@ -66,30 +66,302 @@
 	unsigned int pmu_type;
 };
 
-struct cs_etm_queue {
-	struct cs_etm_auxtrace *etm;
-	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;
+struct cs_etm_traceid_queue {
+	u8 trace_chan_id;
 	pid_t pid, tid;
-	int cpu;
-	u64 time;
-	u64 timestamp;
-	u64 offset;
 	u64 period_instructions;
+	size_t last_branch_pos;
+	union perf_event *event_buf;
+	struct thread *thread;
 	struct branch_stack *last_branch;
 	struct branch_stack *last_branch_rb;
-	size_t last_branch_pos;
 	struct cs_etm_packet *prev_packet;
 	struct cs_etm_packet *packet;
+	struct cs_etm_packet_queue packet_queue;
+};
+
+struct cs_etm_queue {
+	struct cs_etm_auxtrace *etm;
+	struct cs_etm_decoder *decoder;
+	struct auxtrace_buffer *buffer;
+	unsigned int queue_nr;
+	u8 pending_timestamp;
+	u64 offset;
+	const unsigned char *buf;
+	size_t buf_len, buf_used;
+	/* Conversion between traceID and index in traceid_queues array */
+	struct intlist *traceid_queues_list;
+	struct cs_etm_traceid_queue **traceid_queues;
 };
 
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
+static int cs_etm__process_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);
+static int cs_etm__get_data_block(struct cs_etm_queue *etmq);
+static int cs_etm__decode_data_block(struct cs_etm_queue *etmq);
+
+/* PTMs ETMIDR [11:8] set to b0011 */
+#define ETMIDR_PTM_VERSION 0x00000300
+
+/*
+ * A struct auxtrace_heap_item only has a queue_nr and a timestamp to
+ * work with.  One option is to modify to auxtrace_heap_XYZ() API or simply
+ * encode the etm queue number as the upper 16 bit and the channel as
+ * the lower 16 bit.
+ */
+#define TO_CS_QUEUE_NR(queue_nr, trace_id_chan)	\
+		      (queue_nr << 16 | trace_chan_id)
+#define TO_QUEUE_NR(cs_queue_nr) (cs_queue_nr >> 16)
+#define TO_TRACE_CHAN_ID(cs_queue_nr) (cs_queue_nr & 0x0000ffff)
+
+static u32 cs_etm__get_v7_protocol_version(u32 etmidr)
+{
+	etmidr &= ETMIDR_PTM_VERSION;
+
+	if (etmidr == ETMIDR_PTM_VERSION)
+		return CS_ETM_PROTO_PTM;
+
+	return CS_ETM_PROTO_ETMV3;
+}
+
+static int cs_etm__get_magic(u8 trace_chan_id, u64 *magic)
+{
+	struct int_node *inode;
+	u64 *metadata;
+
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return -EINVAL;
+
+	metadata = inode->priv;
+	*magic = metadata[CS_ETM_MAGIC];
+	return 0;
+}
+
+int cs_etm__get_cpu(u8 trace_chan_id, int *cpu)
+{
+	struct int_node *inode;
+	u64 *metadata;
+
+	inode = intlist__find(traceid_list, trace_chan_id);
+	if (!inode)
+		return -EINVAL;
+
+	metadata = inode->priv;
+	*cpu = (int)metadata[CS_ETM_CPU];
+	return 0;
+}
+
+void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
+					      u8 trace_chan_id)
+{
+	/*
+	 * Wnen a timestamp packet is encountered the backend code
+	 * is stopped so that the front end has time to process packets
+	 * that were accumulated in the traceID queue.  Since there can
+	 * be more than one channel per cs_etm_queue, we need to specify
+	 * what traceID queue needs servicing.
+	 */
+	etmq->pending_timestamp = trace_chan_id;
+}
+
+static u64 cs_etm__etmq_get_timestamp(struct cs_etm_queue *etmq,
+				      u8 *trace_chan_id)
+{
+	struct cs_etm_packet_queue *packet_queue;
+
+	if (!etmq->pending_timestamp)
+		return 0;
+
+	if (trace_chan_id)
+		*trace_chan_id = etmq->pending_timestamp;
+
+	packet_queue = cs_etm__etmq_get_packet_queue(etmq,
+						     etmq->pending_timestamp);
+	if (!packet_queue)
+		return 0;
+
+	/* Acknowledge pending status */
+	etmq->pending_timestamp = 0;
+
+	/* See function cs_etm_decoder__do_{hard|soft}_timestamp() */
+	return packet_queue->timestamp;
+}
+
+static void cs_etm__clear_packet_queue(struct cs_etm_packet_queue *queue)
+{
+	int i;
+
+	queue->head = 0;
+	queue->tail = 0;
+	queue->packet_count = 0;
+	for (i = 0; i < CS_ETM_PACKET_MAX_BUFFER; i++) {
+		queue->packet_buffer[i].isa = CS_ETM_ISA_UNKNOWN;
+		queue->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+		queue->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
+		queue->packet_buffer[i].instr_count = 0;
+		queue->packet_buffer[i].last_instr_taken_branch = false;
+		queue->packet_buffer[i].last_instr_size = 0;
+		queue->packet_buffer[i].last_instr_type = 0;
+		queue->packet_buffer[i].last_instr_subtype = 0;
+		queue->packet_buffer[i].last_instr_cond = 0;
+		queue->packet_buffer[i].flags = 0;
+		queue->packet_buffer[i].exception_number = UINT32_MAX;
+		queue->packet_buffer[i].trace_chan_id = UINT8_MAX;
+		queue->packet_buffer[i].cpu = INT_MIN;
+	}
+}
+
+static void cs_etm__clear_all_packet_queues(struct cs_etm_queue *etmq)
+{
+	int idx;
+	struct int_node *inode;
+	struct cs_etm_traceid_queue *tidq;
+	struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+	intlist__for_each_entry(inode, traceid_queues_list) {
+		idx = (int)(intptr_t)inode->priv;
+		tidq = etmq->traceid_queues[idx];
+		cs_etm__clear_packet_queue(&tidq->packet_queue);
+	}
+}
+
+static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
+				      struct cs_etm_traceid_queue *tidq,
+				      u8 trace_chan_id)
+{
+	int rc = -ENOMEM;
+	struct auxtrace_queue *queue;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+
+	cs_etm__clear_packet_queue(&tidq->packet_queue);
+
+	queue = &etmq->etm->queues.queue_array[etmq->queue_nr];
+	tidq->tid = queue->tid;
+	tidq->pid = -1;
+	tidq->trace_chan_id = trace_chan_id;
+
+	tidq->packet = zalloc(sizeof(struct cs_etm_packet));
+	if (!tidq->packet)
+		goto out;
+
+	tidq->prev_packet = zalloc(sizeof(struct cs_etm_packet));
+	if (!tidq->prev_packet)
+		goto out_free;
+
+	if (etm->synth_opts.last_branch) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += etm->synth_opts.last_branch_sz *
+		      sizeof(struct branch_entry);
+		tidq->last_branch = zalloc(sz);
+		if (!tidq->last_branch)
+			goto out_free;
+		tidq->last_branch_rb = zalloc(sz);
+		if (!tidq->last_branch_rb)
+			goto out_free;
+	}
+
+	tidq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+	if (!tidq->event_buf)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	zfree(&tidq->last_branch_rb);
+	zfree(&tidq->last_branch);
+	zfree(&tidq->prev_packet);
+	zfree(&tidq->packet);
+out:
+	return rc;
+}
+
+static struct cs_etm_traceid_queue
+*cs_etm__etmq_get_traceid_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
+{
+	int idx;
+	struct int_node *inode;
+	struct intlist *traceid_queues_list;
+	struct cs_etm_traceid_queue *tidq, **traceid_queues;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+
+	if (etm->timeless_decoding)
+		trace_chan_id = CS_ETM_PER_THREAD_TRACEID;
+
+	traceid_queues_list = etmq->traceid_queues_list;
+
+	/*
+	 * Check if the traceid_queue exist for this traceID by looking
+	 * in the queue list.
+	 */
+	inode = intlist__find(traceid_queues_list, trace_chan_id);
+	if (inode) {
+		idx = (int)(intptr_t)inode->priv;
+		return etmq->traceid_queues[idx];
+	}
+
+	/* We couldn't find a traceid_queue for this traceID, allocate one */
+	tidq = malloc(sizeof(*tidq));
+	if (!tidq)
+		return NULL;
+
+	memset(tidq, 0, sizeof(*tidq));
+
+	/* Get a valid index for the new traceid_queue */
+	idx = intlist__nr_entries(traceid_queues_list);
+	/* Memory for the inode is free'ed in cs_etm_free_traceid_queues () */
+	inode = intlist__findnew(traceid_queues_list, trace_chan_id);
+	if (!inode)
+		goto out_free;
+
+	/* Associate this traceID with this index */
+	inode->priv = (void *)(intptr_t)idx;
+
+	if (cs_etm__init_traceid_queue(etmq, tidq, trace_chan_id))
+		goto out_free;
+
+	/* Grow the traceid_queues array by one unit */
+	traceid_queues = etmq->traceid_queues;
+	traceid_queues = reallocarray(traceid_queues,
+				      idx + 1,
+				      sizeof(*traceid_queues));
+
+	/*
+	 * On failure reallocarray() returns NULL and the original block of
+	 * memory is left untouched.
+	 */
+	if (!traceid_queues)
+		goto out_free;
+
+	traceid_queues[idx] = tidq;
+	etmq->traceid_queues = traceid_queues;
+
+	return etmq->traceid_queues[idx];
+
+out_free:
+	/*
+	 * Function intlist__remove() removes the inode from the list
+	 * and delete the memory associated to it.
+	 */
+	intlist__remove(traceid_queues_list, inode);
+	free(tidq);
+
+	return NULL;
+}
+
+struct cs_etm_packet_queue
+*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id)
+{
+	struct cs_etm_traceid_queue *tidq;
+
+	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+	if (tidq)
+		return &tidq->packet_queue;
+
+	return NULL;
+}
 
 static void cs_etm__packet_dump(const char *pkt_string)
 {
@@ -104,10 +376,83 @@
 	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;
@@ -121,32 +466,22 @@
 
 	/* 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++) {
-		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;
 
@@ -161,6 +496,9 @@
 	} 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,
@@ -176,15 +514,52 @@
 	if (!tool->ordered_events)
 		return -EINVAL;
 
-	if (!etm->timeless_decoding)
-		return -EINVAL;
-
 	ret = cs_etm__update_queues(etm);
 
 	if (ret < 0)
 		return ret;
 
-	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
+	if (etm->timeless_decoding)
+		return cs_etm__process_timeless_queues(etm, -1);
+
+	return cs_etm__process_queues(etm);
+}
+
+static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
+{
+	int idx;
+	uintptr_t priv;
+	struct int_node *inode, *tmp;
+	struct cs_etm_traceid_queue *tidq;
+	struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+	intlist__for_each_entry_safe(inode, tmp, traceid_queues_list) {
+		priv = (uintptr_t)inode->priv;
+		idx = priv;
+
+		/* Free this traceid_queue from the array */
+		tidq = etmq->traceid_queues[idx];
+		thread__zput(tidq->thread);
+		zfree(&tidq->event_buf);
+		zfree(&tidq->last_branch);
+		zfree(&tidq->last_branch_rb);
+		zfree(&tidq->prev_packet);
+		zfree(&tidq->packet);
+		zfree(&tidq);
+
+		/*
+		 * Function intlist__remove() removes the inode from the list
+		 * and delete the memory associated to it.
+		 */
+		intlist__remove(traceid_queues_list, inode);
+	}
+
+	/* Then the RB tree itself */
+	intlist__delete(traceid_queues_list);
+	etmq->traceid_queues_list = NULL;
+
+	/* finally free the traceid_queues array */
+	zfree(&etmq->traceid_queues);
 }
 
 static void cs_etm__free_queue(void *priv)
@@ -194,13 +569,8 @@
 	if (!etmq)
 		return;
 
-	thread__zput(etmq->thread);
 	cs_etm_decoder__free(etmq->decoder);
-	zfree(&etmq->event_buf);
-	zfree(&etmq->last_branch);
-	zfree(&etmq->last_branch_rb);
-	zfree(&etmq->prev_packet);
-	zfree(&etmq->packet);
+	cs_etm__free_traceid_queues(etmq);
 	free(etmq);
 }
 
@@ -230,7 +600,7 @@
 	cs_etm__free_events(session);
 	session->auxtrace = NULL;
 
-	/* First remove all traceID/CPU# nodes for the RB tree */
+	/* First remove all traceID/metadata nodes for the RB tree */
 	intlist__for_each_entry_safe(inode, tmp, traceid_list)
 		intlist__remove(traceid_list, inode);
 	/* Then the RB tree itself */
@@ -265,26 +635,30 @@
 	}
 }
 
-static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
-			      size_t size, u8 *buffer)
+static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
+			      u64 address, size_t size, u8 *buffer)
 {
 	u8  cpumode;
 	u64 offset;
 	int len;
-	struct	 thread *thread;
-	struct	 machine *machine;
-	struct	 addr_location al;
+	struct thread *thread;
+	struct machine *machine;
+	struct addr_location al;
+	struct cs_etm_traceid_queue *tidq;
 
 	if (!etmq)
-		return -1;
+		return 0;
 
 	machine = etmq->etm->machine;
 	cpumode = cs_etm__cpu_mode(etmq, address);
+	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+	if (!tidq)
+		return 0;
 
-	thread = etmq->thread;
+	thread = tidq->thread;
 	if (!thread) {
 		if (cpumode != PERF_RECORD_MISC_KERNEL)
-			return -EINVAL;
+			return 0;
 		thread = etmq->etm->unknown_thread;
 	}
 
@@ -307,83 +681,36 @@
 	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);
 
 	etmq = zalloc(sizeof(*etmq));
 	if (!etmq)
 		return NULL;
 
-	etmq->packet = zalloc(szp);
-	if (!etmq->packet)
+	etmq->traceid_queues_list = intlist__new(NULL);
+	if (!etmq->traceid_queues_list)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch || etm->sample_branches) {
-		etmq->prev_packet = zalloc(szp);
-		if (!etmq->prev_packet)
-			goto out_free;
-	}
-
-	if (etm->synth_opts.last_branch) {
-		size_t sz = sizeof(struct branch_stack);
-
-		sz += etm->synth_opts.last_branch_sz *
-		      sizeof(struct branch_entry);
-		etmq->last_branch = zalloc(sz);
-		if (!etmq->last_branch)
-			goto out_free;
-		etmq->last_branch_rb = zalloc(sz);
-		if (!etmq->last_branch_rb)
-			goto out_free;
-	}
-
-	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
-	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++) {
-		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;
 
@@ -396,19 +723,13 @@
 					      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(&etmq->event_buf);
-	zfree(&etmq->last_branch);
-	zfree(&etmq->last_branch_rb);
-	zfree(&etmq->prev_packet);
-	zfree(&etmq->packet);
+	intlist__delete(etmq->traceid_queues_list);
 	free(etmq);
 
 	return NULL;
@@ -418,24 +739,90 @@
 			       struct auxtrace_queue *queue,
 			       unsigned int queue_nr)
 {
+	int ret = 0;
+	unsigned int cs_queue_nr;
+	u8 trace_chan_id;
+	u64 timestamp;
 	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;
+	etmq->etm = etm;
+	etmq->queue_nr = queue_nr;
+	etmq->offset = 0;
 
-	if (queue->cpu != -1)
-		etmq->cpu = queue->cpu;
+	if (etm->timeless_decoding)
+		goto out;
 
-	etmq->tid = queue->tid;
+	/*
+	 * We are under a CPU-wide trace scenario.  As such we need to know
+	 * when the code that generated the traces started to execute so that
+	 * it can be correlated with execution on other CPUs.  So we get a
+	 * handle on the beginning of traces and decode until we find a
+	 * timestamp.  The timestamp is then added to the auxtrace min heap
+	 * in order to know what nibble (of all the etmqs) to decode first.
+	 */
+	while (1) {
+		/*
+		 * Fetch an aux_buffer from this etmq.  Bail if no more
+		 * blocks or an error has been encountered.
+		 */
+		ret = cs_etm__get_data_block(etmq);
+		if (ret <= 0)
+			goto out;
 
-	return 0;
+		/*
+		 * Run decoder on the trace block.  The decoder will stop when
+		 * encountering a timestamp, a full packet queue or the end of
+		 * trace for that block.
+		 */
+		ret = cs_etm__decode_data_block(etmq);
+		if (ret)
+			goto out;
+
+		/*
+		 * Function cs_etm_decoder__do_{hard|soft}_timestamp() does all
+		 * the timestamp calculation for us.
+		 */
+		timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
+
+		/* We found a timestamp, no need to continue. */
+		if (timestamp)
+			break;
+
+		/*
+		 * We didn't find a timestamp so empty all the traceid packet
+		 * queues before looking for another timestamp packet, either
+		 * in the current data block or a new one.  Packets that were
+		 * just decoded are useless since no timestamp has been
+		 * associated with them.  As such simply discard them.
+		 */
+		cs_etm__clear_all_packet_queues(etmq);
+	}
+
+	/*
+	 * We have a timestamp.  Add it to the min heap to reflect when
+	 * instructions conveyed by the range packets of this traceID queue
+	 * started to execute.  Once the same has been done for all the traceID
+	 * queues of each etmq, redenring and decoding can start in
+	 * chronological order.
+	 *
+	 * Note that packets decoded above are still in the traceID's packet
+	 * queue and will be processed in cs_etm__process_queues().
+	 */
+	cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_id_chan);
+	ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
+out:
+	return ret;
 }
 
 static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
@@ -443,6 +830,9 @@
 	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)
@@ -462,10 +852,12 @@
 	return 0;
 }
 
-static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq)
+static inline
+void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq,
+				 struct cs_etm_traceid_queue *tidq)
 {
-	struct branch_stack *bs_src = etmq->last_branch_rb;
-	struct branch_stack *bs_dst = etmq->last_branch;
+	struct branch_stack *bs_src = tidq->last_branch_rb;
+	struct branch_stack *bs_dst = tidq->last_branch;
 	size_t nr = 0;
 
 	/*
@@ -485,9 +877,9 @@
 	 * two steps.  First, copy the branches from the most recently inserted
 	 * branch ->last_branch_pos until the end of bs_src->entries buffer.
 	 */
-	nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos;
+	nr = etmq->etm->synth_opts.last_branch_sz - tidq->last_branch_pos;
 	memcpy(&bs_dst->entries[0],
-	       &bs_src->entries[etmq->last_branch_pos],
+	       &bs_src->entries[tidq->last_branch_pos],
 	       sizeof(struct branch_entry) * nr);
 
 	/*
@@ -500,68 +892,75 @@
 	if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
 		memcpy(&bs_dst->entries[nr],
 		       &bs_src->entries[0],
-		       sizeof(struct branch_entry) * etmq->last_branch_pos);
+		       sizeof(struct branch_entry) * tidq->last_branch_pos);
 	}
 }
 
-static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
+static inline
+void cs_etm__reset_last_branch_rb(struct cs_etm_traceid_queue *tidq)
 {
-	etmq->last_branch_pos = 0;
-	etmq->last_branch_rb->nr = 0;
+	tidq->last_branch_pos = 0;
+	tidq->last_branch_rb->nr = 0;
 }
 
-static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
+static inline int cs_etm__t32_instr_size(struct cs_etm_queue *etmq,
+					 u8 trace_chan_id, u64 addr)
 {
-	/* Returns 0 for the CS_ETM_TRACE_ON packet */
-	if (packet->sample_type == CS_ETM_TRACE_ON)
-		return 0;
+	u8 instrBytes[2];
 
+	cs_etm__mem_access(etmq, trace_chan_id, addr,
+			   ARRAY_SIZE(instrBytes), instrBytes);
 	/*
-	 * The packet records the execution range with an exclusive end address
-	 *
-	 * A64 instructions are constant size, so the last executed
-	 * instruction is A64_INSTR_SIZE before the end address
-	 * Will need to do instruction level decode for T32 instructions as
-	 * they can be variable size (not yet supported).
+	 * T32 instruction size is indicated by bits[15:11] of the first
+	 * 16-bit word of the instruction: 0b11101, 0b11110 and 0b11111
+	 * denote a 32-bit instruction.
 	 */
-	return packet->end_addr - A64_INSTR_SIZE;
+	return ((instrBytes[1] & 0xF8) >= 0xE8) ? 4 : 2;
 }
 
 static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
 {
-	/* Returns 0 for the CS_ETM_TRACE_ON packet */
-	if (packet->sample_type == CS_ETM_TRACE_ON)
+	/* Returns 0 for the CS_ETM_DISCONTINUITY packet */
+	if (packet->sample_type == CS_ETM_DISCONTINUITY)
 		return 0;
 
 	return packet->start_addr;
 }
 
-static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
+static inline
+u64 cs_etm__last_executed_instr(const struct cs_etm_packet *packet)
 {
-	/*
-	 * Only A64 instructions are currently supported, so can get
-	 * instruction count by dividing.
-	 * Will need to do instruction level decode for T32 instructions as
-	 * they can be variable size (not yet supported).
-	 */
-	return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE;
+	/* Returns 0 for the CS_ETM_DISCONTINUITY packet */
+	if (packet->sample_type == CS_ETM_DISCONTINUITY)
+		return 0;
+
+	return packet->end_addr - packet->last_instr_size;
 }
 
-static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet,
+static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
+				     u64 trace_chan_id,
+				     const struct cs_etm_packet *packet,
 				     u64 offset)
 {
-	/*
-	 * Only A64 instructions are currently supported, so can get
-	 * instruction address by muliplying.
-	 * Will need to do instruction level decode for T32 instructions as
-	 * they can be variable size (not yet supported).
-	 */
-	return packet->start_addr + offset * A64_INSTR_SIZE;
+	if (packet->isa == CS_ETM_ISA_T32) {
+		u64 addr = packet->start_addr;
+
+		while (offset > 0) {
+			addr += cs_etm__t32_instr_size(etmq,
+						       trace_chan_id, addr);
+			offset--;
+		}
+		return addr;
+	}
+
+	/* Assume a 4 byte instruction size (A32/A64) */
+	return packet->start_addr + offset * 4;
 }
 
-static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
+static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
+					  struct cs_etm_traceid_queue *tidq)
 {
-	struct branch_stack *bs = etmq->last_branch_rb;
+	struct branch_stack *bs = tidq->last_branch_rb;
 	struct branch_entry *be;
 
 	/*
@@ -570,14 +969,14 @@
 	 * buffer down.  After writing the first element of the stack, move the
 	 * insert position back to the end of the buffer.
 	 */
-	if (!etmq->last_branch_pos)
-		etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
+	if (!tidq->last_branch_pos)
+		tidq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
 
-	etmq->last_branch_pos -= 1;
+	tidq->last_branch_pos -= 1;
 
-	be       = &bs->entries[etmq->last_branch_pos];
-	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = cs_etm__first_executed_instr(etmq->packet);
+	be       = &bs->entries[tidq->last_branch_pos];
+	be->from = cs_etm__last_executed_instr(tidq->prev_packet);
+	be->to	 = cs_etm__first_executed_instr(tidq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -599,7 +998,7 @@
 
 
 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;
@@ -613,7 +1012,7 @@
 	if (!aux_buffer) {
 		if (old_buffer)
 			auxtrace_buffer__drop_data(old_buffer);
-		buff->len = 0;
+		etmq->buf_len = 0;
 		return 0;
 	}
 
@@ -633,41 +1032,90 @@
 	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,
-				    struct auxtrace_queue *queue)
+				    struct cs_etm_traceid_queue *tidq)
 {
-	struct cs_etm_queue *etmq = queue->priv;
+	if ((!tidq->thread) && (tidq->tid != -1))
+		tidq->thread = machine__find_thread(etm->machine, -1,
+						    tidq->tid);
 
-	/* CPU-wide tracing isn't supported yet */
-	if (queue->tid == -1)
+	if (tidq->thread)
+		tidq->pid = tidq->thread->pid_;
+}
+
+int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
+			 pid_t tid, u8 trace_chan_id)
+{
+	int cpu, err = -EINVAL;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_traceid_queue *tidq;
+
+	tidq = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+	if (!tidq)
+		return err;
+
+	if (cs_etm__get_cpu(trace_chan_id, &cpu) < 0)
+		return err;
+
+	err = machine__set_current_tid(etm->machine, cpu, tid, tid);
+	if (err)
+		return err;
+
+	tidq->tid = tid;
+	thread__zput(tidq->thread);
+
+	cs_etm__set_pid_tid_cpu(etm, tidq);
+	return 0;
+}
+
+bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
+{
+	return !!etmq->etm->timeless_decoding;
+}
+
+static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
+			      u64 trace_chan_id,
+			      const struct cs_etm_packet *packet,
+			      struct perf_sample *sample)
+{
+	/*
+	 * It's pointless to read instructions for the CS_ETM_DISCONTINUITY
+	 * packet, so directly bail out with 'insn_len' = 0.
+	 */
+	if (packet->sample_type == CS_ETM_DISCONTINUITY) {
+		sample->insn_len = 0;
 		return;
-
-	if ((!etmq->thread) && (etmq->tid != -1))
-		etmq->thread = machine__find_thread(etm->machine, -1,
-						    etmq->tid);
-
-	if (etmq->thread) {
-		etmq->pid = etmq->thread->pid_;
-		if (queue->cpu == -1)
-			etmq->cpu = etmq->thread->cpu;
 	}
+
+	/*
+	 * T32 instruction size might be 32-bit or 16-bit, decide by calling
+	 * cs_etm__t32_instr_size().
+	 */
+	if (packet->isa == CS_ETM_ISA_T32)
+		sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id,
+							  sample->ip);
+	/* Otherwise, A64 and A32 instruction size are always 32-bit. */
+	else
+		sample->insn_len = 4;
+
+	cs_etm__mem_access(etmq, trace_chan_id, sample->ip,
+			   sample->insn_len, (void *)sample->insn);
 }
 
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
+					    struct cs_etm_traceid_queue *tidq,
 					    u64 addr, u64 period)
 {
 	int ret = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	union perf_event *event = etmq->event_buf;
+	union perf_event *event = tidq->event_buf;
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
@@ -675,19 +1123,20 @@
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = addr;
-	sample.pid = etmq->pid;
-	sample.tid = etmq->tid;
+	sample.pid = tidq->pid;
+	sample.tid = tidq->tid;
 	sample.id = etmq->etm->instructions_id;
 	sample.stream_id = etmq->etm->instructions_id;
 	sample.period = period;
-	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
-	sample.insn_len = 1;
+	sample.cpu = tidq->packet->cpu;
+	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
+
 	if (etm->synth_opts.last_branch) {
-		cs_etm__copy_last_branch_rb(etmq);
-		sample.branch_stack = etmq->last_branch;
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+		sample.branch_stack = tidq->last_branch;
 	}
 
 	if (etm->synth_opts.inject) {
@@ -705,7 +1154,7 @@
 			ret);
 
 	if (etm->synth_opts.last_branch)
-		cs_etm__reset_last_branch_rb(etmq);
+		cs_etm__reset_last_branch_rb(tidq);
 
 	return ret;
 }
@@ -714,35 +1163,39 @@
  * The cs etm packet encodes an instruction range between a branch target
  * and the next taken branch. Generate sample accordingly.
  */
-static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
+				       struct cs_etm_traceid_queue *tidq)
 {
 	int ret = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct perf_sample sample = {.ip = 0,};
-	union perf_event *event = etmq->event_buf;
+	union perf_event *event = tidq->event_buf;
 	struct dummy_branch_stack {
 		u64			nr;
 		struct branch_entry	entries;
 	} dummy_bs;
 	u64 ip;
 
-	ip = cs_etm__last_executed_instr(etmq->prev_packet);
+	ip = cs_etm__last_executed_instr(tidq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = ip;
-	sample.pid = etmq->pid;
-	sample.tid = etmq->tid;
-	sample.addr = cs_etm__first_executed_instr(etmq->packet);
+	sample.pid = tidq->pid;
+	sample.tid = tidq->tid;
+	sample.addr = cs_etm__first_executed_instr(tidq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
-	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.cpu = tidq->packet->cpu;
+	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet,
+			  &sample);
+
 	/*
 	 * perf report cannot handle events without a branch stack
 	 */
@@ -806,15 +1259,15 @@
 static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 				struct perf_session *session)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct perf_evsel *evsel;
+	struct evlist *evlist = session->evlist;
+	struct evsel *evsel;
 	struct perf_event_attr attr;
 	bool found = false;
 	u64 id;
 	int err;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type == etm->pmu_type) {
+		if (evsel->core.attr.type == etm->pmu_type) {
 			found = true;
 			break;
 		}
@@ -828,7 +1281,7 @@
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD;
 	if (etm->timeless_decoding)
@@ -836,16 +1289,16 @@
 	else
 		attr.sample_type |= PERF_SAMPLE_TIME;
 
-	attr.exclude_user = evsel->attr.exclude_user;
-	attr.exclude_kernel = evsel->attr.exclude_kernel;
-	attr.exclude_hv = evsel->attr.exclude_hv;
-	attr.exclude_host = evsel->attr.exclude_host;
-	attr.exclude_guest = evsel->attr.exclude_guest;
-	attr.sample_id_all = evsel->attr.sample_id_all;
-	attr.read_format = evsel->attr.read_format;
+	attr.exclude_user = evsel->core.attr.exclude_user;
+	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
+	attr.exclude_hv = evsel->core.attr.exclude_hv;
+	attr.exclude_host = evsel->core.attr.exclude_host;
+	attr.exclude_guest = evsel->core.attr.exclude_guest;
+	attr.sample_id_all = evsel->core.attr.sample_id_all;
+	attr.read_format = evsel->core.attr.read_format;
 
 	/* create new id val to be a fixed offset from evsel id */
-	id = evsel->id[0] + 1000000000;
+	id = evsel->core.id[0] + 1000000000;
 
 	if (!id)
 		id = 1;
@@ -883,35 +1336,35 @@
 	return 0;
 }
 
-static int cs_etm__sample(struct cs_etm_queue *etmq)
+static int cs_etm__sample(struct cs_etm_queue *etmq,
+			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 	int ret;
-	u64 instrs_executed;
+	u8 trace_chan_id = tidq->trace_chan_id;
+	u64 instrs_executed = tidq->packet->instr_count;
 
-	instrs_executed = cs_etm__instr_count(etmq->packet);
-	etmq->period_instructions += instrs_executed;
+	tidq->period_instructions += instrs_executed;
 
 	/*
 	 * Record a branch when the last instruction in
 	 * PREV_PACKET is a branch.
 	 */
 	if (etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch)
-		cs_etm__update_last_branch_rb(etmq);
+	    tidq->prev_packet->sample_type == CS_ETM_RANGE &&
+	    tidq->prev_packet->last_instr_taken_branch)
+		cs_etm__update_last_branch_rb(etmq, tidq);
 
 	if (etm->sample_instructions &&
-	    etmq->period_instructions >= etm->instructions_sample_period) {
+	    tidq->period_instructions >= etm->instructions_sample_period) {
 		/*
 		 * Emit instruction sample periodically
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
 		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = etmq->period_instructions -
+		u64 instrs_over = tidq->period_instructions -
 			etm->instructions_sample_period;
 
 		/*
@@ -920,31 +1373,32 @@
 		 * executed, but PC has not advanced to next instruction)
 		 */
 		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq->packet, offset);
+		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
+					      tidq->packet, offset);
 
 		ret = cs_etm__synth_instruction_sample(
-			etmq, addr, etm->instructions_sample_period);
+			etmq, tidq, addr, etm->instructions_sample_period);
 		if (ret)
 			return ret;
 
 		/* Carry remaining instructions into next sample period */
-		etmq->period_instructions = instrs_over;
+		tidq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches && etmq->prev_packet) {
+	if (etm->sample_branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
-		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+		if (tidq->prev_packet->sample_type == CS_ETM_DISCONTINUITY)
 			generate_sample = true;
 
 		/* Generate sample for branch taken packet */
-		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-		    etmq->prev_packet->last_instr_taken_branch)
+		if (tidq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    tidq->prev_packet->last_instr_taken_branch)
 			generate_sample = true;
 
 		if (generate_sample) {
-			ret = cs_etm__synth_branch_sample(etmq);
+			ret = cs_etm__synth_branch_sample(etmq, tidq);
 			if (ret)
 				return ret;
 		}
@@ -955,29 +1409,46 @@
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
 		 */
-		tmp = etmq->packet;
-		etmq->packet = etmq->prev_packet;
-		etmq->prev_packet = tmp;
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
 	}
 
 	return 0;
 }
 
-static int cs_etm__flush(struct cs_etm_queue *etmq)
+static int cs_etm__exception(struct cs_etm_traceid_queue *tidq)
+{
+	/*
+	 * When the exception packet is inserted, whether the last instruction
+	 * in previous range packet is taken branch or not, we need to force
+	 * to set 'prev_packet->last_instr_taken_branch' to true.  This ensures
+	 * to generate branch sample for the instruction range before the
+	 * exception is trapped to kernel or before the exception returning.
+	 *
+	 * The exception packet includes the dummy address values, so don't
+	 * swap PACKET with PREV_PACKET.  This keeps PREV_PACKET to be useful
+	 * for generating instruction and branch samples.
+	 */
+	if (tidq->prev_packet->sample_type == CS_ETM_RANGE)
+		tidq->prev_packet->last_instr_taken_branch = true;
+
+	return 0;
+}
+
+static int cs_etm__flush(struct cs_etm_queue *etmq,
+			 struct cs_etm_traceid_queue *tidq)
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
-	if (!etmq->prev_packet)
-		return 0;
-
 	/* Handle start tracing packet */
-	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
 
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -985,129 +1456,610 @@
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
-			etmq, addr,
-			etmq->period_instructions);
+			etmq, tidq, addr,
+			tidq->period_instructions);
 		if (err)
 			return err;
 
-		etmq->period_instructions = 0;
+		tidq->period_instructions = 0;
 
 	}
 
 	if (etm->sample_branches &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
-		err = cs_etm__synth_branch_sample(etmq);
+	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq, tidq);
 		if (err)
 			return err;
 	}
 
 swap_packet:
-	if (etmq->etm->synth_opts.last_branch) {
+	if (etm->sample_branches || etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
 		 */
-		tmp = etmq->packet;
-		etmq->packet = etmq->prev_packet;
-		etmq->prev_packet = tmp;
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
 	}
 
 	return err;
 }
 
+static int cs_etm__end_block(struct cs_etm_queue *etmq,
+			     struct cs_etm_traceid_queue *tidq)
+{
+	int err;
+
+	/*
+	 * It has no new packet coming and 'etmq->packet' contains the stale
+	 * packet which was set at the previous time with packets swapping;
+	 * so skip to generate branch sample to avoid stale packet.
+	 *
+	 * For this case only flush branch stack and generate a last branch
+	 * event for the branches left in the circular buffer at the end of
+	 * the trace.
+	 */
+	if (etmq->etm->synth_opts.last_branch &&
+	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		/*
+		 * Use the address of the end of the last reported execution
+		 * range.
+		 */
+		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+
+		err = cs_etm__synth_instruction_sample(
+			etmq, tidq, addr,
+			tidq->period_instructions);
+		if (err)
+			return err;
+
+		tidq->period_instructions = 0;
+	}
+
+	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, u8 trace_chan_id,
+				 struct cs_etm_packet *packet,
+				 u64 end_addr)
+{
+	/* Initialise to keep compiler happy */
+	u16 instr16 = 0;
+	u32 instr32 = 0;
+	u64 addr;
+
+	switch (packet->isa) {
+	case CS_ETM_ISA_T32:
+		/*
+		 * The SVC of T32 is defined in ARM DDI 0487D.a, F5.1.247:
+		 *
+		 *  b'15         b'8
+		 * +-----------------+--------+
+		 * | 1 1 0 1 1 1 1 1 |  imm8  |
+		 * +-----------------+--------+
+		 *
+		 * According to the specifiction, it only defines SVC for T32
+		 * with 16 bits instruction and has no definition for 32bits;
+		 * so below only read 2 bytes as instruction size for T32.
+		 */
+		addr = end_addr - 2;
+		cs_etm__mem_access(etmq, trace_chan_id, addr,
+				   sizeof(instr16), (u8 *)&instr16);
+		if ((instr16 & 0xFF00) == 0xDF00)
+			return true;
+
+		break;
+	case CS_ETM_ISA_A32:
+		/*
+		 * The SVC of A32 is defined in ARM DDI 0487D.a, F5.1.247:
+		 *
+		 *  b'31 b'28 b'27 b'24
+		 * +---------+---------+-------------------------+
+		 * |  !1111  | 1 1 1 1 |        imm24            |
+		 * +---------+---------+-------------------------+
+		 */
+		addr = end_addr - 4;
+		cs_etm__mem_access(etmq, trace_chan_id, addr,
+				   sizeof(instr32), (u8 *)&instr32);
+		if ((instr32 & 0x0F000000) == 0x0F000000 &&
+		    (instr32 & 0xF0000000) != 0xF0000000)
+			return true;
+
+		break;
+	case CS_ETM_ISA_A64:
+		/*
+		 * The SVC of A64 is defined in ARM DDI 0487D.a, C6.2.294:
+		 *
+		 *  b'31               b'21           b'4     b'0
+		 * +-----------------------+---------+-----------+
+		 * | 1 1 0 1 0 1 0 0 0 0 0 |  imm16  | 0 0 0 0 1 |
+		 * +-----------------------+---------+-----------+
+		 */
+		addr = end_addr - 4;
+		cs_etm__mem_access(etmq, trace_chan_id, addr,
+				   sizeof(instr32), (u8 *)&instr32);
+		if ((instr32 & 0xFFE0001F) == 0xd4000001)
+			return true;
+
+		break;
+	case CS_ETM_ISA_UNKNOWN:
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static bool cs_etm__is_syscall(struct cs_etm_queue *etmq,
+			       struct cs_etm_traceid_queue *tidq, u64 magic)
+{
+	u8 trace_chan_id = tidq->trace_chan_id;
+	struct cs_etm_packet *packet = tidq->packet;
+	struct cs_etm_packet *prev_packet = tidq->prev_packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_SVC)
+			return true;
+
+	/*
+	 * ETMv4 exception type CS_ETMV4_EXC_CALL covers SVC, SMC and
+	 * HVC cases; need to check if it's SVC instruction based on
+	 * packet address.
+	 */
+	if (magic == __perf_cs_etmv4_magic) {
+		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
+		    cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
+					 prev_packet->end_addr))
+			return true;
+	}
+
+	return false;
+}
+
+static bool cs_etm__is_async_exception(struct cs_etm_traceid_queue *tidq,
+				       u64 magic)
+{
+	struct cs_etm_packet *packet = tidq->packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_DEBUG_HALT ||
+		    packet->exception_number == CS_ETMV3_EXC_ASYNC_DATA_ABORT ||
+		    packet->exception_number == CS_ETMV3_EXC_PE_RESET ||
+		    packet->exception_number == CS_ETMV3_EXC_IRQ ||
+		    packet->exception_number == CS_ETMV3_EXC_FIQ)
+			return true;
+
+	if (magic == __perf_cs_etmv4_magic)
+		if (packet->exception_number == CS_ETMV4_EXC_RESET ||
+		    packet->exception_number == CS_ETMV4_EXC_DEBUG_HALT ||
+		    packet->exception_number == CS_ETMV4_EXC_SYSTEM_ERROR ||
+		    packet->exception_number == CS_ETMV4_EXC_INST_DEBUG ||
+		    packet->exception_number == CS_ETMV4_EXC_DATA_DEBUG ||
+		    packet->exception_number == CS_ETMV4_EXC_IRQ ||
+		    packet->exception_number == CS_ETMV4_EXC_FIQ)
+			return true;
+
+	return false;
+}
+
+static bool cs_etm__is_sync_exception(struct cs_etm_queue *etmq,
+				      struct cs_etm_traceid_queue *tidq,
+				      u64 magic)
+{
+	u8 trace_chan_id = tidq->trace_chan_id;
+	struct cs_etm_packet *packet = tidq->packet;
+	struct cs_etm_packet *prev_packet = tidq->prev_packet;
+
+	if (magic == __perf_cs_etmv3_magic)
+		if (packet->exception_number == CS_ETMV3_EXC_SMC ||
+		    packet->exception_number == CS_ETMV3_EXC_HYP ||
+		    packet->exception_number == CS_ETMV3_EXC_JAZELLE_THUMBEE ||
+		    packet->exception_number == CS_ETMV3_EXC_UNDEFINED_INSTR ||
+		    packet->exception_number == CS_ETMV3_EXC_PREFETCH_ABORT ||
+		    packet->exception_number == CS_ETMV3_EXC_DATA_FAULT ||
+		    packet->exception_number == CS_ETMV3_EXC_GENERIC)
+			return true;
+
+	if (magic == __perf_cs_etmv4_magic) {
+		if (packet->exception_number == CS_ETMV4_EXC_TRAP ||
+		    packet->exception_number == CS_ETMV4_EXC_ALIGNMENT ||
+		    packet->exception_number == CS_ETMV4_EXC_INST_FAULT ||
+		    packet->exception_number == CS_ETMV4_EXC_DATA_FAULT)
+			return true;
+
+		/*
+		 * For CS_ETMV4_EXC_CALL, except SVC other instructions
+		 * (SMC, HVC) are taken as sync exceptions.
+		 */
+		if (packet->exception_number == CS_ETMV4_EXC_CALL &&
+		    !cs_etm__is_svc_instr(etmq, trace_chan_id, prev_packet,
+					  prev_packet->end_addr))
+			return true;
+
+		/*
+		 * ETMv4 has 5 bits for exception number; if the numbers
+		 * are in the range ( CS_ETMV4_EXC_FIQ, CS_ETMV4_EXC_END ]
+		 * they are implementation defined exceptions.
+		 *
+		 * For this case, simply take it as sync exception.
+		 */
+		if (packet->exception_number > CS_ETMV4_EXC_FIQ &&
+		    packet->exception_number <= CS_ETMV4_EXC_END)
+			return true;
+	}
+
+	return false;
+}
+
+static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq,
+				    struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *packet = tidq->packet;
+	struct cs_etm_packet *prev_packet = tidq->prev_packet;
+	u8 trace_chan_id = tidq->trace_chan_id;
+	u64 magic;
+	int ret;
+
+	switch (packet->sample_type) {
+	case CS_ETM_RANGE:
+		/*
+		 * Immediate branch instruction without neither link nor
+		 * return flag, it's normal branch instruction within
+		 * the function.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_NONE) {
+			packet->flags = PERF_IP_FLAG_BRANCH;
+
+			if (packet->last_instr_cond)
+				packet->flags |= PERF_IP_FLAG_CONDITIONAL;
+		}
+
+		/*
+		 * Immediate branch instruction with link (e.g. BL), this is
+		 * branch instruction for function call.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/*
+		 * Indirect branch instruction with link (e.g. BLR), this is
+		 * branch instruction for function call.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_BR_LINK)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL;
+
+		/*
+		 * Indirect branch instruction with subtype of
+		 * OCSD_S_INSTR_V7_IMPLIED_RET, this is explicit hint for
+		 * function return for A32/T32.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_V7_IMPLIED_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Indirect branch instruction without link (e.g. BR), usually
+		 * this is used for function return, especially for functions
+		 * within dynamic link lib.
+		 */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_NONE)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/* Return instruction for function return. */
+		if (packet->last_instr_type == OCSD_INSTR_BR_INDIRECT &&
+		    packet->last_instr_subtype == OCSD_S_INSTR_V8_RET)
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_RETURN;
+
+		/*
+		 * Decoder might insert a discontinuity in the middle of
+		 * instruction packets, fixup prev_packet with flag
+		 * PERF_IP_FLAG_TRACE_BEGIN to indicate restarting trace.
+		 */
+		if (prev_packet->sample_type == CS_ETM_DISCONTINUITY)
+			prev_packet->flags |= PERF_IP_FLAG_BRANCH |
+					      PERF_IP_FLAG_TRACE_BEGIN;
+
+		/*
+		 * If the previous packet is an exception return packet
+		 * and the return address just follows SVC instuction,
+		 * it needs to calibrate the previous packet sample flags
+		 * as PERF_IP_FLAG_SYSCALLRET.
+		 */
+		if (prev_packet->flags == (PERF_IP_FLAG_BRANCH |
+					   PERF_IP_FLAG_RETURN |
+					   PERF_IP_FLAG_INTERRUPT) &&
+		    cs_etm__is_svc_instr(etmq, trace_chan_id,
+					 packet, packet->start_addr))
+			prev_packet->flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_RETURN |
+					     PERF_IP_FLAG_SYSCALLRET;
+		break;
+	case CS_ETM_DISCONTINUITY:
+		/*
+		 * The trace is discontinuous, if the previous packet is
+		 * instruction packet, set flag PERF_IP_FLAG_TRACE_END
+		 * for previous packet.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags |= PERF_IP_FLAG_BRANCH |
+					      PERF_IP_FLAG_TRACE_END;
+		break;
+	case CS_ETM_EXCEPTION:
+		ret = cs_etm__get_magic(packet->trace_chan_id, &magic);
+		if (ret)
+			return ret;
+
+		/* The exception is for system call. */
+		if (cs_etm__is_syscall(etmq, tidq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_SYSCALLRET;
+		/*
+		 * The exceptions are triggered by external signals from bus,
+		 * interrupt controller, debug module, PE reset or halt.
+		 */
+		else if (cs_etm__is_async_exception(tidq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_ASYNC |
+					PERF_IP_FLAG_INTERRUPT;
+		/*
+		 * Otherwise, exception is caused by trap, instruction &
+		 * data fault, or alignment errors.
+		 */
+		else if (cs_etm__is_sync_exception(etmq, tidq, magic))
+			packet->flags = PERF_IP_FLAG_BRANCH |
+					PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_INTERRUPT;
+
+		/*
+		 * When the exception packet is inserted, since exception
+		 * packet is not used standalone for generating samples
+		 * and it's affiliation to the previous instruction range
+		 * packet; so set previous range packet flags to tell perf
+		 * it is an exception taken branch.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags = packet->flags;
+		break;
+	case CS_ETM_EXCEPTION_RET:
+		/*
+		 * When the exception return packet is inserted, since
+		 * exception return packet is not used standalone for
+		 * generating samples and it's affiliation to the previous
+		 * instruction range packet; so set previous range packet
+		 * flags to tell perf it is an exception return branch.
+		 *
+		 * The exception return can be for either system call or
+		 * other exception types; unfortunately the packet doesn't
+		 * contain exception type related info so we cannot decide
+		 * the exception type purely based on exception return packet.
+		 * If we record the exception number from exception packet and
+		 * reuse it for excpetion return packet, this is not reliable
+		 * due the trace can be discontinuity or the interrupt can
+		 * be nested, thus the recorded exception number cannot be
+		 * used for exception return packet for these two cases.
+		 *
+		 * For exception return packet, we only need to distinguish the
+		 * packet is for system call or for other types.  Thus the
+		 * decision can be deferred when receive the next packet which
+		 * contains the return address, based on the return address we
+		 * can read out the previous instruction and check if it's a
+		 * system call instruction and then calibrate the sample flag
+		 * as needed.
+		 */
+		if (prev_packet->sample_type == CS_ETM_RANGE)
+			prev_packet->flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_RETURN |
+					     PERF_IP_FLAG_INTERRUPT;
+		break;
+	case CS_ETM_EMPTY:
+	default:
+		break;
+	}
+
+	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_traceid_queue(struct cs_etm_queue *etmq,
+					 struct cs_etm_traceid_queue *tidq)
+{
+	int ret;
+	struct cs_etm_packet_queue *packet_queue;
+
+	packet_queue = &tidq->packet_queue;
+
+	/* Process each packet in this chunk */
+	while (1) {
+		ret = cs_etm_decoder__get_packet(packet_queue,
+						 tidq->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, tidq);
+		if (ret < 0)
+			break;
+
+		switch (tidq->packet->sample_type) {
+		case CS_ETM_RANGE:
+			/*
+			 * If the packet contains an instruction
+			 * range, generate instruction sequence
+			 * events.
+			 */
+			cs_etm__sample(etmq, tidq);
+			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(tidq);
+			break;
+		case CS_ETM_DISCONTINUITY:
+			/*
+			 * Discontinuity in trace, flush
+			 * previous branch stack
+			 */
+			cs_etm__flush(etmq, tidq);
+			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 void cs_etm__clear_all_traceid_queues(struct cs_etm_queue *etmq)
+{
+	int idx;
+	struct int_node *inode;
+	struct cs_etm_traceid_queue *tidq;
+	struct intlist *traceid_queues_list = etmq->traceid_queues_list;
+
+	intlist__for_each_entry(inode, traceid_queues_list) {
+		idx = (int)(intptr_t)inode->priv;
+		tidq = etmq->traceid_queues[idx];
+
+		/* Ignore return value */
+		cs_etm__process_traceid_queue(etmq, tidq);
+
+		/*
+		 * Generate an instruction sample with the remaining
+		 * branchstack entries.
+		 */
+		cs_etm__flush(etmq, tidq);
+	}
+}
+
 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;
+	struct cs_etm_traceid_queue *tidq;
 
-	if (!etm->kernel_start)
-		etm->kernel_start = machine__kernel_start(etm->machine);
+	tidq = cs_etm__etmq_get_traceid_queue(etmq, CS_ETM_PER_THREAD_TRACEID);
+	if (!tidq)
+		return -EINVAL;
 
 	/* 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_traceid_queue(etmq, tidq);
 
-			/* 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;
-
-				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_TRACE_ON:
-					/*
-					 * 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 */
-			err = cs_etm__flush(etmq);
+			err = cs_etm__end_block(etmq, tidq);
 	}
 
 	return err;
 }
 
 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;
@@ -1115,10 +2067,19 @@
 	for (i = 0; i < queues->nr_queues; i++) {
 		struct auxtrace_queue *queue = &etm->queues.queue_array[i];
 		struct cs_etm_queue *etmq = queue->priv;
+		struct cs_etm_traceid_queue *tidq;
 
-		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
-			etmq->time = time_;
-			cs_etm__set_pid_tid_cpu(etm, queue);
+		if (!etmq)
+			continue;
+
+		tidq = cs_etm__etmq_get_traceid_queue(etmq,
+						CS_ETM_PER_THREAD_TRACEID);
+
+		if (!tidq)
+			continue;
+
+		if ((tid == -1) || (tidq->tid == tid)) {
+			cs_etm__set_pid_tid_cpu(etm, tidq);
 			cs_etm__run_decoder(etmq);
 		}
 	}
@@ -1126,6 +2087,164 @@
 	return 0;
 }
 
+static int cs_etm__process_queues(struct cs_etm_auxtrace *etm)
+{
+	int ret = 0;
+	unsigned int cs_queue_nr, queue_nr;
+	u8 trace_chan_id;
+	u64 timestamp;
+	struct auxtrace_queue *queue;
+	struct cs_etm_queue *etmq;
+	struct cs_etm_traceid_queue *tidq;
+
+	while (1) {
+		if (!etm->heap.heap_cnt)
+			goto out;
+
+		/* Take the entry at the top of the min heap */
+		cs_queue_nr = etm->heap.heap_array[0].queue_nr;
+		queue_nr = TO_QUEUE_NR(cs_queue_nr);
+		trace_chan_id = TO_TRACE_CHAN_ID(cs_queue_nr);
+		queue = &etm->queues.queue_array[queue_nr];
+		etmq = queue->priv;
+
+		/*
+		 * Remove the top entry from the heap since we are about
+		 * to process it.
+		 */
+		auxtrace_heap__pop(&etm->heap);
+
+		tidq  = cs_etm__etmq_get_traceid_queue(etmq, trace_chan_id);
+		if (!tidq) {
+			/*
+			 * No traceID queue has been allocated for this traceID,
+			 * which means something somewhere went very wrong.  No
+			 * other choice than simply exit.
+			 */
+			ret = -EINVAL;
+			goto out;
+		}
+
+		/*
+		 * Packets associated with this timestamp are already in
+		 * the etmq's traceID queue, so process them.
+		 */
+		ret = cs_etm__process_traceid_queue(etmq, tidq);
+		if (ret < 0)
+			goto out;
+
+		/*
+		 * Packets for this timestamp have been processed, time to
+		 * move on to the next timestamp, fetching a new auxtrace_buffer
+		 * if need be.
+		 */
+refetch:
+		ret = cs_etm__get_data_block(etmq);
+		if (ret < 0)
+			goto out;
+
+		/*
+		 * No more auxtrace_buffers to process in this etmq, simply
+		 * move on to another entry in the auxtrace_heap.
+		 */
+		if (!ret)
+			continue;
+
+		ret = cs_etm__decode_data_block(etmq);
+		if (ret)
+			goto out;
+
+		timestamp = cs_etm__etmq_get_timestamp(etmq, &trace_chan_id);
+
+		if (!timestamp) {
+			/*
+			 * Function cs_etm__decode_data_block() returns when
+			 * there is no more traces to decode in the current
+			 * auxtrace_buffer OR when a timestamp has been
+			 * encountered on any of the traceID queues.  Since we
+			 * did not get a timestamp, there is no more traces to
+			 * process in this auxtrace_buffer.  As such empty and
+			 * flush all traceID queues.
+			 */
+			cs_etm__clear_all_traceid_queues(etmq);
+
+			/* Fetch another auxtrace_buffer for this etmq */
+			goto refetch;
+		}
+
+		/*
+		 * Add to the min heap the timestamp for packets that have
+		 * just been decoded.  They will be processed and synthesized
+		 * during the next call to cs_etm__process_traceid_queue() for
+		 * this queue/traceID.
+		 */
+		cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id);
+		ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, timestamp);
+	}
+
+out:
+	return ret;
+}
+
+static int cs_etm__process_itrace_start(struct cs_etm_auxtrace *etm,
+					union perf_event *event)
+{
+	struct thread *th;
+
+	if (etm->timeless_decoding)
+		return 0;
+
+	/*
+	 * Add the tid/pid to the log so that we can get a match when
+	 * we get a contextID from the decoder.
+	 */
+	th = machine__findnew_thread(etm->machine,
+				     event->itrace_start.pid,
+				     event->itrace_start.tid);
+	if (!th)
+		return -ENOMEM;
+
+	thread__put(th);
+
+	return 0;
+}
+
+static int cs_etm__process_switch_cpu_wide(struct cs_etm_auxtrace *etm,
+					   union perf_event *event)
+{
+	struct thread *th;
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+
+	/*
+	 * Context switch in per-thread mode are irrelevant since perf
+	 * will start/stop tracing as the process is scheduled.
+	 */
+	if (etm->timeless_decoding)
+		return 0;
+
+	/*
+	 * SWITCH_IN events carry the next process to be switched out while
+	 * SWITCH_OUT events carry the process to be switched in.  As such
+	 * we don't care about IN events.
+	 */
+	if (!out)
+		return 0;
+
+	/*
+	 * Add the tid/pid to the log so that we can get a match when
+	 * we get a contextID from the decoder.
+	 */
+	th = machine__findnew_thread(etm->machine,
+				     event->context_switch.next_prev_pid,
+				     event->context_switch.next_prev_tid);
+	if (!th)
+		return -ENOMEM;
+
+	thread__put(th);
+
+	return 0;
+}
+
 static int cs_etm__process_event(struct perf_session *session,
 				 union perf_event *event,
 				 struct perf_sample *sample,
@@ -1145,9 +2264,6 @@
 		return -EINVAL;
 	}
 
-	if (!etm->timeless_decoding)
-		return -EINVAL;
-
 	if (sample->time && (sample->time != (u64) -1))
 		timestamp = sample->time;
 	else
@@ -1159,10 +2275,19 @@
 			return err;
 	}
 
-	if (event->header.type == PERF_RECORD_EXIT)
+	if (etm->timeless_decoding &&
+	    event->header.type == PERF_RECORD_EXIT)
 		return cs_etm__process_timeless_queues(etm,
-						       event->fork.tid,
-						       sample->time);
+						       event->fork.tid);
+
+	if (event->header.type == PERF_RECORD_ITRACE_START)
+		return cs_etm__process_itrace_start(etm, event);
+	else if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
+		return cs_etm__process_switch_cpu_wide(etm, event);
+
+	if (!etm->timeless_decoding &&
+	    event->header.type == PERF_RECORD_AUX)
+		return cs_etm__process_queues(etm);
 
 	return 0;
 }
@@ -1206,8 +2331,8 @@
 
 static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm)
 {
-	struct perf_evsel *evsel;
-	struct perf_evlist *evlist = etm->session->evlist;
+	struct evsel *evsel;
+	struct evlist *evlist = etm->session->evlist;
 	bool timeless_decoding = true;
 
 	/*
@@ -1215,7 +2340,7 @@
 	 * with the time bit set.
 	 */
 	evlist__for_each_entry(evlist, evsel) {
-		if ((evsel->attr.sample_type & PERF_SAMPLE_TIME))
+		if ((evsel->core.attr.sample_type & PERF_SAMPLE_TIME))
 			timeless_decoding = false;
 	}
 
@@ -1249,7 +2374,7 @@
 	[CS_ETMV4_TRCAUTHSTATUS] = "	TRCAUTHSTATUS		       %llx\n",
 };
 
-static void cs_etm__print_auxtrace_info(u64 *val, int num)
+static void cs_etm__print_auxtrace_info(__u64 *val, int num)
 {
 	int i, j, cpu = 0;
 
@@ -1272,7 +2397,7 @@
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session)
 {
-	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	struct cs_etm_auxtrace *etm = NULL;
 	struct int_node *inode;
 	unsigned int pmu_type;
@@ -1316,9 +2441,9 @@
 				    0xffffffff);
 
 	/*
-	 * Create an RB tree for traceID-CPU# tuple. Since the conversion has
-	 * to be made for each packet that gets decoded, optimizing access in
-	 * anything other than a sequential array is worth doing.
+	 * Create an RB tree for traceID-metadata tuple.  Since the conversion
+	 * has to be made for each packet that gets decoded, optimizing access
+	 * in anything other than a sequential array is worth doing.
 	 */
 	traceid_list = intlist__new(NULL);
 	if (!traceid_list) {
@@ -1372,7 +2497,7 @@
 
 		/* Something went wrong, no need to continue */
 		if (!inode) {
-			err = PTR_ERR(inode);
+			err = -ENOMEM;
 			goto err_free_metadata;
 		}
 
@@ -1384,8 +2509,8 @@
 			err = -EINVAL;
 			goto err_free_metadata;
 		}
-		/* All good, associate the traceID with the CPU# */
-		inode->priv = &metadata[j][CS_ETM_CPU];
+		/* All good, associate the traceID with the metadata pointer */
+		inode->priv = metadata[j];
 	}
 
 	/*
@@ -1429,8 +2554,10 @@
 	session->auxtrace = &etm->auxtrace;
 
 	etm->unknown_thread = thread__new(999999999, 999999999);
-	if (!etm->unknown_thread)
+	if (!etm->unknown_thread) {
+		err = -ENOMEM;
 		goto err_free_queues;
+	}
 
 	/*
 	 * Initialize list node so that at thread__zput() we can avoid
@@ -1442,18 +2569,21 @@
 	if (err)
 		goto err_delete_thread;
 
-	if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+	if (thread__init_map_groups(etm->unknown_thread, etm->machine)) {
+		err = -ENOMEM;
 		goto err_delete_thread;
+	}
 
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
 		return 0;
 	}
 
-	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+	if (session->itrace_synth_opts->set) {
 		etm->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&etm->synth_opts);
+		itrace_synth_opts__set_default(&etm->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
 	}
 
@@ -1479,12 +2609,12 @@
 err_free_metadata:
 	/* No need to check @metadata[j], free(NULL) is supported */
 	for (j = 0; j < num_cpu; j++)
-		free(metadata[j]);
+		zfree(&metadata[j]);
 	zfree(&metadata);
 err_free_traceid_list:
 	intlist__delete(traceid_list);
 err_free_hdr:
 	zfree(&hdr);
 
-	return -EINVAL;
+	return err;
 }
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 37f8d48..650ecc2 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -8,7 +8,9 @@
 #define INCLUDE__UTIL_PERF_CS_ETM_H__
 
 #include "util/event.h"
-#include "util/session.h"
+#include <linux/bits.h>
+
+struct perf_session;
 
 /* Versionning header in case things need tro change in the future.  That way
  * decoding of old snapshot is still possible.
@@ -53,22 +55,134 @@
 	CS_ETMV4_PRIV_MAX,
 };
 
-/* RB tree for quick conversion between traceID and CPUs */
+/*
+ * ETMv3 exception encoding number:
+ * See Embedded Trace Macrocell spcification (ARM IHI 0014Q)
+ * table 7-12 Encoding of Exception[3:0] for non-ARMv7-M processors.
+ */
+enum {
+	CS_ETMV3_EXC_NONE = 0,
+	CS_ETMV3_EXC_DEBUG_HALT = 1,
+	CS_ETMV3_EXC_SMC = 2,
+	CS_ETMV3_EXC_HYP = 3,
+	CS_ETMV3_EXC_ASYNC_DATA_ABORT = 4,
+	CS_ETMV3_EXC_JAZELLE_THUMBEE = 5,
+	CS_ETMV3_EXC_PE_RESET = 8,
+	CS_ETMV3_EXC_UNDEFINED_INSTR = 9,
+	CS_ETMV3_EXC_SVC = 10,
+	CS_ETMV3_EXC_PREFETCH_ABORT = 11,
+	CS_ETMV3_EXC_DATA_FAULT = 12,
+	CS_ETMV3_EXC_GENERIC = 13,
+	CS_ETMV3_EXC_IRQ = 14,
+	CS_ETMV3_EXC_FIQ = 15,
+};
+
+/*
+ * ETMv4 exception encoding number:
+ * See ARM Embedded Trace Macrocell Architecture Specification (ARM IHI 0064D)
+ * table 6-12 Possible values for the TYPE field in an Exception instruction
+ * trace packet, for ARMv7-A/R and ARMv8-A/R PEs.
+ */
+enum {
+	CS_ETMV4_EXC_RESET = 0,
+	CS_ETMV4_EXC_DEBUG_HALT = 1,
+	CS_ETMV4_EXC_CALL = 2,
+	CS_ETMV4_EXC_TRAP = 3,
+	CS_ETMV4_EXC_SYSTEM_ERROR = 4,
+	CS_ETMV4_EXC_INST_DEBUG = 6,
+	CS_ETMV4_EXC_DATA_DEBUG = 7,
+	CS_ETMV4_EXC_ALIGNMENT = 10,
+	CS_ETMV4_EXC_INST_FAULT = 11,
+	CS_ETMV4_EXC_DATA_FAULT = 12,
+	CS_ETMV4_EXC_IRQ = 14,
+	CS_ETMV4_EXC_FIQ = 15,
+	CS_ETMV4_EXC_END = 31,
+};
+
+enum cs_etm_sample_type {
+	CS_ETM_EMPTY,
+	CS_ETM_RANGE,
+	CS_ETM_DISCONTINUITY,
+	CS_ETM_EXCEPTION,
+	CS_ETM_EXCEPTION_RET,
+};
+
+enum cs_etm_isa {
+	CS_ETM_ISA_UNKNOWN,
+	CS_ETM_ISA_A64,
+	CS_ETM_ISA_A32,
+	CS_ETM_ISA_T32,
+};
+
+/* RB tree for quick conversion between traceID and metadata pointers */
 struct intlist *traceid_list;
 
+struct cs_etm_queue;
+
+struct cs_etm_packet {
+	enum cs_etm_sample_type sample_type;
+	enum cs_etm_isa isa;
+	u64 start_addr;
+	u64 end_addr;
+	u32 instr_count;
+	u32 last_instr_type;
+	u32 last_instr_subtype;
+	u32 flags;
+	u32 exception_number;
+	u8 last_instr_cond;
+	u8 last_instr_taken_branch;
+	u8 last_instr_size;
+	u8 trace_chan_id;
+	int cpu;
+};
+
+#define CS_ETM_PACKET_MAX_BUFFER 1024
+
+/*
+ * When working with per-thread scenarios the process under trace can
+ * be scheduled on any CPU and as such, more than one traceID may be
+ * associated with the same process.  Since a traceID of '0' is illegal
+ * as per the CoreSight architecture, use that specific value to
+ * identify the queue where all packets (with any traceID) are
+ * aggregated.
+ */
+#define CS_ETM_PER_THREAD_TRACEID 0
+
+struct cs_etm_packet_queue {
+	u32 packet_count;
+	u32 head;
+	u32 tail;
+	u32 instr_count;
+	u64 timestamp;
+	u64 next_timestamp;
+	struct cs_etm_packet packet_buffer[CS_ETM_PACKET_MAX_BUFFER];
+};
+
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
 
+#define CS_ETM_INVAL_ADDR 0xdeadbeefdeadbeefUL
+
+#define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
+
 #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))
 
 #ifdef HAVE_CSTRACE_SUPPORT
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
+int cs_etm__get_cpu(u8 trace_chan_id, int *cpu);
+int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq,
+			 pid_t tid, u8 trace_chan_id);
+bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq);
+void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq,
+					      u8 trace_chan_id);
+struct cs_etm_packet_queue
+*cs_etm__etmq_get_packet_queue(struct cs_etm_queue *etmq, u8 trace_chan_id);
 #else
 static inline int
 cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
@@ -76,6 +190,38 @@
 {
 	return -1;
 }
+
+static inline int cs_etm__get_cpu(u8 trace_chan_id __maybe_unused,
+				  int *cpu __maybe_unused)
+{
+	return -1;
+}
+
+static inline int cs_etm__etmq_set_tid(
+				struct cs_etm_queue *etmq __maybe_unused,
+				pid_t tid __maybe_unused,
+				u8 trace_chan_id __maybe_unused)
+{
+	return -1;
+}
+
+static inline bool cs_etm__etmq_is_timeless(
+				struct cs_etm_queue *etmq __maybe_unused)
+{
+	/* What else to return? */
+	return true;
+}
+
+static inline void cs_etm__etmq_set_traceid_queue_timestamp(
+				struct cs_etm_queue *etmq __maybe_unused,
+				u8 trace_chan_id __maybe_unused) {}
+
+static inline struct cs_etm_packet_queue *cs_etm__etmq_get_packet_queue(
+				struct cs_etm_queue *etmq __maybe_unused,
+				u8 trace_chan_id __maybe_unused)
+{
+	return NULL;
+}
 #endif
 
 #endif
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
deleted file mode 100644
index ee4c1e8..0000000
--- a/tools/perf/util/ctype.c
+++ /dev/null
@@ -1,49 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Sane locale-independent, ASCII ctype.
- *
- * No surprises, and works with signed and unsigned chars.
- */
-#include "sane_ctype.h"
-
-enum {
-	S = GIT_SPACE,
-	A = GIT_ALPHA,
-	D = GIT_DIGIT,
-	G = GIT_GLOB_SPECIAL,	/* *, ?, [, \\ */
-	R = GIT_REGEX_SPECIAL,	/* $, (, ), +, ., ^, {, | * */
-	P = GIT_PRINT_EXTRA,	/* printable - alpha - digit - glob - regex */
-
-	PS = GIT_SPACE | GIT_PRINT_EXTRA,
-};
-
-unsigned char sane_ctype[256] = {
-/*	0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F			    */
-
-	0, 0, 0, 0, 0, 0, 0, 0, 0, S, S, 0, 0, S, 0, 0,		/*   0.. 15 */
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,		/*  16.. 31 */
-	PS,P, P, P, R, P, P, P, R, R, G, R, P, P, R, P,		/*  32.. 47 */
-	D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, G,		/*  48.. 63 */
-	P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  64.. 79 */
-	A, A, A, A, A, A, A, A, A, A, A, G, G, P, R, P,		/*  80.. 95 */
-	P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  96..111 */
-	A, A, A, A, A, A, A, A, A, A, A, R, R, P, P, 0,		/* 112..127 */
-	/* Nothing in the 128.. range */
-};
-
-const char *graph_line =
-	"_____________________________________________________________________"
-	"_____________________________________________________________________"
-	"_____________________________________________________________________";
-const char *graph_dotted_line =
-	"---------------------------------------------------------------------"
-	"---------------------------------------------------------------------"
-	"---------------------------------------------------------------------";
-const char *spaces =
-	"                                                                     "
-	"                                                                     "
-	"                                                                     ";
-const char *dots =
-	"....................................................................."
-	"....................................................................."
-	".....................................................................";
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index abd38ab..dbc772b 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1,16 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * CTF writing support via babeltrace.
  *
  * Copyright (C) 2014, Jiri Olsa <jolsa@redhat.com>
  * Copyright (C) 2014, Sebastian Andrzej Siewior <bigeasy@linutronix.de>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <babeltrace/ctf-writer/writer.h>
 #include <babeltrace/ctf-writer/clock.h>
 #include <babeltrace/ctf-writer/stream.h>
@@ -23,14 +23,14 @@
 #include "asm/bug.h"
 #include "data-convert-bt.h"
 #include "session.h"
-#include "util.h"
 #include "debug.h"
 #include "tool.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "machine.h"
 #include "config.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/err.h>
 
 #define pr_N(n, fmt, ...) \
 	eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
@@ -182,20 +182,20 @@
 }
 
 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
@@ -271,7 +271,7 @@
 				if (i > 0)
 					strncpy(buffer, string, i);
 			}
-			strncat(buffer + p, numstr, 4);
+			memcpy(buffer + p, numstr, 4);
 			p += 3;
 		}
 	}
@@ -287,7 +287,7 @@
 				      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;
@@ -304,20 +304,20 @@
 	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,
+		tmp_val = tep_read_number(fmtf->event->tep,
 					  data + offset, len);
 		offset = tmp_val;
 		len = offset >> 16;
 		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 @@
 	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);
@@ -348,16 +348,16 @@
 			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;
 
 			value_int = tep_read_number(
-					fmtf->event->pevent,
+					fmtf->event->tep,
 					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 @@
 			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 @@
 		}
 		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 @@
 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) {
@@ -414,11 +414,11 @@
 static int add_tracepoint_values(struct ctf_writer *cw,
 				 struct bt_ctf_event_class *event_class,
 				 struct bt_ctf_event *event,
-				 struct perf_evsel *evsel,
+				 struct 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,
@@ -585,10 +585,10 @@
 
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
-			      struct perf_evsel *evsel,
+			      struct evsel *evsel,
 			      struct perf_sample *sample)
 {
-	u64 type = evsel->attr.sample_type;
+	u64 type = evsel->core.attr.sample_type;
 	int ret;
 
 	/*
@@ -754,11 +754,11 @@
 }
 
 static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
-			  struct perf_evsel *evsel)
+			  struct evsel *evsel)
 {
 	int cpu = 0;
 
-	if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+	if (evsel->core.attr.sample_type & PERF_SAMPLE_CPU)
 		cpu = sample->cpu;
 
 	if (cpu > cw->stream_cnt) {
@@ -786,7 +786,7 @@
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *_event,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel,
+				struct evsel *evsel,
 				struct machine *machine __maybe_unused)
 {
 	struct convert *c = container_of(tool, struct convert, tool);
@@ -796,7 +796,7 @@
 	struct bt_ctf_event_class *event_class;
 	struct bt_ctf_event *event;
 	int ret;
-	unsigned long type = evsel->attr.sample_type;
+	unsigned long type = evsel->core.attr.sample_type;
 
 	if (WARN_ONCE(!priv, "Failed to setup all events.\n"))
 		return 0;
@@ -821,7 +821,7 @@
 	if (ret)
 		return -1;
 
-	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
 		ret = add_tracepoint_values(cw, event_class, event,
 					    evsel, sample);
 		if (ret)
@@ -970,7 +970,7 @@
 
 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 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 @@
 		 * 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) {
@@ -1052,11 +1052,11 @@
 }
 
 static int add_tracepoint_types(struct ctf_writer *cw,
-				struct perf_evsel *evsel,
+				struct 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);
@@ -1085,10 +1085,10 @@
 	return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
 }
 
-static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
+static int add_generic_types(struct ctf_writer *cw, struct evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
-	u64 type = evsel->attr.sample_type;
+	u64 type = evsel->core.attr.sample_type;
 
 	/*
 	 * missing:
@@ -1151,14 +1151,14 @@
 	return 0;
 }
 
-static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
+static int add_event(struct ctf_writer *cw, struct evsel *evsel)
 {
 	struct bt_ctf_event_class *event_class;
 	struct evsel_priv *priv;
 	const char *name = perf_evsel__name(evsel);
 	int ret;
 
-	pr("Adding event '%s' (type %d)\n", name, evsel->attr.type);
+	pr("Adding event '%s' (type %d)\n", name, evsel->core.attr.type);
 
 	event_class = bt_ctf_event_class_create(name);
 	if (!event_class)
@@ -1168,7 +1168,7 @@
 	if (ret)
 		goto err;
 
-	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
 		ret = add_tracepoint_types(cw, evsel, event_class);
 		if (ret)
 			goto err;
@@ -1202,8 +1202,8 @@
 
 static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct perf_evsel *evsel;
+	struct evlist *evlist = session->evlist;
+	struct evsel *evsel;
 	int ret;
 
 	evlist__for_each_entry(evlist, evsel) {
@@ -1309,8 +1309,8 @@
 
 static void cleanup_events(struct perf_session *session)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct perf_evsel *evsel;
+	struct evlist *evlist = session->evlist;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		struct evsel_priv *priv;
@@ -1320,7 +1320,7 @@
 		zfree(&evsel->priv);
 	}
 
-	perf_evlist__delete(evlist);
+	evlist__delete(evlist);
 	session->evlist = NULL;
 }
 
@@ -1354,7 +1354,7 @@
 	for (cpu = 0; cpu < cw->stream_cnt; cpu++)
 		ctf_stream__delete(cw->stream[cpu]);
 
-	free(cw->stream);
+	zfree(&cw->stream);
 }
 
 static int ctf_writer__setup_env(struct ctf_writer *cw,
@@ -1578,7 +1578,7 @@
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file.path = input,
+		.path	   = input,
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
@@ -1620,8 +1620,10 @@
 	err = -1;
 	/* perf.data session */
 	session = perf_session__new(&data, 0, &c.tool);
-	if (!session)
+	if (IS_ERR(session)) {
+		err = PTR_ERR(session);
 		goto free_writer;
+	}
 
 	if (c.queue_size) {
 		ordered_events__set_alloc_size(&session->ordered_events,
@@ -1650,7 +1652,7 @@
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
-		data.file.path, path);
+		data.path, path);
 
 	fprintf(stderr,
 		"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index d8cfc19..88fba2b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -1,16 +1,156 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
+#include <asm/bug.h>
+#include <dirent.h>
 
 #include "data.h"
-#include "util.h"
+#include "util.h" // rm_rf_perf_data()
 #include "debug.h"
+#include "header.h"
+#include <internal/lib.h>
+
+static void close_dir(struct perf_data_file *files, int nr)
+{
+	while (--nr >= 1) {
+		close(files[nr].fd);
+		zfree(&files[nr].path);
+	}
+	free(files);
+}
+
+void perf_data__close_dir(struct perf_data *data)
+{
+	close_dir(data->dir.files, data->dir.nr);
+}
+
+int perf_data__create_dir(struct perf_data *data, int nr)
+{
+	struct perf_data_file *files = NULL;
+	int i, ret = -1;
+
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
+	files = zalloc(nr * sizeof(*files));
+	if (!files)
+		return -ENOMEM;
+
+	data->dir.version = PERF_DIR_VERSION;
+	data->dir.files   = files;
+	data->dir.nr      = nr;
+
+	for (i = 0; i < nr; i++) {
+		struct perf_data_file *file = &files[i];
+
+		if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0)
+			goto out_err;
+
+		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
+		if (ret < 0)
+			goto out_err;
+
+		file->fd = ret;
+	}
+
+	return 0;
+
+out_err:
+	close_dir(files, i);
+	return ret;
+}
+
+int perf_data__open_dir(struct perf_data *data)
+{
+	struct perf_data_file *files = NULL;
+	struct dirent *dent;
+	int ret = -1;
+	DIR *dir;
+	int nr = 0;
+
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
+	/* The version is provided by DIR_FORMAT feature. */
+	if (WARN_ON(data->dir.version != PERF_DIR_VERSION))
+		return -1;
+
+	dir = opendir(data->path);
+	if (!dir)
+		return -EINVAL;
+
+	while ((dent = readdir(dir)) != NULL) {
+		struct perf_data_file *file;
+		char path[PATH_MAX];
+		struct stat st;
+
+		snprintf(path, sizeof(path), "%s/%s", data->path, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4))
+			continue;
+
+		ret = -ENOMEM;
+
+		file = realloc(files, (nr + 1) * sizeof(*files));
+		if (!file)
+			goto out_err;
+
+		files = file;
+		file = &files[nr++];
+
+		file->path = strdup(path);
+		if (!file->path)
+			goto out_err;
+
+		ret = open(file->path, O_RDONLY);
+		if (ret < 0)
+			goto out_err;
+
+		file->fd = ret;
+		file->size = st.st_size;
+	}
+
+	if (!files)
+		return -EINVAL;
+
+	data->dir.files = files;
+	data->dir.nr    = nr;
+	return 0;
+
+out_err:
+	close_dir(files, nr);
+	return ret;
+}
+
+int perf_data__update_dir(struct perf_data *data)
+{
+	int i;
+
+	if (WARN_ON(!data->is_dir))
+		return -EINVAL;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		struct perf_data_file *file = &data->dir.files[i];
+		struct stat st;
+
+		if (fstat(file->fd, &st))
+			return -1;
+
+		file->size = st.st_size;
+	}
+
+	return 0;
+}
 
 static bool check_pipe(struct perf_data *data)
 {
@@ -19,11 +159,11 @@
 	int fd = perf_data__is_read(data) ?
 		 STDIN_FILENO : STDOUT_FILENO;
 
-	if (!data->file.path) {
+	if (!data->path) {
 		if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
 			is_pipe = true;
 	} else {
-		if (!strcmp(data->file.path, "-"))
+		if (!strcmp(data->path, "-"))
 			is_pipe = true;
 	}
 
@@ -37,18 +177,46 @@
 {
 	struct stat st;
 
-	if (!stat(data->file.path, &st) && st.st_size) {
-		/* TODO check errors properly */
+	if (perf_data__is_read(data))
+		return 0;
+
+	if (!stat(data->path, &st) && st.st_size) {
 		char oldname[PATH_MAX];
+		int ret;
+
 		snprintf(oldname, sizeof(oldname), "%s.old",
-			 data->file.path);
-		unlink(oldname);
-		rename(data->file.path, oldname);
+			 data->path);
+
+		ret = rm_rf_perf_data(oldname);
+		if (ret) {
+			pr_err("Can't remove old data: %s (%s)\n",
+			       ret == -2 ?
+			       "Unknown file found" : strerror(errno),
+			       oldname);
+			return -1;
+		}
+
+		if (rename(data->path, oldname)) {
+			pr_err("Can't move data: %s (%s to %s)\n",
+			       strerror(errno),
+			       data->path, oldname);
+			return -1;
+		}
 	}
 
 	return 0;
 }
 
+static bool is_dir(struct perf_data *data)
+{
+	struct stat st;
+
+	if (stat(data->path, &st))
+		return false;
+
+	return (st.st_mode & S_IFMT) == S_IFDIR;
+}
+
 static int open_file_read(struct perf_data *data)
 {
 	struct stat st;
@@ -82,7 +250,7 @@
 		goto out_close;
 	}
 
-	data->size = st.st_size;
+	data->file.size = st.st_size;
 	return fd;
 
  out_close:
@@ -95,9 +263,6 @@
 	int fd;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (check_backup(data))
-		return -1;
-
 	fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
 		  S_IRUSR|S_IWUSR);
 
@@ -115,8 +280,46 @@
 	fd = perf_data__is_read(data) ?
 	     open_file_read(data) : open_file_write(data);
 
+	if (fd < 0) {
+		zfree(&data->file.path);
+		return -1;
+	}
+
 	data->file.fd = fd;
-	return fd < 0 ? -1 : 0;
+	return 0;
+}
+
+static int open_file_dup(struct perf_data *data)
+{
+	data->file.path = strdup(data->path);
+	if (!data->file.path)
+		return -ENOMEM;
+
+	return open_file(data);
+}
+
+static int open_dir(struct perf_data *data)
+{
+	int ret;
+
+	/*
+	 * So far we open only the header, so we can read the data version and
+	 * layout.
+	 */
+	if (asprintf(&data->file.path, "%s/header", data->path) < 0)
+		return -1;
+
+	if (perf_data__is_write(data) &&
+	    mkdir(data->path, S_IRWXU) < 0)
+		return -1;
+
+	ret = open_file(data);
+
+	/* Cleanup whatever we managed to create so far. */
+	if (ret && perf_data__is_write(data))
+		rm_rf_perf_data(data->path);
+
+	return ret;
 }
 
 int perf_data__open(struct perf_data *data)
@@ -124,14 +327,25 @@
 	if (check_pipe(data))
 		return 0;
 
-	if (!data->file.path)
-		data->file.path = "perf.data";
+	if (!data->path)
+		data->path = "perf.data";
 
-	return open_file(data);
+	if (check_backup(data))
+		return -1;
+
+	if (perf_data__is_read(data))
+		data->is_dir = is_dir(data);
+
+	return perf_data__is_dir(data) ?
+	       open_dir(data) : open_file_dup(data);
 }
 
 void perf_data__close(struct perf_data *data)
 {
+	if (perf_data__is_dir(data))
+		perf_data__close_dir(data);
+
+	zfree(&data->file.path);
 	close(data->file.fd);
 }
 
@@ -149,9 +363,9 @@
 
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
-			   size_t pos, bool at_exit)
+			   size_t pos, bool at_exit,
+			   char **new_filepath)
 {
-	char *new_filepath;
 	int ret;
 
 	if (check_pipe(data))
@@ -159,15 +373,15 @@
 	if (perf_data__is_read(data))
 		return -EINVAL;
 
-	if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
+	if (asprintf(new_filepath, "%s.%s", data->path, postfix) < 0)
 		return -ENOMEM;
 
 	/*
 	 * Only fire a warning, don't return error, continue fill
 	 * original file.
 	 */
-	if (rename(data->file.path, new_filepath))
-		pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
+	if (rename(data->path, *new_filepath))
+		pr_warning("Failed to rename %s to %s\n", data->path, *new_filepath);
 
 	if (!at_exit) {
 		close(data->file.fd);
@@ -184,6 +398,22 @@
 	}
 	ret = data->file.fd;
 out:
-	free(new_filepath);
 	return ret;
 }
+
+unsigned long perf_data__size(struct perf_data *data)
+{
+	u64 size = data->file.size;
+	int i;
+
+	if (!data->is_dir)
+		return size;
+
+	for (i = 0; i < data->dir.nr; i++) {
+		struct perf_data_file *file = &data->dir.files[i];
+
+		size += file->size;
+	}
+
+	return size;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 4828f7f..259868a 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,16 +10,24 @@
 };
 
 struct perf_data_file {
-	const char	*path;
+	char		*path;
 	int		 fd;
+	unsigned long	 size;
 };
 
 struct perf_data {
+	const char		*path;
 	struct perf_data_file	 file;
 	bool			 is_pipe;
+	bool			 is_dir;
 	bool			 force;
-	unsigned long		 size;
 	enum perf_data_mode	 mode;
+
+	struct {
+		u64			 version;
+		struct perf_data_file	*files;
+		int			 nr;
+	} dir;
 };
 
 static inline bool perf_data__is_read(struct perf_data *data)
@@ -37,16 +45,16 @@
 	return data->is_pipe;
 }
 
+static inline bool perf_data__is_dir(struct perf_data *data)
+{
+	return data->is_dir;
+}
+
 static inline int perf_data__fd(struct perf_data *data)
 {
 	return data->file.fd;
 }
 
-static inline unsigned long perf_data__size(struct perf_data *data)
-{
-	return data->size;
-}
-
 int perf_data__open(struct perf_data *data);
 void perf_data__close(struct perf_data *data);
 ssize_t perf_data__write(struct perf_data *data,
@@ -62,5 +70,11 @@
  */
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
-			   size_t pos, bool at_exit);
+			   size_t pos, bool at_exit, char **new_filepath);
+
+int perf_data__create_dir(struct perf_data *data, int nr);
+int perf_data__open_dir(struct perf_data *data);
+void perf_data__close_dir(struct perf_data *data);
+int perf_data__update_dir(struct perf_data *data);
+unsigned long perf_data__size(struct perf_data *data);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 7123746..752227b 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -1,101 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * db-export.c: Support for exporting data suitable for import to a database
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <errno.h>
+#include <stdlib.h>
 
+#include "dso.h"
 #include "evsel.h"
 #include "machine.h"
 #include "thread.h"
 #include "comm.h"
 #include "symbol.h"
+#include "map.h"
 #include "event.h"
-#include "util.h"
 #include "thread-stack.h"
 #include "callchain.h"
 #include "call-path.h"
 #include "db-export.h"
-
-struct deferred_export {
-	struct list_head node;
-	struct comm *comm;
-};
-
-static int db_export__deferred(struct db_export *dbe)
-{
-	struct deferred_export *de;
-	int err;
-
-	while (!list_empty(&dbe->deferred)) {
-		de = list_entry(dbe->deferred.next, struct deferred_export,
-				node);
-		err = dbe->export_comm(dbe, de->comm);
-		list_del(&de->node);
-		free(de);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static void db_export__free_deferred(struct db_export *dbe)
-{
-	struct deferred_export *de;
-
-	while (!list_empty(&dbe->deferred)) {
-		de = list_entry(dbe->deferred.next, struct deferred_export,
-				node);
-		list_del(&de->node);
-		free(de);
-	}
-}
-
-static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
-{
-	struct deferred_export *de;
-
-	de = zalloc(sizeof(struct deferred_export));
-	if (!de)
-		return -ENOMEM;
-
-	de->comm = comm;
-	list_add_tail(&de->node, &dbe->deferred);
-
-	return 0;
-}
+#include <linux/zalloc.h>
 
 int db_export__init(struct db_export *dbe)
 {
 	memset(dbe, 0, sizeof(struct db_export));
-	INIT_LIST_HEAD(&dbe->deferred);
 	return 0;
 }
 
-int db_export__flush(struct db_export *dbe)
-{
-	return db_export__deferred(dbe);
-}
-
 void db_export__exit(struct db_export *dbe)
 {
-	db_export__free_deferred(dbe);
 	call_return_processor__free(dbe->crp);
 	dbe->crp = NULL;
 }
 
-int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
+int db_export__evsel(struct db_export *dbe, struct evsel *evsel)
 {
 	if (evsel->db_id)
 		return 0;
@@ -122,71 +60,73 @@
 }
 
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-		      struct machine *machine, struct comm *comm)
+		      struct machine *machine, struct thread *main_thread)
 {
-	struct thread *main_thread;
 	u64 main_thread_db_id = 0;
-	int err;
 
 	if (thread->db_id)
 		return 0;
 
 	thread->db_id = ++dbe->thread_last_db_id;
 
-	if (thread->pid_ != -1) {
-		if (thread->pid_ == thread->tid) {
-			main_thread = thread;
-		} else {
-			main_thread = machine__findnew_thread(machine,
-							      thread->pid_,
-							      thread->pid_);
-			if (!main_thread)
-				return -ENOMEM;
-			err = db_export__thread(dbe, main_thread, machine,
-						comm);
-			if (err)
-				goto out_put;
-			if (comm) {
-				err = db_export__comm_thread(dbe, comm, thread);
-				if (err)
-					goto out_put;
-			}
-		}
+	if (main_thread)
 		main_thread_db_id = main_thread->db_id;
-		if (main_thread != thread)
-			thread__put(main_thread);
-	}
 
 	if (dbe->export_thread)
 		return dbe->export_thread(dbe, thread, main_thread_db_id,
 					  machine);
 
 	return 0;
+}
 
-out_put:
-	thread__put(main_thread);
-	return err;
+static int __db_export__comm(struct db_export *dbe, struct comm *comm,
+			     struct thread *thread)
+{
+	comm->db_id = ++dbe->comm_last_db_id;
+
+	if (dbe->export_comm)
+		return dbe->export_comm(dbe, comm, thread);
+
+	return 0;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-		    struct thread *main_thread)
+		    struct thread *thread)
+{
+	if (comm->db_id)
+		return 0;
+
+	return __db_export__comm(dbe, comm, thread);
+}
+
+/*
+ * Export the "exec" comm. The "exec" comm is the program / application command
+ * name at the time it first executes. It is used to group threads for the same
+ * program. Note that the main thread pid (or thread group id tgid) cannot be
+ * used because it does not change when a new program is exec'ed.
+ */
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+			 struct thread *main_thread)
 {
 	int err;
 
 	if (comm->db_id)
 		return 0;
 
-	comm->db_id = ++dbe->comm_last_db_id;
+	err = __db_export__comm(dbe, comm, main_thread);
+	if (err)
+		return err;
 
-	if (dbe->export_comm) {
-		if (main_thread->comm_set)
-			err = dbe->export_comm(dbe, comm);
-		else
-			err = db_export__defer_comm(dbe, comm);
-		if (err)
-			return err;
-	}
-
+	/*
+	 * Record the main thread for this comm. Note that the main thread can
+	 * have many "exec" comms because there will be a new one every time it
+	 * exec's. An "exec" comm however will only ever have 1 main thread.
+	 * That is different to any other threads for that same program because
+	 * exec() will effectively kill them, so the relationship between the
+	 * "exec" comm and non-main threads is 1-to-1. That is why
+	 * db_export__comm_thread() is called here for the main thread, but it
+	 * is called for non-main threads when they are exported.
+	 */
 	return db_export__comm_thread(dbe, comm, main_thread);
 }
 
@@ -270,7 +210,7 @@
 					       struct machine *machine,
 					       struct thread *thread,
 					       struct perf_sample *sample,
-					       struct perf_evsel *evsel)
+					       struct evsel *evsel)
 {
 	u64 kernel_start = machine__kernel_start(machine);
 	struct call_path *current = &dbe->cpr->call_path;
@@ -347,11 +287,65 @@
 	return 0;
 }
 
+static int db_export__threads(struct db_export *dbe, struct thread *thread,
+			      struct thread *main_thread,
+			      struct machine *machine, struct comm **comm_ptr)
+{
+	struct comm *comm = NULL;
+	struct comm *curr_comm;
+	int err;
+
+	if (main_thread) {
+		/*
+		 * A thread has a reference to the main thread, so export the
+		 * main thread first.
+		 */
+		err = db_export__thread(dbe, main_thread, machine, main_thread);
+		if (err)
+			return err;
+		/*
+		 * Export comm before exporting the non-main thread because
+		 * db_export__comm_thread() can be called further below.
+		 */
+		comm = machine__thread_exec_comm(machine, main_thread);
+		if (comm) {
+			err = db_export__exec_comm(dbe, comm, main_thread);
+			if (err)
+				return err;
+			*comm_ptr = comm;
+		}
+	}
+
+	if (thread != main_thread) {
+		/*
+		 * For a non-main thread, db_export__comm_thread() must be
+		 * called only if thread has not previously been exported.
+		 */
+		bool export_comm_thread = comm && !thread->db_id;
+
+		err = db_export__thread(dbe, thread, machine, main_thread);
+		if (err)
+			return err;
+
+		if (export_comm_thread) {
+			err = db_export__comm_thread(dbe, comm, thread);
+			if (err)
+				return err;
+		}
+	}
+
+	curr_comm = thread__comm(thread);
+	if (curr_comm)
+		return db_export__comm(dbe, curr_comm, thread);
+
+	return 0;
+}
+
 int db_export__sample(struct db_export *dbe, union perf_event *event,
-		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct perf_sample *sample, struct evsel *evsel,
 		      struct addr_location *al)
 {
-	struct thread* thread = al->thread;
+	struct thread *thread = al->thread;
 	struct export_sample es = {
 		.event = event,
 		.sample = sample,
@@ -371,19 +365,13 @@
 		return err;
 
 	main_thread = thread__main_thread(al->machine, thread);
-	if (main_thread)
-		comm = machine__thread_exec_comm(al->machine, main_thread);
 
-	err = db_export__thread(dbe, thread, al->machine, comm);
+	err = db_export__threads(dbe, thread, main_thread, al->machine, &comm);
 	if (err)
 		goto out_put;
 
-	if (comm) {
-		err = db_export__comm(dbe, comm, main_thread);
-		if (err)
-			goto out_put;
+	if (comm)
 		es.comm_db_id = comm->db_id;
-	}
 
 	es.db_id = ++dbe->sample_last_db_id;
 
@@ -401,8 +389,8 @@
 		}
 	}
 
-	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	    sample_addr_correlates_sym(&evsel->attr)) {
+	if ((evsel->core.attr.sample_type & PERF_SAMPLE_ADDR) &&
+	    sample_addr_correlates_sym(&evsel->core.attr)) {
 		struct addr_location addr_al;
 
 		thread__resolve(thread, &addr_al, sample);
@@ -463,6 +451,28 @@
 		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;
 }
 
@@ -487,21 +497,115 @@
 	return 0;
 }
 
-int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+int db_export__call_return(struct db_export *dbe, struct call_return *cr,
+			   u64 *parent_db_id)
 {
 	int err;
 
-	if (cr->db_id)
-		return 0;
-
 	err = db_export__call_path(dbe, cr->cp);
 	if (err)
 		return err;
 
-	cr->db_id = ++dbe->call_return_last_db_id;
+	if (!cr->db_id)
+		cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (parent_db_id) {
+		if (!*parent_db_id)
+			*parent_db_id = ++dbe->call_return_last_db_id;
+		cr->parent_db_id = *parent_db_id;
+	}
 
 	if (dbe->export_call_return)
 		return dbe->export_call_return(dbe, cr);
 
 	return 0;
 }
+
+static int db_export__pid_tid(struct db_export *dbe, struct machine *machine,
+			      pid_t pid, pid_t tid, u64 *db_id,
+			      struct comm **comm_ptr, bool *is_idle)
+{
+	struct thread *thread = machine__find_thread(machine, pid, tid);
+	struct thread *main_thread;
+	int err = 0;
+
+	if (!thread || !thread->comm_set)
+		goto out_put;
+
+	*is_idle = !thread->pid_ && !thread->tid;
+
+	main_thread = thread__main_thread(machine, thread);
+
+	err = db_export__threads(dbe, thread, main_thread, machine, comm_ptr);
+
+	*db_id = thread->db_id;
+
+	thread__put(main_thread);
+out_put:
+	thread__put(thread);
+
+	return err;
+}
+
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct machine *machine)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	bool out_preempt = out &&
+		(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT);
+	int flags = out | (out_preempt << 1);
+	bool is_idle_a = false, is_idle_b = false;
+	u64 th_a_id = 0, th_b_id = 0;
+	u64 comm_out_id, comm_in_id;
+	struct comm *comm_a = NULL;
+	struct comm *comm_b = NULL;
+	u64 th_out_id, th_in_id;
+	u64 db_id;
+	int err;
+
+	err = db_export__machine(dbe, machine);
+	if (err)
+		return err;
+
+	err = db_export__pid_tid(dbe, machine, sample->pid, sample->tid,
+				 &th_a_id, &comm_a, &is_idle_a);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+		pid_t pid = event->context_switch.next_prev_pid;
+		pid_t tid = event->context_switch.next_prev_tid;
+
+		err = db_export__pid_tid(dbe, machine, pid, tid, &th_b_id,
+					 &comm_b, &is_idle_b);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Do not export if both threads are unknown (i.e. not being traced),
+	 * or one is unknown and the other is the idle task.
+	 */
+	if ((!th_a_id || is_idle_a) && (!th_b_id || is_idle_b))
+		return 0;
+
+	db_id = ++dbe->context_switch_last_db_id;
+
+	if (out) {
+		th_out_id   = th_a_id;
+		th_in_id    = th_b_id;
+		comm_out_id = comm_a ? comm_a->db_id : 0;
+		comm_in_id  = comm_b ? comm_b->db_id : 0;
+	} else {
+		th_out_id   = th_b_id;
+		th_in_id    = th_a_id;
+		comm_out_id = comm_b ? comm_b->db_id : 0;
+		comm_in_id  = comm_a ? comm_a->db_id : 0;
+	}
+
+	if (dbe->export_context_switch)
+		return dbe->export_context_switch(dbe, db_id, machine, sample,
+						  th_out_id, comm_out_id,
+						  th_in_id, comm_in_id, flags);
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index 67bc6b8..9c3d38f 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * db-export.h: Support for exporting data suitable for import to a database
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef __PERF_DB_EXPORT_H
@@ -19,7 +10,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 
-struct perf_evsel;
+struct evsel;
 struct machine;
 struct thread;
 struct comm;
@@ -34,7 +25,7 @@
 struct export_sample {
 	union perf_event	*event;
 	struct perf_sample	*sample;
-	struct perf_evsel	*evsel;
+	struct evsel		*evsel;
 	struct addr_location	*al;
 	u64			db_id;
 	u64			comm_db_id;
@@ -48,11 +39,12 @@
 };
 
 struct db_export {
-	int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel);
+	int (*export_evsel)(struct db_export *dbe, struct evsel *evsel);
 	int (*export_machine)(struct db_export *dbe, struct machine *machine);
 	int (*export_thread)(struct db_export *dbe, struct thread *thread,
 			     u64 main_thread_db_id, struct machine *machine);
-	int (*export_comm)(struct db_export *dbe, struct comm *comm);
+	int (*export_comm)(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread);
 	int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
 				  struct comm *comm, struct thread *thread);
 	int (*export_dso)(struct db_export *dbe, struct dso *dso,
@@ -65,6 +57,11 @@
 	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
 	int (*export_call_return)(struct db_export *dbe,
 				  struct call_return *cr);
+	int (*export_context_switch)(struct db_export *dbe, u64 db_id,
+				     struct machine *machine,
+				     struct perf_sample *sample,
+				     u64 th_out_id, u64 comm_out_id,
+				     u64 th_in_id, u64 comm_in_id, int flags);
 	struct call_return_processor *crp;
 	struct call_path_root *cpr;
 	u64 evsel_last_db_id;
@@ -77,18 +74,19 @@
 	u64 sample_last_db_id;
 	u64 call_path_last_db_id;
 	u64 call_return_last_db_id;
-	struct list_head deferred;
+	u64 context_switch_last_db_id;
 };
 
 int db_export__init(struct db_export *dbe);
-int db_export__flush(struct db_export *dbe);
 void db_export__exit(struct db_export *dbe);
-int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
+int db_export__evsel(struct db_export *dbe, struct evsel *evsel);
 int db_export__machine(struct db_export *dbe, struct machine *machine);
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-		      struct machine *machine, struct comm *comm);
+		      struct machine *machine, struct thread *main_thread);
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-		    struct thread *main_thread);
+		    struct thread *thread);
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+			 struct thread *main_thread);
 int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
 			   struct thread *thread);
 int db_export__dso(struct db_export *dbe, struct dso *dso,
@@ -98,12 +96,15 @@
 int db_export__branch_type(struct db_export *dbe, u32 branch_type,
 			   const char *name);
 int db_export__sample(struct db_export *dbe, union perf_event *event,
-		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct perf_sample *sample, struct evsel *evsel,
 		      struct addr_location *al);
 
 int db_export__branch_types(struct db_export *dbe);
 
 int db_export__call_path(struct db_export *dbe, struct call_path *cp);
-int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr,
+			   u64 *parent_db_id);
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct machine *machine);
 
 #endif
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 3d64596..e55114f 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -1,27 +1,27 @@
 // SPDX-License-Identifier: GPL-2.0
 /* For general debugging purposes */
 
-#include "../perf.h"
-
 #include <inttypes.h>
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/wait.h>
 #include <api/debug.h>
+#include <linux/kernel.h>
 #include <linux/time64.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
-#include "cache.h"
 #include "color.h"
 #include "event.h"
 #include "debug.h"
 #include "print_binary.h"
-#include "util.h"
 #include "target.h"
+#include "ui/helpline.h"
+#include "ui/ui.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 int verbose;
 bool dump_trace = false, quiet = false;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 77445df..d25ae1c 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,13 +3,9 @@
 #ifndef __PERF_DEBUG_H
 #define __PERF_DEBUG_H
 
+#include <stdarg.h>
 #include <stdbool.h>
-#include <string.h>
 #include <linux/compiler.h>
-#include "event.h"
-#include "../ui/helpline.h"
-#include "../ui/progress.h"
-#include "../ui/util.h"
 
 extern int verbose;
 extern bool quiet, dump_trace;
@@ -42,6 +38,8 @@
 
 #define STRERR_BUFSIZE	128	/* For the buffer size of str_error_r */
 
+union perf_event;
+
 int dump_printf(const char *fmt, ...) __printf(1, 2);
 void trace_event(union perf_event *event);
 
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
index e4c4867..6fb7f34 100644
--- a/tools/perf/util/demangle-java.c
+++ b/tools/perf/util/demangle-java.c
@@ -1,14 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
-#include "util.h"
-#include "debug.h"
 #include "symbol.h"
 
 #include "demangle-java.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/kernel.h>
 
 enum {
 	MODE_PREFIX = 0,
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
index 423afbb..a659fc6 100644
--- a/tools/perf/util/demangle-rust.c
+++ b/tools/perf/util/demangle-rust.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <string.h>
-#include "util.h"
 #include "debug.h"
 
 #include "demangle-rust.h"
diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c
deleted file mode 100644
index eec7542..0000000
--- a/tools/perf/util/drv_configs.c
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * drv_configs.h: Interface to apply PMU specific configuration
- * Copyright (c) 2016-2018, Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- */
-
-#include "drv_configs.h"
-#include "evlist.h"
-#include "evsel.h"
-#include "pmu.h"
-#include <errno.h>
-
-static int
-perf_evsel__apply_drv_configs(struct perf_evsel *evsel,
-			      struct perf_evsel_config_term **err_term)
-{
-	bool found = false;
-	int err = 0;
-	struct perf_evsel_config_term *term;
-	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
-		if (pmu->type == evsel->attr.type) {
-			found = true;
-			break;
-		}
-
-	list_for_each_entry(term, &evsel->config_terms, list) {
-		if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG)
-			continue;
-
-		/*
-		 * We have a configuration term, report an error if we
-		 * can't find the PMU or if the PMU driver doesn't support
-		 * cmd line driver configuration.
-		 */
-		if (!found || !pmu->set_drv_config) {
-			err = -EINVAL;
-			*err_term = term;
-			break;
-		}
-
-		err = pmu->set_drv_config(term);
-		if (err) {
-			*err_term = term;
-			break;
-		}
-	}
-
-	return err;
-}
-
-int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
-				   struct perf_evsel **err_evsel,
-				   struct perf_evsel_config_term **err_term)
-{
-	struct perf_evsel *evsel;
-	int err = 0;
-
-	evlist__for_each_entry(evlist, evsel) {
-		err = perf_evsel__apply_drv_configs(evsel, err_term);
-		if (err) {
-			*err_evsel = evsel;
-			break;
-		}
-	}
-
-	return err;
-}
diff --git a/tools/perf/util/drv_configs.h b/tools/perf/util/drv_configs.h
deleted file mode 100644
index 32bc9ba..0000000
--- a/tools/perf/util/drv_configs.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * drv_configs.h: Interface to apply PMU specific configuration
- * Copyright (c) 2016-2018, Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- */
-
-#ifndef __PERF_DRV_CONFIGS_H
-#define __PERF_DRV_CONFIGS_H
-
-#include "drv_configs.h"
-#include "evlist.h"
-#include "evsel.h"
-
-int perf_evlist__apply_drv_configs(struct perf_evlist *evlist,
-				   struct perf_evsel **err_evsel,
-				   struct perf_evsel_config_term **term);
-#endif
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index bbed90e..e11ddf8 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <asm/bug.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
@@ -8,14 +10,21 @@
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <stdlib.h>
+#include <bpf/libbpf.h>
+#include "bpf-event.h"
 #include "compress.h"
+#include "env.h"
+#include "namespaces.h"
 #include "path.h"
+#include "map.h"
 #include "symbol.h"
 #include "srcline.h"
 #include "dso.h"
+#include "dsos.h"
 #include "machine.h"
 #include "auxtrace.h"
-#include "util.h"
+#include "util.h" /* O_CLOEXEC for older systems */
 #include "debug.h"
 #include "string2.h"
 #include "vdso.h"
@@ -181,6 +190,7 @@
 	case DSO_BINARY_TYPE__KALLSYMS:
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 		ret = -1;
 		break;
@@ -295,7 +305,7 @@
 		unlink(tmpbuf);
 
 	if (pathname && (fd >= 0))
-		strncpy(pathname, tmpbuf, len);
+		strlcpy(pathname, tmpbuf, len);
 
 	return fd;
 }
@@ -388,7 +398,7 @@
 				return -ENOMEM;
 		}
 
-		strxfrchar(m->name, '-', '_');
+		strreplace(m->name, '-', '_');
 	}
 
 	return 0;
@@ -426,7 +436,7 @@
 
 static void dso__list_del(struct dso *dso)
 {
-	list_del(&dso->data.open_entry);
+	list_del_init(&dso->data.open_entry);
 	WARN_ONCE(dso__data_open_cnt <= 0,
 		  "DSO data fd counter out of bounds.");
 	dso__data_open_cnt--;
@@ -702,6 +712,44 @@
 	return false;
 }
 
+static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
+{
+	struct bpf_prog_info_node *node;
+	ssize_t size = DSO__DATA_CACHE_SIZE;
+	u64 len;
+	u8 *buf;
+
+	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	if (!node || !node->info_linear) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		return -1;
+	}
+
+	len = node->info_linear->info.jited_prog_len;
+	buf = (u8 *)(uintptr_t)node->info_linear->info.jited_prog_insns;
+
+	if (offset >= len)
+		return -1;
+
+	size = (ssize_t)min(len - offset, (u64)size);
+	memcpy(data, buf + offset, size);
+	return size;
+}
+
+static int bpf_size(struct dso *dso)
+{
+	struct bpf_prog_info_node *node;
+
+	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	if (!node || !node->info_linear) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		return -1;
+	}
+
+	dso->data.file_size = node->info_linear->info.jited_prog_len;
+	return 0;
+}
+
 static void
 dso_cache__free(struct dso *dso)
 {
@@ -790,48 +838,53 @@
 	return cache_size;
 }
 
+static ssize_t file_read(struct dso *dso, struct machine *machine,
+			 u64 offset, char *data)
+{
+	ssize_t ret;
+
+	pthread_mutex_lock(&dso__data_open_lock);
+
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		ret = -errno;
+		goto out;
+	}
+
+	ret = pread(dso->data.fd, data, DSO__DATA_CACHE_SIZE, offset);
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
+}
+
 static ssize_t
 dso_cache__read(struct dso *dso, struct machine *machine,
 		u64 offset, u8 *data, ssize_t size)
 {
+	u64 cache_offset = offset & DSO__DATA_CACHE_MASK;
 	struct dso_cache *cache;
 	struct dso_cache *old;
 	ssize_t ret;
 
-	do {
-		u64 cache_offset;
+	cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+	if (!cache)
+		return -ENOMEM;
 
-		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
-		if (!cache)
-			return -ENOMEM;
-
-		pthread_mutex_lock(&dso__data_open_lock);
-
-		/*
-		 * dso->data.fd might be closed if other thread opened another
-		 * file (dso) due to open file limit (RLIMIT_NOFILE).
-		 */
-		try_to_open_dso(dso, machine);
-
-		if (dso->data.fd < 0) {
-			ret = -errno;
-			dso->data.status = DSO_DATA_STATUS_ERROR;
-			break;
-		}
-
-		cache_offset = offset & DSO__DATA_CACHE_MASK;
-
-		ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
-		if (ret <= 0)
-			break;
-
-		cache->offset = cache_offset;
-		cache->size   = ret;
-	} while (0);
-
-	pthread_mutex_unlock(&dso__data_open_lock);
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		ret = bpf_read(dso, cache_offset, cache->data);
+	else
+		ret = file_read(dso, machine, cache_offset, cache->data);
 
 	if (ret > 0) {
+		cache->offset = cache_offset;
+		cache->size   = ret;
+
 		old = dso_cache__insert(dso, cache);
 		if (old) {
 			/* we lose the race */
@@ -894,18 +947,12 @@
 	return r;
 }
 
-static int data_file_size(struct dso *dso, struct machine *machine)
+static int file_size(struct dso *dso, struct machine *machine)
 {
 	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (dso->data.file_size)
-		return 0;
-
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
@@ -934,6 +981,20 @@
 	return ret;
 }
 
+int dso__data_file_size(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.file_size)
+		return 0;
+
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return bpf_size(dso);
+
+	return file_size(dso, machine);
+}
+
 /**
  * dso__data_size - Return dso data size
  * @dso: dso object
@@ -943,7 +1004,7 @@
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	if (data_file_size(dso, machine))
+	if (dso__data_file_size(dso, machine))
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
@@ -953,7 +1014,7 @@
 static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
 				u64 offset, u8 *data, ssize_t size)
 {
-	if (data_file_size(dso, machine))
+	if (dso__data_file_size(dso, machine))
 		return -1;
 
 	/* Check the offset sanity. */
@@ -1035,66 +1096,6 @@
 	return dso;
 }
 
-/*
- * Find a matching entry and/or link current entry to RB tree.
- * Either one of the dso or name parameter must be non-NULL or the
- * function will not work.
- */
-static struct dso *__dso__findlink_by_longname(struct rb_root *root,
-					       struct dso *dso, const char *name)
-{
-	struct rb_node **p = &root->rb_node;
-	struct rb_node  *parent = NULL;
-
-	if (!name)
-		name = dso->long_name;
-	/*
-	 * Find node with the matching name
-	 */
-	while (*p) {
-		struct dso *this = rb_entry(*p, struct dso, rb_node);
-		int rc = strcmp(name, this->long_name);
-
-		parent = *p;
-		if (rc == 0) {
-			/*
-			 * In case the new DSO is a duplicate of an existing
-			 * one, print a one-time warning & put the new entry
-			 * at the end of the list of duplicates.
-			 */
-			if (!dso || (dso == this))
-				return this;	/* Find matching dso */
-			/*
-			 * The core kernel DSOs may have duplicated long name.
-			 * In this case, the short name should be different.
-			 * Comparing the short names to differentiate the DSOs.
-			 */
-			rc = strcmp(dso->short_name, this->short_name);
-			if (rc == 0) {
-				pr_err("Duplicated dso name: %s\n", name);
-				return NULL;
-			}
-		}
-		if (rc < 0)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
-	}
-	if (dso) {
-		/* Add new node and rebalance tree */
-		rb_link_node(&dso->rb_node, parent, p);
-		rb_insert_color(&dso->rb_node, root);
-		dso->root = root;
-	}
-	return NULL;
-}
-
-static inline struct dso *__dso__find_by_longname(struct rb_root *root,
-						  const char *name)
-{
-	return __dso__findlink_by_longname(root, NULL, name);
-}
-
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	struct rb_root *root = dso->root;
@@ -1108,7 +1109,7 @@
 	if (root) {
 		rb_erase(&dso->rb_node, root);
 		/*
-		 * __dso__findlink_by_longname() isn't guaranteed to add it
+		 * __dsos__findnew_link_by_longname() isn't guaranteed to add it
 		 * back, so a clean removal is required here.
 		 */
 		RB_CLEAR_NODE(&dso->rb_node);
@@ -1120,7 +1121,7 @@
 	dso->long_name_allocated = name_allocated;
 
 	if (root)
-		__dso__findlink_by_longname(root, dso, NULL);
+		__dsos__findnew_link_by_longname(root, dso, NULL);
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
@@ -1136,32 +1137,6 @@
 	dso->short_name_allocated = name_allocated;
 }
 
-static void dso__set_basename(struct dso *dso)
-{
-       /*
-        * basename() may modify path buffer, so we must pass
-        * a copy.
-        */
-       char *base, *lname = strdup(dso->long_name);
-
-       if (!lname)
-               return;
-
-       /*
-        * basename() may return a pointer to internal
-        * storage which is reused in subsequent calls
-        * so copy the result.
-        */
-       base = strdup(basename(lname));
-
-       free(lname);
-
-       if (!base)
-               return;
-
-       dso__set_short_name(dso, base, true);
-}
-
 int dso__name_len(const struct dso *dso)
 {
 	if (!dso)
@@ -1195,10 +1170,10 @@
 		strcpy(dso->name, name);
 		dso__set_long_name(dso, dso->name, false);
 		dso__set_short_name(dso, dso->name, false);
-		dso->symbols = dso->symbol_names = RB_ROOT;
+		dso->symbols = dso->symbol_names = RB_ROOT_CACHED;
 		dso->data.cache = RB_ROOT;
-		dso->inlined_nodes = RB_ROOT;
-		dso->srclines = RB_ROOT;
+		dso->inlined_nodes = RB_ROOT_CACHED;
+		dso->srclines = RB_ROOT_CACHED;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1312,143 +1287,6 @@
 	return 0;
 }
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
-{
-	bool have_build_id = false;
-	struct dso *pos;
-	struct nscookie nsc;
-
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit && !dso__is_vdso(pos))
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		nsinfo__mountns_enter(pos->nsinfo, &nsc);
-		if (filename__read_build_id(pos->long_name, pos->build_id,
-					    sizeof(pos->build_id)) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		}
-		nsinfo__mountns_exit(&nsc);
-	}
-
-	return have_build_id;
-}
-
-void __dsos__add(struct dsos *dsos, struct dso *dso)
-{
-	list_add_tail(&dso->node, &dsos->head);
-	__dso__findlink_by_longname(&dsos->root, dso, NULL);
-	/*
-	 * It is now in the linked list, grab a reference, then garbage collect
-	 * this when needing memory, by looking at LRU dso instances in the
-	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
-	 * anywhere besides the one for the list, do, under a lock for the
-	 * list: remove it from the list, then a dso__put(), that probably will
-	 * be the last and will then call dso__delete(), end of life.
-	 *
-	 * That, or at the end of the 'struct machine' lifetime, when all
-	 * 'struct dso' instances will be removed from the list, in
-	 * dsos__exit(), if they have no other reference from some other data
-	 * structure.
-	 *
-	 * E.g.: after processing a 'perf.data' file and storing references
-	 * to objects instantiated while processing events, we will have
-	 * references to the 'thread', 'map', 'dso' structs all from 'struct
-	 * hist_entry' instances, but we may not need anything not referenced,
-	 * so we might as well call machines__exit()/machines__delete() and
-	 * garbage collect it.
-	 */
-	dso__get(dso);
-}
-
-void dsos__add(struct dsos *dsos, struct dso *dso)
-{
-	down_write(&dsos->lock);
-	__dsos__add(dsos, dso);
-	up_write(&dsos->lock);
-}
-
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
-{
-	struct dso *pos;
-
-	if (cmp_short) {
-		list_for_each_entry(pos, &dsos->head, node)
-			if (strcmp(pos->short_name, name) == 0)
-				return pos;
-		return NULL;
-	}
-	return __dso__find_by_longname(&dsos->root, name);
-}
-
-struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
-{
-	struct dso *dso;
-	down_read(&dsos->lock);
-	dso = __dsos__find(dsos, name, cmp_short);
-	up_read(&dsos->lock);
-	return dso;
-}
-
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso = dso__new(name);
-
-	if (dso != NULL) {
-		__dsos__add(dsos, dso);
-		dso__set_basename(dso);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
-	}
-	return dso;
-}
-
-struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso = __dsos__find(dsos, name, false);
-
-	return dso ? dso : __dsos__addnew(dsos, name);
-}
-
-struct dso *dsos__findnew(struct dsos *dsos, const char *name)
-{
-	struct dso *dso;
-	down_write(&dsos->lock);
-	dso = dso__get(__dsos__findnew(dsos, name));
-	up_write(&dsos->lock);
-	return dso;
-}
-
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		if (skip && skip(pos, parm))
-			continue;
-		ret += dso__fprintf_buildid(pos, fp);
-		ret += fprintf(fp, " %s\n", pos->long_name);
-	}
-	return ret;
-}
-
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
-{
-	struct dso *pos;
-	size_t ret = 0;
-
-	list_for_each_entry(pos, head, node) {
-		ret += dso__fprintf(pos, fp);
-	}
-
-	return ret;
-}
-
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
@@ -1467,7 +1305,7 @@
 	ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c538050..e4dddb7 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -2,18 +2,23 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <pthread.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include "rwsem.h"
-#include <linux/types.h>
+#include <stdio.h>
 #include <linux/bitops.h>
-#include "map.h"
-#include "namespaces.h"
 #include "build-id.h"
 
+struct machine;
+struct map;
+struct perf_env;
+
+#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
+#define DSO__NAME_KCORE		"[kernel.kcore]"
+
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
 	DSO_BINARY_TYPE__GUEST_KALLSYMS,
@@ -34,6 +39,7 @@
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BPF_PROG_INFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -123,16 +129,6 @@
 	char data[0];
 };
 
-/*
- * DSOs are put into both a list for fast iteration and rbtree for fast
- * long name lookup.
- */
-struct dsos {
-	struct list_head head;
-	struct rb_root	 root;	/* rbtree root sorted by long name */
-	struct rw_semaphore lock;
-};
-
 struct auxtrace_cache;
 
 struct dso {
@@ -140,10 +136,10 @@
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
-	struct rb_root	 symbols;
-	struct rb_root	 symbol_names;
-	struct rb_root	 inlined_nodes;
-	struct rb_root	 srclines;
+	struct rb_root_cached symbols;
+	struct rb_root_cached symbol_names;
+	struct rb_root_cached inlined_nodes;
+	struct rb_root_cached srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
@@ -188,6 +184,12 @@
 		u64		 debug_frame_offset;
 		u64		 eh_frame_hdr_offset;
 	} data;
+	/* bpf prog information */
+	struct {
+		u32		id;
+		u32		sub_id;
+		struct perf_env	*env;
+	} bpf_prog;
 
 	union { /* Tool specific area */
 		void	 *priv;
@@ -235,7 +237,7 @@
 
 static inline bool dso__has_symbols(const struct dso *dso)
 {
-	return !RB_EMPTY_ROOT(&dso->symbols);
+	return !RB_EMPTY_ROOT(&dso->symbols.rb_root);
 }
 
 bool dso__sorted_by_name(const struct dso *dso);
@@ -322,6 +324,7 @@
 void dso__data_put_fd(struct dso *dso);
 void dso__data_close(struct dso *dso);
 
+int dso__data_file_size(struct dso *dso, struct machine *machine);
 off_t dso__data_size(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size);
@@ -334,21 +337,8 @@
 struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
 				    const char *short_name, int dso_type);
 
-void __dsos__add(struct dsos *dsos, struct dso *dso);
-void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
-struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
-struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
-struct dso *dsos__findnew(struct dsos *dsos, const char *name);
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-
 void dso__reset_find_symbol_cache(struct dso *dso);
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm);
-size_t __dsos__fprintf(struct list_head *head, FILE *fp);
-
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
 size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
 size_t dso__fprintf(struct dso *dso, FILE *fp);
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
new file mode 100644
index 0000000..3ea80d2
--- /dev/null
+++ b/tools/perf/util/dsos.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
+#include "dsos.h"
+#include "dso.h"
+#include "vdso.h"
+#include "namespaces.h"
+#include <libgen.h>
+#include <stdlib.h>
+#include <string.h>
+#include <symbol.h> // filename__read_build_id
+
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+{
+	bool have_build_id = false;
+	struct dso *pos;
+	struct nscookie nsc;
+
+	list_for_each_entry(pos, head, node) {
+		if (with_hits && !pos->hit && !dso__is_vdso(pos))
+			continue;
+		if (pos->has_build_id) {
+			have_build_id = true;
+			continue;
+		}
+		nsinfo__mountns_enter(pos->nsinfo, &nsc);
+		if (filename__read_build_id(pos->long_name, pos->build_id,
+					    sizeof(pos->build_id)) > 0) {
+			have_build_id	  = true;
+			pos->has_build_id = true;
+		}
+		nsinfo__mountns_exit(&nsc);
+	}
+
+	return have_build_id;
+}
+
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node  *parent = NULL;
+
+	if (!name)
+		name = dso->long_name;
+	/*
+	 * Find node with the matching name
+	 */
+	while (*p) {
+		struct dso *this = rb_entry(*p, struct dso, rb_node);
+		int rc = strcmp(name, this->long_name);
+
+		parent = *p;
+		if (rc == 0) {
+			/*
+			 * In case the new DSO is a duplicate of an existing
+			 * one, print a one-time warning & put the new entry
+			 * at the end of the list of duplicates.
+			 */
+			if (!dso || (dso == this))
+				return this;	/* Find matching dso */
+			/*
+			 * The core kernel DSOs may have duplicated long name.
+			 * In this case, the short name should be different.
+			 * Comparing the short names to differentiate the DSOs.
+			 */
+			rc = strcmp(dso->short_name, this->short_name);
+			if (rc == 0) {
+				pr_err("Duplicated dso name: %s\n", name);
+				return NULL;
+			}
+		}
+		if (rc < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	if (dso) {
+		/* Add new node and rebalance tree */
+		rb_link_node(&dso->rb_node, parent, p);
+		rb_insert_color(&dso->rb_node, root);
+		dso->root = root;
+	}
+	return NULL;
+}
+
+void __dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	list_add_tail(&dso->node, &dsos->head);
+	__dsos__findnew_link_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	down_write(&dsos->lock);
+	__dsos__add(dsos, dso);
+	up_write(&dsos->lock);
+}
+
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *pos;
+
+	if (cmp_short) {
+		list_for_each_entry(pos, &dsos->head, node)
+			if (strcmp(pos->short_name, name) == 0)
+				return pos;
+		return NULL;
+	}
+	return __dsos__findnew_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *dso;
+	down_read(&dsos->lock);
+	dso = __dsos__find(dsos, name, cmp_short);
+	up_read(&dsos->lock);
+	return dso;
+}
+
+static void dso__set_basename(struct dso *dso)
+{
+	char *base, *lname;
+	int tid;
+
+	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
+		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
+			return;
+	} else {
+	      /*
+	       * basename() may modify path buffer, so we must pass
+               * a copy.
+               */
+		lname = strdup(dso->long_name);
+		if (!lname)
+			return;
+
+		/*
+		 * basename() may return a pointer to internal
+		 * storage which is reused in subsequent calls
+		 * so copy the result.
+		 */
+		base = strdup(basename(lname));
+
+		free(lname);
+
+		if (!base)
+			return;
+	}
+	dso__set_short_name(dso, base, true);
+}
+
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso = dso__new(name);
+
+	if (dso != NULL) {
+		__dsos__add(dsos, dso);
+		dso__set_basename(dso);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
+	}
+	return dso;
+}
+
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso = __dsos__find(dsos, name, false);
+
+	return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso;
+	down_write(&dsos->lock);
+	dso = dso__get(__dsos__findnew(dsos, name));
+	up_write(&dsos->lock);
+	return dso;
+}
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		if (skip && skip(pos, parm))
+			continue;
+		ret += dso__fprintf_buildid(pos, fp);
+		ret += fprintf(fp, " %s\n", pos->long_name);
+	}
+	return ret;
+}
+
+size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+{
+	struct dso *pos;
+	size_t ret = 0;
+
+	list_for_each_entry(pos, head, node) {
+		ret += dso__fprintf(pos, fp);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h
new file mode 100644
index 0000000..32f1fbe
--- /dev/null
+++ b/tools/perf/util/dsos.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_DSOS
+#define __PERF_DSOS
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include "rwsem.h"
+
+struct dso;
+
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+	struct list_head    head;
+	struct rb_root	    root;	/* rbtree root sorted by long name */
+	struct rw_semaphore lock;
+};
+
+void __dsos__add(struct dsos *dsos, struct dso *dso);
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
+
+struct dso *__dsos__findnew_link_by_longname(struct rb_root *root, struct dso *dso, const char *name);
+
+static inline struct dso *__dsos__findnew_by_longname(struct rb_root *root, const char *name)
+{
+	return __dsos__findnew_link_by_longname(root, NULL, name);
+}
+
+bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
+
+size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+			       bool (skip)(struct dso *dso, int parm), int parm);
+size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+
+#endif /* __PERF_DSOS */
diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c
index 10988d3..2bd8585 100644
--- a/tools/perf/util/dump-insn.c
+++ b/tools/perf/util/dump-insn.c
@@ -13,3 +13,11 @@
 		*lenp = 0;
 	return "?";
 }
+
+__weak
+int arch_is_branch(const unsigned char *buf __maybe_unused,
+		   size_t len __maybe_unused,
+		   int x86_64 __maybe_unused)
+{
+	return 0;
+}
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
index 0e06280..6501250 100644
--- a/tools/perf/util/dump-insn.h
+++ b/tools/perf/util/dump-insn.h
@@ -20,4 +20,6 @@
 
 const char *dump_insn(struct perf_insn *x, u64 ip,
 		      u8 *inbuf, int inlen, int *lenp);
+int arch_is_branch(const unsigned char *buf, size_t len, int x86_64);
+
 #endif
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 7eb7de5..df6cee5 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1,28 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * dwarf-aux.c : libdw auxiliary interfaces
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  */
 
 #include <errno.h>
 #include <inttypes.h>
 #include <stdbool.h>
-#include "util.h"
+#include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "strbuf.h"
 #include "string2.h"
 
 /**
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 8ac53bf..f204e58 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -1,22 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 #ifndef _DWARF_AUX_H
 #define _DWARF_AUX_H
 /*
  * dwarf-aux.h : libdw auxiliary interfaces
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  */
 
 #include <dwarf.h>
@@ -24,6 +10,8 @@
 #include <elfutils/libdwfl.h>
 #include <elfutils/version.h>
 
+struct strbuf;
+
 /* Find the realpath of the target file */
 const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname);
 
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index db55edd..1b49ece 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -5,7 +5,6 @@
  * Written by: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
-#include <util.h>
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 59f38c7..3baca06 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -1,17 +1,172 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "cpumap.h"
+#include "debug.h"
 #include "env.h"
-#include "sane_ctype.h"
-#include "util.h"
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
+#include "bpf-event.h"
 #include <errno.h>
 #include <sys/utsname.h>
+#include <bpf/libbpf.h>
+#include <stdlib.h>
+#include <string.h>
 
 struct perf_env perf_env;
 
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+				    struct bpf_prog_info_node *info_node)
+{
+	__u32 prog_id = info_node->info_linear->info.id;
+	struct bpf_prog_info_node *node;
+	struct rb_node *parent = NULL;
+	struct rb_node **p;
+
+	down_write(&env->bpf_progs.lock);
+	p = &env->bpf_progs.infos.rb_node;
+
+	while (*p != NULL) {
+		parent = *p;
+		node = rb_entry(parent, struct bpf_prog_info_node, rb_node);
+		if (prog_id < node->info_linear->info.id) {
+			p = &(*p)->rb_left;
+		} else if (prog_id > node->info_linear->info.id) {
+			p = &(*p)->rb_right;
+		} else {
+			pr_debug("duplicated bpf prog info %u\n", prog_id);
+			goto out;
+		}
+	}
+
+	rb_link_node(&info_node->rb_node, parent, p);
+	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
+	env->bpf_progs.infos_cnt++;
+out:
+	up_write(&env->bpf_progs.lock);
+}
+
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+							__u32 prog_id)
+{
+	struct bpf_prog_info_node *node = NULL;
+	struct rb_node *n;
+
+	down_read(&env->bpf_progs.lock);
+	n = env->bpf_progs.infos.rb_node;
+
+	while (n) {
+		node = rb_entry(n, struct bpf_prog_info_node, rb_node);
+		if (prog_id < node->info_linear->info.id)
+			n = n->rb_left;
+		else if (prog_id > node->info_linear->info.id)
+			n = n->rb_right;
+		else
+			goto out;
+	}
+	node = NULL;
+
+out:
+	up_read(&env->bpf_progs.lock);
+	return node;
+}
+
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
+	struct rb_node *parent = NULL;
+	__u32 btf_id = btf_node->id;
+	struct btf_node *node;
+	struct rb_node **p;
+
+	down_write(&env->bpf_progs.lock);
+	p = &env->bpf_progs.btfs.rb_node;
+
+	while (*p != NULL) {
+		parent = *p;
+		node = rb_entry(parent, struct btf_node, rb_node);
+		if (btf_id < node->id) {
+			p = &(*p)->rb_left;
+		} else if (btf_id > node->id) {
+			p = &(*p)->rb_right;
+		} else {
+			pr_debug("duplicated btf %u\n", btf_id);
+			goto out;
+		}
+	}
+
+	rb_link_node(&btf_node->rb_node, parent, p);
+	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
+	env->bpf_progs.btfs_cnt++;
+out:
+	up_write(&env->bpf_progs.lock);
+}
+
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
+	struct btf_node *node = NULL;
+	struct rb_node *n;
+
+	down_read(&env->bpf_progs.lock);
+	n = env->bpf_progs.btfs.rb_node;
+
+	while (n) {
+		node = rb_entry(n, struct btf_node, rb_node);
+		if (btf_id < node->id)
+			n = n->rb_left;
+		else if (btf_id > node->id)
+			n = n->rb_right;
+		else
+			goto out;
+	}
+	node = NULL;
+
+out:
+	up_read(&env->bpf_progs.lock);
+	return node;
+}
+
+/* purge data in bpf_progs.infos tree */
+static void perf_env__purge_bpf(struct perf_env *env)
+{
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_write(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+
+	while (next) {
+		struct bpf_prog_info_node *node;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+		rb_erase(&node->rb_node, root);
+		free(node);
+	}
+
+	env->bpf_progs.infos_cnt = 0;
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		rb_erase(&node->rb_node, root);
+		free(node);
+	}
+
+	env->bpf_progs.btfs_cnt = 0;
+
+	up_write(&env->bpf_progs.lock);
+}
+
 void perf_env__exit(struct perf_env *env)
 {
 	int i;
 
+	perf_env__purge_bpf(env);
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -26,7 +181,7 @@
 	zfree(&env->cpu);
 
 	for (i = 0; i < env->nr_numa_nodes; i++)
-		cpu_map__put(env->numa_nodes[i].map);
+		perf_cpu_map__put(env->numa_nodes[i].map);
 	zfree(&env->numa_nodes);
 
 	for (i = 0; i < env->caches_cnt; i++)
@@ -34,10 +189,17 @@
 	zfree(&env->caches);
 
 	for (i = 0; i < env->nr_memory_nodes; i++)
-		free(env->memory_nodes[i].set);
+		zfree(&env->memory_nodes[i].set);
 	zfree(&env->memory_nodes);
 }
 
+void perf_env__init(struct perf_env *env)
+{
+	env->bpf_progs.infos = RB_ROOT;
+	env->bpf_progs.btfs = RB_ROOT;
+	init_rwsem(&env->bpf_progs.lock);
+}
+
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
 	int i;
@@ -87,6 +249,7 @@
 	for (cpu = 0; cpu < nr_cpus; ++cpu) {
 		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);
 		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);
+		env->cpu[cpu].die_id	= cpu_map__get_die_id(cpu);
 	}
 
 	env->nr_cpus_avail = nr_cpus;
@@ -126,9 +289,9 @@
 
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
-	free(cache->type);
-	free(cache->map);
-	free(cache->size);
+	zfree(&cache->type);
+	zfree(&cache->map);
+	zfree(&cache->size);
 }
 
 /*
@@ -166,7 +329,7 @@
 	struct utsname uts;
 	char *arch_name;
 
-	if (!env) { /* Assume local operation */
+	if (!env || !env->arch) { /* Assume local operation */
 		if (uname(&uts) < 0)
 			return NULL;
 		arch_name = uts.machine;
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc3..db40906 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -3,10 +3,14 @@
 #define __PERF_ENV_H
 
 #include <linux/types.h>
-#include "cpumap.h"
+#include <linux/rbtree.h>
+#include "rwsem.h"
+
+struct perf_cpu_map;
 
 struct cpu_topology_map {
 	int	socket_id;
+	int	die_id;
 	int	core_id;
 };
 
@@ -24,7 +28,7 @@
 	u32		 node;
 	u64		 mem_total;
 	u64		 mem_free;
-	struct cpu_map	*map;
+	struct perf_cpu_map	*map;
 };
 
 struct memory_node {
@@ -47,6 +51,7 @@
 
 	int			nr_cmdline;
 	int			nr_sibling_cores;
+	int			nr_sibling_dies;
 	int			nr_sibling_threads;
 	int			nr_numa_nodes;
 	int			nr_memory_nodes;
@@ -55,16 +60,44 @@
 	char			*cmdline;
 	const char		**cmdline_argv;
 	char			*sibling_cores;
+	char			*sibling_dies;
 	char			*sibling_threads;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
+	u32			comp_ratio;
+	u32			comp_ver;
+	u32			comp_type;
+	u32			comp_level;
+	u32			comp_mmap_len;
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	u64                     clockid_res_ns;
+
+	/*
+	 * bpf_info_lock protects bpf rbtrees. This is needed because the
+	 * trees are accessed by different threads in perf-top
+	 */
+	struct {
+		struct rw_semaphore	lock;
+		struct rb_root		infos;
+		u32			infos_cnt;
+		struct rb_root		btfs;
+		u32			btfs_cnt;
+	} bpf_progs;
 };
 
+enum perf_compress_type {
+	PERF_COMP_NONE = 0,
+	PERF_COMP_ZSTD,
+	PERF_COMP_MAX
+};
+
+struct bpf_prog_info_node;
+struct btf_node;
+
 extern struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env);
@@ -79,4 +112,11 @@
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
+void perf_env__init(struct perf_env *env);
+void perf_env__insert_bpf_prog_info(struct perf_env *env,
+				    struct bpf_prog_info_node *info_node);
+struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
+							__u32 prog_id);
+void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc64618..fc1e5a9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,16 +1,17 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <dirent.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <perf/cpumap.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
-#include <api/fs/fs.h>
 #include <linux/perf_event.h>
+#include <linux/zalloc.h>
+#include "cpumap.h"
+#include "dso.h"
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -20,10 +21,18 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
-#include "sane_ctype.h"
+#include "time-utils.h"
+#include <linux/ctype.h>
+#include "map.h"
+#include "util/namespaces.h"
+#include "symbol.h"
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
+#include "session.h"
+#include "bpf-event.h"
+#include "tool.h"
+#include "../perf.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
@@ -43,6 +52,8 @@
 	[PERF_RECORD_SWITCH]			= "SWITCH",
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
+	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
+	[PERF_RECORD_BPF_EVENT]			= "BPF_EVENT",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -60,16 +71,7 @@
 	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
-};
-
-static const char *perf_ns__names[] = {
-	[NET_NS_INDEX]		= "net",
-	[UTS_NS_INDEX]		= "uts",
-	[IPC_NS_INDEX]		= "ipc",
-	[PID_NS_INDEX]		= "pid",
-	[USER_NS_INDEX]		= "user",
-	[MNT_NS_INDEX]		= "mnt",
-	[CGROUP_NS_INDEX]	= "cgroup",
+	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -81,786 +83,6 @@
 	return perf_event__names[id];
 }
 
-static const char *perf_ns__name(unsigned int id)
-{
-	if (id >= ARRAY_SIZE(perf_ns__names))
-		return "UNKNOWN";
-	return perf_ns__names[id];
-}
-
-int perf_tool__process_synth_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct machine *machine,
-				   perf_event__handler_t process)
-{
-	struct perf_sample synth_sample = {
-	.pid	   = -1,
-	.tid	   = -1,
-	.time	   = -1,
-	.stream_id = -1,
-	.cpu	   = -1,
-	.period	   = 1,
-	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
-	};
-
-	return process(tool, event, &synth_sample, machine);
-};
-
-/*
- * Assumes that the first 4095 bytes of /proc/pid/stat contains
- * the comm, tgid and ppid.
- */
-static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
-				    pid_t *tgid, pid_t *ppid)
-{
-	char filename[PATH_MAX];
-	char bf[4096];
-	int fd;
-	size_t size = 0;
-	ssize_t n;
-	char *name, *tgids, *ppids;
-
-	*tgid = -1;
-	*ppid = -1;
-
-	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0) {
-		pr_debug("couldn't open %s\n", filename);
-		return -1;
-	}
-
-	n = read(fd, bf, sizeof(bf) - 1);
-	close(fd);
-	if (n <= 0) {
-		pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
-			   pid);
-		return -1;
-	}
-	bf[n] = '\0';
-
-	name = strstr(bf, "Name:");
-	tgids = strstr(bf, "Tgid:");
-	ppids = strstr(bf, "PPid:");
-
-	if (name) {
-		char *nl;
-
-		name += 5;  /* strlen("Name:") */
-		name = ltrim(name);
-
-		nl = strchr(name, '\n');
-		if (nl)
-			*nl = '\0';
-
-		size = strlen(name);
-		if (size >= len)
-			size = len - 1;
-		memcpy(comm, name, size);
-		comm[size] = '\0';
-	} else {
-		pr_debug("Name: string not found for pid %d\n", pid);
-	}
-
-	if (tgids) {
-		tgids += 5;  /* strlen("Tgid:") */
-		*tgid = atoi(tgids);
-	} else {
-		pr_debug("Tgid: string not found for pid %d\n", pid);
-	}
-
-	if (ppids) {
-		ppids += 5;  /* strlen("PPid:") */
-		*ppid = atoi(ppids);
-	} else {
-		pr_debug("PPid: string not found for pid %d\n", pid);
-	}
-
-	return 0;
-}
-
-static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
-				    struct machine *machine,
-				    pid_t *tgid, pid_t *ppid)
-{
-	size_t size;
-
-	*ppid = -1;
-
-	memset(&event->comm, 0, sizeof(event->comm));
-
-	if (machine__is_host(machine)) {
-		if (perf_event__get_comm_ids(pid, event->comm.comm,
-					     sizeof(event->comm.comm),
-					     tgid, ppid) != 0) {
-			return -1;
-		}
-	} else {
-		*tgid = machine->pid;
-	}
-
-	if (*tgid < 0)
-		return -1;
-
-	event->comm.pid = *tgid;
-	event->comm.header.type = PERF_RECORD_COMM;
-
-	size = strlen(event->comm.comm) + 1;
-	size = PERF_ALIGN(size, sizeof(u64));
-	memset(event->comm.comm + size, 0, machine->id_hdr_size);
-	event->comm.header.size = (sizeof(event->comm) -
-				(sizeof(event->comm.comm) - size) +
-				machine->id_hdr_size);
-	event->comm.tid = pid;
-
-	return 0;
-}
-
-pid_t perf_event__synthesize_comm(struct perf_tool *tool,
-					 union perf_event *event, pid_t pid,
-					 perf_event__handler_t process,
-					 struct machine *machine)
-{
-	pid_t tgid, ppid;
-
-	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
-		return -1;
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return tgid;
-}
-
-static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
-					 struct perf_ns_link_info *ns_link_info)
-{
-	struct stat64 st;
-	char proc_ns[128];
-
-	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
-	if (stat64(proc_ns, &st) == 0) {
-		ns_link_info->dev = st.st_dev;
-		ns_link_info->ino = st.st_ino;
-	}
-}
-
-int perf_event__synthesize_namespaces(struct perf_tool *tool,
-				      union perf_event *event,
-				      pid_t pid, pid_t tgid,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	u32 idx;
-	struct perf_ns_link_info *ns_link_info;
-
-	if (!tool || !tool->namespace_events)
-		return 0;
-
-	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
-	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-	       machine->id_hdr_size));
-
-	event->namespaces.pid = tgid;
-	event->namespaces.tid = pid;
-
-	event->namespaces.nr_namespaces = NR_NAMESPACES;
-
-	ns_link_info = event->namespaces.link_info;
-
-	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
-		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
-					     &ns_link_info[idx]);
-
-	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
-
-	event->namespaces.header.size = (sizeof(event->namespaces) +
-			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-			machine->id_hdr_size);
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return 0;
-}
-
-static int perf_event__synthesize_fork(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid, pid_t ppid,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
-
-	/*
-	 * for main thread set parent to ppid from status file. For other
-	 * threads set parent pid to main thread. ie., assume main thread
-	 * spawns all threads in a process
-	*/
-	if (tgid == pid) {
-		event->fork.ppid = ppid;
-		event->fork.ptid = ppid;
-	} else {
-		event->fork.ppid = tgid;
-		event->fork.ptid = tgid;
-	}
-	event->fork.pid  = tgid;
-	event->fork.tid  = pid;
-	event->fork.header.type = PERF_RECORD_FORK;
-
-	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
-
-	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
-		return -1;
-
-	return 0;
-}
-
-int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid,
-				       perf_event__handler_t process,
-				       struct machine *machine,
-				       bool mmap_data,
-				       unsigned int proc_map_timeout)
-{
-	char filename[PATH_MAX];
-	FILE *fp;
-	unsigned long long t;
-	bool truncation = false;
-	unsigned long long timeout = proc_map_timeout * 1000000ULL;
-	int rc = 0;
-	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
-	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
-		 machine->root_dir, pid, pid);
-
-	fp = fopen(filename, "r");
-	if (fp == NULL) {
-		/*
-		 * We raced with a task exiting - just return:
-		 */
-		pr_debug("couldn't open %s\n", filename);
-		return -1;
-	}
-
-	event->header.type = PERF_RECORD_MMAP2;
-	t = rdclock();
-
-	while (1) {
-		char bf[BUFSIZ];
-		char prot[5];
-		char execname[PATH_MAX];
-		char anonstr[] = "//anon";
-		unsigned int ino;
-		size_t size;
-		ssize_t n;
-
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			break;
-
-		if ((rdclock() - t) > timeout) {
-			pr_warning("Reading %s time out. "
-				   "You may want to increase "
-				   "the time limit by --proc-map-timeout\n",
-				   filename);
-			truncation = true;
-			goto out;
-		}
-
-		/* ensure null termination since stack will be reused. */
-		strcpy(execname, "");
-
-		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
-		       &event->mmap2.start, &event->mmap2.len, prot,
-		       &event->mmap2.pgoff, &event->mmap2.maj,
-		       &event->mmap2.min,
-		       &ino, execname);
-
-		/*
- 		 * Anon maps don't have the execname.
- 		 */
-		if (n < 7)
-			continue;
-
-		event->mmap2.ino = (u64)ino;
-
-		/*
-		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
-		 */
-		if (machine__is_host(machine))
-			event->header.misc = PERF_RECORD_MISC_USER;
-		else
-			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
-
-		/* map protection and flags bits */
-		event->mmap2.prot = 0;
-		event->mmap2.flags = 0;
-		if (prot[0] == 'r')
-			event->mmap2.prot |= PROT_READ;
-		if (prot[1] == 'w')
-			event->mmap2.prot |= PROT_WRITE;
-		if (prot[2] == 'x')
-			event->mmap2.prot |= PROT_EXEC;
-
-		if (prot[3] == 's')
-			event->mmap2.flags |= MAP_SHARED;
-		else
-			event->mmap2.flags |= MAP_PRIVATE;
-
-		if (prot[2] != 'x') {
-			if (!mmap_data || prot[0] != 'r')
-				continue;
-
-			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
-		}
-
-out:
-		if (truncation)
-			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
-
-		if (!strcmp(execname, ""))
-			strcpy(execname, anonstr);
-
-		if (hugetlbfs_mnt_len &&
-		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
-			strcpy(execname, anonstr);
-			event->mmap2.flags |= MAP_HUGETLB;
-		}
-
-		size = strlen(execname) + 1;
-		memcpy(event->mmap2.filename, execname, size);
-		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap2.len -= event->mmap.start;
-		event->mmap2.header.size = (sizeof(event->mmap2) -
-					(sizeof(event->mmap2.filename) - size));
-		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-		event->mmap2.header.size += machine->id_hdr_size;
-		event->mmap2.pid = tgid;
-		event->mmap2.tid = pid;
-
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-
-		if (truncation)
-			break;
-	}
-
-	fclose(fp);
-	return rc;
-}
-
-int perf_event__synthesize_modules(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine)
-{
-	int rc = 0;
-	struct map *pos;
-	struct maps *maps = machine__kernel_maps(machine);
-	union perf_event *event = zalloc((sizeof(event->mmap) +
-					  machine->id_hdr_size));
-	if (event == NULL) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for kernel modules\n");
-		return -1;
-	}
-
-	event->header.type = PERF_RECORD_MMAP;
-
-	/*
-	 * kernel uses 0 for user space maps, see kernel/perf_event.c
-	 * __perf_event_mmap
-	 */
-	if (machine__is_host(machine))
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
-	else
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-
-	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
-		size_t size;
-
-		if (!__map__is_kmodule(pos))
-			continue;
-
-		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-		event->mmap.header.type = PERF_RECORD_MMAP;
-		event->mmap.header.size = (sizeof(event->mmap) -
-				        (sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.start = pos->start;
-		event->mmap.len   = pos->end - pos->start;
-		event->mmap.pid   = machine->pid;
-
-		memcpy(event->mmap.filename, pos->dso->long_name,
-		       pos->dso->long_name_len + 1);
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-	}
-
-	free(event);
-	return rc;
-}
-
-static int __event__synthesize_thread(union perf_event *comm_event,
-				      union perf_event *mmap_event,
-				      union perf_event *fork_event,
-				      union perf_event *namespaces_event,
-				      pid_t pid, int full,
-				      perf_event__handler_t process,
-				      struct perf_tool *tool,
-				      struct machine *machine,
-				      bool mmap_data,
-				      unsigned int proc_map_timeout)
-{
-	char filename[PATH_MAX];
-	DIR *tasks;
-	struct dirent *dirent;
-	pid_t tgid, ppid;
-	int rc = 0;
-
-	/* special case: only send one comm event using passed in pid */
-	if (!full) {
-		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
-						   process, machine);
-
-		if (tgid == -1)
-			return -1;
-
-		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
-						      tgid, process, machine) < 0)
-			return -1;
-
-		/*
-		 * send mmap only for thread group leader
-		 * see thread__init_map_groups
-		 */
-		if (pid == tgid &&
-		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						       process, machine, mmap_data,
-						       proc_map_timeout))
-			return -1;
-
-		return 0;
-	}
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
-		 machine->root_dir, pid);
-
-	tasks = opendir(filename);
-	if (tasks == NULL) {
-		pr_debug("couldn't open %s\n", filename);
-		return 0;
-	}
-
-	while ((dirent = readdir(tasks)) != NULL) {
-		char *end;
-		pid_t _pid;
-
-		_pid = strtol(dirent->d_name, &end, 10);
-		if (*end)
-			continue;
-
-		rc = -1;
-		if (perf_event__prepare_comm(comm_event, _pid, machine,
-					     &tgid, &ppid) != 0)
-			break;
-
-		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
-						ppid, process, machine) < 0)
-			break;
-
-		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
-						      tgid, process, machine) < 0)
-			break;
-
-		/*
-		 * Send the prepared comm event
-		 */
-		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
-			break;
-
-		rc = 0;
-		if (_pid == pid) {
-			/* process the parent's maps too */
-			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data, proc_map_timeout);
-			if (rc)
-				break;
-		}
-	}
-
-	closedir(tasks);
-	return rc;
-}
-
-int perf_event__synthesize_thread_map(struct perf_tool *tool,
-				      struct thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine,
-				      bool mmap_data,
-				      unsigned int proc_map_timeout)
-{
-	union perf_event *comm_event, *mmap_event, *fork_event;
-	union perf_event *namespaces_event;
-	int err = -1, thread, j;
-
-	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
-	if (comm_event == NULL)
-		goto out;
-
-	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
-	if (mmap_event == NULL)
-		goto out_free_comm;
-
-	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
-	if (fork_event == NULL)
-		goto out_free_mmap;
-
-	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
-				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-				  machine->id_hdr_size);
-	if (namespaces_event == NULL)
-		goto out_free_fork;
-
-	err = 0;
-	for (thread = 0; thread < threads->nr; ++thread) {
-		if (__event__synthesize_thread(comm_event, mmap_event,
-					       fork_event, namespaces_event,
-					       thread_map__pid(threads, thread), 0,
-					       process, tool, machine,
-					       mmap_data, proc_map_timeout)) {
-			err = -1;
-			break;
-		}
-
-		/*
-		 * comm.pid is set to thread group id by
-		 * perf_event__synthesize_comm
-		 */
-		if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) {
-			bool need_leader = true;
-
-			/* is thread group leader in thread_map? */
-			for (j = 0; j < threads->nr; ++j) {
-				if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) {
-					need_leader = false;
-					break;
-				}
-			}
-
-			/* if not, generate events for it */
-			if (need_leader &&
-			    __event__synthesize_thread(comm_event, mmap_event,
-						       fork_event, namespaces_event,
-						       comm_event->comm.pid, 0,
-						       process, tool, machine,
-						       mmap_data, proc_map_timeout)) {
-				err = -1;
-				break;
-			}
-		}
-	}
-	free(namespaces_event);
-out_free_fork:
-	free(fork_event);
-out_free_mmap:
-	free(mmap_event);
-out_free_comm:
-	free(comm_event);
-out:
-	return err;
-}
-
-static int __perf_event__synthesize_threads(struct perf_tool *tool,
-					    perf_event__handler_t process,
-					    struct machine *machine,
-					    bool mmap_data,
-					    unsigned int proc_map_timeout,
-					    struct dirent **dirent,
-					    int start,
-					    int num)
-{
-	union perf_event *comm_event, *mmap_event, *fork_event;
-	union perf_event *namespaces_event;
-	int err = -1;
-	char *end;
-	pid_t pid;
-	int i;
-
-	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
-	if (comm_event == NULL)
-		goto out;
-
-	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
-	if (mmap_event == NULL)
-		goto out_free_comm;
-
-	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
-	if (fork_event == NULL)
-		goto out_free_mmap;
-
-	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
-				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
-				  machine->id_hdr_size);
-	if (namespaces_event == NULL)
-		goto out_free_fork;
-
-	for (i = start; i < start + num; i++) {
-		if (!isdigit(dirent[i]->d_name[0]))
-			continue;
-
-		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
-		/* only interested in proper numerical dirents */
-		if (*end)
-			continue;
-		/*
-		 * We may race with exiting thread, so don't stop just because
-		 * one thread couldn't be synthesized.
-		 */
-		__event__synthesize_thread(comm_event, mmap_event, fork_event,
-					   namespaces_event, pid, 1, process,
-					   tool, machine, mmap_data,
-					   proc_map_timeout);
-	}
-	err = 0;
-
-	free(namespaces_event);
-out_free_fork:
-	free(fork_event);
-out_free_mmap:
-	free(mmap_event);
-out_free_comm:
-	free(comm_event);
-out:
-	return err;
-}
-
-struct synthesize_threads_arg {
-	struct perf_tool *tool;
-	perf_event__handler_t process;
-	struct machine *machine;
-	bool mmap_data;
-	unsigned int proc_map_timeout;
-	struct dirent **dirent;
-	int num;
-	int start;
-};
-
-static void *synthesize_threads_worker(void *arg)
-{
-	struct synthesize_threads_arg *args = arg;
-
-	__perf_event__synthesize_threads(args->tool, args->process,
-					 args->machine, args->mmap_data,
-					 args->proc_map_timeout, args->dirent,
-					 args->start, args->num);
-	return NULL;
-}
-
-int perf_event__synthesize_threads(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine,
-				   bool mmap_data,
-				   unsigned int proc_map_timeout,
-				   unsigned int nr_threads_synthesize)
-{
-	struct synthesize_threads_arg *args = NULL;
-	pthread_t *synthesize_threads = NULL;
-	char proc_path[PATH_MAX];
-	struct dirent **dirent;
-	int num_per_thread;
-	int m, n, i, j;
-	int thread_nr;
-	int base = 0;
-	int err = -1;
-
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	n = scandir(proc_path, &dirent, 0, alphasort);
-	if (n < 0)
-		return err;
-
-	if (nr_threads_synthesize == UINT_MAX)
-		thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
-	else
-		thread_nr = nr_threads_synthesize;
-
-	if (thread_nr <= 1) {
-		err = __perf_event__synthesize_threads(tool, process,
-						       machine, mmap_data,
-						       proc_map_timeout,
-						       dirent, base, n);
-		goto free_dirent;
-	}
-	if (thread_nr > n)
-		thread_nr = n;
-
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
-	if (synthesize_threads == NULL)
-		goto free_dirent;
-
-	args = calloc(sizeof(*args), thread_nr);
-	if (args == NULL)
-		goto free_threads;
-
-	num_per_thread = n / thread_nr;
-	m = n % thread_nr;
-	for (i = 0; i < thread_nr; i++) {
-		args[i].tool = tool;
-		args[i].process = process;
-		args[i].machine = machine;
-		args[i].mmap_data = mmap_data;
-		args[i].proc_map_timeout = proc_map_timeout;
-		args[i].dirent = dirent;
-	}
-	for (i = 0; i < m; i++) {
-		args[i].num = num_per_thread + 1;
-		args[i].start = i * args[i].num;
-	}
-	if (i != 0)
-		base = args[i-1].start + args[i-1].num;
-	for (j = i; j < thread_nr; j++) {
-		args[j].num = num_per_thread;
-		args[j].start = base + (j - i) * args[i].num;
-	}
-
-	for (i = 0; i < thread_nr; i++) {
-		if (pthread_create(&synthesize_threads[i], NULL,
-				   synthesize_threads_worker, &args[i]))
-			goto out_join;
-	}
-	err = 0;
-out_join:
-	for (i = 0; i < thread_nr; i++)
-		pthread_join(synthesize_threads[i], NULL);
-	free(args);
-free_threads:
-	free(synthesize_threads);
-free_dirent:
-	for (i = 0; i < n; i++)
-		free(dirent[i]);
-	free(dirent);
-
-	return err;
-}
-
 struct process_symbol_args {
 	const char *name;
 	u64	   start;
@@ -895,328 +117,8 @@
 	return 0;
 }
 
-int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
-					      perf_event__handler_t process __maybe_unused,
-					      struct machine *machine __maybe_unused)
-{
-	return 0;
-}
-
-static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-						perf_event__handler_t process,
-						struct machine *machine)
-{
-	size_t size;
-	struct map *map = machine__kernel_map(machine);
-	struct kmap *kmap;
-	int err;
-	union perf_event *event;
-
-	if (symbol_conf.kptr_restrict)
-		return -1;
-	if (map == NULL)
-		return -1;
-
-	/*
-	 * We should get this from /sys/kernel/sections/.text, but till that is
-	 * available use this, and after it is use this as a fallback for older
-	 * kernels.
-	 */
-	event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
-	if (event == NULL) {
-		pr_debug("Not enough memory synthesizing mmap event "
-			 "for kernel modules\n");
-		return -1;
-	}
-
-	if (machine__is_host(machine)) {
-		/*
-		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
-		 * see kernel/perf_event.c __perf_event_mmap
-		 */
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
-	} else {
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-	}
-
-	kmap = map__kmap(map);
-	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
-	size = PERF_ALIGN(size, sizeof(u64));
-	event->mmap.header.type = PERF_RECORD_MMAP;
-	event->mmap.header.size = (sizeof(event->mmap) -
-			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
-	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
-	event->mmap.start = map->start;
-	event->mmap.len   = map->end - event->mmap.start;
-	event->mmap.pid   = machine->pid;
-
-	err = perf_tool__process_synth_event(tool, event, machine, process);
-	free(event);
-
-	return err;
-}
-
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	int err;
-
-	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
-	if (err < 0)
-		return err;
-
-	return perf_event__synthesize_extra_kmaps(tool, process, machine);
-}
-
-int perf_event__synthesize_thread_map2(struct perf_tool *tool,
-				      struct thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	union perf_event *event;
-	int i, err, size;
-
-	size  = sizeof(event->thread_map);
-	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
-
-	event = zalloc(size);
-	if (!event)
-		return -ENOMEM;
-
-	event->header.type = PERF_RECORD_THREAD_MAP;
-	event->header.size = size;
-	event->thread_map.nr = threads->nr;
-
-	for (i = 0; i < threads->nr; i++) {
-		struct thread_map_event_entry *entry = &event->thread_map.entries[i];
-		char *comm = thread_map__comm(threads, i);
-
-		if (!comm)
-			comm = (char *) "";
-
-		entry->pid = thread_map__pid(threads, i);
-		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
-	}
-
-	err = process(tool, event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-static void synthesize_cpus(struct cpu_map_entries *cpus,
-			    struct cpu_map *map)
-{
-	int i;
-
-	cpus->nr = map->nr;
-
-	for (i = 0; i < map->nr; i++)
-		cpus->cpu[i] = map->map[i];
-}
-
-static void synthesize_mask(struct cpu_map_mask *mask,
-			    struct cpu_map *map, int max)
-{
-	int i;
-
-	mask->nr = BITS_TO_LONGS(max);
-	mask->long_size = sizeof(long);
-
-	for (i = 0; i < map->nr; i++)
-		set_bit(map->map[i], mask->mask);
-}
-
-static size_t cpus_size(struct cpu_map *map)
-{
-	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
-}
-
-static size_t mask_size(struct cpu_map *map, int *max)
-{
-	int i;
-
-	*max = 0;
-
-	for (i = 0; i < map->nr; i++) {
-		/* bit possition of the cpu is + 1 */
-		int bit = map->map[i] + 1;
-
-		if (bit > *max)
-			*max = bit;
-	}
-
-	return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
-}
-
-void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
-{
-	size_t size_cpus, size_mask;
-	bool is_dummy = cpu_map__empty(map);
-
-	/*
-	 * Both array and mask data have variable size based
-	 * on the number of cpus and their actual values.
-	 * The size of the 'struct cpu_map_data' is:
-	 *
-	 *   array = size of 'struct cpu_map_entries' +
-	 *           number of cpus * sizeof(u64)
-	 *
-	 *   mask  = size of 'struct cpu_map_mask' +
-	 *           maximum cpu bit converted to size of longs
-	 *
-	 * and finaly + the size of 'struct cpu_map_data'.
-	 */
-	size_cpus = cpus_size(map);
-	size_mask = mask_size(map, max);
-
-	if (is_dummy || (size_cpus < size_mask)) {
-		*size += size_cpus;
-		*type  = PERF_CPU_MAP__CPUS;
-	} else {
-		*size += size_mask;
-		*type  = PERF_CPU_MAP__MASK;
-	}
-
-	*size += sizeof(struct cpu_map_data);
-	*size = PERF_ALIGN(*size, sizeof(u64));
-	return zalloc(*size);
-}
-
-void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
-			      u16 type, int max)
-{
-	data->type = type;
-
-	switch (type) {
-	case PERF_CPU_MAP__CPUS:
-		synthesize_cpus((struct cpu_map_entries *) data->data, map);
-		break;
-	case PERF_CPU_MAP__MASK:
-		synthesize_mask((struct cpu_map_mask *) data->data, map, max);
-	default:
-		break;
-	};
-}
-
-static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
-{
-	size_t size = sizeof(struct cpu_map_event);
-	struct cpu_map_event *event;
-	int max;
-	u16 type;
-
-	event = cpu_map_data__alloc(map, &size, &type, &max);
-	if (!event)
-		return NULL;
-
-	event->header.type = PERF_RECORD_CPU_MAP;
-	event->header.size = size;
-	event->data.type   = type;
-
-	cpu_map_data__synthesize(&event->data, map, type, max);
-	return event;
-}
-
-int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct cpu_map *map,
-				   perf_event__handler_t process,
-				   struct machine *machine)
-{
-	struct cpu_map_event *event;
-	int err;
-
-	event = cpu_map_event__new(map);
-	if (!event)
-		return -ENOMEM;
-
-	err = process(tool, (union perf_event *) event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-int perf_event__synthesize_stat_config(struct perf_tool *tool,
-				       struct perf_stat_config *config,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	struct stat_config_event *event;
-	int size, i = 0, err;
-
-	size  = sizeof(*event);
-	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
-
-	event = zalloc(size);
-	if (!event)
-		return -ENOMEM;
-
-	event->header.type = PERF_RECORD_STAT_CONFIG;
-	event->header.size = size;
-	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
-
-#define ADD(__term, __val)					\
-	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
-	event->data[i].val = __val;				\
-	i++;
-
-	ADD(AGGR_MODE,	config->aggr_mode)
-	ADD(INTERVAL,	config->interval)
-	ADD(SCALE,	config->scale)
-
-	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
-		  "stat config terms unbalanced\n");
-#undef ADD
-
-	err = process(tool, (union perf_event *) event, NULL, machine);
-
-	free(event);
-	return err;
-}
-
-int perf_event__synthesize_stat(struct perf_tool *tool,
-				u32 cpu, u32 thread, u64 id,
-				struct perf_counts_values *count,
-				perf_event__handler_t process,
-				struct machine *machine)
-{
-	struct stat_event event;
-
-	event.header.type = PERF_RECORD_STAT;
-	event.header.size = sizeof(event);
-	event.header.misc = 0;
-
-	event.id        = id;
-	event.cpu       = cpu;
-	event.thread    = thread;
-	event.val       = count->val;
-	event.ena       = count->ena;
-	event.run       = count->run;
-
-	return process(tool, (union perf_event *) &event, NULL, machine);
-}
-
-int perf_event__synthesize_stat_round(struct perf_tool *tool,
-				      u64 evtime, u64 type,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	struct stat_round_event event;
-
-	event.header.type = PERF_RECORD_STAT_ROUND;
-	event.header.size = sizeof(event);
-	event.header.misc = 0;
-
-	event.time = evtime;
-	event.type = type;
-
-	return process(tool, (union perf_event *) &event, NULL, machine);
-}
-
 void perf_event__read_stat_config(struct perf_stat_config *config,
-				  struct stat_config_event *event)
+				  struct perf_record_stat_config *event)
 {
 	unsigned i;
 
@@ -1233,7 +135,7 @@
 		CASE(INTERVAL,  interval)
 #undef CASE
 		default:
-			pr_warning("unknown stat config term %" PRIu64 "\n",
+			pr_warning("unknown stat config term %" PRI_lu64 "\n",
 				   event->data[i].tag);
 		}
 	}
@@ -1334,9 +236,25 @@
 	return machine__process_switch_event(machine, event);
 }
 
+int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine)
+{
+	return machine__process_ksymbol(machine, event, sample);
+}
+
+int perf_event__process_bpf(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine)
+{
+	return machine__process_bpf(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
+	return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 "]: %c %s\n",
 		       event->mmap.pid, event->mmap.tid, event->mmap.start,
 		       event->mmap.len, event->mmap.pgoff,
 		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
@@ -1345,8 +263,8 @@
 
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
+	return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64
+			   " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
@@ -1360,7 +278,7 @@
 
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
 {
-	struct thread_map *threads = thread_map__new_event(&event->thread_map);
+	struct perf_thread_map *threads = thread_map__new_event(&event->thread_map);
 	size_t ret;
 
 	ret = fprintf(fp, " nr: ");
@@ -1370,13 +288,13 @@
 	else
 		ret += fprintf(fp, "failed to get threads from event\n");
 
-	thread_map__put(threads);
+	perf_thread_map__put(threads);
 	return ret;
 }
 
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
 {
-	struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+	struct perf_cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
 	size_t ret;
 
 	ret = fprintf(fp, ": ");
@@ -1386,7 +304,7 @@
 	else
 		ret += fprintf(fp, "failed to get cpumap from event\n");
 
-	cpu_map__put(cpus);
+	perf_cpu_map__put(cpus);
 	return ret;
 }
 
@@ -1431,7 +349,7 @@
 
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
+	return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s]\n",
 		       event->aux.aux_offset, event->aux.aux_size,
 		       event->aux.flags,
 		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
@@ -1463,7 +381,21 @@
 
 static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
+	return fprintf(fp, " lost %" PRI_lu64 "\n", event->lost.lost);
+}
+
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " addr %" PRI_lx64 " len %u type %u flags 0x%x name %s\n",
+		       event->ksymbol.addr, event->ksymbol.len,
+		       event->ksymbol.ksym_type,
+		       event->ksymbol.flags, event->ksymbol.name);
+}
+
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " type %u, flags %u, id %u\n",
+		       event->bpf.type, event->bpf.flags, event->bpf.id);
 }
 
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
@@ -1501,6 +433,12 @@
 	case PERF_RECORD_LOST:
 		ret += perf_event__fprintf_lost(event, fp);
 		break;
+	case PERF_RECORD_KSYMBOL:
+		ret += perf_event__fprintf_ksymbol(event, fp);
+		break;
+	case PERF_RECORD_BPF_EVENT:
+		ret += perf_event__fprintf_bpf(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
@@ -1576,6 +514,24 @@
 	return al->map;
 }
 
+/*
+ * For branch stacks or branch samples, the sample cpumode might not be correct
+ * because it applies only to the sample 'ip' and not necessary to 'addr' or
+ * branch stack addresses. If possible, use a fallback to deal with those cases.
+ */
+struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr,
+				struct addr_location *al)
+{
+	struct map *map = thread__find_map(thread, cpumode, addr, al);
+	struct machine *machine = thread->mg->machine;
+	u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr);
+
+	if (map || addr_cpumode == cpumode)
+		return map;
+
+	return thread__find_map(thread, addr_cpumode, addr, al);
+}
+
 struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
 				   u64 addr, struct addr_location *al)
 {
@@ -1585,6 +541,15 @@
 	return al->sym;
 }
 
+struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
+				      u64 addr, struct addr_location *al)
+{
+	al->sym = NULL;
+	if (thread__find_map_fb(thread, cpumode, addr, al))
+		al->sym = map__find_symbol(al->map, al->addr);
+	return al->sym;
+}
+
 /*
  * Callers need to drop the reference to al->thread, obtained in
  * machine__findnew_thread()
@@ -1678,7 +643,7 @@
 void thread__resolve(struct thread *thread, struct addr_location *al,
 		     struct perf_sample *sample)
 {
-	thread__find_map(thread, sample->cpumode, sample->addr, al);
+	thread__find_map_fb(thread, sample->cpumode, sample->addr, al);
 
 	al->cpu = sample->cpu;
 	al->sym = NULL;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index bfa60bc..a0a0c91 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -1,88 +1,38 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_RECORD_H
 #define __PERF_RECORD_H
-
-#include <limits.h>
+/*
+ * The linux/stddef.h isn't need here, but is needed for __always_inline used
+ * in files included from uapi/linux/perf_event.h such as
+ * /usr/include/linux/swab.h and /usr/include/linux/byteorder/little_endian.h,
+ * detected in at least musl libc, used in Alpine Linux. -acme
+ */
 #include <stdio.h>
-#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <perf/event.h>
+#include <linux/types.h>
 
-#include "../perf.h"
-#include "build-id.h"
 #include "perf_regs.h"
 
-struct mmap_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	u64 start;
-	u64 len;
-	u64 pgoff;
-	char filename[PATH_MAX];
-};
+struct dso;
+struct machine;
+struct perf_event_attr;
 
-struct mmap2_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	u64 start;
-	u64 len;
-	u64 pgoff;
-	u32 maj;
-	u32 min;
-	u64 ino;
-	u64 ino_generation;
-	u32 prot;
-	u32 flags;
-	char filename[PATH_MAX];
-};
-
-struct comm_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	char comm[16];
-};
-
-struct namespaces_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	u64 nr_namespaces;
-	struct perf_ns_link_info link_info[];
-};
-
-struct fork_event {
-	struct perf_event_header header;
-	u32 pid, ppid;
-	u32 tid, ptid;
-	u64 time;
-};
-
-struct lost_event {
-	struct perf_event_header header;
-	u64 id;
-	u64 lost;
-};
-
-struct lost_samples_event {
-	struct perf_event_header header;
-	u64 lost;
-};
-
+#ifdef __LP64__
 /*
- * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
+ * /usr/include/inttypes.h uses just 'lu' for PRIu64, but we end up defining
+ * __u64 as long long unsigned int, and then -Werror=format= kicks in and
+ * complains of the mismatched types, so use these two special extra PRI
+ * macros to overcome that.
  */
-struct read_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-	u64 value;
-	u64 time_enabled;
-	u64 time_running;
-	u64 id;
-};
-
-struct throttle_event {
-	struct perf_event_header header;
-	u64 time;
-	u64 id;
-	u64 stream_id;
-};
+#define PRI_lu64 "l" PRIu64
+#define PRI_lx64 "l" PRIx64
+#define PRI_ld64 "l" PRId64
+#else
+#define PRI_lu64 PRIu64
+#define PRI_lx64 PRIx64
+#define PRI_ld64 PRId64
+#endif
 
 #define PERF_SAMPLE_MASK				\
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
@@ -94,11 +44,6 @@
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
-struct sample_event {
-	struct perf_event_header        header;
-	u64 array[];
-};
-
 struct regs_dump {
 	u64 abi;
 	u64 mask;
@@ -137,26 +82,7 @@
 	u64 ips[0];
 };
 
-struct branch_flags {
-	u64 mispred:1;
-	u64 predicted:1;
-	u64 in_tx:1;
-	u64 abort:1;
-	u64 cycles:16;
-	u64 type:4;
-	u64 reserved:40;
-};
-
-struct branch_entry {
-	u64			from;
-	u64			to;
-	struct branch_flags	flags;
-};
-
-struct branch_stack {
-	u64			nr;
-	struct branch_entry	entries[0];
-};
+struct branch_stack;
 
 enum {
 	PERF_IP_FLAG_BRANCH		= 1ULL << 0,
@@ -198,6 +124,8 @@
 	u64 period;
 	u64 weight;
 	u64 transaction;
+	u64 insn_cnt;
+	u64 cyc_cnt;
 	u32 cpu;
 	u32 raw_size;
 	u64 data_src;
@@ -223,40 +151,6 @@
 	 PERF_MEM_S(LOCK, NA) |\
 	 PERF_MEM_S(TLB, NA))
 
-struct build_id_event {
-	struct perf_event_header header;
-	pid_t			 pid;
-	u8			 build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
-	char			 filename[];
-};
-
-enum perf_user_event_type { /* above any possible kernel type */
-	PERF_RECORD_USER_TYPE_START		= 64,
-	PERF_RECORD_HEADER_ATTR			= 64,
-	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* deprecated */
-	PERF_RECORD_HEADER_TRACING_DATA		= 66,
-	PERF_RECORD_HEADER_BUILD_ID		= 67,
-	PERF_RECORD_FINISHED_ROUND		= 68,
-	PERF_RECORD_ID_INDEX			= 69,
-	PERF_RECORD_AUXTRACE_INFO		= 70,
-	PERF_RECORD_AUXTRACE			= 71,
-	PERF_RECORD_AUXTRACE_ERROR		= 72,
-	PERF_RECORD_THREAD_MAP			= 73,
-	PERF_RECORD_CPU_MAP			= 74,
-	PERF_RECORD_STAT_CONFIG			= 75,
-	PERF_RECORD_STAT			= 76,
-	PERF_RECORD_STAT_ROUND			= 77,
-	PERF_RECORD_EVENT_UPDATE		= 78,
-	PERF_RECORD_TIME_CONV			= 79,
-	PERF_RECORD_HEADER_FEATURE		= 80,
-	PERF_RECORD_HEADER_MAX
-};
-
-enum auxtrace_error_type {
-	PERF_AUXTRACE_ERROR_ITRACE  = 1,
-	PERF_AUXTRACE_ERROR_MAX
-};
-
 /* Attribute type for custom synthesized events */
 #define PERF_TYPE_SYNTH		(INT_MAX + 1U)
 
@@ -378,333 +272,20 @@
 
 #define perf_sample__bad_synth_size(s, d) ((s)->raw_size < sizeof(d) - 4)
 
-/*
- * The kernel collects the number of events it couldn't send in a stretch and
- * when possible sends this number in a PERF_RECORD_LOST event. The number of
- * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
- * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
- * the sum of all struct lost_event.lost fields reported.
- *
- * The kernel discards mixed up samples and sends the number in a
- * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
- * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
- * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
- * all struct lost_samples_event.lost fields reported.
- *
- * The total_period is needed because by default auto-freq is used, so
- * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
- * the total number of low level events, it is necessary to to sum all struct
- * sample_event.period and stash the result in total_period.
- */
-struct events_stats {
-	u64 total_period;
-	u64 total_non_filtered_period;
-	u64 total_lost;
-	u64 total_lost_samples;
-	u64 total_aux_lost;
-	u64 total_aux_partial;
-	u64 total_invalid_chains;
-	u32 nr_events[PERF_RECORD_HEADER_MAX];
-	u32 nr_non_filtered_samples;
-	u32 nr_lost_warned;
-	u32 nr_unknown_events;
-	u32 nr_invalid_chains;
-	u32 nr_unknown_id;
-	u32 nr_unprocessable_samples;
-	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
-	u32 nr_proc_map_timeout;
-};
-
-enum {
-	PERF_CPU_MAP__CPUS = 0,
-	PERF_CPU_MAP__MASK = 1,
-};
-
-struct cpu_map_entries {
-	u16	nr;
-	u16	cpu[];
-};
-
-struct cpu_map_mask {
-	u16	nr;
-	u16	long_size;
-	unsigned long mask[];
-};
-
-struct cpu_map_data {
-	u16	type;
-	char	data[];
-};
-
-struct cpu_map_event {
-	struct perf_event_header	header;
-	struct cpu_map_data		data;
-};
-
-struct attr_event {
-	struct perf_event_header header;
-	struct perf_event_attr attr;
-	u64 id[];
-};
-
-enum {
-	PERF_EVENT_UPDATE__UNIT  = 0,
-	PERF_EVENT_UPDATE__SCALE = 1,
-	PERF_EVENT_UPDATE__NAME  = 2,
-	PERF_EVENT_UPDATE__CPUS  = 3,
-};
-
-struct event_update_event_cpus {
-	struct cpu_map_data cpus;
-};
-
-struct event_update_event_scale {
-	double scale;
-};
-
-struct event_update_event {
-	struct perf_event_header header;
-	u64 type;
-	u64 id;
-
-	char data[];
-};
-
-#define MAX_EVENT_NAME 64
-
-struct perf_trace_event_type {
-	u64	event_id;
-	char	name[MAX_EVENT_NAME];
-};
-
-struct event_type_event {
-	struct perf_event_header header;
-	struct perf_trace_event_type event_type;
-};
-
-struct tracing_data_event {
-	struct perf_event_header header;
-	u32 size;
-};
-
-struct id_index_entry {
-	u64 id;
-	u64 idx;
-	u64 cpu;
-	u64 tid;
-};
-
-struct id_index_event {
-	struct perf_event_header header;
-	u64 nr;
-	struct id_index_entry entries[0];
-};
-
-struct auxtrace_info_event {
-	struct perf_event_header header;
-	u32 type;
-	u32 reserved__; /* For alignment */
-	u64 priv[];
-};
-
-struct auxtrace_event {
-	struct perf_event_header header;
-	u64 size;
-	u64 offset;
-	u64 reference;
-	u32 idx;
-	u32 tid;
-	u32 cpu;
-	u32 reserved__; /* For alignment */
-};
-
-#define MAX_AUXTRACE_ERROR_MSG 64
-
-struct auxtrace_error_event {
-	struct perf_event_header header;
-	u32 type;
-	u32 code;
-	u32 cpu;
-	u32 pid;
-	u32 tid;
-	u32 reserved__; /* For alignment */
-	u64 ip;
-	char msg[MAX_AUXTRACE_ERROR_MSG];
-};
-
-struct aux_event {
-	struct perf_event_header header;
-	u64	aux_offset;
-	u64	aux_size;
-	u64	flags;
-};
-
-struct itrace_start_event {
-	struct perf_event_header header;
-	u32 pid, tid;
-};
-
-struct context_switch_event {
-	struct perf_event_header header;
-	u32 next_prev_pid;
-	u32 next_prev_tid;
-};
-
-struct thread_map_event_entry {
-	u64	pid;
-	char	comm[16];
-};
-
-struct thread_map_event {
-	struct perf_event_header	header;
-	u64				nr;
-	struct thread_map_event_entry	entries[];
-};
-
-enum {
-	PERF_STAT_CONFIG_TERM__AGGR_MODE	= 0,
-	PERF_STAT_CONFIG_TERM__INTERVAL		= 1,
-	PERF_STAT_CONFIG_TERM__SCALE		= 2,
-	PERF_STAT_CONFIG_TERM__MAX		= 3,
-};
-
-struct stat_config_event_entry {
-	u64	tag;
-	u64	val;
-};
-
-struct stat_config_event {
-	struct perf_event_header	header;
-	u64				nr;
-	struct stat_config_event_entry	data[];
-};
-
-struct stat_event {
-	struct perf_event_header	header;
-
-	u64	id;
-	u32	cpu;
-	u32	thread;
-
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-};
-
 enum {
 	PERF_STAT_ROUND_TYPE__INTERVAL	= 0,
 	PERF_STAT_ROUND_TYPE__FINAL	= 1,
 };
 
-struct stat_round_event {
-	struct perf_event_header	header;
-	u64				type;
-	u64				time;
-};
-
-struct time_conv_event {
-	struct perf_event_header header;
-	u64 time_shift;
-	u64 time_mult;
-	u64 time_zero;
-};
-
-struct feature_event {
-	struct perf_event_header 	header;
-	u64				feat_id;
-	char				data[];
-};
-
-union perf_event {
-	struct perf_event_header	header;
-	struct mmap_event		mmap;
-	struct mmap2_event		mmap2;
-	struct comm_event		comm;
-	struct namespaces_event		namespaces;
-	struct fork_event		fork;
-	struct lost_event		lost;
-	struct lost_samples_event	lost_samples;
-	struct read_event		read;
-	struct throttle_event		throttle;
-	struct sample_event		sample;
-	struct attr_event		attr;
-	struct event_update_event	event_update;
-	struct event_type_event		event_type;
-	struct tracing_data_event	tracing_data;
-	struct build_id_event		build_id;
-	struct id_index_event		id_index;
-	struct auxtrace_info_event	auxtrace_info;
-	struct auxtrace_event		auxtrace;
-	struct auxtrace_error_event	auxtrace_error;
-	struct aux_event		aux;
-	struct itrace_start_event	itrace_start;
-	struct context_switch_event	context_switch;
-	struct thread_map_event		thread_map;
-	struct cpu_map_event		cpu_map;
-	struct stat_config_event	stat_config;
-	struct stat_event		stat;
-	struct stat_round_event		stat_round;
-	struct time_conv_event		time_conv;
-	struct feature_event		feat;
-};
-
 void perf_event__print_totals(void);
 
-struct perf_tool;
-struct thread_map;
-struct cpu_map;
+struct perf_cpu_map;
+struct perf_record_stat_config;
 struct perf_stat_config;
-struct perf_counts_values;
+struct perf_tool;
 
-typedef int (*perf_event__handler_t)(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_sample *sample,
-				     struct machine *machine);
-
-int perf_event__synthesize_thread_map(struct perf_tool *tool,
-				      struct thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data,
-				      unsigned int proc_map_timeout);
-int perf_event__synthesize_thread_map2(struct perf_tool *tool,
-				      struct thread_map *threads,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-int perf_event__synthesize_cpu_map(struct perf_tool *tool,
-				   struct cpu_map *cpus,
-				   perf_event__handler_t process,
-				   struct machine *machine);
-int perf_event__synthesize_threads(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data,
-				   unsigned int proc_map_timeout,
-				   unsigned int nr_threads_synthesize);
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine);
-int perf_event__synthesize_stat_config(struct perf_tool *tool,
-				       struct perf_stat_config *config,
-				       perf_event__handler_t process,
-				       struct machine *machine);
 void perf_event__read_stat_config(struct perf_stat_config *config,
-				  struct stat_config_event *event);
-int perf_event__synthesize_stat(struct perf_tool *tool,
-				u32 cpu, u32 thread, u64 id,
-				struct perf_counts_values *count,
-				perf_event__handler_t process,
-				struct machine *machine);
-int perf_event__synthesize_stat_round(struct perf_tool *tool,
-				      u64 time, u64 type,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-int perf_event__synthesize_modules(struct perf_tool *tool,
-				   perf_event__handler_t process,
-				   struct machine *machine);
+				  struct perf_record_stat_config *event);
 
 int perf_event__process_comm(struct perf_tool *tool,
 			     union perf_event *event,
@@ -750,10 +331,14 @@
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
-int perf_tool__process_synth_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct machine *machine,
-				   perf_event__handler_t process);
+int perf_event__process_ksymbol(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine);
+int perf_event__process_bpf(struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -775,35 +360,6 @@
 
 const char *perf_event__name(unsigned int id);
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 read_format);
-int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 read_format,
-				  const struct perf_sample *sample);
-
-pid_t perf_event__synthesize_comm(struct perf_tool *tool,
-				  union perf_event *event, pid_t pid,
-				  perf_event__handler_t process,
-				  struct machine *machine);
-
-int perf_event__synthesize_namespaces(struct perf_tool *tool,
-				      union perf_event *event,
-				      pid_t pid, pid_t tgid,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-
-int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-				       union perf_event *event,
-				       pid_t pid, pid_t tgid,
-				       perf_event__handler_t process,
-				       struct machine *machine,
-				       bool mmap_data,
-				       unsigned int proc_map_timeout);
-
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine);
-
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
@@ -814,20 +370,24 @@
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
 
-void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max);
-void  cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max);
+void  cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
 			       u16 type, int max);
 
 void event_attr_init(struct perf_event_attr *attr);
 
 int perf_event_paranoid(void);
+bool perf_event_paranoid_check(int max_level);
 
 extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
+extern unsigned int proc_map_timeout;
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h
new file mode 100644
index 0000000..859cb34
--- /dev/null
+++ b/tools/perf/util/events_stats.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_EVENTS_STATS_
+#define __PERF_EVENTS_STATS_
+
+#include <stdio.h>
+#include <perf/event.h>
+#include <linux/types.h>
+#include "auxtrace.h"
+
+/*
+ * The kernel collects the number of events it couldn't send in a stretch and
+ * when possible sends this number in a PERF_RECORD_LOST event. The number of
+ * such "chunks" of lost events is stored in .nr_events[PERF_EVENT_LOST] while
+ * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
+ * the sum of all struct perf_record_lost.lost fields reported.
+ *
+ * The kernel discards mixed up samples and sends the number in a
+ * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
+ * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
+ * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
+ * all struct perf_record_lost_samples.lost fields reported.
+ *
+ * The total_period is needed because by default auto-freq is used, so
+ * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
+ * the total number of low level events, it is necessary to to sum all struct
+ * perf_record_sample.period and stash the result in total_period.
+ */
+struct events_stats {
+	u64 total_period;
+	u64 total_non_filtered_period;
+	u64 total_lost;
+	u64 total_lost_samples;
+	u64 total_aux_lost;
+	u64 total_aux_partial;
+	u64 total_invalid_chains;
+	u32 nr_events[PERF_RECORD_HEADER_MAX];
+	u32 nr_non_filtered_samples;
+	u32 nr_lost_warned;
+	u32 nr_unknown_events;
+	u32 nr_invalid_chains;
+	u32 nr_unknown_id;
+	u32 nr_unprocessable_samples;
+	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
+};
+
+void events_stats__inc(struct events_stats *stats, u32 type);
+
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
+
+#endif /* __PERF_EVENTS_STATS_ */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df..de79c73 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1,26 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Parts came from builtin-{top,stat,record}.c, see those files for further
  * copyright notes.
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
-#include "util.h"
 #include <api/fs/fs.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <poll.h>
 #include "cpumap.h"
+#include "util/mmap.h"
 #include "thread_map.h"
 #include "target.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
 #include "units.h"
+#include <internal/lib.h> // page_size
+#include "../perf.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 #include <signal.h>
 #include <unistd.h>
+#include <sched.h>
+#include <stdlib.h>
 
 #include "parse-events.h"
 #include <subcmd/parse-options.h>
@@ -33,52 +37,59 @@
 #include <linux/hash.h>
 #include <linux/log2.h>
 #include <linux/err.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <perf/evlist.h>
+#include <perf/evsel.h>
+#include <perf/cpumap.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+#include <internal/xyarray.h>
 
-void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
-		       struct thread_map *threads)
+#ifdef LACKS_SIGQUEUE_PROTOTYPE
+int sigqueue(pid_t pid, int sig, const union sigval value);
+#endif
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
+
+void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
+		  struct perf_thread_map *threads)
 {
-	int i;
-
-	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
-		INIT_HLIST_HEAD(&evlist->heads[i]);
-	INIT_LIST_HEAD(&evlist->entries);
-	perf_evlist__set_maps(evlist, cpus, threads);
-	fdarray__init(&evlist->pollfd, 64);
+	perf_evlist__init(&evlist->core);
+	perf_evlist__set_maps(&evlist->core, cpus, threads);
+	fdarray__init(&evlist->core.pollfd, 64);
 	evlist->workload.pid = -1;
 	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
 
-struct perf_evlist *perf_evlist__new(void)
+struct evlist *evlist__new(void)
 {
-	struct perf_evlist *evlist = zalloc(sizeof(*evlist));
+	struct evlist *evlist = zalloc(sizeof(*evlist));
 
 	if (evlist != NULL)
-		perf_evlist__init(evlist, NULL, NULL);
+		evlist__init(evlist, NULL, NULL);
 
 	return evlist;
 }
 
-struct perf_evlist *perf_evlist__new_default(void)
+struct evlist *perf_evlist__new_default(void)
 {
-	struct perf_evlist *evlist = perf_evlist__new();
+	struct evlist *evlist = evlist__new();
 
 	if (evlist && perf_evlist__add_default(evlist)) {
-		perf_evlist__delete(evlist);
+		evlist__delete(evlist);
 		evlist = NULL;
 	}
 
 	return evlist;
 }
 
-struct perf_evlist *perf_evlist__new_dummy(void)
+struct evlist *perf_evlist__new_dummy(void)
 {
-	struct perf_evlist *evlist = perf_evlist__new();
+	struct evlist *evlist = evlist__new();
 
 	if (evlist && perf_evlist__add_dummy(evlist)) {
-		perf_evlist__delete(evlist);
+		evlist__delete(evlist);
 		evlist = NULL;
 	}
 
@@ -92,17 +103,17 @@
  * Events with compatible sample types all have the same id_pos
  * and is_pos.  For convenience, put a copy on evlist.
  */
-void perf_evlist__set_id_pos(struct perf_evlist *evlist)
+void perf_evlist__set_id_pos(struct evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
+	struct evsel *first = evlist__first(evlist);
 
 	evlist->id_pos = first->id_pos;
 	evlist->is_pos = first->is_pos;
 }
 
-static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
+static void perf_evlist__update_id_pos(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
 		perf_evsel__calc_id_pos(evsel);
@@ -110,175 +121,132 @@
 	perf_evlist__set_id_pos(evlist);
 }
 
-static void perf_evlist__purge(struct perf_evlist *evlist)
+static void evlist__purge(struct evlist *evlist)
 {
-	struct perf_evsel *pos, *n;
+	struct evsel *pos, *n;
 
 	evlist__for_each_entry_safe(evlist, n, pos) {
-		list_del_init(&pos->node);
+		list_del_init(&pos->core.node);
 		pos->evlist = NULL;
-		perf_evsel__delete(pos);
+		evsel__delete(pos);
 	}
 
-	evlist->nr_entries = 0;
+	evlist->core.nr_entries = 0;
 }
 
-void perf_evlist__exit(struct perf_evlist *evlist)
+void evlist__exit(struct evlist *evlist)
 {
 	zfree(&evlist->mmap);
 	zfree(&evlist->overwrite_mmap);
-	fdarray__exit(&evlist->pollfd);
+	fdarray__exit(&evlist->core.pollfd);
 }
 
-void perf_evlist__delete(struct perf_evlist *evlist)
+void evlist__delete(struct evlist *evlist)
 {
 	if (evlist == NULL)
 		return;
 
-	perf_evlist__munmap(evlist);
-	perf_evlist__close(evlist);
-	cpu_map__put(evlist->cpus);
-	thread_map__put(evlist->threads);
-	evlist->cpus = NULL;
-	evlist->threads = NULL;
-	perf_evlist__purge(evlist);
-	perf_evlist__exit(evlist);
+	evlist__munmap(evlist);
+	evlist__close(evlist);
+	perf_cpu_map__put(evlist->core.cpus);
+	perf_thread_map__put(evlist->core.threads);
+	evlist->core.cpus = NULL;
+	evlist->core.threads = NULL;
+	evlist__purge(evlist);
+	evlist__exit(evlist);
 	free(evlist);
 }
 
-static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
-					  struct perf_evsel *evsel)
-{
-	/*
-	 * We already have cpus for evsel (via PMU sysfs) so
-	 * keep it, if there's no target cpu list defined.
-	 */
-	if (!evsel->own_cpus || evlist->has_user_cpus) {
-		cpu_map__put(evsel->cpus);
-		evsel->cpus = cpu_map__get(evlist->cpus);
-	} else if (evsel->cpus != evsel->own_cpus) {
-		cpu_map__put(evsel->cpus);
-		evsel->cpus = cpu_map__get(evsel->own_cpus);
-	}
-
-	thread_map__put(evsel->threads);
-	evsel->threads = thread_map__get(evlist->threads);
-}
-
-static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each_entry(evlist, evsel)
-		__perf_evlist__propagate_maps(evlist, evsel);
-}
-
-void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
+void evlist__add(struct evlist *evlist, struct evsel *entry)
 {
 	entry->evlist = evlist;
-	list_add_tail(&entry->node, &evlist->entries);
-	entry->idx = evlist->nr_entries;
+	entry->idx = evlist->core.nr_entries;
 	entry->tracking = !entry->idx;
 
-	if (!evlist->nr_entries++)
-		perf_evlist__set_id_pos(evlist);
+	perf_evlist__add(&evlist->core, &entry->core);
 
-	__perf_evlist__propagate_maps(evlist, entry);
+	if (evlist->core.nr_entries == 1)
+		perf_evlist__set_id_pos(evlist);
 }
 
-void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel)
+void evlist__remove(struct evlist *evlist, struct evsel *evsel)
 {
 	evsel->evlist = NULL;
-	list_del_init(&evsel->node);
-	evlist->nr_entries -= 1;
+	perf_evlist__remove(&evlist->core, &evsel->core);
 }
 
-void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+void perf_evlist__splice_list_tail(struct evlist *evlist,
 				   struct list_head *list)
 {
-	struct perf_evsel *evsel, *temp;
+	struct evsel *evsel, *temp;
 
 	__evlist__for_each_entry_safe(list, temp, evsel) {
-		list_del_init(&evsel->node);
-		perf_evlist__add(evlist, evsel);
+		list_del_init(&evsel->core.node);
+		evlist__add(evlist, evsel);
 	}
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
 {
-	struct perf_evsel *evsel, *leader;
+	struct evsel *evsel, *leader;
 
-	leader = list_entry(list->next, struct perf_evsel, node);
-	evsel = list_entry(list->prev, struct perf_evsel, node);
+	leader = list_entry(list->next, struct evsel, core.node);
+	evsel = list_entry(list->prev, struct evsel, core.node);
 
-	leader->nr_members = evsel->idx - leader->idx + 1;
+	leader->core.nr_members = evsel->idx - leader->idx + 1;
 
 	__evlist__for_each_entry(list, evsel) {
 		evsel->leader = leader;
 	}
 }
 
-void perf_evlist__set_leader(struct perf_evlist *evlist)
+void perf_evlist__set_leader(struct evlist *evlist)
 {
-	if (evlist->nr_entries) {
-		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->entries);
+	if (evlist->core.nr_entries) {
+		evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0;
+		__perf_evlist__set_leader(&evlist->core.entries);
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
+int __perf_evlist__add_default(struct evlist *evlist, bool precise)
 {
-	attr->precise_ip = 3;
-
-	while (attr->precise_ip != 0) {
-		int fd = sys_perf_event_open(attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr->precise_ip;
-	}
-}
-
-int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
-{
-	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
+	struct evsel *evsel = perf_evsel__new_cycles(precise);
 
 	if (evsel == NULL)
 		return -ENOMEM;
 
-	perf_evlist__add(evlist, evsel);
+	evlist__add(evlist, evsel);
 	return 0;
 }
 
-int perf_evlist__add_dummy(struct perf_evlist *evlist)
+int perf_evlist__add_dummy(struct evlist *evlist)
 {
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
+	struct evsel *evsel = perf_evsel__new_idx(&attr, evlist->core.nr_entries);
 
 	if (evsel == NULL)
 		return -ENOMEM;
 
-	perf_evlist__add(evlist, evsel);
+	evlist__add(evlist, evsel);
 	return 0;
 }
 
-static int perf_evlist__add_attrs(struct perf_evlist *evlist,
+static int evlist__add_attrs(struct evlist *evlist,
 				  struct perf_event_attr *attrs, size_t nr_attrs)
 {
-	struct perf_evsel *evsel, *n;
+	struct evsel *evsel, *n;
 	LIST_HEAD(head);
 	size_t i;
 
 	for (i = 0; i < nr_attrs; i++) {
-		evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i);
+		evsel = perf_evsel__new_idx(attrs + i, evlist->core.nr_entries + i);
 		if (evsel == NULL)
 			goto out_delete_partial_list;
-		list_add_tail(&evsel->node, &head);
+		list_add_tail(&evsel->core.node, &head);
 	}
 
 	perf_evlist__splice_list_tail(evlist, &head);
@@ -287,11 +255,11 @@
 
 out_delete_partial_list:
 	__evlist__for_each_entry_safe(&head, n, evsel)
-		perf_evsel__delete(evsel);
+		evsel__delete(evsel);
 	return -1;
 }
 
-int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+int __perf_evlist__add_default_attrs(struct evlist *evlist,
 				     struct perf_event_attr *attrs, size_t nr_attrs)
 {
 	size_t i;
@@ -299,31 +267,31 @@
 	for (i = 0; i < nr_attrs; i++)
 		event_attr_init(attrs + i);
 
-	return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+	return evlist__add_attrs(evlist, attrs, nr_attrs);
 }
 
-struct perf_evsel *
-perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
+struct evsel *
+perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
-		    (int)evsel->attr.config == id)
+		if (evsel->core.attr.type   == PERF_TYPE_TRACEPOINT &&
+		    (int)evsel->core.attr.config == id)
 			return evsel;
 	}
 
 	return NULL;
 }
 
-struct perf_evsel *
-perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+struct evsel *
+perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
 				     const char *name)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
+		if ((evsel->core.attr.type == PERF_TYPE_TRACEPOINT) &&
 		    (strcmp(evsel->name, name) == 0))
 			return evsel;
 	}
@@ -331,66 +299,66 @@
 	return NULL;
 }
 
-int perf_evlist__add_newtp(struct perf_evlist *evlist,
+int perf_evlist__add_newtp(struct evlist *evlist,
 			   const char *sys, const char *name, void *handler)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp(sys, name);
+	struct evsel *evsel = perf_evsel__newtp(sys, name);
 
 	if (IS_ERR(evsel))
 		return -1;
 
 	evsel->handler = handler;
-	perf_evlist__add(evlist, evsel);
+	evlist__add(evlist, evsel);
 	return 0;
 }
 
-static int perf_evlist__nr_threads(struct perf_evlist *evlist,
-				   struct perf_evsel *evsel)
+static int perf_evlist__nr_threads(struct evlist *evlist,
+				   struct evsel *evsel)
 {
-	if (evsel->system_wide)
+	if (evsel->core.system_wide)
 		return 1;
 	else
-		return thread_map__nr(evlist->threads);
+		return perf_thread_map__nr(evlist->core.threads);
 }
 
-void perf_evlist__disable(struct perf_evlist *evlist)
+void evlist__disable(struct evlist *evlist)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		perf_evsel__disable(pos);
+		evsel__disable(pos);
 	}
 
 	evlist->enabled = false;
 }
 
-void perf_evlist__enable(struct perf_evlist *evlist)
+void evlist__enable(struct evlist *evlist)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		perf_evsel__enable(pos);
+		evsel__enable(pos);
 	}
 
 	evlist->enabled = true;
 }
 
-void perf_evlist__toggle_enable(struct perf_evlist *evlist)
+void perf_evlist__toggle_enable(struct evlist *evlist)
 {
-	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
+	(evlist->enabled ? evlist__disable : evlist__enable)(evlist);
 }
 
-static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
-					 struct perf_evsel *evsel, int cpu)
+static int perf_evlist__enable_event_cpu(struct evlist *evlist,
+					 struct evsel *evsel, int cpu)
 {
 	int thread;
 	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
-	if (!evsel->fd)
+	if (!evsel->core.fd)
 		return -EINVAL;
 
 	for (thread = 0; thread < nr_threads; thread++) {
@@ -401,14 +369,14 @@
 	return 0;
 }
 
-static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
-					    struct perf_evsel *evsel,
+static int perf_evlist__enable_event_thread(struct evlist *evlist,
+					    struct evsel *evsel,
 					    int thread)
 {
 	int cpu;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
 
-	if (!evsel->fd)
+	if (!evsel->core.fd)
 		return -EINVAL;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -419,10 +387,10 @@
 	return 0;
 }
 
-int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
-				  struct perf_evsel *evsel, int idx)
+int perf_evlist__enable_event_idx(struct evlist *evlist,
+				  struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus);
 
 	if (per_cpu_mmaps)
 		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
@@ -430,154 +398,55 @@
 		return perf_evlist__enable_event_thread(evlist, evsel, idx);
 }
 
-int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+int evlist__add_pollfd(struct evlist *evlist, int fd)
 {
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
-	int nfds = 0;
-	struct perf_evsel *evsel;
-
-	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->system_wide)
-			nfds += nr_cpus;
-		else
-			nfds += nr_cpus * nr_threads;
-	}
-
-	if (fdarray__available_entries(&evlist->pollfd) < nfds &&
-	    fdarray__grow(&evlist->pollfd, nfds) < 0)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
-				     struct perf_mmap *map, short revent)
-{
-	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
-	/*
-	 * Save the idx so that when we filter out fds POLLHUP'ed we can
-	 * close the associated evlist->mmap[] entry.
-	 */
-	if (pos >= 0) {
-		evlist->pollfd.priv[pos].ptr = map;
-
-		fcntl(fd, F_SETFL, O_NONBLOCK);
-	}
-
-	return pos;
-}
-
-int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
-{
-	return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN);
+	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN);
 }
 
 static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
 					 void *arg __maybe_unused)
 {
-	struct perf_mmap *map = fda->priv[fd].ptr;
+	struct mmap *map = fda->priv[fd].ptr;
 
 	if (map)
 		perf_mmap__put(map);
 }
 
-int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
+int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask)
 {
-	return fdarray__filter(&evlist->pollfd, revents_and_mask,
+	return fdarray__filter(&evlist->core.pollfd, revents_and_mask,
 			       perf_evlist__munmap_filtered, NULL);
 }
 
-int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
+int evlist__poll(struct evlist *evlist, int timeout)
 {
-	return fdarray__poll(&evlist->pollfd, timeout);
+	return perf_evlist__poll(&evlist->core, timeout);
 }
 
-static void perf_evlist__id_hash(struct perf_evlist *evlist,
-				 struct perf_evsel *evsel,
-				 int cpu, int thread, u64 id)
-{
-	int hash;
-	struct perf_sample_id *sid = SID(evsel, cpu, thread);
-
-	sid->id = id;
-	sid->evsel = evsel;
-	hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
-	hlist_add_head(&sid->node, &evlist->heads[hash]);
-}
-
-void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id)
-{
-	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
-	evsel->id[evsel->ids++] = id;
-}
-
-int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd)
-{
-	u64 read_data[4] = { 0, };
-	int id_idx = 1; /* The first entry is the counter value */
-	u64 id;
-	int ret;
-
-	ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
-	if (!ret)
-		goto add;
-
-	if (errno != ENOTTY)
-		return -1;
-
-	/* Legacy way to get event id.. All hail to old kernels! */
-
-	/*
-	 * This way does not work with group format read, so bail
-	 * out in that case.
-	 */
-	if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP)
-		return -1;
-
-	if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
-	    read(fd, &read_data, sizeof(read_data)) == -1)
-		return -1;
-
-	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		++id_idx;
-	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		++id_idx;
-
-	id = read_data[id_idx];
-
- add:
-	perf_evlist__id_add(evlist, evsel, cpu, thread, id);
-	return 0;
-}
-
-static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
-				     struct perf_evsel *evsel, int idx, int cpu,
+static void perf_evlist__set_sid_idx(struct evlist *evlist,
+				     struct evsel *evsel, int idx, int cpu,
 				     int thread)
 {
 	struct perf_sample_id *sid = SID(evsel, cpu, thread);
 	sid->idx = idx;
-	if (evlist->cpus && cpu >= 0)
-		sid->cpu = evlist->cpus->map[cpu];
+	if (evlist->core.cpus && cpu >= 0)
+		sid->cpu = evlist->core.cpus->map[cpu];
 	else
 		sid->cpu = -1;
-	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = thread_map__pid(evlist->threads, thread);
+	if (!evsel->core.system_wide && evlist->core.threads && thread >= 0)
+		sid->tid = perf_thread_map__pid(evlist->core.threads, thread);
 	else
 		sid->tid = -1;
 }
 
-struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
+struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
 {
 	struct hlist_head *head;
 	struct perf_sample_id *sid;
 	int hash;
 
 	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
-	head = &evlist->heads[hash];
+	head = &evlist->core.heads[hash];
 
 	hlist_for_each_entry(sid, head, node)
 		if (sid->id == id)
@@ -586,24 +455,24 @@
 	return NULL;
 }
 
-struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id)
 {
 	struct perf_sample_id *sid;
 
-	if (evlist->nr_entries == 1 || !id)
-		return perf_evlist__first(evlist);
+	if (evlist->core.nr_entries == 1 || !id)
+		return evlist__first(evlist);
 
 	sid = perf_evlist__id2sid(evlist, id);
 	if (sid)
-		return sid->evsel;
+		return container_of(sid->evsel, struct evsel, core);
 
 	if (!perf_evlist__sample_id_all(evlist))
-		return perf_evlist__first(evlist);
+		return evlist__first(evlist);
 
 	return NULL;
 }
 
-struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
 						u64 id)
 {
 	struct perf_sample_id *sid;
@@ -613,15 +482,15 @@
 
 	sid = perf_evlist__id2sid(evlist, id);
 	if (sid)
-		return sid->evsel;
+		return container_of(sid->evsel, struct evsel, core);
 
 	return NULL;
 }
 
-static int perf_evlist__event2id(struct perf_evlist *evlist,
+static int perf_evlist__event2id(struct evlist *evlist,
 				 union perf_event *event, u64 *id)
 {
-	const u64 *array = event->sample.array;
+	const __u64 *array = event->sample.array;
 	ssize_t n;
 
 	n = (event->header.size - sizeof(event->header)) >> 3;
@@ -639,19 +508,19 @@
 	return 0;
 }
 
-struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
 					    union perf_event *event)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
+	struct evsel *first = evlist__first(evlist);
 	struct hlist_head *head;
 	struct perf_sample_id *sid;
 	int hash;
 	u64 id;
 
-	if (evlist->nr_entries == 1)
+	if (evlist->core.nr_entries == 1)
 		return first;
 
-	if (!first->attr.sample_id_all &&
+	if (!first->core.attr.sample_id_all &&
 	    event->header.type != PERF_RECORD_SAMPLE)
 		return first;
 
@@ -663,24 +532,24 @@
 		return first;
 
 	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
-	head = &evlist->heads[hash];
+	head = &evlist->core.heads[hash];
 
 	hlist_for_each_entry(sid, head, node) {
 		if (sid->id == id)
-			return sid->evsel;
+			return container_of(sid->evsel, struct evsel, core);
 	}
 	return NULL;
 }
 
-static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
+static int perf_evlist__set_paused(struct evlist *evlist, bool value)
 {
 	int i;
 
 	if (!evlist->overwrite_mmap)
 		return 0;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->overwrite_mmap[i].fd;
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
+		int fd = evlist->overwrite_mmap[i].core.fd;
 		int err;
 
 		if (fd < 0)
@@ -692,52 +561,52 @@
 	return 0;
 }
 
-static int perf_evlist__pause(struct perf_evlist *evlist)
+static int perf_evlist__pause(struct evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, true);
 }
 
-static int perf_evlist__resume(struct perf_evlist *evlist)
+static int perf_evlist__resume(struct evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, false);
 }
 
-static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
+static void evlist__munmap_nofree(struct evlist *evlist)
 {
 	int i;
 
 	if (evlist->mmap)
-		for (i = 0; i < evlist->nr_mmaps; i++)
+		for (i = 0; i < evlist->core.nr_mmaps; i++)
 			perf_mmap__munmap(&evlist->mmap[i]);
 
 	if (evlist->overwrite_mmap)
-		for (i = 0; i < evlist->nr_mmaps; i++)
+		for (i = 0; i < evlist->core.nr_mmaps; i++)
 			perf_mmap__munmap(&evlist->overwrite_mmap[i]);
 }
 
-void perf_evlist__munmap(struct perf_evlist *evlist)
+void evlist__munmap(struct evlist *evlist)
 {
-	perf_evlist__munmap_nofree(evlist);
+	evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
 	zfree(&evlist->overwrite_mmap);
 }
 
-static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist,
-						 bool overwrite)
+static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
+				       bool overwrite)
 {
 	int i;
-	struct perf_mmap *map;
+	struct mmap *map;
 
-	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
-	if (cpu_map__empty(evlist->cpus))
-		evlist->nr_mmaps = thread_map__nr(evlist->threads);
-	map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	evlist->core.nr_mmaps = perf_cpu_map__nr(evlist->core.cpus);
+	if (perf_cpu_map__empty(evlist->core.cpus))
+		evlist->core.nr_mmaps = perf_thread_map__nr(evlist->core.threads);
+	map = zalloc(evlist->core.nr_mmaps * sizeof(struct mmap));
 	if (!map)
 		return NULL;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		map[i].fd = -1;
-		map[i].overwrite = overwrite;
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
+		map[i].core.fd = -1;
+		map[i].core.overwrite = overwrite;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -747,41 +616,41 @@
 		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
 		 * thus does perf_mmap__get() on it.
 		 */
-		refcount_set(&map[i].refcnt, 0);
+		refcount_set(&map[i].core.refcnt, 0);
 	}
 	return map;
 }
 
 static bool
-perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
-			 struct perf_evsel *evsel)
+perf_evlist__should_poll(struct evlist *evlist __maybe_unused,
+			 struct evsel *evsel)
 {
-	if (evsel->attr.write_backward)
+	if (evsel->core.attr.write_backward)
 		return false;
 	return true;
 }
 
-static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
+static int evlist__mmap_per_evsel(struct evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu_idx,
 				       int thread, int *_output, int *_output_overwrite)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	int revent;
-	int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
+	int evlist_cpu = cpu_map__cpu(evlist->core.cpus, cpu_idx);
 
 	evlist__for_each_entry(evlist, evsel) {
-		struct perf_mmap *maps = evlist->mmap;
+		struct mmap *maps = evlist->mmap;
 		int *output = _output;
 		int fd;
 		int cpu;
 
 		mp->prot = PROT_READ | PROT_WRITE;
-		if (evsel->attr.write_backward) {
+		if (evsel->core.attr.write_backward) {
 			output = _output_overwrite;
 			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
-				maps = perf_evlist__alloc_mmap(evlist, true);
+				maps = evlist__alloc_mmap(evlist, true);
 				if (!maps)
 					return -1;
 				evlist->overwrite_mmap = maps;
@@ -791,10 +660,10 @@
 			mp->prot &= ~PROT_WRITE;
 		}
 
-		if (evsel->system_wide && thread)
+		if (evsel->core.system_wide && thread)
 			continue;
 
-		cpu = cpu_map__idx(evsel->cpus, evlist_cpu);
+		cpu = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu);
 		if (cpu == -1)
 			continue;
 
@@ -821,14 +690,14 @@
 		 * other events, so it should not need to be polled anyway.
 		 * Therefore don't add it for polling.
 		 */
-		if (!evsel->system_wide &&
-		    __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) {
+		if (!evsel->core.system_wide &&
+		     perf_evlist__add_pollfd(&evlist->core, fd, &maps[idx], revent) < 0) {
 			perf_mmap__put(&maps[idx]);
 			return -1;
 		}
 
-		if (evsel->attr.read_format & PERF_FORMAT_ID) {
-			if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
+		if (evsel->core.attr.read_format & PERF_FORMAT_ID) {
+			if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread,
 						   fd) < 0)
 				return -1;
 			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
@@ -839,12 +708,12 @@
 	return 0;
 }
 
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
+static int evlist__mmap_per_cpu(struct evlist *evlist,
 				     struct mmap_params *mp)
 {
 	int cpu, thread;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
+	int nr_threads = perf_thread_map__nr(evlist->core.threads);
 
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -855,7 +724,7 @@
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
-			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
+			if (evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
 							thread, &output, &output_overwrite))
 				goto out_unmap;
 		}
@@ -864,15 +733,15 @@
 	return 0;
 
 out_unmap:
-	perf_evlist__munmap_nofree(evlist);
+	evlist__munmap_nofree(evlist);
 	return -1;
 }
 
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
+static int evlist__mmap_per_thread(struct evlist *evlist,
 					struct mmap_params *mp)
 {
 	int thread;
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads = perf_thread_map__nr(evlist->core.threads);
 
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
@@ -882,7 +751,7 @@
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
-		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
+		if (evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
 						&output, &output_overwrite))
 			goto out_unmap;
 	}
@@ -890,7 +759,7 @@
 	return 0;
 
 out_unmap:
-	perf_evlist__munmap_nofree(evlist);
+	evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -917,7 +786,7 @@
 	return pages;
 }
 
-size_t perf_evlist__mmap_size(unsigned long pages)
+size_t evlist__mmap_size(unsigned long pages)
 {
 	if (pages == UINT_MAX)
 		pages = perf_event_mlock_kb_in_pages();
@@ -1000,7 +869,7 @@
 }
 
 /**
- * perf_evlist__mmap_ex - Create mmaps to receive events.
+ * evlist__mmap_ex - Create mmaps to receive events.
  * @evlist: list of events
  * @pages: map length in pages
  * @overwrite: overwrite older events?
@@ -1008,7 +877,7 @@
  * @auxtrace_overwrite - overwrite older auxtrace data?
  *
  * If @overwrite is %false the user needs to signal event consumption using
- * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
+ * perf_mmap__write_tail().  Using evlist__mmap_read() does this
  * automatically.
  *
  * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
@@ -1016,58 +885,60 @@
  *
  * Return: %0 on success, negative error code otherwise.
  */
-int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+int evlist__mmap_ex(struct evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush,
+			 int comp_level)
 {
-	struct perf_evsel *evsel;
-	const struct cpu_map *cpus = evlist->cpus;
-	const struct thread_map *threads = evlist->threads;
+	struct evsel *evsel;
+	const struct perf_cpu_map *cpus = evlist->core.cpus;
+	const struct perf_thread_map *threads = evlist->core.threads;
 	/*
 	 * Delay setting mp.prot: set it before calling perf_mmap__mmap.
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp;
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush,
+				  .comp_level = comp_level };
 
 	if (!evlist->mmap)
-		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
+		evlist->mmap = evlist__alloc_mmap(evlist, false);
 	if (!evlist->mmap)
 		return -ENOMEM;
 
-	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+	if (evlist->core.pollfd.entries == NULL && perf_evlist__alloc_pollfd(&evlist->core) < 0)
 		return -ENOMEM;
 
-	evlist->mmap_len = perf_evlist__mmap_size(pages);
-	pr_debug("mmap size %zuB\n", evlist->mmap_len);
-	mp.mask = evlist->mmap_len - page_size - 1;
+	evlist->core.mmap_len = evlist__mmap_size(pages);
+	pr_debug("mmap size %zuB\n", evlist->core.mmap_len);
+	mp.mask = evlist->core.mmap_len - page_size - 1;
 
-	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
 
 	evlist__for_each_entry(evlist, evsel) {
-		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-		    evsel->sample_id == NULL &&
-		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
+		if ((evsel->core.attr.read_format & PERF_FORMAT_ID) &&
+		    evsel->core.sample_id == NULL &&
+		    perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr) < 0)
 			return -ENOMEM;
 	}
 
-	if (cpu_map__empty(cpus))
-		return perf_evlist__mmap_per_thread(evlist, &mp);
+	if (perf_cpu_map__empty(cpus))
+		return evlist__mmap_per_thread(evlist, &mp);
 
-	return perf_evlist__mmap_per_cpu(evlist, &mp);
+	return evlist__mmap_per_cpu(evlist, &mp);
 }
 
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
+int evlist__mmap(struct evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false);
+	return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0);
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
+int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
 {
 	bool all_threads = (target->per_thread && target->system_wide);
-	struct cpu_map *cpus;
-	struct thread_map *threads;
+	struct perf_cpu_map *cpus;
+	struct perf_thread_map *threads;
 
 	/*
 	 * If specify '-a' and '--per-thread' to perf record, perf record
@@ -1094,68 +965,45 @@
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		cpus = cpu_map__dummy_new();
+		cpus = perf_cpu_map__dummy_new();
 	else
-		cpus = cpu_map__new(target->cpu_list);
+		cpus = perf_cpu_map__new(target->cpu_list);
 
 	if (!cpus)
 		goto out_delete_threads;
 
-	evlist->has_user_cpus = !!target->cpu_list;
+	evlist->core.has_user_cpus = !!target->cpu_list;
 
-	perf_evlist__set_maps(evlist, cpus, threads);
+	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
 	return 0;
 
 out_delete_threads:
-	thread_map__put(threads);
+	perf_thread_map__put(threads);
 	return -1;
 }
 
-void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
-			   struct thread_map *threads)
-{
-	/*
-	 * Allow for the possibility that one or another of the maps isn't being
-	 * changed i.e. don't put it.  Note we are assuming the maps that are
-	 * being applied are brand new and evlist is taking ownership of the
-	 * original reference count of 1.  If that is not the case it is up to
-	 * the caller to increase the reference count.
-	 */
-	if (cpus != evlist->cpus) {
-		cpu_map__put(evlist->cpus);
-		evlist->cpus = cpu_map__get(cpus);
-	}
-
-	if (threads != evlist->threads) {
-		thread_map__put(evlist->threads);
-		evlist->threads = thread_map__get(threads);
-	}
-
-	perf_evlist__propagate_maps(evlist);
-}
-
-void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
+void __perf_evlist__set_sample_bit(struct evlist *evlist,
 				   enum perf_event_sample_format bit)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__set_sample_bit(evsel, bit);
 }
 
-void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
+void __perf_evlist__reset_sample_bit(struct evlist *evlist,
 				     enum perf_event_sample_format bit)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
 		__perf_evsel__reset_sample_bit(evsel, bit);
 }
 
-int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
+int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	int err = 0;
 
 	evlist__for_each_entry(evlist, evsel) {
@@ -1166,7 +1014,7 @@
 		 * filters only work for tracepoint event, which doesn't have cpu limit.
 		 * So evlist and evsel should always be same.
 		 */
-		err = perf_evsel__apply_filter(evsel, evsel->filter);
+		err = perf_evsel__apply_filter(&evsel->core, evsel->filter);
 		if (err) {
 			*err_evsel = evsel;
 			break;
@@ -1176,13 +1024,13 @@
 	return err;
 }
 
-int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
+int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	int err = 0;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
 		err = perf_evsel__set_filter(evsel, filter);
@@ -1193,7 +1041,7 @@
 	return err;
 }
 
-int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids)
+int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
 {
 	char *filter;
 	int ret = -1;
@@ -1214,22 +1062,22 @@
 		}
 	}
 
-	ret = perf_evlist__set_filter(evlist, filter);
+	ret = perf_evlist__set_tp_filter(evlist, filter);
 out_free:
 	free(filter);
 	return ret;
 }
 
-int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid)
+int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
 {
-	return perf_evlist__set_filter_pids(evlist, 1, &pid);
+	return perf_evlist__set_tp_filter_pids(evlist, 1, &pid);
 }
 
-bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(struct evlist *evlist)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
-	if (evlist->nr_entries == 1)
+	if (evlist->core.nr_entries == 1)
 		return true;
 
 	if (evlist->id_pos < 0 || evlist->is_pos < 0)
@@ -1244,43 +1092,43 @@
 	return true;
 }
 
-u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+u64 __perf_evlist__combined_sample_type(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	if (evlist->combined_sample_type)
 		return evlist->combined_sample_type;
 
 	evlist__for_each_entry(evlist, evsel)
-		evlist->combined_sample_type |= evsel->attr.sample_type;
+		evlist->combined_sample_type |= evsel->core.attr.sample_type;
 
 	return evlist->combined_sample_type;
 }
 
-u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+u64 perf_evlist__combined_sample_type(struct evlist *evlist)
 {
 	evlist->combined_sample_type = 0;
 	return __perf_evlist__combined_sample_type(evlist);
 }
 
-u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist)
+u64 perf_evlist__combined_branch_type(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	u64 branch_type = 0;
 
 	evlist__for_each_entry(evlist, evsel)
-		branch_type |= evsel->attr.branch_sample_type;
+		branch_type |= evsel->core.attr.branch_sample_type;
 	return branch_type;
 }
 
-bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
+bool perf_evlist__valid_read_format(struct evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
-	u64 read_format = first->attr.read_format;
-	u64 sample_type = first->attr.sample_type;
+	struct evsel *first = evlist__first(evlist), *pos = first;
+	u64 read_format = first->core.attr.read_format;
+	u64 sample_type = first->core.attr.sample_type;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (read_format != pos->attr.read_format)
+		if (read_format != pos->core.attr.read_format)
 			return false;
 	}
 
@@ -1293,23 +1141,17 @@
 	return true;
 }
 
-u64 perf_evlist__read_format(struct perf_evlist *evlist)
+u16 perf_evlist__id_hdr_size(struct evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
-	return first->attr.read_format;
-}
-
-u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
-{
-	struct perf_evsel *first = perf_evlist__first(evlist);
+	struct evsel *first = evlist__first(evlist);
 	struct perf_sample *data;
 	u64 sample_type;
 	u16 size = 0;
 
-	if (!first->attr.sample_id_all)
+	if (!first->core.attr.sample_id_all)
 		goto out;
 
-	sample_type = first->attr.sample_type;
+	sample_type = first->core.attr.sample_type;
 
 	if (sample_type & PERF_SAMPLE_TID)
 		size += sizeof(data->tid) * 2;
@@ -1332,42 +1174,42 @@
 	return size;
 }
 
-bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_id_all(struct evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+	struct evsel *first = evlist__first(evlist), *pos = first;
 
 	evlist__for_each_entry_continue(evlist, pos) {
-		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+		if (first->core.attr.sample_id_all != pos->core.attr.sample_id_all)
 			return false;
 	}
 
 	return true;
 }
 
-bool perf_evlist__sample_id_all(struct perf_evlist *evlist)
+bool perf_evlist__sample_id_all(struct evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
-	return first->attr.sample_id_all;
+	struct evsel *first = evlist__first(evlist);
+	return first->core.attr.sample_id_all;
 }
 
-void perf_evlist__set_selected(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel)
+void perf_evlist__set_selected(struct evlist *evlist,
+			       struct evsel *evsel)
 {
 	evlist->selected = evsel;
 }
 
-void perf_evlist__close(struct perf_evlist *evlist)
+void evlist__close(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry_reverse(evlist, evsel)
-		perf_evsel__close(evsel);
+		evsel__close(evsel);
 }
 
-static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
+static int perf_evlist__create_syswide_maps(struct evlist *evlist)
 {
-	struct cpu_map	  *cpus;
-	struct thread_map *threads;
+	struct perf_cpu_map *cpus;
+	struct perf_thread_map *threads;
 	int err = -ENOMEM;
 
 	/*
@@ -1379,32 +1221,32 @@
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	cpus = cpu_map__new(NULL);
+	cpus = perf_cpu_map__new(NULL);
 	if (!cpus)
 		goto out;
 
-	threads = thread_map__new_dummy();
+	threads = perf_thread_map__new_dummy();
 	if (!threads)
 		goto out_put;
 
-	perf_evlist__set_maps(evlist, cpus, threads);
+	perf_evlist__set_maps(&evlist->core, cpus, threads);
 out:
 	return err;
 out_put:
-	cpu_map__put(cpus);
+	perf_cpu_map__put(cpus);
 	goto out;
 }
 
-int perf_evlist__open(struct perf_evlist *evlist)
+int evlist__open(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	int err;
 
 	/*
 	 * Default: one fd per CPU, all threads, aka systemwide
 	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
 	 */
-	if (evlist->threads == NULL && evlist->cpus == NULL) {
+	if (evlist->core.threads == NULL && evlist->core.cpus == NULL) {
 		err = perf_evlist__create_syswide_maps(evlist);
 		if (err < 0)
 			goto out_err;
@@ -1413,19 +1255,19 @@
 	perf_evlist__update_id_pos(evlist);
 
 	evlist__for_each_entry(evlist, evsel) {
-		err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
+		err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
 		if (err < 0)
 			goto out_err;
 	}
 
 	return 0;
 out_err:
-	perf_evlist__close(evlist);
+	evlist__close(evlist);
 	errno = -err;
 	return err;
 }
 
-int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
+int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target,
 				  const char *argv[], bool pipe_output,
 				  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
 {
@@ -1507,12 +1349,12 @@
 	}
 
 	if (target__none(target)) {
-		if (evlist->threads == NULL) {
+		if (evlist->core.threads == NULL) {
 			fprintf(stderr, "FATAL: evlist->threads need to be set at this point (%s:%d).\n",
 				__func__, __LINE__);
 			goto out_close_pipes;
 		}
-		thread_map__set_pid(evlist->threads, 0, evlist->workload.pid);
+		perf_thread_map__set_pid(evlist->core.threads, 0, evlist->workload.pid);
 	}
 
 	close(child_ready_pipe[1]);
@@ -1539,7 +1381,7 @@
 	return -1;
 }
 
-int perf_evlist__start_workload(struct perf_evlist *evlist)
+int perf_evlist__start_workload(struct evlist *evlist)
 {
 	if (evlist->workload.cork_fd > 0) {
 		char bf = 0;
@@ -1558,41 +1400,28 @@
 	return 0;
 }
 
-int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
 			      struct perf_sample *sample)
 {
-	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+	struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
 
 	if (!evsel)
 		return -EFAULT;
 	return perf_evsel__parse_sample(evsel, event, sample);
 }
 
-int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
 					union perf_event *event,
 					u64 *timestamp)
 {
-	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+	struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
 
 	if (!evsel)
 		return -EFAULT;
 	return perf_evsel__parse_sample_timestamp(evsel, event, timestamp);
 }
 
-size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
-{
-	struct perf_evsel *evsel;
-	size_t printed = 0;
-
-	evlist__for_each_entry(evlist, evsel) {
-		printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
-				   perf_evsel__name(evsel));
-	}
-
-	return printed + fprintf(fp, "\n");
-}
-
-int perf_evlist__strerror_open(struct perf_evlist *evlist,
+int perf_evlist__strerror_open(struct evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
@@ -1621,20 +1450,20 @@
 				    "Hint:\tThe current value is %d.", value);
 		break;
 	case EINVAL: {
-		struct perf_evsel *first = perf_evlist__first(evlist);
+		struct evsel *first = evlist__first(evlist);
 		int max_freq;
 
 		if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
 			goto out_default;
 
-		if (first->attr.sample_freq < (u64)max_freq)
+		if (first->core.attr.sample_freq < (u64)max_freq)
 			goto out_default;
 
 		printed = scnprintf(buf, size,
 				    "Error:\t%s.\n"
 				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
 				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
-				    emsg, max_freq, first->attr.sample_freq);
+				    emsg, max_freq, first->core.attr.sample_freq);
 		break;
 	}
 	default:
@@ -1646,10 +1475,10 @@
 	return 0;
 }
 
-int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
+int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size)
 {
 	char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
-	int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
+	int pages_attempted = evlist->core.mmap_len / 1024, pages_max_per_user, printed = 0;
 
 	switch (err) {
 	case EPERM:
@@ -1677,27 +1506,27 @@
 	return 0;
 }
 
-void perf_evlist__to_front(struct perf_evlist *evlist,
-			   struct perf_evsel *move_evsel)
+void perf_evlist__to_front(struct evlist *evlist,
+			   struct evsel *move_evsel)
 {
-	struct perf_evsel *evsel, *n;
+	struct evsel *evsel, *n;
 	LIST_HEAD(move);
 
-	if (move_evsel == perf_evlist__first(evlist))
+	if (move_evsel == evlist__first(evlist))
 		return;
 
 	evlist__for_each_entry_safe(evlist, n, evsel) {
 		if (evsel->leader == move_evsel->leader)
-			list_move_tail(&evsel->node, &move);
+			list_move_tail(&evsel->core.node, &move);
 	}
 
-	list_splice(&move, &evlist->entries);
+	list_splice(&move, &evlist->core.entries);
 }
 
-void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
-				     struct perf_evsel *tracking_evsel)
+void perf_evlist__set_tracking_event(struct evlist *evlist,
+				     struct evsel *tracking_evsel)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	if (tracking_evsel->tracking)
 		return;
@@ -1710,11 +1539,11 @@
 	tracking_evsel->tracking = true;
 }
 
-struct perf_evsel *
-perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+struct evsel *
+perf_evlist__find_evsel_by_str(struct evlist *evlist,
 			       const char *str)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (!evsel->name)
@@ -1726,7 +1555,7 @@
 	return NULL;
 }
 
-void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
+void perf_evlist__toggle_bkw_mmap(struct evlist *evlist,
 				  enum bkw_mmap_state state)
 {
 	enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
@@ -1784,12 +1613,12 @@
 	return;
 }
 
-bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+bool perf_evlist__exclude_kernel(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (!evsel->attr.exclude_kernel)
+		if (!evsel->core.attr.exclude_kernel)
 			return false;
 	}
 
@@ -1801,12 +1630,169 @@
  * the group display. Set the artificial group and set the leader's
  * forced_leader flag to notify the display code.
  */
-void perf_evlist__force_leader(struct perf_evlist *evlist)
+void perf_evlist__force_leader(struct evlist *evlist)
 {
 	if (!evlist->nr_groups) {
-		struct perf_evsel *leader = perf_evlist__first(evlist);
+		struct evsel *leader = evlist__first(evlist);
 
 		perf_evlist__set_leader(evlist);
 		leader->forced_leader = true;
 	}
 }
+
+struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
+						 struct evsel *evsel)
+{
+	struct evsel *c2, *leader;
+	bool is_open = true;
+
+	leader = evsel->leader;
+	pr_debug("Weak group for %s/%d failed\n",
+			leader->name, leader->core.nr_members);
+
+	/*
+	 * for_each_group_member doesn't work here because it doesn't
+	 * include the first entry.
+	 */
+	evlist__for_each_entry(evsel_list, c2) {
+		if (c2 == evsel)
+			is_open = false;
+		if (c2->leader == leader) {
+			if (is_open)
+				perf_evsel__close(&c2->core);
+			c2->leader = c2;
+			c2->core.nr_members = 0;
+		}
+	}
+	return leader;
+}
+
+int perf_evlist__add_sb_event(struct evlist **evlist,
+			      struct perf_event_attr *attr,
+			      perf_evsel__sb_cb_t cb,
+			      void *data)
+{
+	struct evsel *evsel;
+	bool new_evlist = (*evlist) == NULL;
+
+	if (*evlist == NULL)
+		*evlist = evlist__new();
+	if (*evlist == NULL)
+		return -1;
+
+	if (!attr->sample_id_all) {
+		pr_warning("enabling sample_id_all for all side band events\n");
+		attr->sample_id_all = 1;
+	}
+
+	evsel = perf_evsel__new_idx(attr, (*evlist)->core.nr_entries);
+	if (!evsel)
+		goto out_err;
+
+	evsel->side_band.cb = cb;
+	evsel->side_band.data = data;
+	evlist__add(*evlist, evsel);
+	return 0;
+
+out_err:
+	if (new_evlist) {
+		evlist__delete(*evlist);
+		*evlist = NULL;
+	}
+	return -1;
+}
+
+static void *perf_evlist__poll_thread(void *arg)
+{
+	struct evlist *evlist = arg;
+	bool draining = false;
+	int i, done = 0;
+	/*
+	 * In order to read symbols from other namespaces perf to needs to call
+	 * setns(2).  This isn't permitted if the struct_fs has multiple users.
+	 * unshare(2) the fs so that we may continue to setns into namespaces
+	 * that we're observing when, for instance, reading the build-ids at
+	 * the end of a 'perf record' session.
+	 */
+	unshare(CLONE_FS);
+
+	while (!done) {
+		bool got_data = false;
+
+		if (evlist->thread.done)
+			draining = true;
+
+		if (!draining)
+			evlist__poll(evlist, 1000);
+
+		for (i = 0; i < evlist->core.nr_mmaps; i++) {
+			struct mmap *map = &evlist->mmap[i];
+			union perf_event *event;
+
+			if (perf_mmap__read_init(map))
+				continue;
+			while ((event = perf_mmap__read_event(map)) != NULL) {
+				struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+				if (evsel && evsel->side_band.cb)
+					evsel->side_band.cb(event, evsel->side_band.data);
+				else
+					pr_warning("cannot locate proper evsel for the side band event\n");
+
+				perf_mmap__consume(map);
+				got_data = true;
+			}
+			perf_mmap__read_done(map);
+		}
+
+		if (draining && !got_data)
+			break;
+	}
+	return NULL;
+}
+
+int perf_evlist__start_sb_thread(struct evlist *evlist,
+				 struct target *target)
+{
+	struct evsel *counter;
+
+	if (!evlist)
+		return 0;
+
+	if (perf_evlist__create_maps(evlist, target))
+		goto out_delete_evlist;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__open(counter, evlist->core.cpus,
+				     evlist->core.threads) < 0)
+			goto out_delete_evlist;
+	}
+
+	if (evlist__mmap(evlist, UINT_MAX))
+		goto out_delete_evlist;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (evsel__enable(counter))
+			goto out_delete_evlist;
+	}
+
+	evlist->thread.done = 0;
+	if (pthread_create(&evlist->thread.th, NULL, perf_evlist__poll_thread, evlist))
+		goto out_delete_evlist;
+
+	return 0;
+
+out_delete_evlist:
+	evlist__delete(evlist);
+	evlist = NULL;
+	return -1;
+}
+
+void perf_evlist__stop_sb_thread(struct evlist *evlist)
+{
+	if (!evlist)
+		return;
+	evlist->thread.done = 1;
+	pthread_join(evlist->thread.th, NULL);
+	evlist__delete(evlist);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dc66436..7cfe755 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -7,32 +7,51 @@
 #include <linux/refcount.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
-#include <stdio.h>
-#include "../perf.h"
-#include "event.h"
+#include <internal/evlist.h>
+#include <internal/evsel.h>
+#include "events_stats.h"
 #include "evsel.h"
-#include "mmap.h"
-#include "util.h"
+#include <pthread.h>
 #include <signal.h>
 #include <unistd.h>
 
 struct pollfd;
 struct thread_map;
-struct cpu_map;
+struct perf_cpu_map;
 struct record_opts;
 
-#define PERF_EVLIST__HLIST_BITS 8
-#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+	BKW_MMAP_NOTREADY,
+	BKW_MMAP_RUNNING,
+	BKW_MMAP_DATA_PENDING,
+	BKW_MMAP_EMPTY,
+};
 
-struct perf_evlist {
-	struct list_head entries;
-	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
-	int		 nr_entries;
+struct evlist {
+	struct perf_evlist core;
 	int		 nr_groups;
-	int		 nr_mmaps;
 	bool		 enabled;
-	bool		 has_user_cpus;
-	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
 	u64		 combined_sample_type;
@@ -41,55 +60,67 @@
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
-	struct fdarray	 pollfd;
-	struct perf_mmap *mmap;
-	struct perf_mmap *overwrite_mmap;
-	struct thread_map *threads;
-	struct cpu_map	  *cpus;
-	struct perf_evsel *selected;
+	struct mmap *mmap;
+	struct mmap *overwrite_mmap;
+	struct evsel *selected;
 	struct events_stats stats;
 	struct perf_env	*env;
+	void (*trace_event_sample_raw)(struct evlist *evlist,
+				       union perf_event *event,
+				       struct perf_sample *sample);
 	u64		first_sample_time;
 	u64		last_sample_time;
+	struct {
+		pthread_t		th;
+		volatile int		done;
+	} thread;
 };
 
-struct perf_evsel_str_handler {
+struct evsel_str_handler {
 	const char *name;
 	void	   *handler;
 };
 
-struct perf_evlist *perf_evlist__new(void);
-struct perf_evlist *perf_evlist__new_default(void);
-struct perf_evlist *perf_evlist__new_dummy(void);
-void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
-		       struct thread_map *threads);
-void perf_evlist__exit(struct perf_evlist *evlist);
-void perf_evlist__delete(struct perf_evlist *evlist);
+struct evlist *evlist__new(void);
+struct evlist *perf_evlist__new_default(void);
+struct evlist *perf_evlist__new_dummy(void);
+void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
+		  struct perf_thread_map *threads);
+void evlist__exit(struct evlist *evlist);
+void evlist__delete(struct evlist *evlist);
 
-void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
-void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel);
+void evlist__add(struct evlist *evlist, struct evsel *entry);
+void evlist__remove(struct evlist *evlist, struct evsel *evsel);
 
-int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise);
+int __perf_evlist__add_default(struct evlist *evlist, bool precise);
 
-static inline int perf_evlist__add_default(struct perf_evlist *evlist)
+static inline int perf_evlist__add_default(struct evlist *evlist)
 {
 	return __perf_evlist__add_default(evlist, true);
 }
 
-int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+int __perf_evlist__add_default_attrs(struct evlist *evlist,
 				     struct perf_event_attr *attrs, size_t nr_attrs);
 
 #define perf_evlist__add_default_attrs(evlist, array) \
 	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
-int perf_evlist__add_dummy(struct perf_evlist *evlist);
+int perf_evlist__add_dummy(struct evlist *evlist);
 
-int perf_evlist__add_newtp(struct perf_evlist *evlist,
+int perf_evlist__add_sb_event(struct evlist **evlist,
+			      struct perf_event_attr *attr,
+			      perf_evsel__sb_cb_t cb,
+			      void *data);
+int perf_evlist__start_sb_thread(struct evlist *evlist,
+				 struct target *target);
+void perf_evlist__stop_sb_thread(struct evlist *evlist);
+
+int perf_evlist__add_newtp(struct evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
-void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
+void __perf_evlist__set_sample_bit(struct evlist *evlist,
 				   enum perf_event_sample_format bit);
-void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
+void __perf_evlist__reset_sample_bit(struct evlist *evlist,
 				     enum perf_event_sample_format bit);
 
 #define perf_evlist__set_sample_bit(evlist, bit) \
@@ -98,58 +129,51 @@
 #define perf_evlist__reset_sample_bit(evlist, bit) \
 	__perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit)
 
-int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
-int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid);
-int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids);
+int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter);
+int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
-struct perf_evsel *
-perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
+struct evsel *
+perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
 
-struct perf_evsel *
-perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+struct evsel *
+perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
 				     const char *name);
 
-void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
-			 int cpu, int thread, u64 id);
-int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-			   struct perf_evsel *evsel,
-			   int cpu, int thread, int fd);
+int evlist__add_pollfd(struct evlist *evlist, int fd);
+int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask);
 
-int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
-int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
-int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask);
+int evlist__poll(struct evlist *evlist, int timeout);
 
-int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
-
-struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
-struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
+struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id);
+struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
 						u64 id);
 
-struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
+struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id);
 
-void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
+void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state);
 
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+void evlist__mmap_consume(struct evlist *evlist, int idx);
 
-int perf_evlist__open(struct perf_evlist *evlist);
-void perf_evlist__close(struct perf_evlist *evlist);
+int evlist__open(struct evlist *evlist);
+void evlist__close(struct evlist *evlist);
 
 struct callchain_param;
 
-void perf_evlist__set_id_pos(struct perf_evlist *evlist);
+void perf_evlist__set_id_pos(struct evlist *evlist);
 bool perf_can_sample_identifier(void);
 bool perf_can_record_switch_events(void);
 bool perf_can_record_cpu_wide(void);
-void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
+void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 			 struct callchain_param *callchain);
 int record_opts__config(struct record_opts *opts);
 
-int perf_evlist__prepare_workload(struct perf_evlist *evlist,
+int perf_evlist__prepare_workload(struct evlist *evlist,
 				  struct target *target,
 				  const char *argv[], bool pipe_output,
 				  void (*exec_error)(int signo, siginfo_t *info,
 						     void *ucontext));
-int perf_evlist__start_workload(struct perf_evlist *evlist);
+int perf_evlist__start_workload(struct evlist *evlist);
 
 struct option;
 
@@ -160,76 +184,76 @@
 
 unsigned long perf_event_mlock_kb_in_pages(void);
 
-int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+int evlist__mmap_ex(struct evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite);
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
-void perf_evlist__munmap(struct perf_evlist *evlist);
+			 bool auxtrace_overwrite, int nr_cblocks,
+			 int affinity, int flush, int comp_level);
+int evlist__mmap(struct evlist *evlist, unsigned int pages);
+void evlist__munmap(struct evlist *evlist);
 
-size_t perf_evlist__mmap_size(unsigned long pages);
+size_t evlist__mmap_size(unsigned long pages);
 
-void perf_evlist__disable(struct perf_evlist *evlist);
-void perf_evlist__enable(struct perf_evlist *evlist);
-void perf_evlist__toggle_enable(struct perf_evlist *evlist);
+void evlist__disable(struct evlist *evlist);
+void evlist__enable(struct evlist *evlist);
+void perf_evlist__toggle_enable(struct evlist *evlist);
 
-int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
-				  struct perf_evsel *evsel, int idx);
+int perf_evlist__enable_event_idx(struct evlist *evlist,
+				  struct evsel *evsel, int idx);
 
-void perf_evlist__set_selected(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel);
+void perf_evlist__set_selected(struct evlist *evlist,
+			       struct evsel *evsel);
 
-void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
-			   struct thread_map *threads);
-int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
-int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
+int perf_evlist__create_maps(struct evlist *evlist, struct target *target);
+int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel);
 
 void __perf_evlist__set_leader(struct list_head *list);
-void perf_evlist__set_leader(struct perf_evlist *evlist);
+void perf_evlist__set_leader(struct evlist *evlist);
 
-u64 perf_evlist__read_format(struct perf_evlist *evlist);
-u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
-u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
-u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
-u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct evlist *evlist);
+u64 perf_evlist__combined_branch_type(struct evlist *evlist);
+bool perf_evlist__sample_id_all(struct evlist *evlist);
+u16 perf_evlist__id_hdr_size(struct evlist *evlist);
 
-int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
+int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
 			      struct perf_sample *sample);
 
-int perf_evlist__parse_sample_timestamp(struct perf_evlist *evlist,
+int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
 					union perf_event *event,
 					u64 *timestamp);
 
-bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
-bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
-bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_type(struct evlist *evlist);
+bool perf_evlist__valid_sample_id_all(struct evlist *evlist);
+bool perf_evlist__valid_read_format(struct evlist *evlist);
 
-void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+void perf_evlist__splice_list_tail(struct evlist *evlist,
 				   struct list_head *list);
 
-static inline bool perf_evlist__empty(struct perf_evlist *evlist)
+static inline bool perf_evlist__empty(struct evlist *evlist)
 {
-	return list_empty(&evlist->entries);
+	return list_empty(&evlist->core.entries);
 }
 
-static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
+static inline struct evsel *evlist__first(struct evlist *evlist)
 {
-	return list_entry(evlist->entries.next, struct perf_evsel, node);
+	struct perf_evsel *evsel = perf_evlist__first(&evlist->core);
+
+	return container_of(evsel, struct evsel, core);
 }
 
-static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
+static inline struct evsel *evlist__last(struct evlist *evlist)
 {
-	return list_entry(evlist->entries.prev, struct perf_evsel, node);
+	struct perf_evsel *evsel = perf_evlist__last(&evlist->core);
+
+	return container_of(evsel, struct evsel, core);
 }
 
-size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
+int perf_evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size);
+int perf_evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size);
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
-int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
-
-bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
-void perf_evlist__to_front(struct perf_evlist *evlist,
-			   struct perf_evsel *move_evsel);
+bool perf_evlist__can_select_event(struct evlist *evlist, const char *str);
+void perf_evlist__to_front(struct evlist *evlist,
+			   struct evsel *move_evsel);
 
 /**
  * __evlist__for_each_entry - iterate thru all the evsels
@@ -237,7 +261,7 @@
  * @evsel: struct evsel iterator
  */
 #define __evlist__for_each_entry(list, evsel) \
-        list_for_each_entry(evsel, list, node)
+        list_for_each_entry(evsel, list, core.node)
 
 /**
  * evlist__for_each_entry - iterate thru all the evsels
@@ -245,7 +269,7 @@
  * @evsel: struct evsel iterator
  */
 #define evlist__for_each_entry(evlist, evsel) \
-	__evlist__for_each_entry(&(evlist)->entries, evsel)
+	__evlist__for_each_entry(&(evlist)->core.entries, evsel)
 
 /**
  * __evlist__for_each_entry_continue - continue iteration thru all the evsels
@@ -253,7 +277,7 @@
  * @evsel: struct evsel iterator
  */
 #define __evlist__for_each_entry_continue(list, evsel) \
-        list_for_each_entry_continue(evsel, list, node)
+        list_for_each_entry_continue(evsel, list, core.node)
 
 /**
  * evlist__for_each_entry_continue - continue iteration thru all the evsels
@@ -261,7 +285,7 @@
  * @evsel: struct evsel iterator
  */
 #define evlist__for_each_entry_continue(evlist, evsel) \
-	__evlist__for_each_entry_continue(&(evlist)->entries, evsel)
+	__evlist__for_each_entry_continue(&(evlist)->core.entries, evsel)
 
 /**
  * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
@@ -269,7 +293,7 @@
  * @evsel: struct evsel iterator
  */
 #define __evlist__for_each_entry_reverse(list, evsel) \
-        list_for_each_entry_reverse(evsel, list, node)
+        list_for_each_entry_reverse(evsel, list, core.node)
 
 /**
  * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
@@ -277,7 +301,7 @@
  * @evsel: struct evsel iterator
  */
 #define evlist__for_each_entry_reverse(evlist, evsel) \
-	__evlist__for_each_entry_reverse(&(evlist)->entries, evsel)
+	__evlist__for_each_entry_reverse(&(evlist)->core.entries, evsel)
 
 /**
  * __evlist__for_each_entry_safe - safely iterate thru all the evsels
@@ -286,7 +310,7 @@
  * @evsel: struct evsel iterator
  */
 #define __evlist__for_each_entry_safe(list, tmp, evsel) \
-        list_for_each_entry_safe(evsel, tmp, list, node)
+        list_for_each_entry_safe(evsel, tmp, list, core.node)
 
 /**
  * evlist__for_each_entry_safe - safely iterate thru all the evsels
@@ -295,21 +319,21 @@
  * @tmp: struct evsel temp iterator
  */
 #define evlist__for_each_entry_safe(evlist, tmp, evsel) \
-	__evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel)
+	__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
 
-void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
-				     struct perf_evsel *tracking_evsel);
+void perf_evlist__set_tracking_event(struct evlist *evlist,
+				     struct evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+struct evsel *
+perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
 
-struct perf_evsel *
-perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
-
-struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
 					    union perf_event *event);
 
-bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
+bool perf_evlist__exclude_kernel(struct evlist *evlist);
 
-void perf_evlist__force_leader(struct perf_evlist *evlist);
+void perf_evlist__force_leader(struct evlist *evlist);
 
+struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
+						 struct evsel *evsel);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e7dbdcc..abc7fda 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Parts came from builtin-{top,stat,record}.c, see those files for further
  * copyright notes.
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include <byteswap.h>
@@ -18,57 +17,69 @@
 #include <linux/perf_event.h>
 #include <linux/compiler.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <dirent.h>
+#include <stdlib.h>
+#include <perf/evsel.h>
 #include "asm/bug.h"
 #include "callchain.h"
 #include "cgroup.h"
+#include "counts.h"
 #include "event.h"
 #include "evsel.h"
+#include "util/env.h"
+#include "util/evsel_config.h"
+#include "util/evsel_fprintf.h"
 #include "evlist.h"
-#include "util.h"
-#include "cpumap.h"
+#include <perf/cpumap.h>
 #include "thread_map.h"
 #include "target.h"
 #include "perf_regs.h"
+#include "record.h"
 #include "debug.h"
 #include "trace-event.h"
 #include "stat.h"
+#include "string2.h"
 #include "memswap.h"
+#include "util.h"
+#include "../perf-sys.h"
 #include "util/parse-branch-options.h"
+#include <internal/xyarray.h>
+#include <internal/lib.h>
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 
-static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
+static int perf_evsel__no_extra_init(struct evsel *evsel __maybe_unused)
 {
 	return 0;
 }
 
 void __weak test_attr__ready(void) { }
 
-static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
+static void perf_evsel__no_extra_fini(struct evsel *evsel __maybe_unused)
 {
 }
 
 static struct {
 	size_t	size;
-	int	(*init)(struct perf_evsel *evsel);
-	void	(*fini)(struct perf_evsel *evsel);
+	int	(*init)(struct evsel *evsel);
+	void	(*fini)(struct evsel *evsel);
 } perf_evsel__object = {
-	.size = sizeof(struct perf_evsel),
+	.size = sizeof(struct evsel),
 	.init = perf_evsel__no_extra_init,
 	.fini = perf_evsel__no_extra_fini,
 };
 
 int perf_evsel__object_config(size_t object_size,
-			      int (*init)(struct perf_evsel *evsel),
-			      void (*fini)(struct perf_evsel *evsel))
+			      int (*init)(struct evsel *evsel),
+			      void (*fini)(struct evsel *evsel))
 {
 
 	if (object_size == 0)
@@ -89,7 +100,7 @@
 	return 0;
 }
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y))
 
 int __perf_evsel__sample_size(u64 sample_type)
 {
@@ -113,7 +124,7 @@
  *
  * This function returns the position of the event id (PERF_SAMPLE_ID or
  * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
- * sample_event.
+ * perf_record_sample.
  */
 static int __perf_evsel__calc_id_pos(u64 sample_type)
 {
@@ -167,33 +178,33 @@
 	return idx;
 }
 
-void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
+void perf_evsel__calc_id_pos(struct evsel *evsel)
 {
-	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
-	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
+	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type);
+	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type);
 }
 
-void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+void __perf_evsel__set_sample_bit(struct evsel *evsel,
 				  enum perf_event_sample_format bit)
 {
-	if (!(evsel->attr.sample_type & bit)) {
-		evsel->attr.sample_type |= bit;
+	if (!(evsel->core.attr.sample_type & bit)) {
+		evsel->core.attr.sample_type |= bit;
 		evsel->sample_size += sizeof(u64);
 		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
-void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+void __perf_evsel__reset_sample_bit(struct evsel *evsel,
 				    enum perf_event_sample_format bit)
 {
-	if (evsel->attr.sample_type & bit) {
-		evsel->attr.sample_type &= ~bit;
+	if (evsel->core.attr.sample_type & bit) {
+		evsel->core.attr.sample_type &= ~bit;
 		evsel->sample_size -= sizeof(u64);
 		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+void perf_evsel__set_sample_id(struct evsel *evsel,
 			       bool can_sample_identifier)
 {
 	if (can_sample_identifier) {
@@ -202,7 +213,7 @@
 	} else {
 		perf_evsel__set_sample_bit(evsel, ID);
 	}
-	evsel->attr.read_format |= PERF_FORMAT_ID;
+	evsel->core.attr.read_format |= PERF_FORMAT_ID;
 }
 
 /**
@@ -213,7 +224,7 @@
  *
  * Return %true if event is function trace event
  */
-bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+bool perf_evsel__is_function_event(struct evsel *evsel)
 {
 #define FUNCTION_EVENT "ftrace:function"
 
@@ -223,18 +234,19 @@
 #undef FUNCTION_EVENT
 }
 
-void perf_evsel__init(struct perf_evsel *evsel,
-		      struct perf_event_attr *attr, int idx)
+void evsel__init(struct evsel *evsel,
+		 struct perf_event_attr *attr, int idx)
 {
+	perf_evsel__init(&evsel->core, attr);
 	evsel->idx	   = idx;
 	evsel->tracking	   = !idx;
-	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
+	evsel->bpf_obj	   = NULL;
 	evsel->bpf_fd	   = -1;
-	INIT_LIST_HEAD(&evsel->node);
 	INIT_LIST_HEAD(&evsel->config_terms);
 	perf_evsel__object.init(evsel);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
@@ -247,18 +259,18 @@
 	evsel->pmu_name      = NULL;
 }
 
-struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
+struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
-	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
+	struct evsel *evsel = zalloc(perf_evsel__object.size);
 
 	if (!evsel)
 		return NULL;
-	perf_evsel__init(evsel, attr, idx);
+	evsel__init(evsel, attr, idx);
 
 	if (perf_evsel__is_bpf_output(evsel)) {
-		evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+		evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
 					    PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
-		evsel->attr.sample_period = 1;
+		evsel->core.attr.sample_period = 1;
 	}
 
 	if (perf_evsel__is_clock(evsel)) {
@@ -277,41 +289,34 @@
 
 static bool perf_event_can_profile_kernel(void)
 {
-	return geteuid() == 0 || perf_event_paranoid() == -1;
+	return perf_event_paranoid_check(1);
 }
 
-struct perf_evsel *perf_evsel__new_cycles(bool precise)
+struct evsel *perf_evsel__new_cycles(bool precise)
 {
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= PERF_COUNT_HW_CPU_CYCLES,
 		.exclude_kernel	= !perf_event_can_profile_kernel(),
 	};
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	event_attr_init(&attr);
 
 	if (!precise)
 		goto new_event;
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 *
-	 * Just for probing the precise_ip:
-	 */
-	attr.sample_period = 1;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
 	 */
-	attr.sample_period = 0;
 new_event:
-	evsel = perf_evsel__new(&attr);
+	evsel = evsel__new(&attr);
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -321,7 +326,7 @@
 out:
 	return evsel;
 error_free:
-	perf_evsel__delete(evsel);
+	evsel__delete(evsel);
 	evsel = NULL;
 	goto out;
 }
@@ -329,9 +334,9 @@
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
+struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
-	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
+	struct evsel *evsel = zalloc(perf_evsel__object.size);
 	int err = -ENOMEM;
 
 	if (evsel == NULL) {
@@ -355,7 +360,7 @@
 		event_attr_init(&attr);
 		attr.config = evsel->tp_format->id;
 		attr.sample_period = 1;
-		perf_evsel__init(evsel, &attr, idx);
+		evsel__init(evsel, &attr, idx);
 	}
 
 	return evsel;
@@ -388,10 +393,10 @@
 	return "unknown-hardware";
 }
 
-static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 {
 	int colon = 0, r = 0;
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 	bool exclude_guest_default = false;
 
 #define MOD_PRINT(context, mod)	do {					\
@@ -424,9 +429,9 @@
 	return r;
 }
 
-static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
+	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->core.attr.config));
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
@@ -450,9 +455,9 @@
 	return "unknown-software";
 }
 
-static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
+	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->core.attr.config));
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
@@ -474,9 +479,9 @@
 	return r;
 }
 
-static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 	int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
 	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
 }
@@ -574,26 +579,35 @@
 	return scnprintf(bf, size, "%s", err);
 }
 
-static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
+	int ret = __perf_evsel__hw_cache_name(evsel->core.attr.config, bf, size);
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
-static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
+static int perf_evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
+	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
-const char *perf_evsel__name(struct perf_evsel *evsel)
+static int perf_evsel__tool_name(char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "duration_time");
+	return ret;
+}
+
+const char *perf_evsel__name(struct evsel *evsel)
 {
 	char bf[128];
 
+	if (!evsel)
+		goto out_unknown;
+
 	if (evsel->name)
 		return evsel->name;
 
-	switch (evsel->attr.type) {
+	switch (evsel->core.attr.type) {
 	case PERF_TYPE_RAW:
 		perf_evsel__raw_name(evsel, bf, sizeof(bf));
 		break;
@@ -607,7 +621,10 @@
 		break;
 
 	case PERF_TYPE_SOFTWARE:
-		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		if (evsel->tool_event)
+			perf_evsel__tool_name(bf, sizeof(bf));
+		else
+			perf_evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:
@@ -620,16 +637,19 @@
 
 	default:
 		scnprintf(bf, sizeof(bf), "unknown attr type: %d",
-			  evsel->attr.type);
+			  evsel->core.attr.type);
 		break;
 	}
 
 	evsel->name = strdup(bf);
 
-	return evsel->name ?: "unknown";
+	if (evsel->name)
+		return evsel->name;
+out_unknown:
+	return "unknown";
 }
 
-const char *perf_evsel__group_name(struct perf_evsel *evsel)
+const char *perf_evsel__group_name(struct evsel *evsel)
 {
 	return evsel->group_name ?: "anon group";
 }
@@ -644,10 +664,10 @@
  *  For record -e 'cycles,instructions' and report --group
  *    'cycles:u, instructions:u'
  */
-int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
+int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size)
 {
 	int ret = 0;
-	struct perf_evsel *pos;
+	struct evsel *pos;
 	const char *group_name = perf_evsel__group_name(evsel);
 
 	if (!evsel->forced_leader)
@@ -666,17 +686,21 @@
 	return ret;
 }
 
-static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
+static void __perf_evsel__config_callchain(struct evsel *evsel,
 					   struct record_opts *opts,
 					   struct callchain_param *param)
 {
 	bool function = perf_evsel__is_function_event(evsel);
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
 	attr->sample_max_stack = param->max_stack;
 
+	if (opts->kernel_callchains)
+		attr->exclude_callchain_user = 1;
+	if (opts->user_callchains)
+		attr->exclude_callchain_kernel = 1;
 	if (param->record_mode == CALLCHAIN_LBR) {
 		if (!opts->branch_stack) {
 			if (attr->exclude_user) {
@@ -699,7 +723,14 @@
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user |= PERF_REGS_MASK;
+			if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
+				attr->sample_regs_user |= DWARF_MINIMAL_REGS;
+				pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
+					   "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
+					   "so the minimal registers set (IP, SP) is explicitly forced.\n");
+			} else {
+				attr->sample_regs_user |= PERF_REGS_MASK;
+			}
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {
@@ -714,7 +745,7 @@
 	}
 }
 
-void perf_evsel__config_callchain(struct perf_evsel *evsel,
+void perf_evsel__config_callchain(struct evsel *evsel,
 				  struct record_opts *opts,
 				  struct callchain_param *param)
 {
@@ -723,10 +754,10 @@
 }
 
 static void
-perf_evsel__reset_callgraph(struct perf_evsel *evsel,
+perf_evsel__reset_callgraph(struct evsel *evsel,
 			    struct callchain_param *param)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 
 	perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
 	if (param->record_mode == CALLCHAIN_LBR) {
@@ -740,12 +771,12 @@
 	}
 }
 
-static void apply_config_terms(struct perf_evsel *evsel,
+static void apply_config_terms(struct evsel *evsel,
 			       struct record_opts *opts, bool track)
 {
 	struct perf_evsel_config_term *term;
 	struct list_head *config_terms = &evsel->config_terms;
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 	/* callgraph default */
 	struct callchain_param param = {
 		.record_mode = callchain_param.record_mode,
@@ -793,6 +824,9 @@
 		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
 			max_stack = term->val.max_stack;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+			evsel->max_events = term->val.max_events;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
@@ -807,6 +841,11 @@
 			break;
 		case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
 			break;
+		case PERF_EVSEL__CONFIG_TERM_PERCORE:
+			break;
+		case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT:
+			attr->aux_output = term->val.aux_output ? 1 : 0;
+			break;
 		default:
 			break;
 		}
@@ -853,17 +892,17 @@
 			if (sample_address) {
 				perf_evsel__set_sample_bit(evsel, ADDR);
 				perf_evsel__set_sample_bit(evsel, DATA_SRC);
-				evsel->attr.mmap_data = track;
+				evsel->core.attr.mmap_data = track;
 			}
 			perf_evsel__config_callchain(evsel, opts, &param);
 		}
 	}
 }
 
-static bool is_dummy_event(struct perf_evsel *evsel)
+static bool is_dummy_event(struct evsel *evsel)
 {
-	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
-	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+	return (evsel->core.attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->core.attr.config == PERF_COUNT_SW_DUMMY);
 }
 
 /*
@@ -894,11 +933,11 @@
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
+void perf_evsel__config(struct evsel *evsel, struct record_opts *opts,
 			struct callchain_param *callchain)
 {
-	struct perf_evsel *leader = evsel->leader;
-	struct perf_event_attr *attr = &evsel->attr;
+	struct evsel *leader = evsel->leader;
+	struct perf_event_attr *attr = &evsel->core.attr;
 	int track = evsel->tracking;
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
@@ -922,7 +961,7 @@
 		 * Apply group format only if we belong to group
 		 * with more than one members.
 		 */
-		if (leader->nr_members > 1) {
+		if (leader->core.nr_members > 1) {
 			attr->read_format |= PERF_FORMAT_GROUP;
 			attr->inherit = 0;
 		}
@@ -952,13 +991,21 @@
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
+
+		/*
+		 * We don't get sample for slave events, we make them
+		 * when delivering group leader sample. Set the slave
+		 * event to follow the master sample_type to ease up
+		 * report.
+		 */
+		attr->sample_type = leader->core.attr.sample_type;
 	}
 
 	if (opts->no_samples)
 		attr->sample_freq = 0;
 
 	if (opts->inherit_stat) {
-		evsel->attr.read_format |=
+		evsel->core.attr.read_format |=
 			PERF_FORMAT_TOTAL_TIME_ENABLED |
 			PERF_FORMAT_TOTAL_TIME_RUNNING |
 			PERF_FORMAT_ID;
@@ -976,7 +1023,7 @@
 	 * fault handler and its overall trickiness nature.
 	 */
 	if (perf_evsel__is_function_event(evsel))
-		evsel->attr.exclude_callchain_user = 1;
+		evsel->core.attr.exclude_callchain_user = 1;
 
 	if (callchain && callchain->enabled && !evsel->no_aux_samples)
 		perf_evsel__config_callchain(evsel, opts, callchain);
@@ -1031,6 +1078,8 @@
 	attr->mmap  = track;
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
+	attr->ksymbol = track && !perf_missing_features.ksymbol;
+	attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf;
 
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
@@ -1042,7 +1091,7 @@
 		perf_evsel__set_sample_bit(evsel, TRANSACTION);
 
 	if (opts->running_time) {
-		evsel->attr.read_format |=
+		evsel->core.attr.read_format |=
 			PERF_FORMAT_TOTAL_TIME_ENABLED |
 			PERF_FORMAT_TOTAL_TIME_RUNNING;
 	}
@@ -1076,7 +1125,7 @@
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1088,8 +1137,8 @@
 		attr->exclude_user   = 1;
 	}
 
-	if (evsel->own_cpus || evsel->unit)
-		evsel->attr.read_format |= PERF_FORMAT_ID;
+	if (evsel->core.own_cpus || evsel->unit)
+		evsel->core.attr.read_format |= PERF_FORMAT_ID;
 
 	/*
 	 * Apply event specific term settings,
@@ -1116,51 +1165,7 @@
 		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
-static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
-{
-	if (evsel->system_wide)
-		nthreads = 1;
-
-	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
-
-	if (evsel->fd) {
-		int cpu, thread;
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			for (thread = 0; thread < nthreads; thread++) {
-				FD(evsel, cpu, thread) = -1;
-			}
-		}
-	}
-
-	return evsel->fd != NULL ? 0 : -ENOMEM;
-}
-
-static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
-			  int ioc,  void *arg)
-{
-	int cpu, thread;
-
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread),
-			    err = ioctl(fd, ioc, arg);
-
-			if (err)
-				return err;
-		}
-	}
-
-	return 0;
-}
-
-int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
-{
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_SET_FILTER,
-				     (void *)filter);
-}
-
-int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter)
+int perf_evsel__set_filter(struct evsel *evsel, const char *filter)
 {
 	char *new_filter = strdup(filter);
 
@@ -1173,7 +1178,7 @@
 	return -1;
 }
 
-static int perf_evsel__append_filter(struct perf_evsel *evsel,
+static int perf_evsel__append_filter(struct evsel *evsel,
 				     const char *fmt, const char *filter)
 {
 	char *new_filter;
@@ -1190,109 +1195,75 @@
 	return -1;
 }
 
-int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter)
+int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter)
 {
 	return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
 }
 
-int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
+int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 {
 	return perf_evsel__append_filter(evsel, "%s,%s", filter);
 }
 
-int perf_evsel__enable(struct perf_evsel *evsel)
+int evsel__enable(struct evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_ENABLE,
-				     0);
+	int err = perf_evsel__enable(&evsel->core);
+
+	if (!err)
+		evsel->disabled = false;
+
+	return err;
 }
 
-int perf_evsel__disable(struct perf_evsel *evsel)
+int evsel__disable(struct evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_DISABLE,
-				     0);
+	int err = perf_evsel__disable(&evsel->core);
+	/*
+	 * We mark it disabled here so that tools that disable a event can
+	 * ignore events after they disable it. I.e. the ring buffer may have
+	 * already a few more events queued up before the kernel got the stop
+	 * request.
+	 */
+	if (!err)
+		evsel->disabled = true;
+
+	return err;
 }
 
-int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
-{
-	if (ncpus == 0 || nthreads == 0)
-		return 0;
-
-	if (evsel->system_wide)
-		nthreads = 1;
-
-	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
-	if (evsel->sample_id == NULL)
-		return -ENOMEM;
-
-	evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
-	if (evsel->id == NULL) {
-		xyarray__delete(evsel->sample_id);
-		evsel->sample_id = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void perf_evsel__free_fd(struct perf_evsel *evsel)
-{
-	xyarray__delete(evsel->fd);
-	evsel->fd = NULL;
-}
-
-static void perf_evsel__free_id(struct perf_evsel *evsel)
-{
-	xyarray__delete(evsel->sample_id);
-	evsel->sample_id = NULL;
-	zfree(&evsel->id);
-}
-
-static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
+static void perf_evsel__free_config_terms(struct evsel *evsel)
 {
 	struct perf_evsel_config_term *term, *h;
 
 	list_for_each_entry_safe(term, h, &evsel->config_terms, list) {
-		list_del(&term->list);
+		list_del_init(&term->list);
 		free(term);
 	}
 }
 
-void perf_evsel__close_fd(struct perf_evsel *evsel)
+void perf_evsel__exit(struct evsel *evsel)
 {
-	int cpu, thread;
-
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
-		for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-			close(FD(evsel, cpu, thread));
-			FD(evsel, cpu, thread) = -1;
-		}
-}
-
-void perf_evsel__exit(struct perf_evsel *evsel)
-{
-	assert(list_empty(&evsel->node));
+	assert(list_empty(&evsel->core.node));
 	assert(evsel->evlist == NULL);
-	perf_evsel__free_fd(evsel);
-	perf_evsel__free_id(evsel);
+	perf_evsel__free_counts(evsel);
+	perf_evsel__free_fd(&evsel->core);
+	perf_evsel__free_id(&evsel->core);
 	perf_evsel__free_config_terms(evsel);
 	cgroup__put(evsel->cgrp);
-	cpu_map__put(evsel->cpus);
-	cpu_map__put(evsel->own_cpus);
-	thread_map__put(evsel->threads);
+	perf_cpu_map__put(evsel->core.cpus);
+	perf_cpu_map__put(evsel->core.own_cpus);
+	perf_thread_map__put(evsel->core.threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
 }
 
-void perf_evsel__delete(struct perf_evsel *evsel)
+void evsel__delete(struct evsel *evsel)
 {
 	perf_evsel__exit(evsel);
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
+void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -1324,66 +1295,24 @@
 			count->val = 0;
 		} else if (count->run < count->ena) {
 			scaled = 1;
-			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+			count->val = (u64)((double) count->val * count->ena / count->run);
 		}
-	} else
-		count->ena = count->run = 0;
+	}
 
 	if (pscaled)
 		*pscaled = scaled;
 }
 
-static int perf_evsel__read_size(struct perf_evsel *evsel)
-{
-	u64 read_format = evsel->attr.read_format;
-	int entry = sizeof(u64); /* value */
-	int size = 0;
-	int nr = 1;
-
-	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		size += sizeof(u64);
-
-	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		size += sizeof(u64);
-
-	if (read_format & PERF_FORMAT_ID)
-		entry += sizeof(u64);
-
-	if (read_format & PERF_FORMAT_GROUP) {
-		nr = evsel->nr_members;
-		size += sizeof(u64);
-	}
-
-	size += entry * nr;
-	return size;
-}
-
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
-		     struct perf_counts_values *count)
-{
-	size_t size = perf_evsel__read_size(evsel);
-
-	memset(count, 0, sizeof(*count));
-
-	if (FD(evsel, cpu, thread) < 0)
-		return -EINVAL;
-
-	if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
-		return -errno;
-
-	return 0;
-}
-
 static int
-perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread)
+perf_evsel__read_one(struct evsel *evsel, int cpu, int thread)
 {
 	struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
 
-	return perf_evsel__read(evsel, cpu, thread, count);
+	return perf_evsel__read(&evsel->core, cpu, thread, count);
 }
 
 static void
-perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread,
+perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
 		      u64 val, u64 ena, u64 run)
 {
 	struct perf_counts_values *count;
@@ -1393,20 +1322,21 @@
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
-	count->loaded = true;
+
+	perf_counts__set_loaded(counter->counts, cpu, thread, true);
 }
 
 static int
-perf_evsel__process_group_data(struct perf_evsel *leader,
+perf_evsel__process_group_data(struct evsel *leader,
 			       int cpu, int thread, u64 *data)
 {
-	u64 read_format = leader->attr.read_format;
+	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
 	u64 nr, ena = 0, run = 0, i;
 
 	nr = *data++;
 
-	if (nr != (u64) leader->nr_members)
+	if (nr != (u64) leader->core.nr_members)
 		return -EINVAL;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -1421,7 +1351,7 @@
 			      v[0].value, ena, run);
 
 	for (i = 1; i < nr; i++) {
-		struct perf_evsel *counter;
+		struct evsel *counter;
 
 		counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
 		if (!counter)
@@ -1435,11 +1365,11 @@
 }
 
 static int
-perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
+perf_evsel__read_group(struct evsel *leader, int cpu, int thread)
 {
 	struct perf_stat_evsel *ps = leader->stats;
-	u64 read_format = leader->attr.read_format;
-	int size = perf_evsel__read_size(leader);
+	u64 read_format = leader->core.attr.read_format;
+	int size = perf_evsel__read_size(&leader->core);
 	u64 *data = ps->group_data;
 
 	if (!(read_format & PERF_FORMAT_ID))
@@ -1465,9 +1395,9 @@
 	return perf_evsel__process_group_data(leader, cpu, thread, data);
 }
 
-int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread)
+int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread)
 {
-	u64 read_format = evsel->attr.read_format;
+	u64 read_format = evsel->core.attr.read_format;
 
 	if (read_format & PERF_FORMAT_GROUP)
 		return perf_evsel__read_group(evsel, cpu, thread);
@@ -1475,7 +1405,7 @@
 		return perf_evsel__read_one(evsel, cpu, thread);
 }
 
-int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+int __perf_evsel__read_on_cpu(struct evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
 	struct perf_counts_values count;
@@ -1496,9 +1426,9 @@
 	return 0;
 }
 
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
+static int get_group_fd(struct evsel *evsel, int cpu, int thread)
 {
-	struct perf_evsel *leader = evsel->leader;
+	struct evsel *leader = evsel->leader;
 	int fd;
 
 	if (perf_evsel__is_group_leader(evsel))
@@ -1508,7 +1438,7 @@
 	 * Leader must be already processed/open,
 	 * if not it's a bug.
 	 */
-	BUG_ON(!leader->fd);
+	BUG_ON(!leader->core.fd);
 
 	fd = FD(leader, cpu, thread);
 	BUG_ON(fd == -1);
@@ -1516,150 +1446,7 @@
 	return fd;
 }
 
-struct bit_names {
-	int bit;
-	const char *name;
-};
-
-static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
-{
-	bool first_bit = true;
-	int i = 0;
-
-	do {
-		if (value & bits[i].bit) {
-			buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
-			first_bit = false;
-		}
-	} while (bits[++i].name != NULL);
-}
-
-static void __p_sample_type(char *buf, size_t size, u64 value)
-{
-#define bit_name(n) { PERF_SAMPLE_##n, #n }
-	struct bit_names bits[] = {
-		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
-		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
-		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
-		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
-		bit_name(WEIGHT), bit_name(PHYS_ADDR),
-		{ .name = NULL, }
-	};
-#undef bit_name
-	__p_bits(buf, size, value, bits);
-}
-
-static void __p_branch_sample_type(char *buf, size_t size, u64 value)
-{
-#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
-	struct bit_names bits[] = {
-		bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
-		bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
-		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
-		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
-		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
-		{ .name = NULL, }
-	};
-#undef bit_name
-	__p_bits(buf, size, value, bits);
-}
-
-static void __p_read_format(char *buf, size_t size, u64 value)
-{
-#define bit_name(n) { PERF_FORMAT_##n, #n }
-	struct bit_names bits[] = {
-		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
-		bit_name(ID), bit_name(GROUP),
-		{ .name = NULL, }
-	};
-#undef bit_name
-	__p_bits(buf, size, value, bits);
-}
-
-#define BUF_SIZE		1024
-
-#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
-#define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
-#define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
-#define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
-#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
-#define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
-
-#define PRINT_ATTRn(_n, _f, _p)				\
-do {							\
-	if (attr->_f) {					\
-		_p(attr->_f);				\
-		ret += attr__fprintf(fp, _n, buf, priv);\
-	}						\
-} while (0)
-
-#define PRINT_ATTRf(_f, _p)	PRINT_ATTRn(#_f, _f, _p)
-
-int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
-			     attr__fprintf_f attr__fprintf, void *priv)
-{
-	char buf[BUF_SIZE];
-	int ret = 0;
-
-	PRINT_ATTRf(type, p_unsigned);
-	PRINT_ATTRf(size, p_unsigned);
-	PRINT_ATTRf(config, p_hex);
-	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
-	PRINT_ATTRf(sample_type, p_sample_type);
-	PRINT_ATTRf(read_format, p_read_format);
-
-	PRINT_ATTRf(disabled, p_unsigned);
-	PRINT_ATTRf(inherit, p_unsigned);
-	PRINT_ATTRf(pinned, p_unsigned);
-	PRINT_ATTRf(exclusive, p_unsigned);
-	PRINT_ATTRf(exclude_user, p_unsigned);
-	PRINT_ATTRf(exclude_kernel, p_unsigned);
-	PRINT_ATTRf(exclude_hv, p_unsigned);
-	PRINT_ATTRf(exclude_idle, p_unsigned);
-	PRINT_ATTRf(mmap, p_unsigned);
-	PRINT_ATTRf(comm, p_unsigned);
-	PRINT_ATTRf(freq, p_unsigned);
-	PRINT_ATTRf(inherit_stat, p_unsigned);
-	PRINT_ATTRf(enable_on_exec, p_unsigned);
-	PRINT_ATTRf(task, p_unsigned);
-	PRINT_ATTRf(watermark, p_unsigned);
-	PRINT_ATTRf(precise_ip, p_unsigned);
-	PRINT_ATTRf(mmap_data, p_unsigned);
-	PRINT_ATTRf(sample_id_all, p_unsigned);
-	PRINT_ATTRf(exclude_host, p_unsigned);
-	PRINT_ATTRf(exclude_guest, p_unsigned);
-	PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
-	PRINT_ATTRf(exclude_callchain_user, p_unsigned);
-	PRINT_ATTRf(mmap2, p_unsigned);
-	PRINT_ATTRf(comm_exec, p_unsigned);
-	PRINT_ATTRf(use_clockid, p_unsigned);
-	PRINT_ATTRf(context_switch, p_unsigned);
-	PRINT_ATTRf(write_backward, p_unsigned);
-	PRINT_ATTRf(namespaces, p_unsigned);
-
-	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
-	PRINT_ATTRf(bp_type, p_unsigned);
-	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
-	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
-	PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
-	PRINT_ATTRf(sample_regs_user, p_hex);
-	PRINT_ATTRf(sample_stack_user, p_unsigned);
-	PRINT_ATTRf(clockid, p_signed);
-	PRINT_ATTRf(sample_regs_intr, p_hex);
-	PRINT_ATTRf(aux_watermark, p_unsigned);
-	PRINT_ATTRf(sample_max_stack, p_unsigned);
-
-	return ret;
-}
-
-static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
-				void *priv __maybe_unused)
-{
-	return fprintf(fp, "  %-32s %s\n", name, val);
-}
-
-static void perf_evsel__remove_fd(struct perf_evsel *pos,
+static void perf_evsel__remove_fd(struct evsel *pos,
 				  int nr_cpus, int nr_threads,
 				  int thread_idx)
 {
@@ -1668,11 +1455,11 @@
 			FD(pos, cpu, thread) = FD(pos, cpu, thread + 1);
 }
 
-static int update_fds(struct perf_evsel *evsel,
+static int update_fds(struct evsel *evsel,
 		      int nr_cpus, int cpu_idx,
 		      int nr_threads, int thread_idx)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
 	if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
 		return -EINVAL;
@@ -1692,18 +1479,18 @@
 	return 0;
 }
 
-static bool ignore_missing_thread(struct perf_evsel *evsel,
+static bool ignore_missing_thread(struct evsel *evsel,
 				  int nr_cpus, int cpu,
-				  struct thread_map *threads,
+				  struct perf_thread_map *threads,
 				  int thread, int err)
 {
-	pid_t ignore_pid = thread_map__pid(threads, thread);
+	pid_t ignore_pid = perf_thread_map__pid(threads, thread);
 
 	if (!evsel->ignore_missing_thread)
 		return false;
 
 	/* The system wide setup does not work with threads. */
-	if (evsel->system_wide)
+	if (evsel->core.system_wide)
 		return false;
 
 	/* The -ESRCH is perf event syscall errno for pid's not found. */
@@ -1729,22 +1516,76 @@
 	return true;
 }
 
-int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads)
+static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
+				void *priv __maybe_unused)
+{
+	return fprintf(fp, "  %-32s %s\n", name, val);
+}
+
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->core.attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/* Do not try less precise if not requested. */
+		if (!evsel->precise_max)
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->core.attr.precise_ip) {
+			evsel->core.attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->core.attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip);
+		display_attr(&evsel->core.attr);
+	}
+
+	return fd;
+}
+
+int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
+		struct perf_thread_map *threads)
 {
 	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
-	if (perf_missing_features.write_backward && evsel->attr.write_backward)
+	if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
+	    (perf_missing_features.aux_output     && evsel->core.attr.aux_output))
 		return -EINVAL;
 
 	if (cpus == NULL) {
-		static struct cpu_map *empty_cpu_map;
+		static struct perf_cpu_map *empty_cpu_map;
 
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__dummy_new();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
@@ -1753,7 +1594,7 @@
 	}
 
 	if (threads == NULL) {
-		static struct thread_map *empty_thread_map;
+		static struct perf_thread_map *empty_thread_map;
 
 		if (empty_thread_map == NULL) {
 			empty_thread_map = thread_map__new_by_tid(-1);
@@ -1764,13 +1605,13 @@
 		threads = empty_thread_map;
 	}
 
-	if (evsel->system_wide)
+	if (evsel->core.system_wide)
 		nthreads = 1;
 	else
 		nthreads = threads->nr;
 
-	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
+	if (evsel->core.fd == NULL &&
+	    perf_evsel__alloc_fd(&evsel->core, cpus->nr, nthreads) < 0)
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
@@ -1780,50 +1621,46 @@
 
 fallback_missing_features:
 	if (perf_missing_features.clockid_wrong)
-		evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */
+		evsel->core.attr.clockid = CLOCK_MONOTONIC; /* should always work */
 	if (perf_missing_features.clockid) {
-		evsel->attr.use_clockid = 0;
-		evsel->attr.clockid = 0;
+		evsel->core.attr.use_clockid = 0;
+		evsel->core.attr.clockid = 0;
 	}
 	if (perf_missing_features.cloexec)
 		flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
 	if (perf_missing_features.mmap2)
-		evsel->attr.mmap2 = 0;
+		evsel->core.attr.mmap2 = 0;
 	if (perf_missing_features.exclude_guest)
-		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+		evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
 	if (perf_missing_features.lbr_flags)
-		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
+		evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
-	if (perf_missing_features.group_read && evsel->attr.inherit)
-		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
+	if (perf_missing_features.group_read && evsel->core.attr.inherit)
+		evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
+	if (perf_missing_features.ksymbol)
+		evsel->core.attr.ksymbol = 0;
+	if (perf_missing_features.bpf)
+		evsel->core.attr.bpf_event = 0;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
-		evsel->attr.sample_id_all = 0;
+		evsel->core.attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->core.attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd, group_fd;
 
-			if (!evsel->cgrp && !evsel->system_wide)
-				pid = thread_map__pid(threads, thread);
+			if (!evsel->cgrp && !evsel->core.system_wide)
+				pid = perf_thread_map__pid(threads, thread);
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 
@@ -1915,15 +1752,27 @@
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
+	if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+		perf_missing_features.aux_output = true;
+		pr_debug2("Kernel has no attr.aux_output support, bailing out\n");
+		goto out_close;
+	} else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) {
+		perf_missing_features.bpf = true;
+		pr_debug2("switching off bpf_event\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) {
+		perf_missing_features.ksymbol = true;
+		pr_debug2("switching off ksymbol\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) {
 		perf_missing_features.write_backward = true;
 		pr_debug2("switching off write_backward\n");
 		goto out_close;
-	} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
+	} else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) {
 		perf_missing_features.clockid_wrong = true;
 		pr_debug2("switching off clockid\n");
 		goto fallback_missing_features;
-	} else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
+	} else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) {
 		perf_missing_features.clockid = true;
 		pr_debug2("switching off use_clockid\n");
 		goto fallback_missing_features;
@@ -1931,12 +1780,12 @@
 		perf_missing_features.cloexec = true;
 		pr_debug2("switching off cloexec flag\n");
 		goto fallback_missing_features;
-	} else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+	} else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) {
 		perf_missing_features.mmap2 = true;
 		pr_debug2("switching off mmap2\n");
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.exclude_guest &&
-		   (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+		   (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
 		perf_missing_features.exclude_guest = true;
 		pr_debug2("switching off exclude_guest, exclude_host\n");
 		goto fallback_missing_features;
@@ -1945,15 +1794,15 @@
 		pr_debug2("switching off sample_id_all\n");
 		goto retry_sample_id;
 	} else if (!perf_missing_features.lbr_flags &&
-			(evsel->attr.branch_sample_type &
+			(evsel->core.attr.branch_sample_type &
 			 (PERF_SAMPLE_BRANCH_NO_CYCLES |
 			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
 		perf_missing_features.lbr_flags = true;
 		pr_debug2("switching off branch sample type no (cycles/flags)\n");
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.group_read &&
-		    evsel->attr.inherit &&
-		   (evsel->attr.read_format & PERF_FORMAT_GROUP) &&
+		    evsel->core.attr.inherit &&
+		   (evsel->core.attr.read_format & PERF_FORMAT_GROUP) &&
 		   perf_evsel__is_group_leader(evsel)) {
 		perf_missing_features.group_read = true;
 		pr_debug2("switching off group read\n");
@@ -1973,33 +1822,30 @@
 	return err;
 }
 
-void perf_evsel__close(struct perf_evsel *evsel)
+void evsel__close(struct evsel *evsel)
 {
-	if (evsel->fd == NULL)
-		return;
-
-	perf_evsel__close_fd(evsel);
-	perf_evsel__free_fd(evsel);
+	perf_evsel__close(&evsel->core);
+	perf_evsel__free_id(&evsel->core);
 }
 
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus)
+int perf_evsel__open_per_cpu(struct evsel *evsel,
+			     struct perf_cpu_map *cpus)
 {
-	return perf_evsel__open(evsel, cpus, NULL);
+	return evsel__open(evsel, cpus, NULL);
 }
 
-int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads)
+int perf_evsel__open_per_thread(struct evsel *evsel,
+				struct perf_thread_map *threads)
 {
-	return perf_evsel__open(evsel, NULL, threads);
+	return evsel__open(evsel, NULL, threads);
 }
 
-static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
+static int perf_evsel__parse_id_sample(const struct evsel *evsel,
 				       const union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 type = evsel->attr.sample_type;
-	const u64 *array = event->sample.array;
+	u64 type = evsel->core.attr.sample_type;
+	const __u64 *array = event->sample.array;
 	bool swapped = evsel->needs_swap;
 	union u64_swap u;
 
@@ -2084,12 +1930,12 @@
 	return 0;
 }
 
-int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
-	u64 type = evsel->attr.sample_type;
+	u64 type = evsel->core.attr.sample_type;
 	bool swapped = evsel->needs_swap;
-	const u64 *array;
+	const __u64 *array;
 	u16 max_size = event->header.size;
 	const void *endp = (void *)event + max_size;
 	u64 sz;
@@ -2103,14 +1949,14 @@
 	memset(data, 0, sizeof(*data));
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
-	data->period = evsel->attr.sample_period;
+	data->period = evsel->core.attr.sample_period;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	data->misc    = event->header.misc;
 	data->id = -1ULL;
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
-		if (!evsel->attr.sample_id_all)
+		if (!evsel->core.attr.sample_id_all)
 			return 0;
 		return perf_evsel__parse_id_sample(evsel, event, data);
 	}
@@ -2183,7 +2029,7 @@
 	}
 
 	if (type & PERF_SAMPLE_READ) {
-		u64 read_format = evsel->attr.read_format;
+		u64 read_format = evsel->core.attr.read_format;
 
 		OVERFLOW_CHECK_u64(array);
 		if (read_format & PERF_FORMAT_GROUP)
@@ -2288,9 +2134,9 @@
 		array++;
 
 		if (data->user_regs.abi) {
-			u64 mask = evsel->attr.sample_regs_user;
+			u64 mask = evsel->core.attr.sample_regs_user;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
@@ -2344,9 +2190,9 @@
 		array++;
 
 		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
-			u64 mask = evsel->attr.sample_regs_intr;
+			u64 mask = evsel->core.attr.sample_regs_intr;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->intr_regs.mask = mask;
 			data->intr_regs.regs = (u64 *)array;
@@ -2363,12 +2209,12 @@
 	return 0;
 }
 
-int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
 				       union perf_event *event,
 				       u64 *timestamp)
 {
-	u64 type = evsel->attr.sample_type;
-	const u64 *array;
+	u64 type = evsel->core.attr.sample_type;
+	const __u64 *array;
 
 	if (!(type & PERF_SAMPLE_TIME))
 		return -1;
@@ -2378,7 +2224,7 @@
 			.time = -1ULL,
 		};
 
-		if (!evsel->attr.sample_id_all)
+		if (!evsel->core.attr.sample_id_all)
 			return -1;
 		if (perf_evsel__parse_id_sample(evsel, event, &data))
 			return -1;
@@ -2407,292 +2253,15 @@
 	return 0;
 }
 
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 read_format)
-{
-	size_t sz, result = sizeof(struct sample_event);
-
-	if (type & PERF_SAMPLE_IDENTIFIER)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_IP)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TIME)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_ADDR)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_ID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_STREAM_ID)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_CPU)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_PERIOD)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_READ) {
-		result += sizeof(u64);
-		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-			result += sizeof(u64);
-		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-			result += sizeof(u64);
-		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
-		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		sz = (sample->callchain->nr + 1) * sizeof(u64);
-		result += sz;
-	}
-
-	if (type & PERF_SAMPLE_RAW) {
-		result += sizeof(u32);
-		result += sample->raw_size;
-	}
-
-	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
-		result += sz;
-	}
-
-	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
-			result += sizeof(u64);
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_STACK_USER) {
-		sz = sample->user_stack.size;
-		result += sizeof(u64);
-		if (sz) {
-			result += sz;
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_WEIGHT)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_DATA_SRC)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_TRANSACTION)
-		result += sizeof(u64);
-
-	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
-			result += sizeof(u64);
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
-			result += sz;
-		} else {
-			result += sizeof(u64);
-		}
-	}
-
-	if (type & PERF_SAMPLE_PHYS_ADDR)
-		result += sizeof(u64);
-
-	return result;
-}
-
-int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 read_format,
-				  const struct perf_sample *sample)
-{
-	u64 *array;
-	size_t sz;
-	/*
-	 * used for cross-endian analysis. See git commit 65014ab3
-	 * for why this goofiness is needed.
-	 */
-	union u64_swap u;
-
-	array = event->sample.array;
-
-	if (type & PERF_SAMPLE_IDENTIFIER) {
-		*array = sample->id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_IP) {
-		*array = sample->ip;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TID) {
-		u.val32[0] = sample->pid;
-		u.val32[1] = sample->tid;
-		*array = u.val64;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TIME) {
-		*array = sample->time;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ADDR) {
-		*array = sample->addr;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_ID) {
-		*array = sample->id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_STREAM_ID) {
-		*array = sample->stream_id;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_CPU) {
-		u.val32[0] = sample->cpu;
-		u.val32[1] = 0;
-		*array = u.val64;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_PERIOD) {
-		*array = sample->period;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_READ) {
-		if (read_format & PERF_FORMAT_GROUP)
-			*array = sample->read.group.nr;
-		else
-			*array = sample->read.one.value;
-		array++;
-
-		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
-			*array = sample->read.time_enabled;
-			array++;
-		}
-
-		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
-			*array = sample->read.time_running;
-			array++;
-		}
-
-		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
-		if (read_format & PERF_FORMAT_GROUP) {
-			sz = sample->read.group.nr *
-			     sizeof(struct sample_read_value);
-			memcpy(array, sample->read.group.values, sz);
-			array = (void *)array + sz;
-		} else {
-			*array = sample->read.one.id;
-			array++;
-		}
-	}
-
-	if (type & PERF_SAMPLE_CALLCHAIN) {
-		sz = (sample->callchain->nr + 1) * sizeof(u64);
-		memcpy(array, sample->callchain, sz);
-		array = (void *)array + sz;
-	}
-
-	if (type & PERF_SAMPLE_RAW) {
-		u.val32[0] = sample->raw_size;
-		*array = u.val64;
-		array = (void *)array + sizeof(u32);
-
-		memcpy(array, sample->raw_data, sample->raw_size);
-		array = (void *)array + sample->raw_size;
-	}
-
-	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
-		memcpy(array, sample->branch_stack, sz);
-		array = (void *)array + sz;
-	}
-
-	if (type & PERF_SAMPLE_REGS_USER) {
-		if (sample->user_regs.abi) {
-			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
-			memcpy(array, sample->user_regs.regs, sz);
-			array = (void *)array + sz;
-		} else {
-			*array++ = 0;
-		}
-	}
-
-	if (type & PERF_SAMPLE_STACK_USER) {
-		sz = sample->user_stack.size;
-		*array++ = sz;
-		if (sz) {
-			memcpy(array, sample->user_stack.data, sz);
-			array = (void *)array + sz;
-			*array++ = sz;
-		}
-	}
-
-	if (type & PERF_SAMPLE_WEIGHT) {
-		*array = sample->weight;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_DATA_SRC) {
-		*array = sample->data_src;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_TRANSACTION) {
-		*array = sample->transaction;
-		array++;
-	}
-
-	if (type & PERF_SAMPLE_REGS_INTR) {
-		if (sample->intr_regs.abi) {
-			*array++ = sample->intr_regs.abi;
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
-			memcpy(array, sample->intr_regs.regs, sz);
-			array = (void *)array + sz;
-		} else {
-			*array++ = 0;
-		}
-	}
-
-	if (type & PERF_SAMPLE_PHYS_ADDR) {
-		*array = sample->phys_addr;
-		array++;
-	}
-
-	return 0;
-}
-
-struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
+struct tep_format_field *perf_evsel__field(struct evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
 }
 
-void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
+void *perf_evsel__rawptr(struct 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)
@@ -2700,7 +2269,7 @@
 
 	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;
 	}
@@ -2708,7 +2277,7 @@
 	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;
@@ -2747,10 +2316,10 @@
 	return 0;
 }
 
-u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+u64 perf_evsel__intval(struct 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;
@@ -2758,14 +2327,14 @@
 	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
 }
 
-bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+bool perf_evsel__fallback(struct evsel *evsel, int err,
 			  char *msg, size_t msgsize)
 {
 	int paranoid;
 
 	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
-	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
-	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+	    evsel->core.attr.type   == PERF_TYPE_HARDWARE &&
+	    evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 		/*
 		 * If it's cycles then fall back to hrtimer based
 		 * cpu-clock-tick sw counter, which is always available even if
@@ -2777,12 +2346,12 @@
 		scnprintf(msg, msgsize, "%s",
 "The cycles event is not supported, trying to fall back to cpu-clock-ticks");
 
-		evsel->attr.type   = PERF_TYPE_SOFTWARE;
-		evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
+		evsel->core.attr.type   = PERF_TYPE_SOFTWARE;
+		evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK;
 
 		zfree(&evsel->name);
 		return true;
-	} else if (err == EACCES && !evsel->attr.exclude_kernel &&
+	} else if (err == EACCES && !evsel->core.attr.exclude_kernel &&
 		   (paranoid = perf_event_paranoid()) > 1) {
 		const char *name = perf_evsel__name(evsel);
 		char *new_name;
@@ -2799,9 +2368,11 @@
 		if (evsel->name)
 			free(evsel->name);
 		evsel->name = new_name;
-		scnprintf(msg, msgsize,
-"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
-		evsel->attr.exclude_kernel = 1;
+		scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying "
+			  "to fall back to excluding kernel and hypervisor "
+			  " samples", paranoid);
+		evsel->core.attr.exclude_kernel = 1;
+		evsel->core.attr.exclude_hv     = 1;
 
 		return true;
 	}
@@ -2845,7 +2416,7 @@
 	return ret ? false : true;
 }
 
-int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
+int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
 	char sbuf[STRERR_BUFSIZE];
@@ -2898,15 +2469,15 @@
 	 "No such device - did you specify an out-of-range profile CPU?");
 		break;
 	case EOPNOTSUPP:
-		if (evsel->attr.sample_period != 0)
+		if (evsel->core.attr.sample_period != 0)
 			return scnprintf(msg, size,
 	"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
 					 perf_evsel__name(evsel));
-		if (evsel->attr.precise_ip)
+		if (evsel->core.attr.precise_ip)
 			return scnprintf(msg, size, "%s",
 	"\'precise\' request may not be supported. Try removing 'p' modifier.");
 #if defined(__i386__) || defined(__x86_64__)
-		if (evsel->attr.type == PERF_TYPE_HARDWARE)
+		if (evsel->core.attr.type == PERF_TYPE_HARDWARE)
 			return scnprintf(msg, size, "%s",
 	"No hardware sampling interrupt available.\n");
 #endif
@@ -2918,12 +2489,14 @@
 	"We found oprofile daemon running, please stop it and try again.");
 		break;
 	case EINVAL:
-		if (evsel->attr.write_backward && perf_missing_features.write_backward)
+		if (evsel->core.attr.write_backward && perf_missing_features.write_backward)
 			return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
 		if (perf_missing_features.clockid)
 			return scnprintf(msg, size, "clockid feature not supported.");
 		if (perf_missing_features.clockid_wrong)
 			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
+		if (perf_missing_features.aux_output)
+			return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
 		break;
 	default:
 		break;
@@ -2936,9 +2509,38 @@
 			 perf_evsel__name(evsel));
 }
 
-struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
+struct perf_env *perf_evsel__env(struct evsel *evsel)
 {
 	if (evsel && evsel->evlist)
 		return evsel->evlist->env;
-	return NULL;
+	return &perf_env;
+}
+
+static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
+		     thread++) {
+			int fd = FD(evsel, cpu, thread);
+
+			if (perf_evlist__id_add_fd(&evlist->core, &evsel->core,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist)
+{
+	struct perf_cpu_map *cpus = evsel->core.cpus;
+	struct perf_thread_map *threads = evsel->core.threads;
+
+	if (perf_evsel__alloc_id(&evsel->core, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return store_evsel_ids(evsel, evlist);
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c960..ddc5ee6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -4,124 +4,72 @@
 
 #include <linux/list.h>
 #include <stdbool.h>
-#include <stddef.h>
+#include <sys/types.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
-#include "xyarray.h"
-#include "symbol.h"
-#include "cpumap.h"
-#include "counts.h"
+#include <internal/evsel.h>
+#include <perf/evsel.h>
+#include "symbol_conf.h"
+#include <internal/cpumap.h>
 
-struct perf_evsel;
-
-/*
- * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
- * more than one entry in the evlist.
- */
-struct perf_sample_id {
-	struct hlist_node 	node;
-	u64		 	id;
-	struct perf_evsel	*evsel;
-	int			idx;
-	int			cpu;
-	pid_t			tid;
-
-	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
-	u64			period;
-};
-
+struct bpf_object;
 struct cgroup;
-
-/*
- * The 'struct perf_evsel_config_term' is used to pass event
- * specific configuration data to perf_evsel__config routine.
- * It is allocated within event parsing and attached to
- * perf_evsel::config_terms list head.
-*/
-enum term_type {
-	PERF_EVSEL__CONFIG_TERM_PERIOD,
-	PERF_EVSEL__CONFIG_TERM_FREQ,
-	PERF_EVSEL__CONFIG_TERM_TIME,
-	PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
-	PERF_EVSEL__CONFIG_TERM_STACK_USER,
-	PERF_EVSEL__CONFIG_TERM_INHERIT,
-	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
-	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
-	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
-	PERF_EVSEL__CONFIG_TERM_BRANCH,
-};
-
-struct perf_evsel_config_term {
-	struct list_head	list;
-	enum term_type	type;
-	union {
-		u64	period;
-		u64	freq;
-		bool	time;
-		char	*callgraph;
-		char	*drv_cfg;
-		u64	stack_user;
-		int	max_stack;
-		bool	inherit;
-		bool	overwrite;
-		char	*branch;
-	} val;
-	bool weak;
-};
-
+struct perf_counts;
 struct perf_stat_evsel;
+union perf_event;
 
-/** struct perf_evsel - event selector
+typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
+
+enum perf_tool_event {
+	PERF_TOOL_NONE		= 0,
+	PERF_TOOL_DURATION_TIME = 1,
+};
+
+/** struct evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
- * @node - To insert it into evlist->entries or in other list_heads, say in
- *         the event parsing routines.
+ * @core - libperf evsel object
  * @name - Can be set to retain the original event name passed by the user,
  *         so that when showing results in tools such as 'perf stat', we
  *         show the name used, not some alias.
  * @id_pos: the position of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
- *          struct sample_event
+ *          struct perf_record_sample
  * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
  *          is used there is an id sample appended to non-sample events
  * @priv:   And what is in its containing unnamed union are tool specific
  */
-struct perf_evsel {
-	struct list_head	node;
-	struct perf_evlist	*evlist;
-	struct perf_event_attr	attr;
+struct evsel {
+	struct perf_evsel	core;
+	struct evlist	*evlist;
 	char			*filter;
-	struct xyarray		*fd;
-	struct xyarray		*sample_id;
-	u64			*id;
 	struct perf_counts	*counts;
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
-	u32			ids;
+	unsigned long		max_events;
+	unsigned long		nr_events_printed;
 	char			*name;
 	double			scale;
 	const char		*unit;
-	struct event_format	*tp_format;
+	struct tep_event	*tp_format;
 	off_t			id_offset;
 	struct perf_stat_evsel  *stats;
 	void			*priv;
 	u64			db_id;
 	struct cgroup		*cgrp;
 	void			*handler;
-	struct cpu_map		*cpus;
-	struct cpu_map		*own_cpus;
-	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	enum perf_tool_event	tool_event;
 	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
+	bool 			disabled;
 	bool			no_aux_samples;
 	bool			immediate;
-	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
@@ -130,27 +78,28 @@
 	bool			use_uncore_alias;
 	/* parse modifier helper */
 	int			exclude_GH;
-	int			nr_members;
 	int			sample_read;
 	unsigned long		*per_pkg_mask;
-	struct perf_evsel	*leader;
+	struct evsel		*leader;
 	char			*group_name;
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
+	struct bpf_object	*bpf_obj;
 	int			bpf_fd;
 	bool			auto_merge_stats;
 	bool			merged_stat;
 	const char *		metric_expr;
 	const char *		metric_name;
-	struct perf_evsel	**metric_events;
+	struct evsel		**metric_events;
+	struct evsel		*metric_leader;
 	bool			collect_stat;
 	bool			weak_group;
+	bool			percore;
 	const char		*pmu_name;
-};
-
-union u64_swap {
-	u64 val64;
-	u32 val32[2];
+	struct {
+		perf_evsel__sb_cb_t	*cb;
+		void			*data;
+	} side_band;
 };
 
 struct perf_missing_features {
@@ -163,72 +112,74 @@
 	bool lbr_flags;
 	bool write_backward;
 	bool group_read;
+	bool ksymbol;
+	bool bpf;
+	bool aux_output;
 };
 
 extern struct perf_missing_features perf_missing_features;
 
-struct cpu_map;
+struct perf_cpu_map;
 struct target;
 struct thread_map;
 struct record_opts;
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static inline struct perf_cpu_map *evsel__cpus(struct evsel *evsel)
 {
-	return evsel->cpus;
+	return perf_evsel__cpus(&evsel->core);
 }
 
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+static inline int perf_evsel__nr_cpus(struct evsel *evsel)
 {
-	return perf_evsel__cpus(evsel)->nr;
+	return evsel__cpus(evsel)->nr;
 }
 
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
+void perf_evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
-			      int (*init)(struct perf_evsel *evsel),
-			      void (*fini)(struct perf_evsel *evsel));
+			      int (*init)(struct evsel *evsel),
+			      void (*fini)(struct evsel *evsel));
 
-struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
+struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
-static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
+static inline struct evsel *evsel__new(struct perf_event_attr *attr)
 {
 	return perf_evsel__new_idx(attr, 0);
 }
 
-struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
+struct evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
 
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name)
+static inline struct evsel *perf_evsel__newtp(const char *sys, const char *name)
 {
 	return perf_evsel__newtp_idx(sys, name, 0);
 }
 
-struct perf_evsel *perf_evsel__new_cycles(bool precise);
+struct evsel *perf_evsel__new_cycles(bool precise);
 
-struct event_format *event_format__new(const char *sys, const char *name);
+struct tep_event *event_format__new(const char *sys, const char *name);
 
-void perf_evsel__init(struct perf_evsel *evsel,
-		      struct perf_event_attr *attr, int idx);
-void perf_evsel__exit(struct perf_evsel *evsel);
-void perf_evsel__delete(struct perf_evsel *evsel);
+void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
+void perf_evsel__exit(struct evsel *evsel);
+void evsel__delete(struct evsel *evsel);
 
 struct callchain_param;
 
-void perf_evsel__config(struct perf_evsel *evsel,
+void perf_evsel__config(struct evsel *evsel,
 			struct record_opts *opts,
 			struct callchain_param *callchain);
-void perf_evsel__config_callchain(struct perf_evsel *evsel,
+void perf_evsel__config_callchain(struct evsel *evsel,
 				  struct record_opts *opts,
 				  struct callchain_param *callchain);
 
 int __perf_evsel__sample_size(u64 sample_type);
-void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+void perf_evsel__calc_id_pos(struct evsel *evsel);
 
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
@@ -244,17 +195,14 @@
 extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
-const char *perf_evsel__name(struct perf_evsel *evsel);
+const char *perf_evsel__name(struct evsel *evsel);
 
-const char *perf_evsel__group_name(struct perf_evsel *evsel);
-int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
+const char *perf_evsel__group_name(struct evsel *evsel);
+int perf_evsel__group_desc(struct evsel *evsel, char *buf, size_t size);
 
-int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-void perf_evsel__close_fd(struct perf_evsel *evsel);
-
-void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+void __perf_evsel__set_sample_bit(struct evsel *evsel,
 				  enum perf_event_sample_format bit);
-void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+void __perf_evsel__reset_sample_bit(struct evsel *evsel,
 				    enum perf_event_sample_format bit);
 
 #define perf_evsel__set_sample_bit(evsel, bit) \
@@ -263,68 +211,64 @@
 #define perf_evsel__reset_sample_bit(evsel, bit) \
 	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+void perf_evsel__set_sample_id(struct evsel *evsel,
 			       bool use_sample_identifier);
 
-int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter);
-int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter);
-int perf_evsel__append_addr_filter(struct perf_evsel *evsel,
+int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
+int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
+int perf_evsel__append_addr_filter(struct evsel *evsel,
 				   const char *filter);
-int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
-int perf_evsel__enable(struct perf_evsel *evsel);
-int perf_evsel__disable(struct perf_evsel *evsel);
+int evsel__enable(struct evsel *evsel);
+int evsel__disable(struct evsel *evsel);
 
-int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-			     struct cpu_map *cpus);
-int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-				struct thread_map *threads);
-int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads);
-void perf_evsel__close(struct perf_evsel *evsel);
+int perf_evsel__open_per_cpu(struct evsel *evsel,
+			     struct perf_cpu_map *cpus);
+int perf_evsel__open_per_thread(struct evsel *evsel,
+				struct perf_thread_map *threads);
+int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
+		struct perf_thread_map *threads);
+void evsel__close(struct evsel *evsel);
 
 struct perf_sample;
 
-void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
+void *perf_evsel__rawptr(struct evsel *evsel, struct perf_sample *sample,
 			 const char *name);
-u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+u64 perf_evsel__intval(struct evsel *evsel, struct perf_sample *sample,
 		       const char *name);
 
-static inline char *perf_evsel__strval(struct perf_evsel *evsel,
+static inline char *perf_evsel__strval(struct evsel *evsel,
 				       struct perf_sample *sample,
 				       const char *name)
 {
 	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 evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)		\
-	(evsel->attr.type == PERF_TYPE_##t &&	\
-	 evsel->attr.config == PERF_COUNT_##c)
+	(evsel->core.attr.type == PERF_TYPE_##t &&	\
+	 evsel->core.attr.config == PERF_COUNT_##c)
 
-static inline bool perf_evsel__match2(struct perf_evsel *e1,
-				      struct perf_evsel *e2)
+static inline bool perf_evsel__match2(struct evsel *e1,
+				      struct evsel *e2)
 {
-	return (e1->attr.type == e2->attr.type) &&
-	       (e1->attr.config == e2->attr.config);
+	return (e1->core.attr.type == e2->core.attr.type) &&
+	       (e1->core.attr.config == e2->core.attr.config);
 }
 
 #define perf_evsel__cmp(a, b)			\
 	((a) &&					\
 	 (b) &&					\
-	 (a)->attr.type == (b)->attr.type &&	\
-	 (a)->attr.config == (b)->attr.config)
+	 (a)->core.attr.type == (b)->core.attr.type &&	\
+	 (a)->core.attr.config == (b)->core.attr.config)
 
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
-		     struct perf_counts_values *count);
+int perf_evsel__read_counter(struct evsel *evsel, int cpu, int thread);
 
-int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread);
-
-int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+int __perf_evsel__read_on_cpu(struct evsel *evsel,
 			      int cpu, int thread, bool scale);
 
 /**
@@ -334,7 +278,7 @@
  * @cpu - CPU of interest
  * @thread - thread of interest
  */
-static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+static inline int perf_evsel__read_on_cpu(struct evsel *evsel,
 					  int cpu, int thread)
 {
 	return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
@@ -347,27 +291,27 @@
  * @cpu - CPU of interest
  * @thread - thread of interest
  */
-static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
+static inline int perf_evsel__read_on_cpu_scaled(struct evsel *evsel,
 						 int cpu, int thread)
 {
 	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
 }
 
-int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
+int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 
-int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
+int perf_evsel__parse_sample_timestamp(struct evsel *evsel,
 				       union perf_event *event,
 				       u64 *timestamp);
 
-static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
+static inline struct evsel *perf_evsel__next(struct evsel *evsel)
 {
-	return list_entry(evsel->node.next, struct perf_evsel, node);
+	return list_entry(evsel->core.node.next, struct evsel, core.node);
 }
 
-static inline struct perf_evsel *perf_evsel__prev(struct perf_evsel *evsel)
+static inline struct evsel *perf_evsel__prev(struct evsel *evsel)
 {
-	return list_entry(evsel->node.prev, struct perf_evsel, node);
+	return list_entry(evsel->core.node.prev, struct evsel, core.node);
 }
 
 /**
@@ -377,7 +321,7 @@
  *
  * Return %true if @evsel is a group leader or a stand-alone event
  */
-static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
+static inline bool perf_evsel__is_group_leader(const struct evsel *evsel)
 {
 	return evsel->leader == evsel;
 }
@@ -390,95 +334,60 @@
  * Return %true iff event group view is enabled and @evsel is a actual group
  * leader which has other members in the group
  */
-static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
+static inline bool perf_evsel__is_group_event(struct evsel *evsel)
 {
 	if (!symbol_conf.event_group)
 		return false;
 
-	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
+	return perf_evsel__is_group_leader(evsel) && evsel->core.nr_members > 1;
 }
 
-bool perf_evsel__is_function_event(struct perf_evsel *evsel);
+bool perf_evsel__is_function_event(struct evsel *evsel);
 
-static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+static inline bool perf_evsel__is_bpf_output(struct evsel *evsel)
 {
 	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
 }
 
-static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+static inline bool perf_evsel__is_clock(struct evsel *evsel)
 {
 	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
 	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
-struct perf_attr_details {
-	bool freq;
-	bool verbose;
-	bool event_group;
-	bool force;
-	bool trace_fields;
-};
-
-int perf_evsel__fprintf(struct perf_evsel *evsel,
-			struct perf_attr_details *details, FILE *fp);
-
-#define EVSEL__PRINT_IP			(1<<0)
-#define EVSEL__PRINT_SYM		(1<<1)
-#define EVSEL__PRINT_DSO		(1<<2)
-#define EVSEL__PRINT_SYMOFFSET		(1<<3)
-#define EVSEL__PRINT_ONELINE		(1<<4)
-#define EVSEL__PRINT_SRCLINE		(1<<5)
-#define EVSEL__PRINT_UNKNOWN_AS_ADDR	(1<<6)
-#define EVSEL__PRINT_CALLCHAIN_ARROW	(1<<7)
-#define EVSEL__PRINT_SKIP_IGNORED	(1<<8)
-
-struct callchain_cursor;
-
-int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
-			      unsigned int print_opts,
-			      struct callchain_cursor *cursor, FILE *fp);
-
-int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
-			int left_alignment, unsigned int print_opts,
-			struct callchain_cursor *cursor, FILE *fp);
-
-bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+bool perf_evsel__fallback(struct evsel *evsel, int err,
 			  char *msg, size_t msgsize);
-int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
+int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size);
 
-static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
+static inline int perf_evsel__group_idx(struct evsel *evsel)
 {
 	return evsel->idx - evsel->leader->idx;
 }
 
 /* Iterates group WITHOUT the leader. */
 #define for_each_group_member(_evsel, _leader) 					\
-for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
+for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \
      (_evsel) && (_evsel)->leader == (_leader);					\
-     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+     (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
 
 /* Iterates group WITH the leader. */
 #define for_each_group_evsel(_evsel, _leader) 					\
 for ((_evsel) = _leader; 							\
      (_evsel) && (_evsel)->leader == (_leader);					\
-     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+     (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node))
 
-static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel)
+static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
 {
-	return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
+	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
-static inline bool evsel__has_callchain(const struct perf_evsel *evsel)
+static inline bool evsel__has_callchain(const struct evsel *evsel)
 {
-	return (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
+	return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
 }
 
-typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
+struct perf_env *perf_evsel__env(struct evsel *evsel);
 
-int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
-			     attr__fprintf_f attr__fprintf, void *priv);
-
-struct perf_env *perf_evsel__env(struct perf_evsel *evsel);
-
+int perf_evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h
new file mode 100644
index 0000000..8a76480
--- /dev/null
+++ b/tools/perf/util/evsel_config.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_EVSEL_CONFIG_H
+#define __PERF_EVSEL_CONFIG_H 1
+
+#include <linux/types.h>
+#include <stdbool.h>
+
+/*
+ * The 'struct perf_evsel_config_term' is used to pass event
+ * specific configuration data to perf_evsel__config routine.
+ * It is allocated within event parsing and attached to
+ * perf_evsel::config_terms list head.
+*/
+enum evsel_term_type {
+	PERF_EVSEL__CONFIG_TERM_PERIOD,
+	PERF_EVSEL__CONFIG_TERM_FREQ,
+	PERF_EVSEL__CONFIG_TERM_TIME,
+	PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
+	PERF_EVSEL__CONFIG_TERM_STACK_USER,
+	PERF_EVSEL__CONFIG_TERM_INHERIT,
+	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
+	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
+	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
+	PERF_EVSEL__CONFIG_TERM_BRANCH,
+	PERF_EVSEL__CONFIG_TERM_PERCORE,
+	PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT,
+};
+
+struct perf_evsel_config_term {
+	struct list_head      list;
+	enum evsel_term_type  type;
+	union {
+		u64	      period;
+		u64	      freq;
+		bool	      time;
+		char	      *callgraph;
+		char	      *drv_cfg;
+		u64	      stack_user;
+		int	      max_stack;
+		bool	      inherit;
+		bool	      overwrite;
+		char	      *branch;
+		unsigned long max_events;
+		bool	      percore;
+		bool	      aux_output;
+	} val;
+	bool weak;
+};
+#endif // __PERF_EVSEL_CONFIG_H
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 06dfb02..028df7a 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -4,6 +4,8 @@
 #include <stdbool.h>
 #include <traceevent/event-parse.h>
 #include "evsel.h"
+#include "util/evsel_fprintf.h"
+#include "util/event.h"
 #include "callchain.h"
 #include "map.h"
 #include "strlist.h"
@@ -33,26 +35,26 @@
 	return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val);
 }
 
-int perf_evsel__fprintf(struct perf_evsel *evsel,
+int perf_evsel__fprintf(struct evsel *evsel,
 			struct perf_attr_details *details, FILE *fp)
 {
 	bool first = true;
 	int printed = 0;
 
 	if (details->event_group) {
-		struct perf_evsel *pos;
+		struct evsel *pos;
 
 		if (!perf_evsel__is_group_leader(evsel))
 			return 0;
 
-		if (evsel->nr_members > 1)
+		if (evsel->core.nr_members > 1)
 			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
 
 		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
 		for_each_group_member(pos, evsel)
 			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
 
-		if (evsel->nr_members > 1)
+		if (evsel->core.nr_members > 1)
 			printed += fprintf(fp, "}");
 		goto out;
 	}
@@ -60,22 +62,22 @@
 	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
 
 	if (details->verbose) {
-		printed += perf_event_attr__fprintf(fp, &evsel->attr,
+		printed += perf_event_attr__fprintf(fp, &evsel->core.attr,
 						    __print_attr__fprintf, &first);
 	} else if (details->freq) {
 		const char *term = "sample_freq";
 
-		if (!evsel->attr.freq)
+		if (!evsel->core.attr.freq)
 			term = "sample_period";
 
 		printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
-					 term, (u64)evsel->attr.sample_freq);
+					 term, (u64)evsel->core.attr.sample_freq);
 	}
 
 	if (details->trace_fields) {
-		struct format_field *field;
+		struct tep_format_field *field;
 
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) {
 			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
 			goto out;
 		}
@@ -101,7 +103,7 @@
 
 int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 			      unsigned int print_opts, struct callchain_cursor *cursor,
-			      FILE *fp)
+			      struct strlist *bt_stop_list, FILE *fp)
 {
 	int printed = 0;
 	struct callchain_cursor_node *node;
@@ -173,10 +175,9 @@
 			if (!print_oneline)
 				printed += fprintf(fp, "\n");
 
-			if (symbol_conf.bt_stop_list &&
-			    node->sym &&
-			    strlist__has_entry(symbol_conf.bt_stop_list,
-					       node->sym->name)) {
+			/* Add srccode here too? */
+			if (bt_stop_list && node->sym &&
+			    strlist__has_entry(bt_stop_list, node->sym->name)) {
 				break;
 			}
 
@@ -191,7 +192,7 @@
 
 int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
 			int left_alignment, unsigned int print_opts,
-			struct callchain_cursor *cursor, FILE *fp)
+			struct callchain_cursor *cursor, struct strlist *bt_stop_list, FILE *fp)
 {
 	int printed = 0;
 	int print_ip = print_opts & EVSEL__PRINT_IP;
@@ -202,8 +203,8 @@
 	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
 
 	if (cursor != NULL) {
-		printed += sample__fprintf_callchain(sample, left_alignment,
-						     print_opts, cursor, fp);
+		printed += sample__fprintf_callchain(sample, left_alignment, print_opts,
+						     cursor, bt_stop_list, fp);
 	} else {
 		printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
 
diff --git a/tools/perf/util/evsel_fprintf.h b/tools/perf/util/evsel_fprintf.h
new file mode 100644
index 0000000..47e6c84
--- /dev/null
+++ b/tools/perf/util/evsel_fprintf.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_EVSEL_FPRINTF_H
+#define __PERF_EVSEL_FPRINTF_H 1
+
+#include <stdio.h>
+#include <stdbool.h>
+
+struct evsel;
+
+struct perf_attr_details {
+	bool freq;
+	bool verbose;
+	bool event_group;
+	bool force;
+	bool trace_fields;
+};
+
+int perf_evsel__fprintf(struct evsel *evsel,
+			struct perf_attr_details *details, FILE *fp);
+
+#define EVSEL__PRINT_IP			(1<<0)
+#define EVSEL__PRINT_SYM		(1<<1)
+#define EVSEL__PRINT_DSO		(1<<2)
+#define EVSEL__PRINT_SYMOFFSET		(1<<3)
+#define EVSEL__PRINT_ONELINE		(1<<4)
+#define EVSEL__PRINT_SRCLINE		(1<<5)
+#define EVSEL__PRINT_UNKNOWN_AS_ADDR	(1<<6)
+#define EVSEL__PRINT_CALLCHAIN_ARROW	(1<<7)
+#define EVSEL__PRINT_SKIP_IGNORED	(1<<8)
+
+struct addr_location;
+struct perf_event_attr;
+struct perf_sample;
+struct callchain_cursor;
+struct strlist;
+
+int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
+			      unsigned int print_opts, struct callchain_cursor *cursor,
+			      struct strlist *bt_stop_list, FILE *fp);
+
+int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
+			int left_alignment, unsigned int print_opts,
+			struct callchain_cursor *cursor,
+			struct strlist *bt_stop_list, FILE *fp);
+
+typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
+
+int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
+			     attr__fprintf_f attr__fprintf, void *priv);
+#endif // __PERF_EVSEL_H
diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c
new file mode 100644
index 0000000..3ba72f7
--- /dev/null
+++ b/tools/perf/util/evswitch.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+
+#include "evswitch.h"
+#include "evlist.h"
+
+bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel)
+{
+	if (evswitch->on && evswitch->discarding) {
+		if (evswitch->on != evsel)
+			return true;
+
+		evswitch->discarding = false;
+
+		if (!evswitch->show_on_off_events)
+			return true;
+
+		return false;
+	}
+
+	if (evswitch->off && !evswitch->discarding) {
+		if (evswitch->off != evsel)
+			return false;
+
+		evswitch->discarding = true;
+
+		if (!evswitch->show_on_off_events)
+			return true;
+	}
+
+	return false;
+}
+
+static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *evname)
+{
+	int printed = fprintf(fp, "ERROR: switch-%s event not found (%s)\n", evtype, evname);
+
+	return printed += fprintf(fp, "HINT:  use 'perf evlist' to see the available event names\n");
+}
+
+int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
+{
+	if (evswitch->on_name) {
+		evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name);
+		if (evswitch->on == NULL) {
+			evswitch__fprintf_enoent(fp, "on", evswitch->on_name);
+			return -ENOENT;
+		}
+		evswitch->discarding = true;
+	}
+
+	if (evswitch->off_name) {
+		evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name);
+		if (evswitch->off == NULL) {
+			evswitch__fprintf_enoent(fp, "off", evswitch->off_name);
+			return -ENOENT;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/evswitch.h b/tools/perf/util/evswitch.h
new file mode 100644
index 0000000..fd30460
--- /dev/null
+++ b/tools/perf/util/evswitch.h
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+#ifndef __PERF_EVSWITCH_H
+#define __PERF_EVSWITCH_H 1
+
+#include <stdbool.h>
+#include <stdio.h>
+
+struct evsel;
+struct evlist;
+
+struct evswitch {
+	struct evsel *on, *off;
+	const char   *on_name, *off_name;
+	bool	     discarding;
+	bool	     show_on_off_events;
+};
+
+int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp);
+
+bool evswitch__discard(struct evswitch *evswitch, struct evsel *evsel);
+
+#define OPTS_EVSWITCH(evswitch)								  \
+	OPT_STRING(0, "switch-on", &(evswitch)->on_name,				  \
+		   "event", "Consider events after the ocurrence of this event"),	  \
+	OPT_STRING(0, "switch-off", &(evswitch)->off_name,				  \
+		   "event", "Stop considering events after the ocurrence of this event"), \
+	OPT_BOOLEAN(0, "show-on-off-events", &(evswitch)->show_on_off_events,		  \
+		    "Show the on/off switch events, used with --switch-on and --switch-off")
+
+#endif /* __PERF_EVSWITCH_H */
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 432b856..f9a20a3 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -2,9 +2,11 @@
 %{
 #include "util.h"
 #include "util/debug.h"
+#include <stdlib.h> // strtod()
 #define IN_EXPR_Y 1
 #include "expr.h"
 #include "smt.h"
+#include <assert.h>
 #include <string.h>
 
 #define MAXIDLEN 256
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c
similarity index 71%
rename from tools/perf/util/find-vdso-map.c
rename to tools/perf/util/find-map.c
index d7823e3..7b23005 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-map.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
 	FILE *maps;
 	char line[128];
@@ -7,7 +7,7 @@
 
 	maps = fopen("/proc/self/maps", "r");
 	if (!maps) {
-		fprintf(stderr, "vdso: cannot open maps\n");
+		fprintf(stderr, "cannot open maps\n");
 		return -1;
 	}
 
@@ -21,8 +21,7 @@
 		if (m < 0)
 			continue;
 
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
+		if (!strncmp(&line[m], name, strlen(name)))
 			found = 1;
 	}
 
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index aafbe54..f9f18b8 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * genelf.c
  * Copyright (C) 2014, Google, Inc
  *
  * Contributed by:
  * 	Stephane Eranian <eranian@gmail.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include <sys/types.h>
@@ -15,6 +14,7 @@
 #include <libelf.h>
 #include <string.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <inttypes.h>
 #include <limits.h>
 #include <fcntl.h>
@@ -23,9 +23,9 @@
 #include <dwarf.h>
 #endif
 
-#include "perf.h"
 #include "genelf.h"
 #include "../util/jitdump.h"
+#include <linux/compiler.h>
 
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d5..d413755 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,15 @@
 #elif defined(__powerpc__)
 #define GEN_ELF_ARCH	EM_PPC
 #define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH	EM_SPARCV9
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH	EM_SPARC
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__s390x__)
+#define GEN_ELF_ARCH	EM_S390
+#define GEN_ELF_CLASS	ELFCLASS64
 #else
 #error "unsupported architecture"
 #endif
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
index 40789d8..30e9f61 100644
--- a/tools/perf/util/genelf_debug.c
+++ b/tools/perf/util/genelf_debug.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * genelf_debug.c
  * Copyright (C) 2015, Google, Inc
@@ -5,8 +6,6 @@
  * Contributed by:
  * 	Stephane Eranian <eranian@google.com>
  *
- * Released under the GPL v2.
- *
  * based on GPLv2 source code from Oprofile
  * @remark Copyright 2007 OProfile authors
  * @author Philippe Elie
@@ -25,7 +24,6 @@
 #include <err.h>
 #include <dwarf.h>
 
-#include "perf.h"
 #include "genelf.h"
 #include "../util/jitdump.h"
 
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
new file mode 100644
index 0000000..b205d92
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: LGPL-2.1
+// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "get_current_dir_name.h"
+#include <unistd.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME
diff --git a/tools/perf/util/get_current_dir_name.h b/tools/perf/util/get_current_dir_name.h
new file mode 100644
index 0000000..69f7d55
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.h
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
+// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef __PERF_GET_CURRENT_DIR_NAME_H
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif // HAVE_GET_CURRENT_DIR_NAME
+#endif // __PERF_GET_CURRENT_DIR_NAME_H
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3cadc25..becc2d1 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
-#include "util.h"
 #include "string2.h"
 #include <sys/param.h>
 #include <sys/types.h>
@@ -13,17 +12,22 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <linux/string.h>
 #include <linux/stringify.h>
+#include <linux/zalloc.h>
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <linux/time64.h>
 #include <dirent.h>
+#include <bpf/libbpf.h>
+#include <perf/cpumap.h>
 
+#include "dso.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "util/evsel_fprintf.h"
 #include "header.h"
 #include "memswap.h"
-#include "../perf.h"
 #include "trace-event.h"
 #include "session.h"
 #include "symbol.h"
@@ -39,8 +43,12 @@
 #include "tool.h"
 #include "time-utils.h"
 #include "units.h"
+#include "util/util.h" // perf_exe()
+#include "cputopo.h"
+#include "bpf-event.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <internal/lib.h>
 
 /*
  * magic2 = "PERFILE2"
@@ -64,15 +72,6 @@
 	struct perf_file_section	ids;
 };
 
-struct feat_fd {
-	struct perf_header	*ph;
-	int			fd;
-	void			*buf;	/* Either buf != NULL or fd >= 0 */
-	ssize_t			offset;
-	size_t			size;
-	struct perf_evsel	*events;
-};
-
 void perf_header__set_feat(struct perf_header *header, int feat)
 {
 	set_bit(feat, header->adds_features);
@@ -295,16 +294,16 @@
 }
 
 static int write_tracing_data(struct feat_fd *ff,
-			      struct perf_evlist *evlist)
+			      struct evlist *evlist)
 {
 	if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
 		return -1;
 
-	return read_tracing_data(ff->fd, &evlist->entries);
+	return read_tracing_data(ff->fd, &evlist->core.entries);
 }
 
 static int write_build_id(struct feat_fd *ff,
-			  struct perf_evlist *evlist __maybe_unused)
+			  struct evlist *evlist __maybe_unused)
 {
 	struct perf_session *session;
 	int err;
@@ -328,7 +327,7 @@
 }
 
 static int write_hostname(struct feat_fd *ff,
-			  struct perf_evlist *evlist __maybe_unused)
+			  struct evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -341,7 +340,7 @@
 }
 
 static int write_osrelease(struct feat_fd *ff,
-			   struct perf_evlist *evlist __maybe_unused)
+			   struct evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -354,7 +353,7 @@
 }
 
 static int write_arch(struct feat_fd *ff,
-		      struct perf_evlist *evlist __maybe_unused)
+		      struct evlist *evlist __maybe_unused)
 {
 	struct utsname uts;
 	int ret;
@@ -367,7 +366,7 @@
 }
 
 static int write_version(struct feat_fd *ff,
-			 struct perf_evlist *evlist __maybe_unused)
+			 struct evlist *evlist __maybe_unused)
 {
 	return do_write_string(ff, perf_version_string);
 }
@@ -413,10 +412,8 @@
 	while (*p) {
 		if (isspace(*p)) {
 			char *r = p + 1;
-			char *q = r;
+			char *q = skip_spaces(r);
 			*p = ' ';
-			while (*q && isspace(*q))
-				q++;
 			if (q != (p+1))
 				while ((*r++ = *q++));
 		}
@@ -430,9 +427,27 @@
 }
 
 static int write_cpudesc(struct feat_fd *ff,
-		       struct perf_evlist *evlist __maybe_unused)
+		       struct evlist *evlist __maybe_unused)
 {
+#if defined(__powerpc__) || defined(__hppa__) || defined(__sparc__)
+#define CPUINFO_PROC	{ "cpu", }
+#elif defined(__s390__)
+#define CPUINFO_PROC	{ "vendor_id", }
+#elif defined(__sh__)
+#define CPUINFO_PROC	{ "cpu type", }
+#elif defined(__alpha__) || defined(__mips__)
+#define CPUINFO_PROC	{ "cpu model", }
+#elif defined(__arm__)
+#define CPUINFO_PROC	{ "model name", "Processor", }
+#elif defined(__arc__)
+#define CPUINFO_PROC	{ "Processor", }
+#elif defined(__xtensa__)
+#define CPUINFO_PROC	{ "core ID", }
+#else
+#define CPUINFO_PROC	{ "model name", }
+#endif
 	const char *cpuinfo_procs[] = CPUINFO_PROC;
+#undef CPUINFO_PROC
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
@@ -446,7 +461,7 @@
 
 
 static int write_nrcpus(struct feat_fd *ff,
-			struct perf_evlist *evlist __maybe_unused)
+			struct evlist *evlist __maybe_unused)
 {
 	long nr;
 	u32 nrc, nra;
@@ -468,13 +483,13 @@
 }
 
 static int write_event_desc(struct feat_fd *ff,
-			    struct perf_evlist *evlist)
+			    struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	u32 nre, nri, sz;
 	int ret;
 
-	nre = evlist->nr_entries;
+	nre = evlist->core.nr_entries;
 
 	/*
 	 * write number of events
@@ -486,13 +501,13 @@
 	/*
 	 * size of perf_event_attr struct
 	 */
-	sz = (u32)sizeof(evsel->attr);
+	sz = (u32)sizeof(evsel->core.attr);
 	ret = do_write(ff, &sz, sizeof(sz));
 	if (ret < 0)
 		return ret;
 
 	evlist__for_each_entry(evlist, evsel) {
-		ret = do_write(ff, &evsel->attr, sz);
+		ret = do_write(ff, &evsel->core.attr, sz);
 		if (ret < 0)
 			return ret;
 		/*
@@ -502,7 +517,7 @@
 		 * copy into an nri to be independent of the
 		 * type of ids,
 		 */
-		nri = evsel->ids;
+		nri = evsel->core.ids;
 		ret = do_write(ff, &nri, sizeof(nri));
 		if (ret < 0)
 			return ret;
@@ -516,7 +531,7 @@
 		/*
 		 * write unique ids for this event
 		 */
-		ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64));
+		ret = do_write(ff, evsel->core.id, evsel->core.ids * sizeof(u64));
 		if (ret < 0)
 			return ret;
 	}
@@ -524,19 +539,13 @@
 }
 
 static int write_cmdline(struct feat_fd *ff,
-			 struct perf_evlist *evlist __maybe_unused)
+			 struct evlist *evlist __maybe_unused)
 {
-	char buf[MAXPATHLEN];
-	u32 n;
-	int i, ret;
+	char pbuf[MAXPATHLEN], *buf;
+	int i, ret, n;
 
 	/* actual path to perf binary */
-	ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
-	if (ret <= 0)
-		return -1;
-
-	/* readlink() does not add null termination */
-	buf[ret] = '\0';
+	buf = perf_exe(pbuf, MAXPATHLEN);
 
 	/* account for binary path */
 	n = perf_env.nr_cmdline + 1;
@@ -557,160 +566,15 @@
 	return 0;
 }
 
-#define CORE_SIB_FMT \
-	"/sys/devices/system/cpu/cpu%d/topology/core_siblings_list"
-#define THRD_SIB_FMT \
-	"/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;
-	char **thread_siblings;
-};
-
-static int build_cpu_topo(struct cpu_topo *tp, int cpu)
-{
-	FILE *fp;
-	char filename[MAXPATHLEN];
-	char *buf = NULL, *p;
-	size_t len = 0;
-	ssize_t sret;
-	u32 i = 0;
-	int ret = -1;
-
-	sprintf(filename, CORE_SIB_FMT, cpu);
-	fp = fopen(filename, "r");
-	if (!fp)
-		goto try_threads;
-
-	sret = getline(&buf, &len, fp);
-	fclose(fp);
-	if (sret <= 0)
-		goto try_threads;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	for (i = 0; i < tp->core_sib; i++) {
-		if (!strcmp(buf, tp->core_siblings[i]))
-			break;
-	}
-	if (i == tp->core_sib) {
-		tp->core_siblings[i] = buf;
-		tp->core_sib++;
-		buf = NULL;
-		len = 0;
-	}
-	ret = 0;
-
-try_threads:
-	sprintf(filename, THRD_SIB_FMT, cpu);
-	fp = fopen(filename, "r");
-	if (!fp)
-		goto done;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	for (i = 0; i < tp->thread_sib; i++) {
-		if (!strcmp(buf, tp->thread_siblings[i]))
-			break;
-	}
-	if (i == tp->thread_sib) {
-		tp->thread_siblings[i] = buf;
-		tp->thread_sib++;
-		buf = NULL;
-	}
-	ret = 0;
-done:
-	if(fp)
-		fclose(fp);
-	free(buf);
-	return ret;
-}
-
-static void free_cpu_topo(struct cpu_topo *tp)
-{
-	u32 i;
-
-	if (!tp)
-		return;
-
-	for (i = 0 ; i < tp->core_sib; i++)
-		zfree(&tp->core_siblings[i]);
-
-	for (i = 0 ; i < tp->thread_sib; i++)
-		zfree(&tp->thread_siblings[i]);
-
-	free(tp);
-}
-
-static struct cpu_topo *build_cpu_topology(void)
-{
-	struct cpu_topo *tp = NULL;
-	void *addr;
-	u32 nr, i;
-	size_t sz;
-	long ncpus;
-	int ret = -1;
-	struct cpu_map *map;
-
-	ncpus = cpu__max_present_cpu();
-
-	/* build online CPU map */
-	map = cpu_map__new(NULL);
-	if (map == NULL) {
-		pr_debug("failed to get system cpumap\n");
-		return NULL;
-	}
-
-	nr = (u32)(ncpus & UINT_MAX);
-
-	sz = nr * sizeof(char *);
-	addr = calloc(1, sizeof(*tp) + 2 * sz);
-	if (!addr)
-		goto out_free;
-
-	tp = addr;
-	tp->cpu_nr = nr;
-	addr += sizeof(*tp);
-	tp->core_siblings = addr;
-	addr += sz;
-	tp->thread_siblings = addr;
-
-	for (i = 0; i < nr; i++) {
-		if (!cpu_map__has(map, i))
-			continue;
-
-		ret = build_cpu_topo(tp, i);
-		if (ret < 0)
-			break;
-	}
-
-out_free:
-	cpu_map__put(map);
-	if (ret) {
-		free_cpu_topo(tp);
-		tp = NULL;
-	}
-	return tp;
-}
 
 static int write_cpu_topology(struct feat_fd *ff,
-			      struct perf_evlist *evlist __maybe_unused)
+			      struct evlist *evlist __maybe_unused)
 {
-	struct cpu_topo *tp;
+	struct cpu_topology *tp;
 	u32 i;
 	int ret, j;
 
-	tp = build_cpu_topology();
+	tp = cpu_topology__new();
 	if (!tp)
 		return -1;
 
@@ -747,15 +611,36 @@
 		if (ret < 0)
 			return ret;
 	}
+
+	if (!tp->die_sib)
+		goto done;
+
+	ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib));
+	if (ret < 0)
+		goto done;
+
+	for (i = 0; i < tp->die_sib; i++) {
+		ret = do_write_string(ff, tp->die_siblings[i]);
+		if (ret < 0)
+			goto done;
+	}
+
+	for (j = 0; j < perf_env.nr_cpus_avail; j++) {
+		ret = do_write(ff, &perf_env.cpu[j].die_id,
+			       sizeof(perf_env.cpu[j].die_id));
+		if (ret < 0)
+			return ret;
+	}
+
 done:
-	free_cpu_topo(tp);
+	cpu_topology__delete(tp);
 	return ret;
 }
 
 
 
 static int write_total_mem(struct feat_fd *ff,
-			   struct perf_evlist *evlist __maybe_unused)
+			   struct evlist *evlist __maybe_unused)
 {
 	char *buf = NULL;
 	FILE *fp;
@@ -783,112 +668,45 @@
 	return ret;
 }
 
-static int write_topo_node(struct feat_fd *ff, int node)
-{
-	char str[MAXPATHLEN];
-	char field[32];
-	char *buf = NULL, *p;
-	size_t len = 0;
-	FILE *fp;
-	u64 mem_total, mem_free, mem;
-	int ret = -1;
-
-	sprintf(str, "/sys/devices/system/node/node%d/meminfo", node);
-	fp = fopen(str, "r");
-	if (!fp)
-		return -1;
-
-	while (getline(&buf, &len, fp) > 0) {
-		/* skip over invalid lines */
-		if (!strchr(buf, ':'))
-			continue;
-		if (sscanf(buf, "%*s %*d %31s %"PRIu64, field, &mem) != 2)
-			goto done;
-		if (!strcmp(field, "MemTotal:"))
-			mem_total = mem;
-		if (!strcmp(field, "MemFree:"))
-			mem_free = mem;
-	}
-
-	fclose(fp);
-	fp = NULL;
-
-	ret = do_write(ff, &mem_total, sizeof(u64));
-	if (ret)
-		goto done;
-
-	ret = do_write(ff, &mem_free, sizeof(u64));
-	if (ret)
-		goto done;
-
-	ret = -1;
-	sprintf(str, "/sys/devices/system/node/node%d/cpulist", node);
-
-	fp = fopen(str, "r");
-	if (!fp)
-		goto done;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
-
-	p = strchr(buf, '\n');
-	if (p)
-		*p = '\0';
-
-	ret = do_write_string(ff, buf);
-done:
-	free(buf);
-	if (fp)
-		fclose(fp);
-	return ret;
-}
-
 static int write_numa_topology(struct feat_fd *ff,
-			       struct perf_evlist *evlist __maybe_unused)
+			       struct evlist *evlist __maybe_unused)
 {
-	char *buf = NULL;
-	size_t len = 0;
-	FILE *fp;
-	struct cpu_map *node_map = NULL;
-	char *c;
-	u32 nr, i, j;
+	struct numa_topology *tp;
 	int ret = -1;
+	u32 i;
 
-	fp = fopen("/sys/devices/system/node/online", "r");
-	if (!fp)
-		return -1;
+	tp = numa_topology__new();
+	if (!tp)
+		return -ENOMEM;
 
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
-
-	c = strchr(buf, '\n');
-	if (c)
-		*c = '\0';
-
-	node_map = cpu_map__new(buf);
-	if (!node_map)
-		goto done;
-
-	nr = (u32)node_map->nr;
-
-	ret = do_write(ff, &nr, sizeof(nr));
+	ret = do_write(ff, &tp->nr, sizeof(u32));
 	if (ret < 0)
-		goto done;
+		goto err;
 
-	for (i = 0; i < nr; i++) {
-		j = (u32)node_map->map[i];
-		ret = do_write(ff, &j, sizeof(j));
-		if (ret < 0)
-			break;
+	for (i = 0; i < tp->nr; i++) {
+		struct numa_topology_node *n = &tp->nodes[i];
 
-		ret = write_topo_node(ff, i);
+		ret = do_write(ff, &n->node, sizeof(u32));
 		if (ret < 0)
-			break;
+			goto err;
+
+		ret = do_write(ff, &n->mem_total, sizeof(u64));
+		if (ret)
+			goto err;
+
+		ret = do_write(ff, &n->mem_free, sizeof(u64));
+		if (ret)
+			goto err;
+
+		ret = do_write_string(ff, n->cpus);
+		if (ret < 0)
+			goto err;
 	}
-done:
-	free(buf);
-	fclose(fp);
-	cpu_map__put(node_map);
+
+	ret = 0;
+
+err:
+	numa_topology__delete(tp);
 	return ret;
 }
 
@@ -905,7 +723,7 @@
  */
 
 static int write_pmu_mappings(struct feat_fd *ff,
-			      struct perf_evlist *evlist __maybe_unused)
+			      struct evlist *evlist __maybe_unused)
 {
 	struct perf_pmu *pmu = NULL;
 	u32 pmu_num = 0;
@@ -954,10 +772,10 @@
  * };
  */
 static int write_group_desc(struct feat_fd *ff,
-			    struct perf_evlist *evlist)
+			    struct evlist *evlist)
 {
 	u32 nr_groups = evlist->nr_groups;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	int ret;
 
 	ret = do_write(ff, &nr_groups, sizeof(nr_groups));
@@ -966,10 +784,10 @@
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
-		    evsel->nr_members > 1) {
+		    evsel->core.nr_members > 1) {
 			const char *name = evsel->group_name ?: "{anon_group}";
 			u32 leader_idx = evsel->idx;
-			u32 nr_members = evsel->nr_members;
+			u32 nr_members = evsel->core.nr_members;
 
 			ret = do_write_string(ff, name);
 			if (ret < 0)
@@ -988,6 +806,45 @@
 }
 
 /*
+ * Return the CPU id as a raw string.
+ *
+ * Each architecture should provide a more precise id string that
+ * can be use to match the architecture's "mapfile".
+ */
+char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
+/* Return zero when the cpuid from the mapfile.csv matches the
+ * cpuid string generated on this platform.
+ * Otherwise return non-zero.
+ */
+int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, cpuid, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+		/* Verify the entire string matched. */
+		if (match_len == strlen(cpuid))
+			return 0;
+	}
+	return 1;
+}
+
+/*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(SRCARCH)/util/header.c
  */
@@ -997,28 +854,26 @@
 }
 
 static int write_cpuid(struct feat_fd *ff,
-		       struct perf_evlist *evlist __maybe_unused)
+		       struct evlist *evlist __maybe_unused)
 {
 	char buffer[64];
 	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);
 }
 
 static int write_branch_stack(struct feat_fd *ff __maybe_unused,
-			      struct perf_evlist *evlist __maybe_unused)
+			      struct evlist *evlist __maybe_unused)
 {
 	return 0;
 }
 
 static int write_auxtrace(struct feat_fd *ff,
-			  struct perf_evlist *evlist __maybe_unused)
+			  struct evlist *evlist __maybe_unused)
 {
 	struct perf_session *session;
 	int err;
@@ -1034,6 +889,111 @@
 	return err;
 }
 
+static int write_clockid(struct feat_fd *ff,
+			 struct evlist *evlist __maybe_unused)
+{
+	return do_write(ff, &ff->ph->env.clockid_res_ns,
+			sizeof(ff->ph->env.clockid_res_ns));
+}
+
+static int write_dir_format(struct feat_fd *ff,
+			    struct evlist *evlist __maybe_unused)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	if (WARN_ON(!perf_data__is_dir(data)))
+		return -1;
+
+	return do_write(ff, &data->dir.version, sizeof(data->dir.version));
+}
+
+#ifdef HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff,
+			       struct evlist *evlist __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+	int ret;
+
+	down_read(&env->bpf_progs.lock);
+
+	ret = do_write(ff, &env->bpf_progs.infos_cnt,
+		       sizeof(env->bpf_progs.infos_cnt));
+	if (ret < 0)
+		goto out;
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+	while (next) {
+		struct bpf_prog_info_node *node;
+		size_t len;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+		len = sizeof(struct bpf_prog_info_linear) +
+			node->info_linear->data_len;
+
+		/* before writing to file, translate address to offset */
+		bpf_program__bpil_addr_to_offs(node->info_linear);
+		ret = do_write(ff, node->info_linear, len);
+		/*
+		 * translate back to address even when do_write() fails,
+		 * so that this function never changes the data.
+		 */
+		bpf_program__bpil_offs_to_addr(node->info_linear);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	up_read(&env->bpf_progs.lock);
+	return ret;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused,
+			       struct evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+static int write_bpf_btf(struct feat_fd *ff,
+			 struct evlist *evlist __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+	int ret;
+
+	down_read(&env->bpf_progs.lock);
+
+	ret = do_write(ff, &env->bpf_progs.btfs_cnt,
+		       sizeof(env->bpf_progs.btfs_cnt));
+
+	if (ret < 0)
+		goto out;
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		ret = do_write(ff, &node->id,
+			       sizeof(u32) * 2 + node->data_size);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	up_read(&env->bpf_progs.lock);
+	return ret;
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1101,26 +1061,26 @@
 		return -1;
 
 	cache->type[len] = 0;
-	cache->type = rtrim(cache->type);
+	cache->type = strim(cache->type);
 
 	scnprintf(file, PATH_MAX, "%s/size", path);
 	if (sysfs__read_str(file, &cache->size, &len)) {
-		free(cache->type);
+		zfree(&cache->type);
 		return -1;
 	}
 
 	cache->size[len] = 0;
-	cache->size = rtrim(cache->size);
+	cache->size = strim(cache->size);
 
 	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
 	if (sysfs__read_str(file, &cache->map, &len)) {
-		free(cache->map);
-		free(cache->type);
+		zfree(&cache->size);
+		zfree(&cache->type);
 		return -1;
 	}
 
 	cache->map[len] = 0;
-	cache->map = rtrim(cache->map);
+	cache->map = strim(cache->map);
 	return 0;
 }
 
@@ -1173,16 +1133,17 @@
 	return 0;
 }
 
-#define MAX_CACHES 2000
+#define MAX_CACHE_LVL 4
 
 static int write_cache(struct feat_fd *ff,
-		       struct perf_evlist *evlist __maybe_unused)
+		       struct evlist *evlist __maybe_unused)
 {
-	struct cpu_cache_level caches[MAX_CACHES];
+	u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL;
+	struct cpu_cache_level caches[max_caches];
 	u32 cnt = 0, i, version = 1;
 	int ret;
 
-	ret = build_caches(caches, MAX_CACHES, &cnt);
+	ret = build_caches(caches, max_caches, &cnt);
 	if (ret)
 		goto out;
 
@@ -1228,13 +1189,13 @@
 }
 
 static int write_stat(struct feat_fd *ff __maybe_unused,
-		      struct perf_evlist *evlist __maybe_unused)
+		      struct evlist *evlist __maybe_unused)
 {
 	return 0;
 }
 
 static int write_sample_time(struct feat_fd *ff,
-			     struct perf_evlist *evlist)
+			     struct evlist *evlist)
 {
 	int ret;
 
@@ -1335,8 +1296,10 @@
 			continue;
 
 		if (WARN_ONCE(cnt >= size,
-			      "failed to write MEM_TOPOLOGY, way too many nodes\n"))
+			"failed to write MEM_TOPOLOGY, way too many nodes\n")) {
+			closedir(dir);
 			return -1;
+		}
 
 		ret = memory_node__read(&nodes[cnt++], idx);
 	}
@@ -1368,7 +1331,7 @@
  * 48 - bitmap           | bitmap of memory indexes that belongs to node
  */
 static int write_mem_topology(struct feat_fd *ff __maybe_unused,
-			      struct perf_evlist *evlist __maybe_unused)
+			      struct evlist *evlist __maybe_unused)
 {
 	static struct memory_node nodes[MAX_MEMORY_NODES];
 	u64 bsize, version = 1, i, nr;
@@ -1417,6 +1380,30 @@
 	return ret;
 }
 
+static int write_compressed(struct feat_fd *ff __maybe_unused,
+			    struct evlist *evlist __maybe_unused)
+{
+	int ret;
+
+	ret = do_write(ff, &(ff->ph->env.comp_ver), sizeof(ff->ph->env.comp_ver));
+	if (ret)
+		return ret;
+
+	ret = do_write(ff, &(ff->ph->env.comp_type), sizeof(ff->ph->env.comp_type));
+	if (ret)
+		return ret;
+
+	ret = do_write(ff, &(ff->ph->env.comp_level), sizeof(ff->ph->env.comp_level));
+	if (ret)
+		return ret;
+
+	ret = do_write(ff, &(ff->ph->env.comp_ratio), sizeof(ff->ph->env.comp_ratio));
+	if (ret)
+		return ret;
+
+	return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len));
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1488,10 +1475,20 @@
 	str = ph->env.sibling_cores;
 
 	for (i = 0; i < nr; i++) {
-		fprintf(fp, "# sibling cores   : %s\n", str);
+		fprintf(fp, "# sibling sockets : %s\n", str);
 		str += strlen(str) + 1;
 	}
 
+	if (ph->env.nr_sibling_dies) {
+		nr = ph->env.nr_sibling_dies;
+		str = ph->env.sibling_dies;
+
+		for (i = 0; i < nr; i++) {
+			fprintf(fp, "# sibling dies    : %s\n", str);
+			str += strlen(str) + 1;
+		}
+	}
+
 	nr = ph->env.nr_sibling_threads;
 	str = ph->env.sibling_threads;
 
@@ -1500,32 +1497,111 @@
 		str += strlen(str) + 1;
 	}
 
-	if (ph->env.cpu != NULL) {
-		for (i = 0; i < cpu_nr; i++)
-			fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
-				ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
-	} else
-		fprintf(fp, "# Core ID and Socket ID information is not available\n");
+	if (ph->env.nr_sibling_dies) {
+		if (ph->env.cpu != NULL) {
+			for (i = 0; i < cpu_nr; i++)
+				fprintf(fp, "# CPU %d: Core ID %d, "
+					    "Die ID %d, Socket ID %d\n",
+					    i, ph->env.cpu[i].core_id,
+					    ph->env.cpu[i].die_id,
+					    ph->env.cpu[i].socket_id);
+		} else
+			fprintf(fp, "# Core ID, Die ID and Socket ID "
+				    "information is not available\n");
+	} else {
+		if (ph->env.cpu != NULL) {
+			for (i = 0; i < cpu_nr; i++)
+				fprintf(fp, "# CPU %d: Core ID %d, "
+					    "Socket ID %d\n",
+					    i, ph->env.cpu[i].core_id,
+					    ph->env.cpu[i].socket_id);
+		} else
+			fprintf(fp, "# Core ID and Socket ID "
+				    "information is not available\n");
+	}
 }
 
-static void free_event_desc(struct perf_evsel *events)
+static void print_clockid(struct feat_fd *ff, FILE *fp)
 {
-	struct perf_evsel *evsel;
+	fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+		ff->ph->env.clockid_res_ns * 1000);
+}
+
+static void print_dir_format(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version);
+}
+
+static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_read(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.infos;
+	next = rb_first(root);
+
+	while (next) {
+		struct bpf_prog_info_node *node;
+
+		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
+		next = rb_next(&node->rb_node);
+
+		bpf_event__print_bpf_prog_info(&node->info_linear->info,
+					       env, fp);
+	}
+
+	up_read(&env->bpf_progs.lock);
+}
+
+static void print_bpf_btf(struct feat_fd *ff, FILE *fp)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct rb_root *root;
+	struct rb_node *next;
+
+	down_read(&env->bpf_progs.lock);
+
+	root = &env->bpf_progs.btfs;
+	next = rb_first(root);
+
+	while (next) {
+		struct btf_node *node;
+
+		node = rb_entry(next, struct btf_node, rb_node);
+		next = rb_next(&node->rb_node);
+		fprintf(fp, "# btf info of id %u\n", node->id);
+	}
+
+	up_read(&env->bpf_progs.lock);
+}
+
+static void free_event_desc(struct evsel *events)
+{
+	struct evsel *evsel;
 
 	if (!events)
 		return;
 
-	for (evsel = events; evsel->attr.size; evsel++) {
+	for (evsel = events; evsel->core.attr.size; evsel++) {
 		zfree(&evsel->name);
-		zfree(&evsel->id);
+		zfree(&evsel->core.id);
 	}
 
 	free(events);
 }
 
-static struct perf_evsel *read_event_desc(struct feat_fd *ff)
+static struct evsel *read_event_desc(struct feat_fd *ff)
 {
-	struct perf_evsel *evsel, *events = NULL;
+	struct evsel *evsel, *events = NULL;
 	u64 *id;
 	void *buf = NULL;
 	u32 nre, sz, nr, i, j;
@@ -1543,12 +1619,12 @@
 	if (!buf)
 		goto error;
 
-	/* the last event terminates with evsel->attr.size == 0: */
+	/* the last event terminates with evsel->core.attr.size == 0: */
 	events = calloc(nre + 1, sizeof(*events));
 	if (!events)
 		goto error;
 
-	msz = sizeof(evsel->attr);
+	msz = sizeof(evsel->core.attr);
 	if (sz < msz)
 		msz = sz;
 
@@ -1565,7 +1641,7 @@
 		if (ff->ph->needs_swap)
 			perf_event__attr_swap(buf);
 
-		memcpy(&evsel->attr, buf, msz);
+		memcpy(&evsel->core.attr, buf, msz);
 
 		if (do_read_u32(ff, &nr))
 			goto error;
@@ -1583,8 +1659,8 @@
 		id = calloc(nr, sizeof(*id));
 		if (!id)
 			goto error;
-		evsel->ids = nr;
-		evsel->id = id;
+		evsel->core.ids = nr;
+		evsel->core.id = id;
 
 		for (j = 0 ; j < nr; j++) {
 			if (do_read_u64(ff, id))
@@ -1609,7 +1685,7 @@
 
 static void print_event_desc(struct feat_fd *ff, FILE *fp)
 {
-	struct perf_evsel *evsel, *events;
+	struct evsel *evsel, *events;
 	u32 j;
 	u64 *id;
 
@@ -1623,12 +1699,12 @@
 		return;
 	}
 
-	for (evsel = events; evsel->attr.size; evsel++) {
+	for (evsel = events; evsel->core.attr.size; evsel++) {
 		fprintf(fp, "# event : name = %s, ", evsel->name);
 
-		if (evsel->ids) {
+		if (evsel->core.ids) {
 			fprintf(fp, ", id = {");
-			for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
+			for (j = 0, id = evsel->core.id; j < evsel->core.ids; j++, id++) {
 				if (j)
 					fputc(',', fp);
 				fprintf(fp, " %"PRIu64, *id);
@@ -1636,7 +1712,7 @@
 			fprintf(fp, " }");
 		}
 
-		perf_event_attr__fprintf(fp, &evsel->attr, __desc_attr__fprintf, NULL);
+		perf_event_attr__fprintf(fp, &evsel->core.attr, __desc_attr__fprintf, NULL);
 
 		fputc('\n', fp);
 	}
@@ -1698,6 +1774,13 @@
 	}
 }
 
+static void print_compressed(struct feat_fd *ff, FILE *fp)
+{
+	fprintf(fp, "# compressed : %s, level = %d, ratio = %d\n",
+		ff->ph->env.comp_type == PERF_COMP_ZSTD ? "Zstd" : "Unknown",
+		ff->ph->env.comp_level, ff->ph->env.comp_ratio);
+}
+
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
 {
 	const char *delimiter = "# pmu mappings: ";
@@ -1737,18 +1820,18 @@
 static void print_group_desc(struct feat_fd *ff, FILE *fp)
 {
 	struct perf_session *session;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	u32 nr = 0;
 
 	session = container_of(ff->ph, struct perf_session, header);
 
 	evlist__for_each_entry(session->evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
-		    evsel->nr_members > 1) {
+		    evsel->core.nr_members > 1) {
 			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
 				perf_evsel__name(evsel));
 
-			nr = evsel->nr_members - 1;
+			nr = evsel->core.nr_members - 1;
 		} else if (nr) {
 			fprintf(fp, ",%s", perf_evsel__name(evsel));
 
@@ -1809,7 +1892,7 @@
 	}
 }
 
-static int __event_process_build_id(struct build_id_event *bev,
+static int __event_process_build_id(struct perf_record_header_build_id *bev,
 				    char *filename,
 				    struct perf_session *session)
 {
@@ -1878,7 +1961,7 @@
 		u8			   build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
 		char			   filename[0];
 	} old_bev;
-	struct build_id_event bev;
+	struct perf_record_header_build_id bev;
 	char filename[PATH_MAX];
 	u64 limit = offset + size;
 
@@ -1919,7 +2002,7 @@
 				       int input, u64 offset, u64 size)
 {
 	struct perf_session *session = container_of(header, struct perf_session, header);
-	struct build_id_event bev;
+	struct perf_record_header_build_id bev;
 	char filename[PATH_MAX];
 	u64 limit = offset + size, orig_offset = offset;
 	int err = -1;
@@ -1941,7 +2024,7 @@
 		 *
 		 * "perf: 'perf kvm' tool for monitoring guest performance from host"
 		 *
-		 * Added a field to struct build_id_event that broke the file
+		 * Added a field to struct perf_record_header_build_id that broke the file
 		 * format.
 		 *
 		 * Since the kernel build-id is the first entry, process the
@@ -2022,10 +2105,10 @@
 	return 0;
 }
 
-static struct perf_evsel *
-perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
+static struct evsel *
+perf_evlist__find_by_index(struct evlist *evlist, int idx)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->idx == idx)
@@ -2036,10 +2119,10 @@
 }
 
 static void
-perf_evlist__set_event_name(struct perf_evlist *evlist,
-			    struct perf_evsel *event)
+perf_evlist__set_event_name(struct evlist *evlist,
+			    struct evsel *event)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	if (!event->name)
 		return;
@@ -2058,7 +2141,7 @@
 process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 {
 	struct perf_session *session;
-	struct perf_evsel *evsel, *events = read_event_desc(ff);
+	struct evsel *evsel, *events = read_event_desc(ff);
 
 	if (!events)
 		return 0;
@@ -2071,7 +2154,7 @@
 		ff->events = events;
 	}
 
-	for (evsel = events; evsel->attr.size; evsel++)
+	for (evsel = events; evsel->core.attr.size; evsel++)
 		perf_evlist__set_event_name(session->evlist, evsel);
 
 	if (!session->data->is_pipe)
@@ -2184,8 +2267,10 @@
 	/* On s390 the socket_id number is not related to the numbers of cpus.
 	 * The socket_id number might be higher than the numbers of cpus.
 	 * This depends on the configuration.
+	 * AArch64 is the same.
 	 */
-	if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+	if (ph->env.arch && (!strncmp(ph->env.arch, "s390", 4)
+			  || !strncmp(ph->env.arch, "aarch64", 7)))
 		do_core_id_test = false;
 
 	for (i = 0; i < (u32)cpu_nr; i++) {
@@ -2193,6 +2278,7 @@
 			goto free_cpu;
 
 		ph->env.cpu[i].core_id = nr;
+		size += sizeof(u32);
 
 		if (do_read_u32(ff, &nr))
 			goto free_cpu;
@@ -2204,6 +2290,40 @@
 		}
 
 		ph->env.cpu[i].socket_id = nr;
+		size += sizeof(u32);
+	}
+
+	/*
+	 * The header may be from old perf,
+	 * which doesn't include die information.
+	 */
+	if (ff->size <= size)
+		return 0;
+
+	if (do_read_u32(ff, &nr))
+		return -1;
+
+	ph->env.nr_sibling_dies = nr;
+	size += sizeof(u32);
+
+	for (i = 0; i < nr; i++) {
+		str = do_read_string(ff);
+		if (!str)
+			goto error;
+
+		/* include a NULL character at the end */
+		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+			goto error;
+		size += string_size(str);
+		free(str);
+	}
+	ph->env.sibling_dies = strbuf_detach(&sb, NULL);
+
+	for (i = 0; i < (u32)cpu_nr; i++) {
+		if (do_read_u32(ff, &nr))
+			goto free_cpu;
+
+		ph->env.cpu[i].die_id = nr;
 	}
 
 	return 0;
@@ -2246,7 +2366,7 @@
 		if (!str)
 			goto error;
 
-		n->map = cpu_map__new(str);
+		n->map = perf_cpu_map__new(str);
 		if (!n->map)
 			goto error;
 
@@ -2313,7 +2433,7 @@
 	size_t ret = -1;
 	u32 i, nr, nr_groups;
 	struct perf_session *session;
-	struct perf_evsel *evsel, *leader = NULL;
+	struct evsel *evsel, *leader = NULL;
 	struct group_desc {
 		char *name;
 		u32 leader_idx;
@@ -2360,7 +2480,7 @@
 				evsel->group_name = desc[i].name;
 				desc[i].name = NULL;
 			}
-			evsel->nr_members = desc[i].nr_members;
+			evsel->core.nr_members = desc[i].nr_members;
 
 			if (i >= nr_groups || nr > 0) {
 				pr_debug("invalid group desc\n");
@@ -2368,7 +2488,7 @@
 			}
 
 			leader = evsel;
-			nr = evsel->nr_members - 1;
+			nr = evsel->core.nr_members - 1;
 			i++;
 		} else if (nr) {
 			/* This is a group member */
@@ -2531,14 +2651,172 @@
 	return ret;
 }
 
-struct feature_ops {
-	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
-	void (*print)(struct feat_fd *ff, FILE *fp);
-	int (*process)(struct feat_fd *ff, void *data);
-	const char *name;
-	bool full_only;
-	bool synthesize;
-};
+static int process_clockid(struct feat_fd *ff,
+			   void *data __maybe_unused)
+{
+	if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+		return -1;
+
+	return 0;
+}
+
+static int process_dir_format(struct feat_fd *ff,
+			      void *_data __maybe_unused)
+{
+	struct perf_session *session;
+	struct perf_data *data;
+
+	session = container_of(ff->ph, struct perf_session, header);
+	data = session->data;
+
+	if (WARN_ON(!perf_data__is_dir(data)))
+		return -1;
+
+	return do_read_u64(ff, &data->dir.version);
+}
+
+#ifdef HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info_node *info_node;
+	struct perf_env *env = &ff->ph->env;
+	u32 count, i;
+	int err = -1;
+
+	if (ff->ph->needs_swap) {
+		pr_warning("interpreting bpf_prog_info from systems with endianity is not yet supported\n");
+		return 0;
+	}
+
+	if (do_read_u32(ff, &count))
+		return -1;
+
+	down_write(&env->bpf_progs.lock);
+
+	for (i = 0; i < count; ++i) {
+		u32 info_len, data_len;
+
+		info_linear = NULL;
+		info_node = NULL;
+		if (do_read_u32(ff, &info_len))
+			goto out;
+		if (do_read_u32(ff, &data_len))
+			goto out;
+
+		if (info_len > sizeof(struct bpf_prog_info)) {
+			pr_warning("detected invalid bpf_prog_info\n");
+			goto out;
+		}
+
+		info_linear = malloc(sizeof(struct bpf_prog_info_linear) +
+				     data_len);
+		if (!info_linear)
+			goto out;
+		info_linear->info_len = sizeof(struct bpf_prog_info);
+		info_linear->data_len = data_len;
+		if (do_read_u64(ff, (u64 *)(&info_linear->arrays)))
+			goto out;
+		if (__do_read(ff, &info_linear->info, info_len))
+			goto out;
+		if (info_len < sizeof(struct bpf_prog_info))
+			memset(((void *)(&info_linear->info)) + info_len, 0,
+			       sizeof(struct bpf_prog_info) - info_len);
+
+		if (__do_read(ff, info_linear->data, data_len))
+			goto out;
+
+		info_node = malloc(sizeof(struct bpf_prog_info_node));
+		if (!info_node)
+			goto out;
+
+		/* after reading from file, translate offset to address */
+		bpf_program__bpil_offs_to_addr(info_linear);
+		info_node->info_linear = info_linear;
+		perf_env__insert_bpf_prog_info(env, info_node);
+	}
+
+	up_write(&env->bpf_progs.lock);
+	return 0;
+out:
+	free(info_linear);
+	free(info_node);
+	up_write(&env->bpf_progs.lock);
+	return err;
+}
+#else // HAVE_LIBBPF_SUPPORT
+static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
+{
+	struct perf_env *env = &ff->ph->env;
+	struct btf_node *node = NULL;
+	u32 count, i;
+	int err = -1;
+
+	if (ff->ph->needs_swap) {
+		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
+		return 0;
+	}
+
+	if (do_read_u32(ff, &count))
+		return -1;
+
+	down_write(&env->bpf_progs.lock);
+
+	for (i = 0; i < count; ++i) {
+		u32 id, data_size;
+
+		if (do_read_u32(ff, &id))
+			goto out;
+		if (do_read_u32(ff, &data_size))
+			goto out;
+
+		node = malloc(sizeof(struct btf_node) + data_size);
+		if (!node)
+			goto out;
+
+		node->id = id;
+		node->data_size = data_size;
+
+		if (__do_read(ff, node->data, data_size))
+			goto out;
+
+		perf_env__insert_btf(env, node);
+		node = NULL;
+	}
+
+	err = 0;
+out:
+	up_write(&env->bpf_progs.lock);
+	free(node);
+	return err;
+}
+
+static int process_compressed(struct feat_fd *ff,
+			      void *data __maybe_unused)
+{
+	if (do_read_u32(ff, &(ff->ph->env.comp_ver)))
+		return -1;
+
+	if (do_read_u32(ff, &(ff->ph->env.comp_type)))
+		return -1;
+
+	if (do_read_u32(ff, &(ff->ph->env.comp_level)))
+		return -1;
+
+	if (do_read_u32(ff, &(ff->ph->env.comp_ratio)))
+		return -1;
+
+	if (do_read_u32(ff, &(ff->ph->env.comp_mmap_len)))
+		return -1;
+
+	return 0;
+}
 
 #define FEAT_OPR(n, func, __full_only) \
 	[HEADER_##n] = {					\
@@ -2566,8 +2844,10 @@
 #define process_branch_stack	NULL
 #define process_stat		NULL
 
+// Only used in util/synthetic-events.c
+const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE];
 
-static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
+const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(TRACING_DATA,	tracing_data,	false),
 	FEAT_OPN(BUILD_ID,	build_id,	false),
 	FEAT_OPR(HOSTNAME,	hostname,	false),
@@ -2590,6 +2870,11 @@
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
+	FEAT_OPR(CLOCKID,	clockid,	false),
+	FEAT_OPN(DIR_FORMAT,	dir_format,	false),
+	FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
+	FEAT_OPR(BPF_BTF,       bpf_btf,        false),
+	FEAT_OPR(COMPRESSED,	compressed,	false),
 };
 
 struct header_print_data {
@@ -2636,6 +2921,7 @@
 	struct perf_header *header = &session->header;
 	int fd = perf_data__fd(session->data);
 	struct stat st;
+	time_t stctime;
 	int ret, bit;
 
 	hd.fp = fp;
@@ -2645,7 +2931,8 @@
 	if (ret == -1)
 		return -1;
 
-	fprintf(fp, "# captured on    : %s", ctime(&st.st_ctime));
+	stctime = st.st_ctime;
+	fprintf(fp, "# captured on    : %s", ctime(&stctime));
 
 	fprintf(fp, "# header version : %u\n", header->version);
 	fprintf(fp, "# data offset    : %" PRIu64 "\n", header->data_offset);
@@ -2670,7 +2957,7 @@
 
 static int do_write_feat(struct feat_fd *ff, int type,
 			 struct perf_file_section **p,
-			 struct perf_evlist *evlist)
+			 struct evlist *evlist)
 {
 	int err;
 	int ret = 0;
@@ -2700,7 +2987,7 @@
 }
 
 static int perf_header__adds_write(struct perf_header *header,
-				   struct perf_evlist *evlist, int fd)
+				   struct evlist *evlist, int fd)
 {
 	int nr_sections;
 	struct feat_fd ff;
@@ -2736,7 +3023,7 @@
 	lseek(fd, sec_start, SEEK_SET);
 	/*
 	 * may write more than needed due to dropped feature, but
-	 * this is okay, reader will skip the mising entries
+	 * this is okay, reader will skip the missing entries
 	 */
 	err = do_write(&ff, feat_sec, sec_size);
 	if (err < 0)
@@ -2768,13 +3055,13 @@
 }
 
 int perf_session__write_header(struct perf_session *session,
-			       struct perf_evlist *evlist,
+			       struct evlist *evlist,
 			       int fd, bool at_exit)
 {
 	struct perf_file_header f_header;
 	struct perf_file_attr   f_attr;
 	struct perf_header *header = &session->header;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct feat_fd ff;
 	u64 attr_offset;
 	int err;
@@ -2784,7 +3071,7 @@
 
 	evlist__for_each_entry(session->evlist, evsel) {
 		evsel->id_offset = lseek(fd, 0, SEEK_CUR);
-		err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64));
+		err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64));
 		if (err < 0) {
 			pr_debug("failed to write perf header\n");
 			return err;
@@ -2795,10 +3082,10 @@
 
 	evlist__for_each_entry(evlist, evsel) {
 		f_attr = (struct perf_file_attr){
-			.attr = evsel->attr,
+			.attr = evsel->core.attr,
 			.ids  = {
 				.offset = evsel->id_offset,
-				.size   = evsel->ids * sizeof(u64),
+				.size   = evsel->core.ids * sizeof(u64),
 			}
 		};
 		err = do_write(&ff, &f_attr, sizeof(f_attr));
@@ -2824,7 +3111,7 @@
 		.attr_size = sizeof(f_attr),
 		.attrs = {
 			.offset = attr_offset,
-			.size   = evlist->nr_entries * sizeof(f_attr),
+			.size   = evlist->core.nr_entries * sizeof(f_attr),
 		},
 		.data = {
 			.offset = header->data_offset,
@@ -3203,10 +3490,10 @@
 	return ret <= 0 ? -1 : 0;
 }
 
-static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
+static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel,
 						struct tep_handle *pevent)
 {
-	struct event_format *event;
+	struct tep_event *event;
 	char bf[128];
 
 	/* already prepared */
@@ -3218,9 +3505,9 @@
 		return -1;
 	}
 
-	event = tep_find_event(pevent, evsel->attr.config);
+	event = tep_find_event(pevent, evsel->core.attr.config);
 	if (event == NULL) {
-		pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
+		pr_debug("cannot find event format for %d\n", (int)evsel->core.attr.config);
 		return -1;
 	}
 
@@ -3235,13 +3522,13 @@
 	return 0;
 }
 
-static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
+static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist,
 						  struct tep_handle *pevent)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
+		if (pos->core.attr.type == PERF_TYPE_TRACEPOINT &&
 		    perf_evsel__prepare_tracepoint_event(pos, pevent))
 			return -1;
 	}
@@ -3259,7 +3546,7 @@
 	int nr_attrs, nr_ids, i, j;
 	int fd = perf_data__fd(data);
 
-	session->evlist = perf_evlist__new();
+	session->evlist = evlist__new();
 	if (session->evlist == NULL)
 		return -ENOMEM;
 
@@ -3283,11 +3570,18 @@
 			   data->file.path);
 	}
 
+	if (f_header.attr_size == 0) {
+		pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+		       "Was the 'perf record' command properly terminated?\n",
+		       data->file.path);
+		return -EINVAL;
+	}
+
 	nr_attrs = f_header.attrs.size / f_header.attr_size;
 	lseek(fd, f_header.attrs.offset, SEEK_SET);
 
 	for (i = 0; i < nr_attrs; i++) {
-		struct perf_evsel *evsel;
+		struct evsel *evsel;
 		off_t tmp;
 
 		if (read_attr(fd, header, &f_attr) < 0)
@@ -3300,7 +3594,7 @@
 		}
 
 		tmp = lseek(fd, 0, SEEK_CUR);
-		evsel = perf_evsel__new(&f_attr.attr);
+		evsel = evsel__new(&f_attr.attr);
 
 		if (evsel == NULL)
 			goto out_delete_evlist;
@@ -3308,9 +3602,9 @@
 		evsel->needs_swap = header->needs_swap;
 		/*
 		 * Do it before so that if perf_evsel__alloc_id fails, this
-		 * entry gets purged too at perf_evlist__delete().
+		 * entry gets purged too at evlist__delete().
 		 */
-		perf_evlist__add(session->evlist, evsel);
+		evlist__add(session->evlist, evsel);
 
 		nr_ids = f_attr.ids.size / sizeof(u64);
 		/*
@@ -3318,7 +3612,7 @@
 		 * for allocating the perf_sample_id table we fake 1 cpu and
 		 * hattr->ids threads.
 		 */
-		if (perf_evsel__alloc_id(evsel, 1, nr_ids))
+		if (perf_evsel__alloc_id(&evsel->core, 1, nr_ids))
 			goto out_delete_evlist;
 
 		lseek(fd, f_attr.ids.offset, SEEK_SET);
@@ -3327,7 +3621,7 @@
 			if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id)))
 				goto out_errno;
 
-			perf_evlist__id_add(session->evlist, evsel, 0, j, f_id);
+			perf_evlist__id_add(&session->evlist->core, &evsel->core, 0, j, f_id);
 		}
 
 		lseek(fd, tmp, SEEK_SET);
@@ -3345,115 +3639,17 @@
 	return -errno;
 
 out_delete_evlist:
-	perf_evlist__delete(session->evlist);
+	evlist__delete(session->evlist);
 	session->evlist = NULL;
 	return -ENOMEM;
 }
 
-int perf_event__synthesize_attr(struct perf_tool *tool,
-				struct perf_event_attr *attr, u32 ids, u64 *id,
-				perf_event__handler_t process)
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event)
 {
-	union perf_event *ev;
-	size_t size;
-	int err;
-
-	size = sizeof(struct perf_event_attr);
-	size = PERF_ALIGN(size, sizeof(u64));
-	size += sizeof(struct perf_event_header);
-	size += ids * sizeof(u64);
-
-	ev = malloc(size);
-
-	if (ev == NULL)
-		return -ENOMEM;
-
-	ev->attr.attr = *attr;
-	memcpy(ev->attr.id, id, ids * sizeof(u64));
-
-	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
-	ev->attr.header.size = (u16)size;
-
-	if (ev->attr.header.size == size)
-		err = process(tool, ev, NULL, NULL);
-	else
-		err = -E2BIG;
-
-	free(ev);
-
-	return err;
-}
-
-int perf_event__synthesize_features(struct perf_tool *tool,
-				    struct perf_session *session,
-				    struct perf_evlist *evlist,
-				    perf_event__handler_t process)
-{
-	struct perf_header *header = &session->header;
-	struct feat_fd ff;
-	struct feature_event *fe;
-	size_t sz, sz_hdr;
-	int feat, ret;
-
-	sz_hdr = sizeof(fe->header);
-	sz = sizeof(union perf_event);
-	/* get a nice alignment */
-	sz = PERF_ALIGN(sz, page_size);
-
-	memset(&ff, 0, sizeof(ff));
-
-	ff.buf = malloc(sz);
-	if (!ff.buf)
-		return -ENOMEM;
-
-	ff.size = sz - sz_hdr;
-
-	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
-		if (!feat_ops[feat].synthesize) {
-			pr_debug("No record header feature for header :%d\n", feat);
-			continue;
-		}
-
-		ff.offset = sizeof(*fe);
-
-		ret = feat_ops[feat].write(&ff, evlist);
-		if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
-			pr_debug("Error writing feature\n");
-			continue;
-		}
-		/* ff.buf may have changed due to realloc in do_write() */
-		fe = ff.buf;
-		memset(fe, 0, sizeof(*fe));
-
-		fe->feat_id = feat;
-		fe->header.type = PERF_RECORD_HEADER_FEATURE;
-		fe->header.size = ff.offset;
-
-		ret = process(tool, ff.buf, NULL, NULL);
-		if (ret) {
-			free(ff.buf);
-			return ret;
-		}
-	}
-
-	/* Send HEADER_LAST_FEATURE mark. */
-	fe = ff.buf;
-	fe->feat_id     = HEADER_LAST_FEATURE;
-	fe->header.type = PERF_RECORD_HEADER_FEATURE;
-	fe->header.size = sizeof(*fe);
-
-	ret = process(tool, ff.buf, NULL, NULL);
-
-	free(ff.buf);
-	return ret;
-}
-
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session __maybe_unused)
-{
+	struct perf_tool *tool = session->tool;
 	struct feat_fd ff = { .fd = 0 };
-	struct feature_event *fe = (struct feature_event *)event;
+	struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event;
 	int type = fe->header.type;
 	u64 feat = fe->feat_id;
 
@@ -3470,7 +3666,7 @@
 		return 0;
 
 	ff.buf  = (void *)fe->data;
-	ff.size = event->header.size - sizeof(event->header);
+	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
 	if (feat_ops[feat].process(&ff, NULL))
@@ -3490,126 +3686,19 @@
 	return 0;
 }
 
-static struct event_update_event *
-event_update_event__new(size_t size, u64 type, u64 id)
-{
-	struct event_update_event *ev;
-
-	size += sizeof(*ev);
-	size  = PERF_ALIGN(size, sizeof(u64));
-
-	ev = zalloc(size);
-	if (ev) {
-		ev->header.type = PERF_RECORD_EVENT_UPDATE;
-		ev->header.size = (u16)size;
-		ev->type = type;
-		ev->id = id;
-	}
-	return ev;
-}
-
-int
-perf_event__synthesize_event_update_unit(struct perf_tool *tool,
-					 struct perf_evsel *evsel,
-					 perf_event__handler_t process)
-{
-	struct event_update_event *ev;
-	size_t size = strlen(evsel->unit);
-	int err;
-
-	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	strncpy(ev->data, evsel->unit, size);
-	err = process(tool, (union perf_event *)ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_scale(struct perf_tool *tool,
-					  struct perf_evsel *evsel,
-					  perf_event__handler_t process)
-{
-	struct event_update_event *ev;
-	struct event_update_event_scale *ev_data;
-	int err;
-
-	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	ev_data = (struct event_update_event_scale *) ev->data;
-	ev_data->scale = evsel->scale;
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_name(struct perf_tool *tool,
-					 struct perf_evsel *evsel,
-					 perf_event__handler_t process)
-{
-	struct event_update_event *ev;
-	size_t len = strlen(evsel->name);
-	int err;
-
-	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
-	if (ev == NULL)
-		return -ENOMEM;
-
-	strncpy(ev->data, evsel->name, len);
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
-int
-perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
-					struct perf_evsel *evsel,
-					perf_event__handler_t process)
-{
-	size_t size = sizeof(struct event_update_event);
-	struct event_update_event *ev;
-	int max, err;
-	u16 type;
-
-	if (!evsel->own_cpus)
-		return 0;
-
-	ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max);
-	if (!ev)
-		return -ENOMEM;
-
-	ev->header.type = PERF_RECORD_EVENT_UPDATE;
-	ev->header.size = (u16)size;
-	ev->type = PERF_EVENT_UPDATE__CPUS;
-	ev->id   = evsel->id[0];
-
-	cpu_map_data__synthesize((struct cpu_map_data *) ev->data,
-				 evsel->own_cpus,
-				 type, max);
-
-	err = process(tool, (union perf_event*) ev, NULL, NULL);
-	free(ev);
-	return err;
-}
-
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 {
-	struct event_update_event *ev = &event->event_update;
-	struct event_update_event_scale *ev_scale;
-	struct event_update_event_cpus *ev_cpus;
-	struct cpu_map *map;
+	struct perf_record_event_update *ev = &event->event_update;
+	struct perf_record_event_update_scale *ev_scale;
+	struct perf_record_event_update_cpus *ev_cpus;
+	struct perf_cpu_map *map;
 	size_t ret;
 
-	ret = fprintf(fp, "\n... id:    %" PRIu64 "\n", ev->id);
+	ret = fprintf(fp, "\n... id:    %" PRI_lu64 "\n", ev->id);
 
 	switch (ev->type) {
 	case PERF_EVENT_UPDATE__SCALE:
-		ev_scale = (struct event_update_event_scale *) ev->data;
+		ev_scale = (struct perf_record_event_update_scale *)ev->data;
 		ret += fprintf(fp, "... scale: %f\n", ev_scale->scale);
 		break;
 	case PERF_EVENT_UPDATE__UNIT:
@@ -3619,7 +3708,7 @@
 		ret += fprintf(fp, "... name:  %s\n", ev->data);
 		break;
 	case PERF_EVENT_UPDATE__CPUS:
-		ev_cpus = (struct event_update_event_cpus *) ev->data;
+		ev_cpus = (struct perf_record_event_update_cpus *)ev->data;
 		ret += fprintf(fp, "... ");
 
 		map = cpu_map__new_data(&ev_cpus->cpus);
@@ -3636,112 +3725,25 @@
 	return ret;
 }
 
-int perf_event__synthesize_attrs(struct perf_tool *tool,
-				   struct perf_session *session,
-				   perf_event__handler_t process)
-{
-	struct perf_evsel *evsel;
-	int err = 0;
-
-	evlist__for_each_entry(session->evlist, evsel) {
-		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
-						  evsel->id, process);
-		if (err) {
-			pr_debug("failed to create perf header attribute\n");
-			return err;
-		}
-	}
-
-	return err;
-}
-
-static bool has_unit(struct perf_evsel *counter)
-{
-	return counter->unit && *counter->unit;
-}
-
-static bool has_scale(struct perf_evsel *counter)
-{
-	return counter->scale != 1;
-}
-
-int perf_event__synthesize_extra_attr(struct perf_tool *tool,
-				      struct perf_evlist *evsel_list,
-				      perf_event__handler_t process,
-				      bool is_pipe)
-{
-	struct perf_evsel *counter;
-	int err;
-
-	/*
-	 * Synthesize other events stuff not carried within
-	 * attr event - unit, scale, name
-	 */
-	evlist__for_each_entry(evsel_list, counter) {
-		if (!counter->supported)
-			continue;
-
-		/*
-		 * Synthesize unit and scale only if it's defined.
-		 */
-		if (has_unit(counter)) {
-			err = perf_event__synthesize_event_update_unit(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel unit.\n");
-				return err;
-			}
-		}
-
-		if (has_scale(counter)) {
-			err = perf_event__synthesize_event_update_scale(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel counter.\n");
-				return err;
-			}
-		}
-
-		if (counter->own_cpus) {
-			err = perf_event__synthesize_event_update_cpus(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel cpus.\n");
-				return err;
-			}
-		}
-
-		/*
-		 * Name is needed only for pipe output,
-		 * perf.data carries event names.
-		 */
-		if (is_pipe) {
-			err = perf_event__synthesize_event_update_name(tool, counter, process);
-			if (err < 0) {
-				pr_err("Couldn't synthesize evsel name.\n");
-				return err;
-			}
-		}
-	}
-	return 0;
-}
-
 int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
-			     struct perf_evlist **pevlist)
+			     struct evlist **pevlist)
 {
 	u32 i, ids, n_ids;
-	struct perf_evsel *evsel;
-	struct perf_evlist *evlist = *pevlist;
+	struct evsel *evsel;
+	struct evlist *evlist = *pevlist;
 
 	if (evlist == NULL) {
-		*pevlist = evlist = perf_evlist__new();
+		*pevlist = evlist = evlist__new();
 		if (evlist == NULL)
 			return -ENOMEM;
 	}
 
-	evsel = perf_evsel__new(&event->attr.attr);
+	evsel = evsel__new(&event->attr.attr);
 	if (evsel == NULL)
 		return -ENOMEM;
 
-	perf_evlist__add(evlist, evsel);
+	evlist__add(evlist, evsel);
 
 	ids = event->header.size;
 	ids -= (void *)&event->attr.id - (void *)event;
@@ -3751,11 +3753,11 @@
 	 * for allocating the perf_sample_id table we fake 1 cpu and
 	 * hattr->ids threads.
 	 */
-	if (perf_evsel__alloc_id(evsel, 1, n_ids))
+	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
 	for (i = 0; i < n_ids; i++) {
-		perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
+		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
 	}
 
 	return 0;
@@ -3763,14 +3765,14 @@
 
 int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
-				     struct perf_evlist **pevlist)
+				     struct evlist **pevlist)
 {
-	struct event_update_event *ev = &event->event_update;
-	struct event_update_event_scale *ev_scale;
-	struct event_update_event_cpus *ev_cpus;
-	struct perf_evlist *evlist;
-	struct perf_evsel *evsel;
-	struct cpu_map *map;
+	struct perf_record_event_update *ev = &event->event_update;
+	struct perf_record_event_update_scale *ev_scale;
+	struct perf_record_event_update_cpus *ev_cpus;
+	struct evlist *evlist;
+	struct evsel *evsel;
+	struct perf_cpu_map *map;
 
 	if (!pevlist || *pevlist == NULL)
 		return -EINVAL;
@@ -3789,15 +3791,15 @@
 		evsel->name = strdup(ev->data);
 		break;
 	case PERF_EVENT_UPDATE__SCALE:
-		ev_scale = (struct event_update_event_scale *) ev->data;
+		ev_scale = (struct perf_record_event_update_scale *)ev->data;
 		evsel->scale = ev_scale->scale;
 		break;
 	case PERF_EVENT_UPDATE__CPUS:
-		ev_cpus = (struct event_update_event_cpus *) ev->data;
+		ev_cpus = (struct perf_record_event_update_cpus *)ev->data;
 
 		map = cpu_map__new_data(&ev_cpus->cpus);
 		if (map)
-			evsel->own_cpus = map;
+			evsel->core.own_cpus = map;
 		else
 			pr_err("failed to get event_update cpus\n");
 	default:
@@ -3807,58 +3809,8 @@
 	return 0;
 }
 
-int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
-					struct perf_evlist *evlist,
-					perf_event__handler_t process)
-{
-	union perf_event ev;
-	struct tracing_data *tdata;
-	ssize_t size = 0, aligned_size = 0, padding;
-	struct feat_fd ff;
-	int err __maybe_unused = 0;
-
-	/*
-	 * We are going to store the size of the data followed
-	 * by the data contents. Since the fd descriptor is a pipe,
-	 * we cannot seek back to store the size of the data once
-	 * we know it. Instead we:
-	 *
-	 * - write the tracing data to the temp file
-	 * - get/write the data size to pipe
-	 * - write the tracing data from the temp file
-	 *   to the pipe
-	 */
-	tdata = tracing_data_get(&evlist->entries, fd, true);
-	if (!tdata)
-		return -1;
-
-	memset(&ev, 0, sizeof(ev));
-
-	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-	size = tdata->size;
-	aligned_size = PERF_ALIGN(size, sizeof(u64));
-	padding = aligned_size - size;
-	ev.tracing_data.header.size = sizeof(ev.tracing_data);
-	ev.tracing_data.size = aligned_size;
-
-	process(tool, &ev, NULL, NULL);
-
-	/*
-	 * The put function will copy all the tracing data
-	 * stored in temp file to the pipe.
-	 */
-	tracing_data_put(tdata);
-
-	ff = (struct feat_fd){ .fd = fd };
-	if (write_padded(&ff, NULL, 0, padding))
-		return -1;
-
-	return aligned_size;
-}
-
-int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
-				     union perf_event *event,
-				     struct perf_session *session)
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
 	int fd = perf_data__fd(session->data);
@@ -3866,7 +3818,7 @@
 	char buf[BUFSIZ];
 
 	/* setup for reading amidst mmap */
-	lseek(fd, offset + sizeof(struct tracing_data_event),
+	lseek(fd, offset + sizeof(struct perf_record_header_tracing_data),
 	      SEEK_SET);
 
 	size_read = trace_report(fd, &session->tevent,
@@ -3896,37 +3848,8 @@
 	return size_read + padding;
 }
 
-int perf_event__synthesize_build_id(struct perf_tool *tool,
-				    struct dso *pos, u16 misc,
-				    perf_event__handler_t process,
-				    struct machine *machine)
-{
-	union perf_event ev;
-	size_t len;
-	int err = 0;
-
-	if (!pos->hit)
-		return err;
-
-	memset(&ev, 0, sizeof(ev));
-
-	len = pos->long_name_len + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
-	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
-	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
-	ev.build_id.header.misc = misc;
-	ev.build_id.pid = machine->pid;
-	ev.build_id.header.size = sizeof(ev.build_id) + len;
-	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
-
-	err = process(tool, &ev, NULL, machine);
-
-	return err;
-}
-
-int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event)
 {
 	__event_process_build_id(&event->build_id,
 				 event->build_id.filename,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6d7fe44..ca53a92 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -5,10 +5,10 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <sys/types.h>
+#include <stdio.h> // FILE
 #include <stdbool.h>
 #include <linux/bitmap.h>
 #include <linux/types.h>
-#include "event.h"
 #include "env.h"
 #include "pmu.h"
 
@@ -38,6 +38,11 @@
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
+	HEADER_DIR_FORMAT,
+	HEADER_BPF_PROG_INFO,
+	HEADER_BPF_BTF,
+	HEADER_COMPRESSED,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -47,6 +52,10 @@
 	PERF_HEADER_VERSION_2,
 };
 
+enum perf_dir_version {
+	PERF_DIR_VERSION	= 1,
+};
+
 struct perf_file_section {
 	u64 offset;
 	u64 size;
@@ -83,12 +92,32 @@
 	struct perf_env 	env;
 };
 
-struct perf_evlist;
+struct feat_fd {
+	struct perf_header *ph;
+	int		   fd;
+	void		   *buf;	/* Either buf != NULL or fd >= 0 */
+	ssize_t		   offset;
+	size_t		   size;
+	struct evsel	   *events;
+};
+
+struct perf_header_feature_ops {
+	int	   (*write)(struct feat_fd *ff, struct evlist *evlist);
+	void	   (*print)(struct feat_fd *ff, FILE *fp);
+	int	   (*process)(struct feat_fd *ff, void *data);
+	const char *name;
+	bool	   full_only;
+	bool	   synthesize;
+};
+
+struct evlist;
 struct perf_session;
+struct perf_tool;
+union perf_event;
 
 int perf_session__read_header(struct perf_session *session);
 int perf_session__write_header(struct perf_session *session,
-			       struct perf_evlist *evlist,
+			       struct evlist *evlist,
 			       int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
@@ -106,59 +135,18 @@
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int perf_event__synthesize_features(struct perf_tool *tool,
-				    struct perf_session *session,
-				    struct perf_evlist *evlist,
-				    perf_event__handler_t process);
-
-int perf_event__synthesize_extra_attr(struct perf_tool *tool,
-				      struct perf_evlist *evsel_list,
-				      perf_event__handler_t process,
-				      bool is_pipe);
-
-int perf_event__process_feature(struct perf_tool *tool,
-				union perf_event *event,
-				struct perf_session *session);
-
-int perf_event__synthesize_attr(struct perf_tool *tool,
-				struct perf_event_attr *attr, u32 ids, u64 *id,
-				perf_event__handler_t process);
-int perf_event__synthesize_attrs(struct perf_tool *tool,
-				 struct perf_session *session,
-				 perf_event__handler_t process);
-int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
-					     struct perf_evsel *evsel,
-					     perf_event__handler_t process);
-int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
-					      struct perf_evsel *evsel,
-					      perf_event__handler_t process);
-int perf_event__synthesize_event_update_name(struct perf_tool *tool,
-					     struct perf_evsel *evsel,
-					     perf_event__handler_t process);
-int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
-					     struct perf_evsel *evsel,
-					     perf_event__handler_t process);
+int perf_event__process_feature(struct perf_session *session,
+				union perf_event *event);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
-			     struct perf_evlist **pevlist);
+			     struct evlist **pevlist);
 int perf_event__process_event_update(struct perf_tool *tool,
 				     union perf_event *event,
-				     struct perf_evlist **pevlist);
+				     struct evlist **pevlist);
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
-
-int perf_event__synthesize_tracing_data(struct perf_tool *tool,
-					int fd, struct perf_evlist *evlist,
-					perf_event__handler_t process);
-int perf_event__process_tracing_data(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_session *session);
-
-int perf_event__synthesize_build_id(struct perf_tool *tool,
-				    struct dso *pos, u16 misc,
-				    perf_event__handler_t process,
-				    struct machine *machine);
-int perf_event__process_build_id(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
+int perf_event__process_tracing_data(struct perf_session *session,
+				     union perf_event *event);
+int perf_event__process_build_id(struct perf_session *session,
+				 union perf_event *event);
 bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 4f07a5b..ab9e161 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -3,9 +3,11 @@
 #include "config.h"
 #include <poll.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
+#include <linux/zalloc.h>
 
 static int autocorrect;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 828cb97..7b6eaf5 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,8 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
+#include "callchain.h"
+#include "debug.h"
+#include "dso.h"
 #include "build-id.h"
 #include "hist.h"
 #include "map.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "mem-events.h"
 #include "session.h"
 #include "namespaces.h"
 #include "sort.h"
@@ -11,12 +16,17 @@
 #include "evsel.h"
 #include "annotate.h"
 #include "srcline.h"
+#include "symbol.h"
 #include "thread.h"
 #include "ui/progress.h"
 #include <errno.h>
 #include <math.h>
 #include <inttypes.h>
 #include <sys/param.h>
+#include <linux/rbtree.h>
+#include <linux/string.h>
+#include <linux/time64.h>
+#include <linux/zalloc.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
 				       struct hist_entry *he);
@@ -190,6 +200,10 @@
 	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
+	if (symbol_conf.nanosecs)
+		hists__new_col_len(hists, HISTC_TIME, 16);
+	else
+		hists__new_col_len(hists, HISTC_TIME, 12);
 
 	if (h->srcline) {
 		len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
@@ -209,7 +223,7 @@
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 	int row = 0;
 
@@ -244,6 +258,14 @@
 	}
 }
 
+static long hist_time(unsigned long htime)
+{
+	unsigned long time_quantum = symbol_conf.time_quantum;
+	if (time_quantum)
+		return (htime / time_quantum) * time_quantum;
+	return htime;
+}
+
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
 				u64 weight)
 {
@@ -296,7 +318,7 @@
 
 	if (!he->leaf) {
 		struct hist_entry *child;
-		struct rb_node *node = rb_first(&he->hroot_out);
+		struct rb_node *node = rb_first_cached(&he->hroot_out);
 		while (node) {
 			child = rb_entry(node, struct hist_entry, rb_node);
 			node = rb_next(node);
@@ -311,8 +333,8 @@
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	struct rb_root *root_in;
-	struct rb_root *root_out;
+	struct rb_root_cached *root_in;
+	struct rb_root_cached *root_out;
 
 	if (he->parent_he) {
 		root_in  = &he->parent_he->hroot_in;
@@ -325,8 +347,8 @@
 		root_out = &hists->entries;
 	}
 
-	rb_erase(&he->rb_node_in, root_in);
-	rb_erase(&he->rb_node, root_out);
+	rb_erase_cached(&he->rb_node_in, root_in);
+	rb_erase_cached(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -337,7 +359,7 @@
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 
 	while (next) {
@@ -353,7 +375,7 @@
 
 void hists__delete_entries(struct hists *hists)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct hist_entry *n;
 
 	while (next) {
@@ -364,6 +386,24 @@
 	}
 }
 
+struct hist_entry *hists__get_entry(struct hists *hists, int idx)
+{
+	struct rb_node *next = rb_first_cached(&hists->entries);
+	struct hist_entry *n;
+	int i = 0;
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		if (i == idx)
+			return n;
+
+		next = rb_next(&n->rb_node);
+		i++;
+	}
+
+	return NULL;
+}
+
 /*
  * histogram, sorted on item, collects periods
  */
@@ -394,11 +434,8 @@
 		 * adding new entries.  So we need to save a copy.
 		 */
 		he->branch_info = malloc(sizeof(*he->branch_info));
-		if (he->branch_info == NULL) {
-			map__zput(he->ms.map);
-			free(he->stat_acc);
-			return -ENOMEM;
-		}
+		if (he->branch_info == NULL)
+			goto err;
 
 		memcpy(he->branch_info, template->branch_info,
 		       sizeof(*he->branch_info));
@@ -417,31 +454,53 @@
 
 	if (he->raw_data) {
 		he->raw_data = memdup(he->raw_data, he->raw_size);
-
-		if (he->raw_data == NULL) {
-			map__put(he->ms.map);
-			if (he->branch_info) {
-				map__put(he->branch_info->from.map);
-				map__put(he->branch_info->to.map);
-				free(he->branch_info);
-			}
-			if (he->mem_info) {
-				map__put(he->mem_info->iaddr.map);
-				map__put(he->mem_info->daddr.map);
-			}
-			free(he->stat_acc);
-			return -ENOMEM;
-		}
+		if (he->raw_data == NULL)
+			goto err_infos;
 	}
+
+	if (he->srcline) {
+		he->srcline = strdup(he->srcline);
+		if (he->srcline == NULL)
+			goto err_rawdata;
+	}
+
+	if (symbol_conf.res_sample) {
+		he->res_samples = calloc(sizeof(struct res_sample),
+					symbol_conf.res_sample);
+		if (!he->res_samples)
+			goto err_srcline;
+	}
+
 	INIT_LIST_HEAD(&he->pairs.node);
 	thread__get(he->thread);
-	he->hroot_in  = RB_ROOT;
-	he->hroot_out = RB_ROOT;
+	he->hroot_in  = RB_ROOT_CACHED;
+	he->hroot_out = RB_ROOT_CACHED;
 
 	if (!symbol_conf.report_hierarchy)
 		he->leaf = true;
 
 	return 0;
+
+err_srcline:
+	zfree(&he->srcline);
+
+err_rawdata:
+	zfree(&he->raw_data);
+
+err_infos:
+	if (he->branch_info) {
+		map__put(he->branch_info->from.map);
+		map__put(he->branch_info->to.map);
+		zfree(&he->branch_info);
+	}
+	if (he->mem_info) {
+		map__put(he->mem_info->iaddr.map);
+		map__put(he->mem_info->daddr.map);
+	}
+err:
+	map__zput(he->ms.map);
+	zfree(&he->stat_acc);
+	return -ENOMEM;
 }
 
 static void *hist_entry__zalloc(size_t size)
@@ -513,8 +572,9 @@
 	int64_t cmp;
 	u64 period = entry->stat.period;
 	u64 weight = entry->stat.weight;
+	bool leftmost = true;
 
-	p = &hists->entries_in->rb_node;
+	p = &hists->entries_in->rb_root.rb_node;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -542,6 +602,8 @@
 			 */
 			mem_info__zput(entry->mem_info);
 
+			block_info__zput(entry->block_info);
+
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
 			 * similar, update it.  Otherwise we will
@@ -557,8 +619,10 @@
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(entry, sample_self);
@@ -570,7 +634,7 @@
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
-	rb_insert_color(&he->rb_node_in, hists->entries_in);
+	rb_insert_color_cached(&he->rb_node_in, hists->entries_in, leftmost);
 out:
 	if (sample_self)
 		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
@@ -579,12 +643,39 @@
 	return he;
 }
 
+static unsigned random_max(unsigned high)
+{
+	unsigned thresh = -high % high;
+	for (;;) {
+		unsigned r = random();
+		if (r >= thresh)
+			return r % high;
+	}
+}
+
+static void hists__res_sample(struct hist_entry *he, struct perf_sample *sample)
+{
+	struct res_sample *r;
+	int j;
+
+	if (he->num_res < symbol_conf.res_sample) {
+		j = he->num_res++;
+	} else {
+		j = random_max(symbol_conf.res_sample);
+	}
+	r = &he->res_samples[j];
+	r->time = sample->time;
+	r->cpu = sample->cpu;
+	r->tid = sample->tid;
+}
+
 static struct hist_entry*
 __hists__add_entry(struct hists *hists,
 		   struct addr_location *al,
 		   struct symbol *sym_parent,
 		   struct branch_info *bi,
 		   struct mem_info *mi,
+		   struct block_info *block_info,
 		   struct perf_sample *sample,
 		   bool sample_self,
 		   struct hist_entry_ops *ops)
@@ -601,7 +692,7 @@
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.srcline = al->srcline ? strdup(al->srcline) : NULL,
+		.srcline = (char *) al->srcline,
 		.socket	 = al->socket,
 		.cpu	 = al->cpu,
 		.cpumode = al->cpumode,
@@ -617,14 +708,18 @@
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,
+		.block_info = block_info,
 		.transaction = sample->transaction,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
 		.ops = ops,
+		.time = hist_time(sample->time),
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
 		hists->has_callchains = true;
+	if (he && symbol_conf.res_sample)
+		hists__res_sample(he, sample);
 	return he;
 }
 
@@ -636,7 +731,7 @@
 				    struct perf_sample *sample,
 				    bool sample_self)
 {
-	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+	return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL,
 				  sample, sample_self, NULL);
 }
 
@@ -649,10 +744,22 @@
 					struct perf_sample *sample,
 					bool sample_self)
 {
-	return __hists__add_entry(hists, al, sym_parent, bi, mi,
+	return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL,
 				  sample, sample_self, ops);
 }
 
+struct hist_entry *hists__add_entry_block(struct hists *hists,
+					  struct addr_location *al,
+					  struct block_info *block_info)
+{
+	struct hist_entry entry = {
+		.block_info = block_info,
+		.hists = hists,
+	}, *he = hists__findnew_entry(hists, &entry, al, false);
+
+	return he;
+}
+
 static int
 iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
 		    struct addr_location *al __maybe_unused)
@@ -719,7 +826,7 @@
 iter_finish_mem_entry(struct hist_entry_iter *iter,
 		      struct addr_location *al __maybe_unused)
 {
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he = iter->he;
 	int err = -EINVAL;
@@ -789,7 +896,7 @@
 iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
 	struct branch_info *bi;
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he = NULL;
@@ -841,7 +948,7 @@
 static int
 iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
 {
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
@@ -859,7 +966,7 @@
 			 struct addr_location *al __maybe_unused)
 {
 	struct hist_entry *he = iter->he;
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct perf_sample *sample = iter->sample;
 
 	if (he == NULL)
@@ -899,7 +1006,7 @@
 iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 				 struct addr_location *al)
 {
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry **he_cache = iter->priv;
@@ -944,7 +1051,7 @@
 iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			       struct addr_location *al)
 {
-	struct perf_evsel *evsel = iter->evsel;
+	struct evsel *evsel = iter->evsel;
 	struct perf_sample *sample = iter->sample;
 	struct hist_entry **he_cache = iter->priv;
 	struct hist_entry *he;
@@ -958,7 +1065,7 @@
 			.map = al->map,
 			.sym = al->sym,
 		},
-		.srcline = al->srcline ? strdup(al->srcline) : NULL,
+		.srcline = (char *) al->srcline,
 		.parent = iter->parent,
 		.raw_data = sample->raw_data,
 		.raw_size = sample->raw_size,
@@ -1048,8 +1155,10 @@
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
-	if (err)
+	if (err) {
+		map__put(alm);
 		return err;
+	}
 
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
@@ -1148,19 +1257,23 @@
 		mem_info__zput(he->mem_info);
 	}
 
+	if (he->block_info)
+		block_info__zput(he->block_info);
+
+	zfree(&he->res_samples);
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	if (he->srcfile && he->srcfile[0])
-		free(he->srcfile);
+		zfree(&he->srcfile);
 	free_callchain(he->callchain);
-	free(he->trace_output);
-	free(he->raw_data);
+	zfree(&he->trace_output);
+	zfree(&he->raw_data);
 	ops->free(he);
 }
 
 /*
  * If this is not the last column, then we need to pad it according to the
- * pre-calculated max lenght for this column, otherwise don't bother adding
+ * pre-calculated max length for this column, otherwise don't bother adding
  * spaces because that would break viewing this with, for instance, 'less',
  * that would show tons of trailing spaces when a long C++ demangled method
  * names is sampled.
@@ -1279,16 +1392,17 @@
 }
 
 static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
-						 struct rb_root *root,
+						 struct rb_root_cached *root,
 						 struct hist_entry *he,
 						 struct hist_entry *parent_he,
 						 struct perf_hpp_list *hpp_list)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter, *new;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1308,8 +1422,10 @@
 
 		if (cmp < 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	new = hist_entry__new(he, true);
@@ -1343,12 +1459,12 @@
 	}
 
 	rb_link_node(&new->rb_node_in, parent, p);
-	rb_insert_color(&new->rb_node_in, root);
+	rb_insert_color_cached(&new->rb_node_in, root, leftmost);
 	return new;
 }
 
 static int hists__hierarchy_insert_entry(struct hists *hists,
-					 struct rb_root *root,
+					 struct rb_root_cached *root,
 					 struct hist_entry *he)
 {
 	struct perf_hpp_list_node *node;
@@ -1395,13 +1511,14 @@
 }
 
 static int hists__collapse_insert_entry(struct hists *hists,
-					struct rb_root *root,
+					struct rb_root_cached *root,
 					struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	int64_t cmp;
+	bool leftmost = true;
 
 	if (symbol_conf.report_hierarchy)
 		return hists__hierarchy_insert_entry(hists, root, he);
@@ -1432,19 +1549,21 @@
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
-	rb_insert_color(&he->rb_node_in, root);
+	rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 	return 1;
 }
 
-struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 
 	pthread_mutex_lock(&hists->lock);
 
@@ -1467,7 +1586,7 @@
 
 int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 	int ret;
@@ -1479,7 +1598,7 @@
 
 	root = hists__get_rotate_entries_in(hists);
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 
 	while (next) {
 		if (session_done())
@@ -1487,7 +1606,7 @@
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
-		rb_erase(&n->rb_node_in, root);
+		rb_erase_cached(&n->rb_node_in, root);
 		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
 		if (ret < 0)
 			return -1;
@@ -1506,7 +1625,7 @@
 	return 0;
 }
 
-static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
+static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
 	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
@@ -1558,7 +1677,7 @@
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	node = rb_first(&hists->entries);
+	node = rb_first_cached(&hists->entries);
 
 	hists->stats.total_period = 0;
 	hists->stats.total_non_filtered_period = 0;
@@ -1578,13 +1697,14 @@
 	}
 }
 
-static void hierarchy_insert_output_entry(struct rb_root *root,
+static void hierarchy_insert_output_entry(struct rb_root_cached *root,
 					  struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1592,12 +1712,14 @@
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color_cached(&he->rb_node, root, leftmost);
 
 	/* update column width of dynamic entry */
 	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
@@ -1608,16 +1730,16 @@
 
 static void hists__hierarchy_output_resort(struct hists *hists,
 					   struct ui_progress *prog,
-					   struct rb_root *root_in,
-					   struct rb_root *root_out,
+					   struct rb_root_cached *root_in,
+					   struct rb_root_cached *root_out,
 					   u64 min_callchain_hits,
 					   bool use_callchain)
 {
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	*root_out = RB_ROOT;
-	node = rb_first(root_in);
+	*root_out = RB_ROOT_CACHED;
+	node = rb_first_cached(root_in);
 
 	while (node) {
 		he = rb_entry(node, struct hist_entry, rb_node_in);
@@ -1660,15 +1782,16 @@
 	}
 }
 
-static void __hists__insert_output_entry(struct rb_root *entries,
+static void __hists__insert_output_entry(struct rb_root_cached *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
 					 bool use_callchain)
 {
-	struct rb_node **p = &entries->rb_node;
+	struct rb_node **p = &entries->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
 	if (use_callchain) {
 		if (callchain_param.mode == CHAIN_GRAPH_REL) {
@@ -1689,12 +1812,14 @@
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, entries);
+	rb_insert_color_cached(&he->rb_node, entries, leftmost);
 
 	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
 		if (perf_hpp__is_dynamic_entry(fmt) &&
@@ -1704,9 +1829,10 @@
 }
 
 static void output_resort(struct hists *hists, struct ui_progress *prog,
-			  bool use_callchain, hists__resort_cb_t cb)
+			  bool use_callchain, hists__resort_cb_t cb,
+			  void *cb_arg)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 	u64 callchain_total;
@@ -1736,14 +1862,14 @@
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
-	hists->entries = RB_ROOT;
+	next = rb_first_cached(root);
+	hists->entries = RB_ROOT_CACHED;
 
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
 
-		if (cb && cb(n))
+		if (cb && cb(n, cb_arg))
 			continue;
 
 		__hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain);
@@ -1757,7 +1883,8 @@
 	}
 }
 
-void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg)
 {
 	bool use_callchain;
 
@@ -1768,18 +1895,23 @@
 
 	use_callchain |= symbol_conf.show_branchflag_count;
 
-	output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
+	output_resort(evsel__hists(evsel), prog, use_callchain, cb, cb_arg);
+}
+
+void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog)
+{
+	return perf_evsel__output_resort_cb(evsel, prog, NULL, NULL);
 }
 
 void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
-	output_resort(hists, prog, symbol_conf.use_callchain, NULL);
+	output_resort(hists, prog, symbol_conf.use_callchain, NULL, NULL);
 }
 
 void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
 			     hists__resort_cb_t cb)
 {
-	output_resort(hists, prog, symbol_conf.use_callchain, cb);
+	output_resort(hists, prog, symbol_conf.use_callchain, cb, NULL);
 }
 
 static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
@@ -1798,7 +1930,7 @@
 	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
 
 	while (can_goto_child(he, HMD_NORMAL)) {
-		node = rb_last(&he->hroot_out);
+		node = rb_last(&he->hroot_out.rb_root);
 		he = rb_entry(node, struct hist_entry, rb_node);
 	}
 	return node;
@@ -1809,7 +1941,7 @@
 	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
 
 	if (can_goto_child(he, hmd))
-		node = rb_first(&he->hroot_out);
+		node = rb_first_cached(&he->hroot_out);
 	else
 		node = rb_next(node);
 
@@ -1847,7 +1979,7 @@
 	if (he->leaf)
 		return false;
 
-	node = rb_first(&he->hroot_out);
+	node = rb_first_cached(&he->hroot_out);
 	child = rb_entry(node, struct hist_entry, rb_node);
 
 	while (node && child->filtered) {
@@ -1965,7 +2097,7 @@
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		if (filter(hists, h))
@@ -1975,13 +2107,15 @@
 	}
 }
 
-static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root_cached *root,
+				  struct hist_entry *he)
 {
-	struct rb_node **p = &root->rb_node;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
-	struct rb_root new_root = RB_ROOT;
+	struct rb_root_cached new_root = RB_ROOT_CACHED;
 	struct rb_node *nd;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1989,22 +2123,24 @@
 
 		if (hist_entry__sort(he, iter) > 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
+	rb_insert_color_cached(&he->rb_node, root, leftmost);
 
 	if (he->leaf || he->filtered)
 		return;
 
-	nd = rb_first(&he->hroot_out);
+	nd = rb_first_cached(&he->hroot_out);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		nd = rb_next(nd);
-		rb_erase(&h->rb_node, &he->hroot_out);
+		rb_erase_cached(&h->rb_node, &he->hroot_out);
 
 		resort_filtered_entry(&new_root, h);
 	}
@@ -2015,14 +2151,14 @@
 static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
-	struct rb_root new_root = RB_ROOT;
+	struct rb_root_cached new_root = RB_ROOT_CACHED;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	nd = rb_first(&hists->entries);
+	nd = rb_first_cached(&hists->entries);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		int ret;
@@ -2066,12 +2202,12 @@
 	 * resort output after applying a new filter since filter in a lower
 	 * hierarchy can change periods in a upper hierarchy.
 	 */
-	nd = rb_first(&hists->entries);
+	nd = rb_first_cached(&hists->entries);
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		nd = rb_next(nd);
-		rb_erase(&h->rb_node, &hists->entries);
+		rb_erase_cached(&h->rb_node, &hists->entries);
 
 		resort_filtered_entry(&new_root, h);
 	}
@@ -2140,18 +2276,19 @@
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	int64_t cmp;
+	bool leftmost = true;
 
 	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
 
-	p = &root->rb_node;
+	p = &root->rb_root.rb_node;
 
 	while (*p != NULL) {
 		parent = *p;
@@ -2164,8 +2301,10 @@
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(pair, true);
@@ -2175,7 +2314,7 @@
 		if (symbol_conf.cumulate_callchain)
 			memset(he->stat_acc, 0, sizeof(he->stat));
 		rb_link_node(&he->rb_node_in, parent, p);
-		rb_insert_color(&he->rb_node_in, root);
+		rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 		hists__inc_stats(hists, he);
 		he->dummy = true;
 	}
@@ -2184,15 +2323,16 @@
 }
 
 static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists,
-						    struct rb_root *root,
+						    struct rb_root_cached *root,
 						    struct hist_entry *pair)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	struct perf_hpp_fmt *fmt;
+	bool leftmost = true;
 
-	p = &root->rb_node;
+	p = &root->rb_root.rb_node;
 	while (*p != NULL) {
 		int64_t cmp = 0;
 
@@ -2209,14 +2349,16 @@
 
 		if (cmp < 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(pair, true);
 	if (he) {
 		rb_link_node(&he->rb_node_in, parent, p);
-		rb_insert_color(&he->rb_node_in, root);
+		rb_insert_color_cached(&he->rb_node_in, root, leftmost);
 
 		he->dummy = true;
 		he->hists = hists;
@@ -2233,9 +2375,9 @@
 	struct rb_node *n;
 
 	if (hists__has(hists, need_collapse))
-		n = hists->entries_collapsed.rb_node;
+		n = hists->entries_collapsed.rb_root.rb_node;
 	else
-		n = hists->entries_in->rb_node;
+		n = hists->entries_in->rb_root.rb_node;
 
 	while (n) {
 		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in);
@@ -2252,10 +2394,10 @@
 	return NULL;
 }
 
-static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root,
+static struct hist_entry *hists__find_hierarchy_entry(struct rb_root_cached *root,
 						      struct hist_entry *he)
 {
-	struct rb_node *n = root->rb_node;
+	struct rb_node *n = root->rb_root.rb_node;
 
 	while (n) {
 		struct hist_entry *iter;
@@ -2280,13 +2422,13 @@
 	return NULL;
 }
 
-static void hists__match_hierarchy(struct rb_root *leader_root,
-				   struct rb_root *other_root)
+static void hists__match_hierarchy(struct rb_root_cached *leader_root,
+				   struct rb_root_cached *other_root)
 {
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(leader_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(leader_root); nd; nd = rb_next(nd)) {
 		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_hierarchy_entry(other_root, pos);
 
@@ -2302,7 +2444,7 @@
  */
 void hists__match(struct hists *leader, struct hists *other)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
@@ -2317,7 +2459,7 @@
 	else
 		root = leader->entries_in;
 
-	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
 		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_entry(other, pos);
 
@@ -2328,13 +2470,13 @@
 
 static int hists__link_hierarchy(struct hists *leader_hists,
 				 struct hist_entry *parent,
-				 struct rb_root *leader_root,
-				 struct rb_root *other_root)
+				 struct rb_root_cached *leader_root,
+				 struct rb_root_cached *other_root)
 {
 	struct rb_node *nd;
 	struct hist_entry *pos, *leader;
 
-	for (nd = rb_first(other_root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(other_root); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (hist_entry__has_pairs(pos)) {
@@ -2377,7 +2519,7 @@
  */
 int hists__link(struct hists *leader, struct hists *other)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
@@ -2393,7 +2535,7 @@
 	else
 		root = other->entries_in;
 
-	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (!hist_entry__has_pairs(pos)) {
@@ -2407,6 +2549,25 @@
 	return 0;
 }
 
+int hists__unlink(struct hists *hists)
+{
+	struct rb_root_cached *root;
+	struct rb_node *nd;
+	struct hist_entry *pos;
+
+	if (hists__has(hists, need_collapse))
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node_in);
+		list_del_init(&pos->pairs.node);
+	}
+
+	return 0;
+}
+
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  struct perf_sample *sample, bool nonany_branch_mode)
 {
@@ -2441,9 +2602,9 @@
 	}
 }
 
-size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
+size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 	size_t ret = 0;
 
 	evlist__for_each_entry(evlist, pos) {
@@ -2466,11 +2627,11 @@
 	char unit;
 	int printed;
 	const struct dso *dso = hists->dso_filter;
-	const struct thread *thread = hists->thread_filter;
+	struct thread *thread = hists->thread_filter;
 	int socket_id = hists->socket_filter;
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
-	struct perf_evsel *evsel = hists_to_evsel(hists);
+	struct evsel *evsel = hists_to_evsel(hists);
 	const char *ev_name = perf_evsel__name(evsel);
 	char buf[512], sample_freq_str[64] = "";
 	size_t buflen = sizeof(buf);
@@ -2483,7 +2644,7 @@
 	}
 
 	if (perf_evsel__is_group_event(evsel)) {
-		struct perf_evsel *pos;
+		struct evsel *pos;
 
 		perf_evsel__group_desc(evsel, buf, buflen);
 		ev_name = buf;
@@ -2506,12 +2667,12 @@
 		enable_ref = true;
 
 	if (show_freq)
-		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq);
+		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->core.attr.sample_freq);
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
 			   "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
-			   nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			   nr_samples, unit, evsel->core.nr_members > 1 ? "s" : "",
 			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
 
 
@@ -2566,10 +2727,10 @@
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
 	memset(hists, 0, sizeof(*hists));
-	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT_CACHED;
 	hists->entries_in = &hists->entries_in_array[0];
-	hists->entries_collapsed = RB_ROOT;
-	hists->entries = RB_ROOT;
+	hists->entries_collapsed = RB_ROOT_CACHED;
+	hists->entries = RB_ROOT_CACHED;
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
 	hists->hpp_list = hpp_list;
@@ -2577,14 +2738,14 @@
 	return 0;
 }
 
-static void hists__delete_remaining_entries(struct rb_root *root)
+static void hists__delete_remaining_entries(struct rb_root_cached *root)
 {
 	struct rb_node *node;
 	struct hist_entry *he;
 
-	while (!RB_EMPTY_ROOT(root)) {
-		node = rb_first(root);
-		rb_erase(node, root);
+	while (!RB_EMPTY_ROOT(&root->rb_root)) {
+		node = rb_first_cached(root);
+		rb_erase_cached(node, root);
 
 		he = rb_entry(node, struct hist_entry, rb_node_in);
 		hist_entry__delete(he);
@@ -2599,7 +2760,7 @@
 	hists__delete_remaining_entries(&hists->entries_collapsed);
 }
 
-static void hists_evsel__exit(struct perf_evsel *evsel)
+static void hists_evsel__exit(struct evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct perf_hpp_fmt *fmt, *pos;
@@ -2609,15 +2770,15 @@
 
 	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
 		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
-			list_del(&fmt->list);
+			list_del_init(&fmt->list);
 			free(fmt);
 		}
-		list_del(&node->list);
+		list_del_init(&node->list);
 		free(node);
 	}
 }
 
-static int hists_evsel__init(struct perf_evsel *evsel)
+static int hists_evsel__init(struct evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 3badd7f..6a186b6 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -2,18 +2,23 @@
 #ifndef __PERF_HIST_H
 #define __PERF_HIST_H
 
+#include <linux/rbtree.h>
 #include <linux/types.h>
 #include <pthread.h>
-#include "callchain.h"
 #include "evsel.h"
-#include "header.h"
 #include "color.h"
-#include "ui/progress.h"
+#include "events_stats.h"
 
 struct hist_entry;
 struct hist_entry_ops;
 struct addr_location;
+struct map_symbol;
+struct mem_info;
+struct branch_info;
+struct branch_stack;
+struct block_info;
 struct symbol;
+struct ui_progress;
 
 enum hist_filter {
 	HIST_FILTER__DSO,
@@ -28,6 +33,7 @@
 
 enum hist_column {
 	HISTC_SYMBOL,
+	HISTC_TIME,
 	HISTC_DSO,
 	HISTC_THREAD,
 	HISTC_COMM,
@@ -62,6 +68,7 @@
 	HISTC_TRACE,
 	HISTC_SYM_SIZE,
 	HISTC_DSO_SIZE,
+	HISTC_SYMBOL_IPC,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -69,10 +76,10 @@
 struct dso;
 
 struct hists {
-	struct rb_root		entries_in_array[2];
-	struct rb_root		*entries_in;
-	struct rb_root		entries;
-	struct rb_root		entries_collapsed;
+	struct rb_root_cached	entries_in_array[2];
+	struct rb_root_cached	*entries_in;
+	struct rb_root_cached	entries;
+	struct rb_root_cached	entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
 	u64			callchain_period;
@@ -110,7 +117,7 @@
 
 	bool hide_unresolved;
 
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct perf_sample *sample;
 	struct hist_entry *he;
 	struct symbol *parent;
@@ -144,6 +151,10 @@
 					struct perf_sample *sample,
 					bool sample_self);
 
+struct hist_entry *hists__add_entry_block(struct hists *hists,
+					  struct addr_location *al,
+					  struct block_info *bi);
+
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 
@@ -159,9 +170,11 @@
 				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
-typedef int (*hists__resort_cb_t)(struct hist_entry *he);
+typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg);
 
-void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
+void perf_evsel__output_resort_cb(struct evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg);
+void perf_evsel__output_resort(struct evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
 			     hists__resort_cb_t cb);
@@ -171,18 +184,18 @@
 void hists__delete_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
+struct hist_entry *hists__get_entry(struct hists *hists, int idx);
+
 u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
 void hists__inc_nr_samples(struct hists *hists, bool filtered);
-void events_stats__inc(struct events_stats *stats, u32 type);
-size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
 		      bool ignore_callchains);
-size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
+size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
@@ -203,19 +216,20 @@
 
 void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
+int hists__unlink(struct hists *hists);
 
 struct hists_evsel {
-	struct perf_evsel evsel;
+	struct evsel evsel;
 	struct hists	  hists;
 };
 
-static inline struct perf_evsel *hists_to_evsel(struct hists *hists)
+static inline struct evsel *hists_to_evsel(struct hists *hists)
 {
 	struct hists_evsel *hevsel = container_of(hists, struct hists_evsel, hists);
 	return &hevsel->evsel;
 }
 
-static inline struct hists *evsel__hists(struct perf_evsel *evsel)
+static inline struct hists *evsel__hists(struct evsel *evsel)
 {
 	struct hists_evsel *hevsel = (struct hists_evsel *)evsel;
 	return &hevsel->hists;
@@ -229,13 +243,14 @@
 int hists__init(void);
 int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
-struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
+struct rb_root_cached *hists__get_rotate_entries_in(struct hists *hists);
 
 struct perf_hpp {
 	char *buf;
 	size_t size;
 	const char *sep;
 	void *ptr;
+	bool skip;
 };
 
 struct perf_hpp_fmt {
@@ -352,7 +367,7 @@
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
 void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
 int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
-				  struct perf_evlist *evlist);
+				  struct evlist *evlist);
 
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
@@ -417,7 +432,7 @@
 	       : 0;
 }
 
-struct perf_evlist;
+struct evlist;
 
 struct hist_browser_timer {
 	void (*timer)(void *arg);
@@ -426,27 +441,42 @@
 };
 
 struct annotation_options;
+struct res_sample;
+
+enum rstype {
+	A_NORMAL,
+	A_ASM,
+	A_SOURCE
+};
 
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
-int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
+void attr_to_script(char *buf, struct perf_event_attr *attr);
+
+int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 			     struct hist_browser_timer *hbt,
 			     struct annotation_options *annotation_opts);
 
-int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
+int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
 			     struct hist_browser_timer *hbt,
 			     struct annotation_options *annotation_opts);
 
-int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
+int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  float min_pcnt,
 				  struct perf_env *env,
 				  bool warn_lost_event,
 				  struct annotation_options *annotation_options);
-int script_browse(const char *script_opt);
+
+int script_browse(const char *script_opt, struct evsel *evsel);
+
+void run_script(char *cmd);
+int res_sample_browse(struct res_sample *res_samples, int num_res,
+		      struct evsel *evsel, enum rstype rstype);
+void res_sample_init(void);
 #else
 static inline
-int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
 				  const char *help __maybe_unused,
 				  struct hist_browser_timer *hbt __maybe_unused,
 				  float min_pcnt __maybe_unused,
@@ -457,7 +487,7 @@
 	return 0;
 }
 static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
-					   struct perf_evsel *evsel __maybe_unused,
+					   struct evsel *evsel __maybe_unused,
 					   struct hist_browser_timer *hbt __maybe_unused,
 					   struct annotation_options *annotation_options __maybe_unused)
 {
@@ -465,18 +495,29 @@
 }
 
 static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
-					   struct perf_evsel *evsel __maybe_unused,
+					   struct evsel *evsel __maybe_unused,
 					   struct hist_browser_timer *hbt __maybe_unused,
 					   struct annotation_options *annotation_opts __maybe_unused)
 {
 	return 0;
 }
 
-static inline int script_browse(const char *script_opt __maybe_unused)
+static inline int script_browse(const char *script_opt __maybe_unused,
+				struct evsel *evsel __maybe_unused)
 {
 	return 0;
 }
 
+static inline int res_sample_browse(struct res_sample *res_samples __maybe_unused,
+				    int num_res __maybe_unused,
+				    struct evsel *evsel __maybe_unused,
+				    enum rstype rstype __maybe_unused)
+{
+	return 0;
+}
+
+static inline void res_sample_init(void) {}
+
 #define K_LEFT  -1000
 #define K_RIGHT -2000
 #define K_SWITCH_INPUT_DATA -3000
diff --git a/tools/perf/util/include/asm/uaccess.h b/tools/perf/util/include/asm/uaccess.h
index 6a6f4b9..5481003 100644
--- a/tools/perf/util/include/asm/uaccess.h
+++ b/tools/perf/util/include/asm/uaccess.h
@@ -10,6 +10,6 @@
 
 #define get_user	__get_user
 
-#define access_ok(type, addr, size)	1
+#define access_ok(addr, size)	1
 
 #endif
diff --git a/tools/perf/util/include/linux/ctype.h b/tools/perf/util/include/linux/ctype.h
deleted file mode 100644
index a53d4ee..0000000
--- a/tools/perf/util/include/linux/ctype.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../util.h"
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7127bc9..34cb380 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel-bts.c: Intel Processor Trace support
  * Copyright (c) 2013-2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <endian.h>
@@ -21,14 +12,15 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
-#include "cpumap.h"
 #include "color.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
+#include "symbol.h"
 #include "session.h"
-#include "util.h"
+#include "tool.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "debug.h"
@@ -36,6 +28,7 @@
 #include "auxtrace.h"
 #include "intel-pt-decoder/intel-pt-insn-decoder.h"
 #include "intel-bts.h"
+#include "util/synthetic-events.h"
 
 #define MAX_TIMESTAMP (~0ULL)
 
@@ -142,7 +135,7 @@
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
 			     INTEL_BTS_ERR_LOST, sample->cpu, sample->pid,
-			     sample->tid, 0, "Lost trace data");
+			     sample->tid, 0, "Lost trace data", sample->time);
 
 	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
 	if (err)
@@ -326,35 +319,19 @@
 {
 	struct machine *machine = btsq->bts->machine;
 	struct thread *thread;
-	struct addr_location al;
 	unsigned char buf[INTEL_PT_INSN_BUF_SZ];
 	ssize_t len;
-	int x86_64;
-	uint8_t cpumode;
+	bool x86_64;
 	int err = -1;
 
-	if (machine__kernel_ip(machine, ip))
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
-
 	thread = machine__find_thread(machine, -1, btsq->tid);
 	if (!thread)
 		return -1;
 
-	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
-		goto out_put;
-
-	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
-				  INTEL_PT_INSN_BUF_SZ);
+	len = thread__memcpy(thread, machine, buf, ip, INTEL_PT_INSN_BUF_SZ, &x86_64);
 	if (len <= 0)
 		goto out_put;
 
-	/* Load maps to ensure dso->is_64_bit has been updated */
-	map__load(al.map);
-
-	x86_64 = al.map->dso->is_64_bit;
-
 	if (intel_pt_get_insn(buf, len, x86_64, &btsq->intel_pt_insn))
 		goto out_put;
 
@@ -372,7 +349,7 @@
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
 			     INTEL_BTS_ERR_NOINSN, cpu, pid, tid, ip,
-			     "Failed to get instruction");
+			     "Failed to get instruction", 0);
 
 	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
 	if (err)
@@ -451,7 +428,7 @@
 			continue;
 		intel_bts_get_branch_type(btsq, branch);
 		if (btsq->bts->synth_opts.thread_stack)
-			thread_stack__event(thread, btsq->sample_flags,
+			thread_stack__event(thread, btsq->cpu, btsq->sample_flags,
 					    le64_to_cpu(branch->from),
 					    le64_to_cpu(branch->to),
 					    btsq->intel_pt_insn.length,
@@ -523,7 +500,7 @@
 	    !btsq->bts->synth_opts.thread_stack && thread &&
 	    (!old_buffer || btsq->bts->sampling_mode ||
 	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
-		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
+		thread_stack__set_trace_nr(thread, btsq->cpu, buffer->buffer_nr + 1);
 
 	err = intel_bts_process_buffer(btsq, buffer, thread);
 
@@ -783,15 +760,15 @@
 static int intel_bts_synth_events(struct intel_bts *bts,
 				  struct perf_session *session)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct perf_evsel *evsel;
+	struct evlist *evlist = session->evlist;
+	struct evsel *evsel;
 	struct perf_event_attr attr;
 	bool found = false;
 	u64 id;
 	int err;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type == bts->pmu_type && evsel->ids) {
+		if (evsel->core.attr.type == bts->pmu_type && evsel->core.ids) {
 			found = true;
 			break;
 		}
@@ -805,20 +782,20 @@
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD;
 	attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
 	attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
-	attr.exclude_user = evsel->attr.exclude_user;
-	attr.exclude_kernel = evsel->attr.exclude_kernel;
-	attr.exclude_hv = evsel->attr.exclude_hv;
-	attr.exclude_host = evsel->attr.exclude_host;
-	attr.exclude_guest = evsel->attr.exclude_guest;
-	attr.sample_id_all = evsel->attr.sample_id_all;
-	attr.read_format = evsel->attr.read_format;
+	attr.exclude_user = evsel->core.attr.exclude_user;
+	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
+	attr.exclude_hv = evsel->core.attr.exclude_hv;
+	attr.exclude_host = evsel->core.attr.exclude_host;
+	attr.exclude_guest = evsel->core.attr.exclude_guest;
+	attr.sample_id_all = evsel->core.attr.sample_id_all;
+	attr.read_format = evsel->core.attr.read_format;
 
-	id = evsel->id[0] + 1000000000;
+	id = evsel->core.id[0] + 1000000000;
 	if (!id)
 		id = 1;
 
@@ -841,7 +818,7 @@
 		 * We only use sample types from PERF_SAMPLE_MASK so we can use
 		 * __perf_evsel__sample_size() here.
 		 */
-		bts->branches_event_size = sizeof(struct sample_event) +
+		bts->branches_event_size = sizeof(struct perf_record_sample) +
 				__perf_evsel__sample_size(attr.sample_type);
 	}
 
@@ -857,7 +834,7 @@
 	[INTEL_BTS_SNAPSHOT_MODE]	= "  Snapshot mode      %"PRId64"\n",
 };
 
-static void intel_bts_print_info(u64 *arr, int start, int finish)
+static void intel_bts_print_info(__u64 *arr, int start, int finish)
 {
 	int i;
 
@@ -871,12 +848,12 @@
 int intel_bts_process_auxtrace_info(union perf_event *event,
 				    struct perf_session *session)
 {
-	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	size_t min_sz = sizeof(u64) * INTEL_BTS_SNAPSHOT_MODE;
 	struct intel_bts *bts;
 	int err;
 
-	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
 					min_sz)
 		return -EINVAL;
 
@@ -914,12 +891,12 @@
 	if (dump_trace)
 		return 0;
 
-	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+	if (session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&bts->synth_opts);
-		if (session->itrace_synth_opts)
-			bts->synth_opts.thread_stack =
+		itrace_synth_opts__set_default(&bts->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
+		bts->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
 	}
 
diff --git a/tools/perf/util/intel-bts.h b/tools/perf/util/intel-bts.h
index ca65e21..53d5aa0 100644
--- a/tools/perf/util/intel-bts.h
+++ b/tools/perf/util/intel-bts.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel-bts.h: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__PERF_INTEL_BTS_H__
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 1b704fb..bc62935 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,7 +1,7 @@
-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
+inat_tables_script = $(srctree)/tools/arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = $(srctree)/tools/arch/x86/lib/x86-opcode-map.txt
 
 $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
 	$(call rule_mkdir)
@@ -9,23 +9,7 @@
 
 # Busybox's diff doesn't have -I, avoid warning in the case
 
-$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
-	@(diff -I 2>&1 | grep -q 'option requires an argument' && \
-	test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
-	((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
-	((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
-	((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
-	(echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
deleted file mode 100644
index ddd5c4c..0000000
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ /dev/null
@@ -1,392 +0,0 @@
-#!/bin/awk -f
-# SPDX-License-Identifier: GPL-2.0
-# gen-insn-attr-x86.awk: Instruction attribute table generator
-# Written by Masami Hiramatsu <mhiramat@redhat.com>
-#
-# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
-
-# Awk implementation sanity check
-function check_awk_implement() {
-	if (sprintf("%x", 0) != "0")
-		return "Your awk has a printf-format problem."
-	return ""
-}
-
-# Clear working vars
-function clear_vars() {
-	delete table
-	delete lptable2
-	delete lptable1
-	delete lptable3
-	eid = -1 # escape id
-	gid = -1 # group id
-	aid = -1 # AVX id
-	tname = ""
-}
-
-BEGIN {
-	# Implementation error checking
-	awkchecked = check_awk_implement()
-	if (awkchecked != "") {
-		print "Error: " awkchecked > "/dev/stderr"
-		print "Please try to use gawk." > "/dev/stderr"
-		exit 1
-	}
-
-	# Setup generating tables
-	print "/* x86 opcode map generated from x86-opcode-map.txt */"
-	print "/* Do not change this code. */\n"
-	ggid = 1
-	geid = 1
-	gaid = 0
-	delete etable
-	delete gtable
-	delete atable
-
-	opnd_expr = "^[A-Za-z/]"
-	ext_expr = "^\\("
-	sep_expr = "^\\|$"
-	group_expr = "^Grp[0-9A-Za-z]+"
-
-	imm_expr = "^[IJAOL][a-z]"
-	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
-	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
-	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
-	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
-	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
-	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
-	imm_flag["Ob"] = "INAT_MOFFSET"
-	imm_flag["Ov"] = "INAT_MOFFSET"
-	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
-
-	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
-	force64_expr = "\\([df]64\\)"
-	rex_expr = "^REX(\\.[XRWB]+)*"
-	fpu_expr = "^ESC" # TODO
-
-	lprefix1_expr = "\\((66|!F3)\\)"
-	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
-	lprefix_expr = "\\((66|F2|F3)\\)"
-	max_lprefix = 4
-
-	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
-	# accepts VEX prefix
-	vexok_opcode_expr = "^[vk].*"
-	vexok_expr = "\\(v1\\)"
-	# All opcodes with (v) superscript supports *only* VEX prefix
-	vexonly_expr = "\\(v\\)"
-	# All opcodes with (ev) superscript supports *only* EVEX prefix
-	evexonly_expr = "\\(ev\\)"
-
-	prefix_expr = "\\(Prefix\\)"
-	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
-	prefix_num["REPNE"] = "INAT_PFX_REPNE"
-	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
-	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
-	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
-	prefix_num["LOCK"] = "INAT_PFX_LOCK"
-	prefix_num["SEG=CS"] = "INAT_PFX_CS"
-	prefix_num["SEG=DS"] = "INAT_PFX_DS"
-	prefix_num["SEG=ES"] = "INAT_PFX_ES"
-	prefix_num["SEG=FS"] = "INAT_PFX_FS"
-	prefix_num["SEG=GS"] = "INAT_PFX_GS"
-	prefix_num["SEG=SS"] = "INAT_PFX_SS"
-	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
-	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
-	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
-	prefix_num["EVEX"] = "INAT_PFX_EVEX"
-
-	clear_vars()
-}
-
-function semantic_error(msg) {
-	print "Semantic error at " NR ": " msg > "/dev/stderr"
-	exit 1
-}
-
-function debug(msg) {
-	print "DEBUG: " msg
-}
-
-function array_size(arr,   i,c) {
-	c = 0
-	for (i in arr)
-		c++
-	return c
-}
-
-/^Table:/ {
-	print "/* " $0 " */"
-	if (tname != "")
-		semantic_error("Hit Table: before EndTable:.");
-}
-
-/^Referrer:/ {
-	if (NF != 1) {
-		# escape opcode table
-		ref = ""
-		for (i = 2; i <= NF; i++)
-			ref = ref $i
-		eid = escape[ref]
-		tname = sprintf("inat_escape_table_%d", eid)
-	}
-}
-
-/^AVXcode:/ {
-	if (NF != 1) {
-		# AVX/escape opcode table
-		aid = $2
-		if (gaid <= aid)
-			gaid = aid + 1
-		if (tname == "")	# AVX only opcode table
-			tname = sprintf("inat_avx_table_%d", $2)
-	}
-	if (aid == -1 && eid == -1)	# primary opcode table
-		tname = "inat_primary_table"
-}
-
-/^GrpTable:/ {
-	print "/* " $0 " */"
-	if (!($2 in group))
-		semantic_error("No group: " $2 )
-	gid = group[$2]
-	tname = "inat_group_table_" gid
-}
-
-function print_table(tbl,name,fmt,n)
-{
-	print "const insn_attr_t " name " = {"
-	for (i = 0; i < n; i++) {
-		id = sprintf(fmt, i)
-		if (tbl[id])
-			print "	[" id "] = " tbl[id] ","
-	}
-	print "};"
-}
-
-/^EndTable/ {
-	if (gid != -1) {
-		# print group tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
-				    "0x%x", 8)
-			gtable[gid,3] = tname "_3"
-		}
-	} else {
-		# print primary/escaped tables
-		if (array_size(table) != 0) {
-			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,0] = tname
-			if (aid >= 0)
-				atable[aid,0] = tname
-		}
-		if (array_size(lptable1) != 0) {
-			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,1] = tname "_1"
-			if (aid >= 0)
-				atable[aid,1] = tname "_1"
-		}
-		if (array_size(lptable2) != 0) {
-			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,2] = tname "_2"
-			if (aid >= 0)
-				atable[aid,2] = tname "_2"
-		}
-		if (array_size(lptable3) != 0) {
-			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
-				    "0x%02x", 256)
-			etable[eid,3] = tname "_3"
-			if (aid >= 0)
-				atable[aid,3] = tname "_3"
-		}
-	}
-	print ""
-	clear_vars()
-}
-
-function add_flags(old,new) {
-	if (old && new)
-		return old " | " new
-	else if (old)
-		return old
-	else
-		return new
-}
-
-# convert operands to flags.
-function convert_operands(count,opnd,       i,j,imm,mod)
-{
-	imm = null
-	mod = null
-	for (j = 1; j <= count; j++) {
-		i = opnd[j]
-		if (match(i, imm_expr) == 1) {
-			if (!imm_flag[i])
-				semantic_error("Unknown imm opnd: " i)
-			if (imm) {
-				if (i != "Ib")
-					semantic_error("Second IMM error")
-				imm = add_flags(imm, "INAT_SCNDIMM")
-			} else
-				imm = imm_flag[i]
-		} else if (match(i, modrm_expr))
-			mod = "INAT_MODRM"
-	}
-	return add_flags(imm, mod)
-}
-
-/^[0-9a-f]+\:/ {
-	if (NR == 1)
-		next
-	# get index
-	idx = "0x" substr($1, 1, index($1,":") - 1)
-	if (idx in table)
-		semantic_error("Redefine " idx " in " tname)
-
-	# check if escaped opcode
-	if ("escape" == $2) {
-		if ($3 != "#")
-			semantic_error("No escaped name")
-		ref = ""
-		for (i = 4; i <= NF; i++)
-			ref = ref $i
-		if (ref in escape)
-			semantic_error("Redefine escape (" ref ")")
-		escape[ref] = geid
-		geid++
-		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
-		next
-	}
-
-	variant = null
-	# converts
-	i = 2
-	while (i <= NF) {
-		opcode = $(i++)
-		delete opnds
-		ext = null
-		flags = null
-		opnd = null
-		# parse one opcode
-		if (match($i, opnd_expr)) {
-			opnd = $i
-			count = split($(i++), opnds, ",")
-			flags = convert_operands(count, opnds)
-		}
-		if (match($i, ext_expr))
-			ext = $(i++)
-		if (match($i, sep_expr))
-			i++
-		else if (i < NF)
-			semantic_error($i " is not a separator")
-
-		# check if group opcode
-		if (match(opcode, group_expr)) {
-			if (!(opcode in group)) {
-				group[opcode] = ggid
-				ggid++
-			}
-			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
-		}
-		# check force(or default) 64bit
-		if (match(ext, force64_expr))
-			flags = add_flags(flags, "INAT_FORCE64")
-
-		# check REX prefix
-		if (match(opcode, rex_expr))
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
-
-		# check coprocessor escape : TODO
-		if (match(opcode, fpu_expr))
-			flags = add_flags(flags, "INAT_MODRM")
-
-		# check VEX codes
-		if (match(ext, evexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
-		else if (match(ext, vexonly_expr))
-			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
-		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
-			flags = add_flags(flags, "INAT_VEXOK")
-
-		# check prefixes
-		if (match(ext, prefix_expr)) {
-			if (!prefix_num[opcode])
-				semantic_error("Unknown prefix: " opcode)
-			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
-		}
-		if (length(flags) == 0)
-			continue
-		# check if last prefix
-		if (match(ext, lprefix1_expr)) {
-			lptable1[idx] = add_flags(lptable1[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix2_expr)) {
-			lptable2[idx] = add_flags(lptable2[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (match(ext, lprefix3_expr)) {
-			lptable3[idx] = add_flags(lptable3[idx],flags)
-			variant = "INAT_VARIANT"
-		}
-		if (!match(ext, lprefix_expr)){
-			table[idx] = add_flags(table[idx],flags)
-		}
-	}
-	if (variant)
-		table[idx] = add_flags(table[idx],variant)
-}
-
-END {
-	if (awkchecked != "")
-		exit 1
-	# print escape opcode map's array
-	print "/* Escape opcode map array */"
-	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < geid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (etable[i,j])
-				print "	["i"]["j"] = "etable[i,j]","
-	print "};\n"
-	# print group opcode map's array
-	print "/* Group opcode map array */"
-	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < ggid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (gtable[i,j])
-				print "	["i"]["j"] = "gtable[i,j]","
-	print "};\n"
-	# print AVX opcode map's array
-	print "/* AVX opcode map array */"
-	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
-	      "[INAT_LSTPFX_MAX + 1] = {"
-	for (i = 0; i < gaid; i++)
-		for (j = 0; j < max_lprefix; j++)
-			if (atable[i,j])
-				print "	["i"]["j"] = "atable[i,j]","
-	print "};"
-}
diff --git a/tools/perf/util/intel-pt-decoder/inat.c b/tools/perf/util/intel-pt-decoder/inat.c
deleted file mode 100644
index 906d94a..0000000
--- a/tools/perf/util/intel-pt-decoder/inat.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * x86 instruction attribute tables
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-#include "insn.h"
-
-/* Attribute tables are generated from opcode map */
-#include "inat-tables.c"
-
-/* Attribute search APIs */
-insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
-{
-	return inat_primary_table[opcode];
-}
-
-int inat_get_last_prefix_id(insn_byte_t last_pfx)
-{
-	insn_attr_t lpfx_attr;
-
-	lpfx_attr = inat_get_opcode_attribute(last_pfx);
-	return inat_last_prefix_id(lpfx_attr);
-}
-
-insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
-				      insn_attr_t esc_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_escape_id(esc_attr);
-
-	table = inat_escape_tables[n][0];
-	if (!table)
-		return 0;
-	if (inat_has_variant(table[opcode]) && lpfx_id) {
-		table = inat_escape_tables[n][lpfx_id];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
-
-insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
-				     insn_attr_t grp_attr)
-{
-	const insn_attr_t *table;
-	int n;
-
-	n = inat_group_id(grp_attr);
-
-	table = inat_group_tables[n][0];
-	if (!table)
-		return inat_group_common_attribute(grp_attr);
-	if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
-		table = inat_group_tables[n][lpfx_id];
-		if (!table)
-			return inat_group_common_attribute(grp_attr);
-	}
-	return table[X86_MODRM_REG(modrm)] |
-	       inat_group_common_attribute(grp_attr);
-}
-
-insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
-				   insn_byte_t vex_p)
-{
-	const insn_attr_t *table;
-	if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
-		return 0;
-	/* At first, this checks the master table */
-	table = inat_avx_tables[vex_m][0];
-	if (!table)
-		return 0;
-	if (!inat_is_group(table[opcode]) && vex_p) {
-		/* If this is not a group, get attribute directly */
-		table = inat_avx_tables[vex_m][vex_p];
-		if (!table)
-			return 0;
-	}
-	return table[opcode];
-}
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
deleted file mode 100644
index 52dc8d9..0000000
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ /dev/null
@@ -1,244 +0,0 @@
-#ifndef _ASM_X86_INAT_H
-#define _ASM_X86_INAT_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-#include "inat_types.h"
-
-/*
- * Internal bits. Don't use bitmasks directly, because these bits are
- * unstable. You should use checking functions.
- */
-
-#define INAT_OPCODE_TABLE_SIZE 256
-#define INAT_GROUP_TABLE_SIZE 8
-
-/* Legacy last prefixes */
-#define INAT_PFX_OPNDSZ	1	/* 0x66 */ /* LPFX1 */
-#define INAT_PFX_REPE	2	/* 0xF3 */ /* LPFX2 */
-#define INAT_PFX_REPNE	3	/* 0xF2 */ /* LPFX3 */
-/* Other Legacy prefixes */
-#define INAT_PFX_LOCK	4	/* 0xF0 */
-#define INAT_PFX_CS	5	/* 0x2E */
-#define INAT_PFX_DS	6	/* 0x3E */
-#define INAT_PFX_ES	7	/* 0x26 */
-#define INAT_PFX_FS	8	/* 0x64 */
-#define INAT_PFX_GS	9	/* 0x65 */
-#define INAT_PFX_SS	10	/* 0x36 */
-#define INAT_PFX_ADDRSZ	11	/* 0x67 */
-/* x86-64 REX prefix */
-#define INAT_PFX_REX	12	/* 0x4X */
-/* AVX VEX prefixes */
-#define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
-#define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
-#define INAT_PFX_EVEX	15	/* EVEX prefix */
-
-#define INAT_LSTPFX_MAX	3
-#define INAT_LGCPFX_MAX	11
-
-/* Immediate size */
-#define INAT_IMM_BYTE		1
-#define INAT_IMM_WORD		2
-#define INAT_IMM_DWORD		3
-#define INAT_IMM_QWORD		4
-#define INAT_IMM_PTR		5
-#define INAT_IMM_VWORD32	6
-#define INAT_IMM_VWORD		7
-
-/* Legacy prefix */
-#define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
-#define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
-#define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
-/* Escape opcodes */
-#define INAT_ESC_OFFS	(INAT_PFX_OFFS + INAT_PFX_BITS)
-#define INAT_ESC_BITS	2
-#define INAT_ESC_MAX	((1 << INAT_ESC_BITS) - 1)
-#define INAT_ESC_MASK	(INAT_ESC_MAX << INAT_ESC_OFFS)
-/* Group opcodes (1-16) */
-#define INAT_GRP_OFFS	(INAT_ESC_OFFS + INAT_ESC_BITS)
-#define INAT_GRP_BITS	5
-#define INAT_GRP_MAX	((1 << INAT_GRP_BITS) - 1)
-#define INAT_GRP_MASK	(INAT_GRP_MAX << INAT_GRP_OFFS)
-/* Immediates */
-#define INAT_IMM_OFFS	(INAT_GRP_OFFS + INAT_GRP_BITS)
-#define INAT_IMM_BITS	3
-#define INAT_IMM_MASK	(((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS)
-/* Flags */
-#define INAT_FLAG_OFFS	(INAT_IMM_OFFS + INAT_IMM_BITS)
-#define INAT_MODRM	(1 << (INAT_FLAG_OFFS))
-#define INAT_FORCE64	(1 << (INAT_FLAG_OFFS + 1))
-#define INAT_SCNDIMM	(1 << (INAT_FLAG_OFFS + 2))
-#define INAT_MOFFSET	(1 << (INAT_FLAG_OFFS + 3))
-#define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
-#define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
-#define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
-#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
-/* Attribute making macros for attribute tables */
-#define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
-#define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
-#define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
-#define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
-
-/* Identifiers for segment registers */
-#define INAT_SEG_REG_IGNORE	0
-#define INAT_SEG_REG_DEFAULT	1
-#define INAT_SEG_REG_CS		2
-#define INAT_SEG_REG_SS		3
-#define INAT_SEG_REG_DS		4
-#define INAT_SEG_REG_ES		5
-#define INAT_SEG_REG_FS		6
-#define INAT_SEG_REG_GS		7
-
-/* Attribute search APIs */
-extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
-extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
-extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     int lpfx_id,
-					     insn_attr_t esc_attr);
-extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    int lpfx_id,
-					    insn_attr_t esc_attr);
-extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
-					  insn_byte_t vex_m,
-					  insn_byte_t vex_pp);
-
-/* Attribute checking functions */
-static inline int inat_is_legacy_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr && attr <= INAT_LGCPFX_MAX;
-}
-
-static inline int inat_is_address_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ;
-}
-
-static inline int inat_is_operand_size_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ;
-}
-
-static inline int inat_is_rex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
-}
-
-static inline int inat_last_prefix_id(insn_attr_t attr)
-{
-	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
-		return 0;
-	else
-		return attr & INAT_PFX_MASK;
-}
-
-static inline int inat_is_vex_prefix(insn_attr_t attr)
-{
-	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
-	       attr == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_evex_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
-}
-
-static inline int inat_is_vex3_prefix(insn_attr_t attr)
-{
-	return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
-}
-
-static inline int inat_is_escape(insn_attr_t attr)
-{
-	return attr & INAT_ESC_MASK;
-}
-
-static inline int inat_escape_id(insn_attr_t attr)
-{
-	return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS;
-}
-
-static inline int inat_is_group(insn_attr_t attr)
-{
-	return attr & INAT_GRP_MASK;
-}
-
-static inline int inat_group_id(insn_attr_t attr)
-{
-	return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS;
-}
-
-static inline int inat_group_common_attribute(insn_attr_t attr)
-{
-	return attr & ~INAT_GRP_MASK;
-}
-
-static inline int inat_has_immediate(insn_attr_t attr)
-{
-	return attr & INAT_IMM_MASK;
-}
-
-static inline int inat_immediate_size(insn_attr_t attr)
-{
-	return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS;
-}
-
-static inline int inat_has_modrm(insn_attr_t attr)
-{
-	return attr & INAT_MODRM;
-}
-
-static inline int inat_is_force64(insn_attr_t attr)
-{
-	return attr & INAT_FORCE64;
-}
-
-static inline int inat_has_second_immediate(insn_attr_t attr)
-{
-	return attr & INAT_SCNDIMM;
-}
-
-static inline int inat_has_moffset(insn_attr_t attr)
-{
-	return attr & INAT_MOFFSET;
-}
-
-static inline int inat_has_variant(insn_attr_t attr)
-{
-	return attr & INAT_VARIANT;
-}
-
-static inline int inat_accept_vex(insn_attr_t attr)
-{
-	return attr & INAT_VEXOK;
-}
-
-static inline int inat_must_vex(insn_attr_t attr)
-{
-	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
-}
-
-static inline int inat_must_evex(insn_attr_t attr)
-{
-	return attr & INAT_EVEXONLY;
-}
-#endif
diff --git a/tools/perf/util/intel-pt-decoder/inat_types.h b/tools/perf/util/intel-pt-decoder/inat_types.h
deleted file mode 100644
index cb3c20c..0000000
--- a/tools/perf/util/intel-pt-decoder/inat_types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _ASM_X86_INAT_TYPES_H
-#define _ASM_X86_INAT_TYPES_H
-/*
- * x86 instruction attributes
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- */
-
-/* Instruction attributes */
-typedef unsigned int insn_attr_t;
-typedef unsigned char insn_byte_t;
-typedef signed int insn_value_t;
-
-#endif
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
deleted file mode 100644
index ca983e2..0000000
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ /dev/null
@@ -1,606 +0,0 @@
-/*
- * x86 instruction analysis
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2002, 2004, 2009
- */
-
-#ifdef __KERNEL__
-#include <linux/string.h>
-#else
-#include <string.h>
-#endif
-#include "inat.h"
-#include "insn.h"
-
-/* Verify next sizeof(t) bytes can be on the same instruction */
-#define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
-
-#define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
-
-#define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); r; })
-
-#define get_next(t, insn)	\
-	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
-
-#define peek_nbyte_next(t, insn, n)	\
-	({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
-
-#define peek_next(t, insn)	peek_nbyte_next(t, insn, 0)
-
-/**
- * insn_init() - initialize struct insn
- * @insn:	&struct insn to be initialized
- * @kaddr:	address (in kernel memory) of instruction (or copy thereof)
- * @x86_64:	!0 for 64-bit kernel or 64-bit app
- */
-void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
-{
-	/*
-	 * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
-	 * even if the input buffer is long enough to hold them.
-	 */
-	if (buf_len > MAX_INSN_SIZE)
-		buf_len = MAX_INSN_SIZE;
-
-	memset(insn, 0, sizeof(*insn));
-	insn->kaddr = kaddr;
-	insn->end_kaddr = kaddr + buf_len;
-	insn->next_byte = kaddr;
-	insn->x86_64 = x86_64 ? 1 : 0;
-	insn->opnd_bytes = 4;
-	if (x86_64)
-		insn->addr_bytes = 8;
-	else
-		insn->addr_bytes = 4;
-}
-
-/**
- * insn_get_prefixes - scan x86 instruction prefix bytes
- * @insn:	&struct insn containing instruction
- *
- * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
- * to point to the (first) opcode.  No effect if @insn->prefixes.got
- * is already set.
- */
-void insn_get_prefixes(struct insn *insn)
-{
-	struct insn_field *prefixes = &insn->prefixes;
-	insn_attr_t attr;
-	insn_byte_t b, lb;
-	int i, nb;
-
-	if (prefixes->got)
-		return;
-
-	nb = 0;
-	lb = 0;
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	while (inat_is_legacy_prefix(attr)) {
-		/* Skip if same prefix */
-		for (i = 0; i < nb; i++)
-			if (prefixes->bytes[i] == b)
-				goto found;
-		if (nb == 4)
-			/* Invalid instruction */
-			break;
-		prefixes->bytes[nb++] = b;
-		if (inat_is_address_size_prefix(attr)) {
-			/* address size switches 2/4 or 4/8 */
-			if (insn->x86_64)
-				insn->addr_bytes ^= 12;
-			else
-				insn->addr_bytes ^= 6;
-		} else if (inat_is_operand_size_prefix(attr)) {
-			/* oprand size switches 2/4 */
-			insn->opnd_bytes ^= 6;
-		}
-found:
-		prefixes->nbytes++;
-		insn->next_byte++;
-		lb = b;
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-	}
-	/* Set the last prefix */
-	if (lb && lb != insn->prefixes.bytes[3]) {
-		if (unlikely(insn->prefixes.bytes[3])) {
-			/* Swap the last prefix */
-			b = insn->prefixes.bytes[3];
-			for (i = 0; i < nb; i++)
-				if (prefixes->bytes[i] == lb)
-					prefixes->bytes[i] = b;
-		}
-		insn->prefixes.bytes[3] = lb;
-	}
-
-	/* Decode REX prefix */
-	if (insn->x86_64) {
-		b = peek_next(insn_byte_t, insn);
-		attr = inat_get_opcode_attribute(b);
-		if (inat_is_rex_prefix(attr)) {
-			insn->rex_prefix.value = b;
-			insn->rex_prefix.nbytes = 1;
-			insn->next_byte++;
-			if (X86_REX_W(b))
-				/* REX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		}
-	}
-	insn->rex_prefix.got = 1;
-
-	/* Decode VEX prefix */
-	b = peek_next(insn_byte_t, insn);
-	attr = inat_get_opcode_attribute(b);
-	if (inat_is_vex_prefix(attr)) {
-		insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
-		if (!insn->x86_64) {
-			/*
-			 * In 32-bits mode, if the [7:6] bits (mod bits of
-			 * ModRM) on the second byte are not 11b, it is
-			 * LDS or LES or BOUND.
-			 */
-			if (X86_MODRM_MOD(b2) != 3)
-				goto vex_end;
-		}
-		insn->vex_prefix.bytes[0] = b;
-		insn->vex_prefix.bytes[1] = b2;
-		if (inat_is_evex_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			b2 = peek_nbyte_next(insn_byte_t, insn, 3);
-			insn->vex_prefix.bytes[3] = b2;
-			insn->vex_prefix.nbytes = 4;
-			insn->next_byte += 4;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else if (inat_is_vex3_prefix(attr)) {
-			b2 = peek_nbyte_next(insn_byte_t, insn, 2);
-			insn->vex_prefix.bytes[2] = b2;
-			insn->vex_prefix.nbytes = 3;
-			insn->next_byte += 3;
-			if (insn->x86_64 && X86_VEX_W(b2))
-				/* VEX.W overrides opnd_size */
-				insn->opnd_bytes = 8;
-		} else {
-			/*
-			 * For VEX2, fake VEX3-like byte#2.
-			 * Makes it easier to decode vex.W, vex.vvvv,
-			 * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
-			 */
-			insn->vex_prefix.bytes[2] = b2 & 0x7f;
-			insn->vex_prefix.nbytes = 2;
-			insn->next_byte += 2;
-		}
-	}
-vex_end:
-	insn->vex_prefix.got = 1;
-
-	prefixes->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_opcode - collect opcode(s)
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->opcode, updates @insn->next_byte to point past the
- * opcode byte(s), and set @insn->attr (except for groups).
- * If necessary, first collects any preceding (prefix) bytes.
- * Sets @insn->opcode.value = opcode1.  No effect if @insn->opcode.got
- * is already 1.
- */
-void insn_get_opcode(struct insn *insn)
-{
-	struct insn_field *opcode = &insn->opcode;
-	insn_byte_t op;
-	int pfx_id;
-	if (opcode->got)
-		return;
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-
-	/* Get first opcode */
-	op = get_next(insn_byte_t, insn);
-	opcode->bytes[0] = op;
-	opcode->nbytes = 1;
-
-	/* Check if there is VEX prefix or not */
-	if (insn_is_avx(insn)) {
-		insn_byte_t m, p;
-		m = insn_vex_m_bits(insn);
-		p = insn_vex_p_bits(insn);
-		insn->attr = inat_get_avx_attribute(op, m, p);
-		if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
-		    (!inat_accept_vex(insn->attr) &&
-		     !inat_is_group(insn->attr)))
-			insn->attr = 0;	/* This instruction is bad */
-		goto end;	/* VEX has only 1 byte for opcode */
-	}
-
-	insn->attr = inat_get_opcode_attribute(op);
-	while (inat_is_escape(insn->attr)) {
-		/* Get escaped opcode */
-		op = get_next(insn_byte_t, insn);
-		opcode->bytes[opcode->nbytes++] = op;
-		pfx_id = insn_last_prefix_id(insn);
-		insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
-	}
-	if (inat_must_vex(insn->attr))
-		insn->attr = 0;	/* This instruction is bad */
-end:
-	opcode->got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_modrm - collect ModRM byte, if any
- * @insn:	&struct insn containing instruction
- *
- * Populates @insn->modrm and updates @insn->next_byte to point past the
- * ModRM byte, if any.  If necessary, first collects the preceding bytes
- * (prefixes and opcode(s)).  No effect if @insn->modrm.got is already 1.
- */
-void insn_get_modrm(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-	insn_byte_t pfx_id, mod;
-	if (modrm->got)
-		return;
-	if (!insn->opcode.got)
-		insn_get_opcode(insn);
-
-	if (inat_has_modrm(insn->attr)) {
-		mod = get_next(insn_byte_t, insn);
-		modrm->value = mod;
-		modrm->nbytes = 1;
-		if (inat_is_group(insn->attr)) {
-			pfx_id = insn_last_prefix_id(insn);
-			insn->attr = inat_get_group_attribute(mod, pfx_id,
-							      insn->attr);
-			if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
-				insn->attr = 0;	/* This is bad */
-		}
-	}
-
-	if (insn->x86_64 && inat_is_force64(insn->attr))
-		insn->opnd_bytes = 8;
-	modrm->got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.  No effect if @insn->x86_64 is 0.
- */
-int insn_rip_relative(struct insn *insn)
-{
-	struct insn_field *modrm = &insn->modrm;
-
-	if (!insn->x86_64)
-		return 0;
-	if (!modrm->got)
-		insn_get_modrm(insn);
-	/*
-	 * For rip-relative instructions, the mod field (top 2 bits)
-	 * is zero and the r/m field (bottom 3 bits) is 0x5.
-	 */
-	return (modrm->nbytes && (modrm->value & 0xc7) == 0x5);
-}
-
-/**
- * insn_get_sib() - Get the SIB byte of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * ModRM byte.
- */
-void insn_get_sib(struct insn *insn)
-{
-	insn_byte_t modrm;
-
-	if (insn->sib.got)
-		return;
-	if (!insn->modrm.got)
-		insn_get_modrm(insn);
-	if (insn->modrm.nbytes) {
-		modrm = (insn_byte_t)insn->modrm.value;
-		if (insn->addr_bytes != 2 &&
-		    X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
-			insn->sib.value = get_next(insn_byte_t, insn);
-			insn->sib.nbytes = 1;
-		}
-	}
-	insn->sib.got = 1;
-
-err_out:
-	return;
-}
-
-
-/**
- * insn_get_displacement() - Get the displacement of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * SIB byte.
- * Displacement value is sign-expanded.
- */
-void insn_get_displacement(struct insn *insn)
-{
-	insn_byte_t mod, rm, base;
-
-	if (insn->displacement.got)
-		return;
-	if (!insn->sib.got)
-		insn_get_sib(insn);
-	if (insn->modrm.nbytes) {
-		/*
-		 * Interpreting the modrm byte:
-		 * mod = 00 - no displacement fields (exceptions below)
-		 * mod = 01 - 1-byte displacement field
-		 * mod = 10 - displacement field is 4 bytes, or 2 bytes if
-		 * 	address size = 2 (0x67 prefix in 32-bit mode)
-		 * mod = 11 - no memory operand
-		 *
-		 * If address size = 2...
-		 * mod = 00, r/m = 110 - displacement field is 2 bytes
-		 *
-		 * If address size != 2...
-		 * mod != 11, r/m = 100 - SIB byte exists
-		 * mod = 00, SIB base = 101 - displacement field is 4 bytes
-		 * mod = 00, r/m = 101 - rip-relative addressing, displacement
-		 * 	field is 4 bytes
-		 */
-		mod = X86_MODRM_MOD(insn->modrm.value);
-		rm = X86_MODRM_RM(insn->modrm.value);
-		base = X86_SIB_BASE(insn->sib.value);
-		if (mod == 3)
-			goto out;
-		if (mod == 1) {
-			insn->displacement.value = get_next(signed char, insn);
-			insn->displacement.nbytes = 1;
-		} else if (insn->addr_bytes == 2) {
-			if ((mod == 0 && rm == 6) || mod == 2) {
-				insn->displacement.value =
-					 get_next(short, insn);
-				insn->displacement.nbytes = 2;
-			}
-		} else {
-			if ((mod == 0 && rm == 5) || mod == 2 ||
-			    (mod == 0 && base == 5)) {
-				insn->displacement.value = get_next(int, insn);
-				insn->displacement.nbytes = 4;
-			}
-		}
-	}
-out:
-	insn->displacement.got = 1;
-
-err_out:
-	return;
-}
-
-/* Decode moffset16/32/64. Return 0 if failed */
-static int __get_moffset(struct insn *insn)
-{
-	switch (insn->addr_bytes) {
-	case 2:
-		insn->moffset1.value = get_next(short, insn);
-		insn->moffset1.nbytes = 2;
-		break;
-	case 4:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		break;
-	case 8:
-		insn->moffset1.value = get_next(int, insn);
-		insn->moffset1.nbytes = 4;
-		insn->moffset2.value = get_next(int, insn);
-		insn->moffset2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->moffset1.got = insn->moffset2.got = 1;
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v32(Iz). Return 0 if failed */
-static int __get_immv32(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case 4:
-	case 8:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-
-	return 1;
-
-err_out:
-	return 0;
-}
-
-/* Decode imm v64(Iv/Ov), Return 0 if failed */
-static int __get_immv(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/* Decode ptr16:16/32(Ap) */
-static int __get_immptr(struct insn *insn)
-{
-	switch (insn->opnd_bytes) {
-	case 2:
-		insn->immediate1.value = get_next(short, insn);
-		insn->immediate1.nbytes = 2;
-		break;
-	case 4:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		break;
-	case 8:
-		/* ptr16:64 is not exist (no segment) */
-		return 0;
-	default:	/* opnd_bytes must be modified manually */
-		goto err_out;
-	}
-	insn->immediate2.value = get_next(unsigned short, insn);
-	insn->immediate2.nbytes = 2;
-	insn->immediate1.got = insn->immediate2.got = 1;
-
-	return 1;
-err_out:
-	return 0;
-}
-
-/**
- * insn_get_immediate() - Get the immediates of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * displacement bytes.
- * Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
- */
-void insn_get_immediate(struct insn *insn)
-{
-	if (insn->immediate.got)
-		return;
-	if (!insn->displacement.got)
-		insn_get_displacement(insn);
-
-	if (inat_has_moffset(insn->attr)) {
-		if (!__get_moffset(insn))
-			goto err_out;
-		goto done;
-	}
-
-	if (!inat_has_immediate(insn->attr))
-		/* no immediates */
-		goto done;
-
-	switch (inat_immediate_size(insn->attr)) {
-	case INAT_IMM_BYTE:
-		insn->immediate.value = get_next(signed char, insn);
-		insn->immediate.nbytes = 1;
-		break;
-	case INAT_IMM_WORD:
-		insn->immediate.value = get_next(short, insn);
-		insn->immediate.nbytes = 2;
-		break;
-	case INAT_IMM_DWORD:
-		insn->immediate.value = get_next(int, insn);
-		insn->immediate.nbytes = 4;
-		break;
-	case INAT_IMM_QWORD:
-		insn->immediate1.value = get_next(int, insn);
-		insn->immediate1.nbytes = 4;
-		insn->immediate2.value = get_next(int, insn);
-		insn->immediate2.nbytes = 4;
-		break;
-	case INAT_IMM_PTR:
-		if (!__get_immptr(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD32:
-		if (!__get_immv32(insn))
-			goto err_out;
-		break;
-	case INAT_IMM_VWORD:
-		if (!__get_immv(insn))
-			goto err_out;
-		break;
-	default:
-		/* Here, insn must have an immediate, but failed */
-		goto err_out;
-	}
-	if (inat_has_second_immediate(insn->attr)) {
-		insn->immediate2.value = get_next(signed char, insn);
-		insn->immediate2.nbytes = 1;
-	}
-done:
-	insn->immediate.got = 1;
-
-err_out:
-	return;
-}
-
-/**
- * insn_get_length() - Get the length of instruction
- * @insn:	&struct insn containing instruction
- *
- * If necessary, first collects the instruction up to and including the
- * immediates bytes.
- */
-void insn_get_length(struct insn *insn)
-{
-	if (insn->length)
-		return;
-	if (!insn->immediate.got)
-		insn_get_immediate(insn);
-	insn->length = (unsigned char)((unsigned long)insn->next_byte
-				     - (unsigned long)insn->kaddr);
-}
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
deleted file mode 100644
index 2669c9f..0000000
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ /dev/null
@@ -1,229 +0,0 @@
-#ifndef _ASM_X86_INSN_H
-#define _ASM_X86_INSN_H
-/*
- * x86 instruction analysis
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2009
- */
-
-/* insn_attr_t is defined in inat.h */
-#include "inat.h"
-
-struct insn_field {
-	union {
-		insn_value_t value;
-		insn_byte_t bytes[4];
-	};
-	/* !0 if we've run insn_get_xxx() for this field */
-	unsigned char got;
-	unsigned char nbytes;
-};
-
-struct insn {
-	struct insn_field prefixes;	/*
-					 * Prefixes
-					 * prefixes.bytes[3]: last prefix
-					 */
-	struct insn_field rex_prefix;	/* REX prefix */
-	struct insn_field vex_prefix;	/* VEX prefix */
-	struct insn_field opcode;	/*
-					 * opcode.bytes[0]: opcode1
-					 * opcode.bytes[1]: opcode2
-					 * opcode.bytes[2]: opcode3
-					 */
-	struct insn_field modrm;
-	struct insn_field sib;
-	struct insn_field displacement;
-	union {
-		struct insn_field immediate;
-		struct insn_field moffset1;	/* for 64bit MOV */
-		struct insn_field immediate1;	/* for 64bit imm or off16/32 */
-	};
-	union {
-		struct insn_field moffset2;	/* for 64bit MOV */
-		struct insn_field immediate2;	/* for 64bit imm or seg16 */
-	};
-
-	insn_attr_t attr;
-	unsigned char opnd_bytes;
-	unsigned char addr_bytes;
-	unsigned char length;
-	unsigned char x86_64;
-
-	const insn_byte_t *kaddr;	/* kernel address of insn to analyze */
-	const insn_byte_t *end_kaddr;	/* kernel address of last insn in buffer */
-	const insn_byte_t *next_byte;
-};
-
-#define MAX_INSN_SIZE	15
-
-#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6)
-#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3)
-#define X86_MODRM_RM(modrm) ((modrm) & 0x07)
-
-#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6)
-#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
-#define X86_SIB_BASE(sib) ((sib) & 0x07)
-
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
-
-/* VEX bit flags  */
-#define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
-#define X86_VEX_R(vex)	((vex) & 0x80)	/* VEX2/3 Byte1 */
-#define X86_VEX_X(vex)	((vex) & 0x40)	/* VEX3 Byte1 */
-#define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
-#define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
-/* VEX bit fields */
-#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
-#define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
-#define X86_VEX2_M	1			/* VEX2.M always 1 */
-#define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
-#define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
-
-extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
-
-/* Attribute will be determined after getting ModRM (for opcode groups) */
-static inline void insn_get_attribute(struct insn *insn)
-{
-	insn_get_modrm(insn);
-}
-
-/* Instruction uses RIP-relative addressing */
-extern int insn_rip_relative(struct insn *insn);
-
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
-				    const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
-static inline int insn_is_avx(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.value != 0);
-}
-
-static inline int insn_is_evex(struct insn *insn)
-{
-	if (!insn->prefixes.got)
-		insn_get_prefixes(insn);
-	return (insn->vex_prefix.nbytes == 4);
-}
-
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
-	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
-		insn->displacement.got && insn->immediate.got;
-}
-
-static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX2_M;
-	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
-		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
-	else					/* EVEX */
-		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
-}
-
-static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
-{
-	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
-		return X86_VEX_P(insn->vex_prefix.bytes[1]);
-	else
-		return X86_VEX_P(insn->vex_prefix.bytes[2]);
-}
-
-/* Get the last prefix id from last prefix or VEX prefix */
-static inline int insn_last_prefix_id(struct insn *insn)
-{
-	if (insn_is_avx(insn))
-		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
-
-	if (insn->prefixes.bytes[3])
-		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
-
-	return 0;
-}
-
-/* Offset of each field from kaddr */
-static inline int insn_offset_rex_prefix(struct insn *insn)
-{
-	return insn->prefixes.nbytes;
-}
-static inline int insn_offset_vex_prefix(struct insn *insn)
-{
-	return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes;
-}
-static inline int insn_offset_opcode(struct insn *insn)
-{
-	return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes;
-}
-static inline int insn_offset_modrm(struct insn *insn)
-{
-	return insn_offset_opcode(insn) + insn->opcode.nbytes;
-}
-static inline int insn_offset_sib(struct insn *insn)
-{
-	return insn_offset_modrm(insn) + insn->modrm.nbytes;
-}
-static inline int insn_offset_displacement(struct insn *insn)
-{
-	return insn_offset_sib(insn) + insn->sib.nbytes;
-}
-static inline int insn_offset_immediate(struct insn *insn)
-{
-	return insn_offset_displacement(insn) + insn->displacement.nbytes;
-}
-
-#define POP_SS_OPCODE 0x1f
-#define MOV_SREG_OPCODE 0x8e
-
-/*
- * Intel SDM Vol.3A 6.8.3 states;
- * "Any single-step trap that would be delivered following the MOV to SS
- * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
- * suppressed."
- * This function returns true if @insn is MOV SS or POP SS. On these
- * instructions, single stepping is suppressed.
- */
-static inline int insn_masking_exception(struct insn *insn)
-{
-	return insn->opcode.bytes[0] == POP_SS_OPCODE ||
-		(insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
-		 X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
-}
-
-#endif /* _ASM_X86_INSN_H */
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 d404bed..f8ccfd6 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel_pt_decoder.c: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef _GNU_SOURCE
@@ -23,9 +14,10 @@
 #include <stdint.h>
 #include <inttypes.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 
-#include "../cache.h"
-#include "../util.h"
+#include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
 #include "intel-pt-pkt-decoder.h"
@@ -57,6 +49,7 @@
 	INTEL_PT_STATE_NO_IP,
 	INTEL_PT_STATE_ERR_RESYNC,
 	INTEL_PT_STATE_IN_SYNC,
+	INTEL_PT_STATE_TNT_CONT,
 	INTEL_PT_STATE_TNT,
 	INTEL_PT_STATE_TIP,
 	INTEL_PT_STATE_TIP_PGD,
@@ -71,8 +64,9 @@
 	case INTEL_PT_STATE_NO_IP:
 	case INTEL_PT_STATE_ERR_RESYNC:
 	case INTEL_PT_STATE_IN_SYNC:
-	case INTEL_PT_STATE_TNT:
+	case INTEL_PT_STATE_TNT_CONT:
 		return true;
+	case INTEL_PT_STATE_TNT:
 	case INTEL_PT_STATE_TIP:
 	case INTEL_PT_STATE_TIP_PGD:
 	case INTEL_PT_STATE_FUP:
@@ -101,6 +95,7 @@
 			 uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
 			 uint64_t max_insn_cnt, void *data);
 	bool (*pgd_ip)(uint64_t ip, void *data);
+	int (*lookahead)(void *data, intel_pt_lookahead_cb_t cb, void *cb_data);
 	void *data;
 	struct intel_pt_state state;
 	const unsigned char *buf;
@@ -113,6 +108,7 @@
 	bool have_cyc;
 	bool fixup_last_mtc;
 	bool have_last_ip;
+	bool in_psb;
 	enum intel_pt_param_flags flags;
 	uint64_t pos;
 	uint64_t last_ip;
@@ -121,6 +117,7 @@
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t buf_timestamp;
 	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
@@ -136,6 +133,10 @@
 	int mtc_shift;
 	struct intel_pt_stack stack;
 	enum intel_pt_pkt_state pkt_state;
+	enum intel_pt_pkt_ctx pkt_ctx;
+	enum intel_pt_pkt_ctx prev_pkt_ctx;
+	enum intel_pt_blk_type blk_type;
+	int blk_type_pos;
 	struct intel_pt_pkt packet;
 	struct intel_pt_pkt tnt;
 	int pkt_step;
@@ -157,6 +158,11 @@
 	uint64_t period_mask;
 	uint64_t period_ticks;
 	uint64_t last_masked_timestamp;
+	uint64_t tot_cyc_cnt;
+	uint64_t sample_tot_cyc_cnt;
+	uint64_t base_cyc_cnt;
+	uint64_t cyc_cnt_timestamp;
+	double tsc_to_cyc;
 	bool continuous_period;
 	bool overflow;
 	bool set_fup_tx_flags;
@@ -164,6 +170,8 @@
 	bool set_fup_mwait;
 	bool set_fup_pwre;
 	bool set_fup_exstop;
+	bool set_fup_bep;
+	bool sample_cyc;
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
 	uint64_t fup_ptw_payload;
@@ -223,6 +231,7 @@
 	decoder->get_trace          = params->get_trace;
 	decoder->walk_insn          = params->walk_insn;
 	decoder->pgd_ip             = params->pgd_ip;
+	decoder->lookahead          = params->lookahead;
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
 	decoder->branch_enable      = params->branch_enable;
@@ -250,19 +259,15 @@
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
@@ -480,7 +485,21 @@
 	return -EBADMSG;
 }
 
-static int intel_pt_get_data(struct intel_pt_decoder *decoder)
+static inline void intel_pt_update_sample_time(struct intel_pt_decoder *decoder)
+{
+	decoder->sample_timestamp = decoder->timestamp;
+	decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+}
+
+static void intel_pt_reposition(struct intel_pt_decoder *decoder)
+{
+	decoder->ip = 0;
+	decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+	decoder->timestamp = 0;
+	decoder->have_tma = false;
+}
+
+static int intel_pt_get_data(struct intel_pt_decoder *decoder, bool reposition)
 {
 	struct intel_pt_buffer buffer = { .buf = 0, };
 	int ret;
@@ -497,12 +516,10 @@
 		intel_pt_log("No more data\n");
 		return -ENODATA;
 	}
-	if (!buffer.consecutive) {
-		decoder->ip = 0;
-		decoder->pkt_state = INTEL_PT_STATE_NO_PSB;
+	decoder->buf_timestamp = buffer.ref_timestamp;
+	if (!buffer.consecutive || reposition) {
+		intel_pt_reposition(decoder);
 		decoder->ref_timestamp = buffer.ref_timestamp;
-		decoder->timestamp = 0;
-		decoder->have_tma = false;
 		decoder->state.trace_nr = buffer.trace_nr;
 		intel_pt_log("Reference timestamp 0x%" PRIx64 "\n",
 			     decoder->ref_timestamp);
@@ -512,10 +529,11 @@
 	return 0;
 }
 
-static int intel_pt_get_next_data(struct intel_pt_decoder *decoder)
+static int intel_pt_get_next_data(struct intel_pt_decoder *decoder,
+				  bool reposition)
 {
 	if (!decoder->next_buf)
-		return intel_pt_get_data(decoder);
+		return intel_pt_get_data(decoder, reposition);
 
 	decoder->buf = decoder->next_buf;
 	decoder->len = decoder->next_len;
@@ -534,7 +552,7 @@
 	len = decoder->len;
 	memcpy(buf, decoder->buf, len);
 
-	ret = intel_pt_get_data(decoder);
+	ret = intel_pt_get_data(decoder, false);
 	if (ret) {
 		decoder->pos += old_len;
 		return ret < 0 ? ret : -EINVAL;
@@ -546,7 +564,8 @@
 	memcpy(buf + len, decoder->buf, n);
 	len += n;
 
-	ret = intel_pt_get_packet(buf, len, &decoder->packet);
+	decoder->prev_pkt_ctx = decoder->pkt_ctx;
+	ret = intel_pt_get_packet(buf, len, &decoder->packet, &decoder->pkt_ctx);
 	if (ret < (int)old_len) {
 		decoder->next_buf = decoder->buf;
 		decoder->next_len = decoder->len;
@@ -581,6 +600,7 @@
 {
 	struct intel_pt_pkt_info pkt_info;
 	const unsigned char *buf = decoder->buf;
+	enum intel_pt_pkt_ctx pkt_ctx = decoder->pkt_ctx;
 	size_t len = decoder->len;
 	int ret;
 
@@ -599,7 +619,8 @@
 			if (!len)
 				return INTEL_PT_NEED_MORE_BYTES;
 
-			ret = intel_pt_get_packet(buf, len, &pkt_info.packet);
+			ret = intel_pt_get_packet(buf, len, &pkt_info.packet,
+						  &pkt_ctx);
 			if (!ret)
 				return INTEL_PT_NEED_MORE_BYTES;
 			if (ret < 0)
@@ -674,6 +695,10 @@
 	case INTEL_PT_MNT:
 	case INTEL_PT_PTWRITE:
 	case INTEL_PT_PTWRITE_IP:
+	case INTEL_PT_BBP:
+	case INTEL_PT_BIP:
+	case INTEL_PT_BEP:
+	case INTEL_PT_BEP_IP:
 		return 0;
 
 	case INTEL_PT_MTC:
@@ -860,14 +885,15 @@
 		decoder->len -= decoder->pkt_step;
 
 		if (!decoder->len) {
-			ret = intel_pt_get_next_data(decoder);
+			ret = intel_pt_get_next_data(decoder, false);
 			if (ret)
 				return ret;
 		}
 
+		decoder->prev_pkt_ctx = decoder->pkt_ctx;
 		ret = intel_pt_get_packet(decoder->buf, decoder->len,
-					  &decoder->packet);
-		if (ret == INTEL_PT_NEED_MORE_BYTES &&
+					  &decoder->packet, &decoder->pkt_ctx);
+		if (ret == INTEL_PT_NEED_MORE_BYTES && BITS_PER_LONG == 32 &&
 		    decoder->len < INTEL_PT_PKT_MAX_SZ && !decoder->next_buf) {
 			ret = intel_pt_get_split_packet(decoder);
 			if (ret < 0)
@@ -891,16 +917,20 @@
 	timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
 	masked_timestamp = timestamp & decoder->period_mask;
 	if (decoder->continuous_period) {
-		if (masked_timestamp != decoder->last_masked_timestamp)
+		if (masked_timestamp > decoder->last_masked_timestamp)
 			return 1;
 	} else {
 		timestamp += 1;
 		masked_timestamp = timestamp & decoder->period_mask;
-		if (masked_timestamp != decoder->last_masked_timestamp) {
+		if (masked_timestamp > decoder->last_masked_timestamp) {
 			decoder->last_masked_timestamp = masked_timestamp;
 			decoder->continuous_period = true;
 		}
 	}
+
+	if (masked_timestamp < decoder->last_masked_timestamp)
+		return decoder->period_ticks;
+
 	return decoder->period_ticks - (timestamp - masked_timestamp);
 }
 
@@ -929,7 +959,10 @@
 	case INTEL_PT_PERIOD_TICKS:
 		timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
 		masked_timestamp = timestamp & decoder->period_mask;
-		decoder->last_masked_timestamp = masked_timestamp;
+		if (masked_timestamp > decoder->last_masked_timestamp)
+			decoder->last_masked_timestamp = masked_timestamp;
+		else
+			decoder->last_masked_timestamp += decoder->period_ticks;
 		break;
 	case INTEL_PT_PERIOD_NONE:
 	case INTEL_PT_PERIOD_MTC:
@@ -1097,6 +1130,14 @@
 		decoder->state.to_ip = 0;
 		ret = true;
 	}
+	if (decoder->set_fup_bep) {
+		decoder->set_fup_bep = false;
+		decoder->state.type |= INTEL_PT_BLK_ITEMS;
+		decoder->state.type &= ~INTEL_PT_BRANCH;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		ret = true;
+	}
 	return ret;
 }
 
@@ -1165,7 +1206,7 @@
 		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 +1220,13 @@
 			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 +1253,8 @@
 			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",
@@ -1252,7 +1298,9 @@
 				return -ENOENT;
 			}
 			decoder->tnt.count -= 1;
-			if (!decoder->tnt.count)
+			if (decoder->tnt.count)
+				decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+			else
 				decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			decoder->tnt.payload <<= 1;
 			decoder->state.from_ip = decoder->ip;
@@ -1283,7 +1331,9 @@
 
 		if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
 			decoder->tnt.count -= 1;
-			if (!decoder->tnt.count)
+			if (decoder->tnt.count)
+				decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+			else
 				decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 			if (decoder->tnt.payload & BIT63) {
 				decoder->tnt.payload <<= 1;
@@ -1302,9 +1352,12 @@
 				decoder->ip += intel_pt_insn.length;
 				return 0;
 			}
+			decoder->sample_cyc = false;
 			decoder->ip += intel_pt_insn.length;
-			if (!decoder->tnt.count)
+			if (!decoder->tnt.count) {
+				intel_pt_update_sample_time(decoder);
 				return -EAGAIN;
+			}
 			decoder->tnt.payload <<= 1;
 			continue;
 		}
@@ -1336,6 +1389,21 @@
 	return 0;
 }
 
+static uint64_t intel_pt_8b_tsc(uint64_t timestamp, uint64_t ref_timestamp)
+{
+	timestamp |= (ref_timestamp & (0xffULL << 56));
+
+	if (timestamp < ref_timestamp) {
+		if (ref_timestamp - timestamp > (1ULL << 55))
+			timestamp += (1ULL << 56);
+	} else {
+		if (timestamp - ref_timestamp > (1ULL << 55))
+			timestamp -= (1ULL << 56);
+	}
+
+	return timestamp;
+}
+
 static void intel_pt_calc_tsc_timestamp(struct intel_pt_decoder *decoder)
 {
 	uint64_t timestamp;
@@ -1343,15 +1411,8 @@
 	decoder->have_tma = false;
 
 	if (decoder->ref_timestamp) {
-		timestamp = decoder->packet.payload |
-			    (decoder->ref_timestamp & (0xffULL << 56));
-		if (timestamp < decoder->ref_timestamp) {
-			if (decoder->ref_timestamp - timestamp > (1ULL << 55))
-				timestamp += (1ULL << 56);
-		} else {
-			if (timestamp - decoder->ref_timestamp > (1ULL << 55))
-				timestamp -= (1ULL << 56);
-		}
+		timestamp = intel_pt_8b_tsc(decoder->packet.payload,
+					    decoder->ref_timestamp);
 		decoder->tsc_timestamp = timestamp;
 		decoder->timestamp = timestamp;
 		decoder->ref_timestamp = 0;
@@ -1389,13 +1450,48 @@
 {
 	intel_pt_log("ERROR: Buffer overflow\n");
 	intel_pt_clear_tx_flags(decoder);
-	decoder->cbr = 0;
 	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
 	return -EOVERFLOW;
 }
 
+static inline void intel_pt_mtc_cyc_cnt_pge(struct intel_pt_decoder *decoder)
+{
+	if (decoder->have_cyc)
+		return;
+
+	decoder->cyc_cnt_timestamp = decoder->timestamp;
+	decoder->base_cyc_cnt = decoder->tot_cyc_cnt;
+}
+
+static inline void intel_pt_mtc_cyc_cnt_cbr(struct intel_pt_decoder *decoder)
+{
+	decoder->tsc_to_cyc = decoder->cbr / decoder->max_non_turbo_ratio_fp;
+
+	if (decoder->pge)
+		intel_pt_mtc_cyc_cnt_pge(decoder);
+}
+
+static inline void intel_pt_mtc_cyc_cnt_upd(struct intel_pt_decoder *decoder)
+{
+	uint64_t tot_cyc_cnt, tsc_delta;
+
+	if (decoder->have_cyc)
+		return;
+
+	decoder->sample_cyc = true;
+
+	if (!decoder->pge || decoder->timestamp <= decoder->cyc_cnt_timestamp)
+		return;
+
+	tsc_delta = decoder->timestamp - decoder->cyc_cnt_timestamp;
+	tot_cyc_cnt = tsc_delta * decoder->tsc_to_cyc + decoder->base_cyc_cnt;
+
+	if (tot_cyc_cnt > decoder->tot_cyc_cnt)
+		decoder->tot_cyc_cnt = tot_cyc_cnt;
+}
+
 static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
 {
 	uint32_t ctc = decoder->packet.payload;
@@ -1405,6 +1501,11 @@
 	if (!decoder->tsc_ctc_ratio_d)
 		return;
 
+	if (decoder->pge && !decoder->in_psb)
+		intel_pt_mtc_cyc_cnt_pge(decoder);
+	else
+		intel_pt_mtc_cyc_cnt_upd(decoder);
+
 	decoder->last_mtc = (ctc >> decoder->mtc_shift) & 0xff;
 	decoder->ctc_timestamp = decoder->tsc_timestamp - fc;
 	if (decoder->tsc_ctc_mult) {
@@ -1460,6 +1561,8 @@
 	else
 		decoder->timestamp = timestamp;
 
+	intel_pt_mtc_cyc_cnt_upd(decoder);
+
 	decoder->timestamp_insn_cnt = 0;
 	decoder->last_mtc = mtc;
 
@@ -1469,6 +1572,8 @@
 		decoder->have_calc_cyc_to_tsc = false;
 		intel_pt_calc_cyc_to_tsc(decoder, true);
 	}
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
@@ -1482,6 +1587,8 @@
 
 	decoder->cbr = cbr;
 	decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr;
+
+	intel_pt_mtc_cyc_cnt_cbr(decoder);
 }
 
 static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
@@ -1491,6 +1598,9 @@
 	decoder->have_cyc = true;
 
 	decoder->cycle_cnt += decoder->packet.payload;
+	if (decoder->pge)
+		decoder->tot_cyc_cnt += decoder->packet.payload;
+	decoder->sample_cyc = true;
 
 	if (!decoder->cyc_ref_timestamp)
 		return;
@@ -1509,6 +1619,48 @@
 		decoder->timestamp = timestamp;
 
 	decoder->timestamp_insn_cnt = 0;
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
+}
+
+static void intel_pt_bbp(struct intel_pt_decoder *decoder)
+{
+	if (decoder->prev_pkt_ctx == INTEL_PT_NO_CTX) {
+		memset(decoder->state.items.mask, 0, sizeof(decoder->state.items.mask));
+		decoder->state.items.is_32_bit = false;
+	}
+	decoder->blk_type = decoder->packet.payload;
+	decoder->blk_type_pos = intel_pt_blk_type_pos(decoder->blk_type);
+	if (decoder->blk_type == INTEL_PT_GP_REGS)
+		decoder->state.items.is_32_bit = decoder->packet.count;
+	if (decoder->blk_type_pos < 0) {
+		intel_pt_log("WARNING: Unknown block type %u\n",
+			     decoder->blk_type);
+	} else if (decoder->state.items.mask[decoder->blk_type_pos]) {
+		intel_pt_log("WARNING: Duplicate block type %u\n",
+			     decoder->blk_type);
+	}
+}
+
+static void intel_pt_bip(struct intel_pt_decoder *decoder)
+{
+	uint32_t id = decoder->packet.count;
+	uint32_t bit = 1 << id;
+	int pos = decoder->blk_type_pos;
+
+	if (pos < 0 || id >= INTEL_PT_BLK_ITEM_ID_CNT) {
+		intel_pt_log("WARNING: Unknown block item %u type %d\n",
+			     id, decoder->blk_type);
+		return;
+	}
+
+	if (decoder->state.items.mask[pos] & bit) {
+		intel_pt_log("WARNING: Duplicate block item %u type %d\n",
+			     id, decoder->blk_type);
+	}
+
+	decoder->state.items.mask[pos] |= bit;
+	decoder->state.items.val[pos][id] = decoder->packet.payload;
 }
 
 /* Walk PSB+ packets when already in sync. */
@@ -1516,14 +1668,17 @@
 {
 	int err;
 
+	decoder->in_psb = true;
+
 	while (1) {
 		err = intel_pt_get_next_packet(decoder);
 		if (err)
-			return err;
+			goto out;
 
 		switch (decoder->packet.type) {
 		case INTEL_PT_PSBEND:
-			return 0;
+			err = 0;
+			goto out;
 
 		case INTEL_PT_TIP_PGD:
 		case INTEL_PT_TIP_PGE:
@@ -1539,12 +1694,18 @@
 		case INTEL_PT_MWAIT:
 		case INTEL_PT_PWRE:
 		case INTEL_PT_PWRX:
+		case INTEL_PT_BBP:
+		case INTEL_PT_BIP:
+		case INTEL_PT_BEP:
+		case INTEL_PT_BEP_IP:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
-			return -EAGAIN;
+			err = -EAGAIN;
+			goto out;
 
 		case INTEL_PT_OVF:
-			return intel_pt_overflow(decoder);
+			err = intel_pt_overflow(decoder);
+			goto out;
 
 		case INTEL_PT_TSC:
 			intel_pt_calc_tsc_timestamp(decoder);
@@ -1590,6 +1751,10 @@
 			break;
 		}
 	}
+out:
+	decoder->in_psb = false;
+
+	return err;
 }
 
 static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
@@ -1626,6 +1791,10 @@
 		case INTEL_PT_MWAIT:
 		case INTEL_PT_PWRE:
 		case INTEL_PT_PWRX:
+		case INTEL_PT_BBP:
+		case INTEL_PT_BIP:
+		case INTEL_PT_BEP:
+		case INTEL_PT_BEP_IP:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
 			decoder->pkt_step = 0;
@@ -1640,14 +1809,15 @@
 
 		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 +1831,8 @@
 				intel_pt_set_ip(decoder);
 				decoder->state.to_ip = decoder->ip;
 			}
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			intel_pt_mtc_cyc_cnt_pge(decoder);
 			return 0;
 
 		case INTEL_PT_TIP:
@@ -1731,6 +1903,7 @@
 
 		case INTEL_PT_TIP_PGE: {
 			decoder->pge = true;
+			intel_pt_mtc_cyc_cnt_pge(decoder);
 			if (decoder->packet.count == 0) {
 				intel_pt_log_at("Skipping zero TIP.PGE",
 						decoder->pos);
@@ -1739,6 +1912,7 @@
 			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;
 		}
 
@@ -1801,6 +1975,13 @@
 				goto next;
 			if (err)
 				return err;
+			/*
+			 * PSB+ CBR will not have changed but cater for the
+			 * possibility of another CBR change that gets caught up
+			 * in the PSB+.
+			 */
+			if (decoder->cbr != decoder->cbr_seen)
+				return 0;
 			break;
 
 		case INTEL_PT_PIP:
@@ -1841,16 +2022,8 @@
 
 		case INTEL_PT_CBR:
 			intel_pt_calc_cbr(decoder);
-			if (!decoder->branch_enable &&
-			    decoder->cbr != decoder->cbr_seen) {
-				decoder->cbr_seen = decoder->cbr;
-				decoder->state.type = INTEL_PT_CBR_CHG;
-				decoder->state.from_ip = decoder->ip;
-				decoder->state.to_ip = 0;
-				decoder->state.cbr_payload =
-							decoder->packet.payload;
+			if (decoder->cbr != decoder->cbr_seen)
 				return 0;
-			}
 			break;
 
 		case INTEL_PT_MODE_EXEC:
@@ -1942,6 +2115,33 @@
 			decoder->state.pwrx_payload = decoder->packet.payload;
 			return 0;
 
+		case INTEL_PT_BBP:
+			intel_pt_bbp(decoder);
+			break;
+
+		case INTEL_PT_BIP:
+			intel_pt_bip(decoder);
+			break;
+
+		case INTEL_PT_BEP:
+			decoder->state.type = INTEL_PT_BLK_ITEMS;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			return 0;
+
+		case INTEL_PT_BEP_IP:
+			err = intel_pt_get_next_packet(decoder);
+			if (err)
+				return err;
+			if (decoder->packet.type == INTEL_PT_FUP) {
+				decoder->set_fup_bep = true;
+				no_tip = true;
+			} else {
+				intel_pt_log_at("ERROR: Missing FUP after BEP",
+						decoder->pos);
+			}
+			goto next;
+
 		default:
 			return intel_pt_bug(decoder);
 		}
@@ -1960,10 +2160,12 @@
 {
 	int err;
 
+	decoder->in_psb = true;
+
 	while (1) {
 		err = intel_pt_get_next_packet(decoder);
 		if (err)
-			return err;
+			goto out;
 
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
@@ -1978,8 +2180,13 @@
 		case INTEL_PT_MWAIT:
 		case INTEL_PT_PWRE:
 		case INTEL_PT_PWRX:
+		case INTEL_PT_BBP:
+		case INTEL_PT_BIP:
+		case INTEL_PT_BEP:
+		case INTEL_PT_BEP_IP:
 			intel_pt_log("ERROR: Unexpected packet\n");
-			return -ENOENT;
+			err = -ENOENT;
+			goto out;
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
@@ -2038,16 +2245,20 @@
 				decoder->pkt_state = INTEL_PT_STATE_ERR4;
 			else
 				decoder->pkt_state = INTEL_PT_STATE_ERR3;
-			return -ENOENT;
+			err = -ENOENT;
+			goto out;
 
 		case INTEL_PT_BAD: /* Does not happen */
-			return intel_pt_bug(decoder);
+			err = intel_pt_bug(decoder);
+			goto out;
 
 		case INTEL_PT_OVF:
-			return intel_pt_overflow(decoder);
+			err = intel_pt_overflow(decoder);
+			goto out;
 
 		case INTEL_PT_PSBEND:
-			return 0;
+			err = 0;
+			goto out;
 
 		case INTEL_PT_PSB:
 		case INTEL_PT_VMCS:
@@ -2057,6 +2268,10 @@
 			break;
 		}
 	}
+out:
+	decoder->in_psb = false;
+
+	return err;
 }
 
 static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
@@ -2071,15 +2286,31 @@
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
-			__fallthrough;
-		case INTEL_PT_TIP_PGE:
-		case INTEL_PT_TIP:
-			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
+			decoder->pge = false;
 			if (intel_pt_have_ip(decoder))
 				intel_pt_set_ip(decoder);
-			if (decoder->ip)
-				return 0;
-			break;
+			if (!decoder->ip)
+				break;
+			decoder->state.type |= INTEL_PT_TRACE_END;
+			return 0;
+
+		case INTEL_PT_TIP_PGE:
+			decoder->pge = true;
+			intel_pt_mtc_cyc_cnt_pge(decoder);
+			if (intel_pt_have_ip(decoder))
+				intel_pt_set_ip(decoder);
+			if (!decoder->ip)
+				break;
+			decoder->state.type |= INTEL_PT_TRACE_BEGIN;
+			return 0;
+
+		case INTEL_PT_TIP:
+			decoder->pge = true;
+			if (intel_pt_have_ip(decoder))
+				intel_pt_set_ip(decoder);
+			if (!decoder->ip)
+				break;
+			return 0;
 
 		case INTEL_PT_FUP:
 			if (intel_pt_have_ip(decoder))
@@ -2159,6 +2390,10 @@
 		case INTEL_PT_MWAIT:
 		case INTEL_PT_PWRE:
 		case INTEL_PT_PWRX:
+		case INTEL_PT_BBP:
+		case INTEL_PT_BIP:
+		case INTEL_PT_BEP:
+		case INTEL_PT_BEP_IP:
 		default:
 			break;
 		}
@@ -2174,6 +2409,7 @@
 	decoder->set_fup_mwait = false;
 	decoder->set_fup_pwre = false;
 	decoder->set_fup_exstop = false;
+	decoder->set_fup_bep = false;
 
 	if (!decoder->branch_enable) {
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
@@ -2231,7 +2467,7 @@
 	decoder->pos += decoder->len;
 	decoder->len = 0;
 
-	ret = intel_pt_get_next_data(decoder);
+	ret = intel_pt_get_next_data(decoder, false);
 	if (ret)
 		return ret;
 
@@ -2257,7 +2493,7 @@
 	intel_pt_log("Scanning for PSB\n");
 	while (1) {
 		if (!decoder->len) {
-			ret = intel_pt_get_next_data(decoder);
+			ret = intel_pt_get_next_data(decoder, false);
 			if (ret)
 				return ret;
 		}
@@ -2353,6 +2589,7 @@
 			err = intel_pt_walk_trace(decoder);
 			break;
 		case INTEL_PT_STATE_TNT:
+		case INTEL_PT_STATE_TNT_CONT:
 			err = intel_pt_walk_tnt(decoder);
 			if (err == -EAGAIN)
 				err = intel_pt_walk_trace(decoder);
@@ -2384,18 +2621,24 @@
 	if (err) {
 		decoder->state.err = intel_pt_ext_err(err);
 		decoder->state.from_ip = decoder->ip;
-		decoder->sample_timestamp = decoder->timestamp;
-		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		intel_pt_update_sample_time(decoder);
+		decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
 	} else {
 		decoder->state.err = 0;
-		if (decoder->cbr != decoder->cbr_seen && decoder->state.type) {
+		if (decoder->cbr != decoder->cbr_seen) {
 			decoder->cbr_seen = decoder->cbr;
+			if (!decoder->state.type) {
+				decoder->state.from_ip = decoder->ip;
+				decoder->state.to_ip = 0;
+			}
 			decoder->state.type |= INTEL_PT_CBR_CHG;
 			decoder->state.cbr_payload = decoder->cbr_payload;
+			decoder->state.cbr = decoder->cbr;
 		}
 		if (intel_pt_sample_time(decoder->pkt_state)) {
-			decoder->sample_timestamp = decoder->timestamp;
-			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+			intel_pt_update_sample_time(decoder);
+			if (decoder->sample_cyc)
+				decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
 		}
 	}
 
@@ -2403,6 +2646,7 @@
 	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
 	decoder->state.cr3 = decoder->cr3;
 	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
+	decoder->state.tot_cyc_cnt = decoder->sample_tot_cyc_cnt;
 
 	return &decoder->state;
 }
@@ -2506,11 +2750,12 @@
 static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
 			      size_t *rem)
 {
+	enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
 	struct intel_pt_pkt packet;
 	int ret;
 
 	while (len) {
-		ret = intel_pt_get_packet(buf, len, &packet);
+		ret = intel_pt_get_packet(buf, len, &packet, &ctx);
 		if (ret <= 0)
 			return false;
 		if (packet.type == INTEL_PT_TSC) {
@@ -2559,6 +2804,34 @@
 	}
 }
 
+#define MAX_PADDING (PERF_AUXTRACE_RECORD_ALIGNMENT - 1)
+
+/**
+ * adj_for_padding - adjust overlap to account for padding.
+ * @buf_b: second buffer
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ *
+ * @buf_a might have up to 7 bytes of padding appended. Adjust the overlap
+ * accordingly.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts
+ */
+static unsigned char *adj_for_padding(unsigned char *buf_b,
+				      unsigned char *buf_a, size_t len_a)
+{
+	unsigned char *p = buf_b - MAX_PADDING;
+	unsigned char *q = buf_a + len_a - MAX_PADDING;
+	int i;
+
+	for (i = MAX_PADDING; i; i--, p++, q++) {
+		if (*p != *q)
+			break;
+	}
+
+	return p;
+}
+
 /**
  * intel_pt_find_overlap_tsc - determine start of non-overlapped trace data
  *                             using TSC.
@@ -2609,8 +2882,11 @@
 
 			/* Same TSC, so buffers are consecutive */
 			if (!cmp && rem_b >= rem_a) {
+				unsigned char *start;
+
 				*consecutive = true;
-				return buf_b + len_b - (rem_b - rem_a);
+				start = buf_b + len_b - (rem_b - rem_a);
+				return adj_for_padding(start, buf_a, len_a);
 			}
 			if (cmp < 0)
 				return buf_b; /* tsc_a < tsc_b => no overlap */
@@ -2673,7 +2949,7 @@
 		found = memmem(buf_a, len_a, buf_b, len_a);
 		if (found) {
 			*consecutive = true;
-			return buf_b + len_a;
+			return adj_for_padding(buf_b + len_a, buf_a, len_a);
 		}
 
 		/* Try again at next PSB in buffer 'a' */
@@ -2681,3 +2957,131 @@
 			return buf_b; /* No overlap */
 	}
 }
+
+/**
+ * struct fast_forward_data - data used by intel_pt_ff_cb().
+ * @timestamp: timestamp to fast forward towards
+ * @buf_timestamp: buffer timestamp of last buffer with trace data earlier than
+ *                 the fast forward timestamp.
+ */
+struct fast_forward_data {
+	uint64_t timestamp;
+	uint64_t buf_timestamp;
+};
+
+/**
+ * intel_pt_ff_cb - fast forward lookahead callback.
+ * @buffer: Intel PT trace buffer
+ * @data: opaque pointer to fast forward data (struct fast_forward_data)
+ *
+ * Determine if @buffer trace is past the fast forward timestamp.
+ *
+ * Return: 1 (stop lookahead) if @buffer trace is past the fast forward
+ *         timestamp, and 0 otherwise.
+ */
+static int intel_pt_ff_cb(struct intel_pt_buffer *buffer, void *data)
+{
+	struct fast_forward_data *d = data;
+	unsigned char *buf;
+	uint64_t tsc;
+	size_t rem;
+	size_t len;
+
+	buf = (unsigned char *)buffer->buf;
+	len = buffer->len;
+
+	if (!intel_pt_next_psb(&buf, &len) ||
+	    !intel_pt_next_tsc(buf, len, &tsc, &rem))
+		return 0;
+
+	tsc = intel_pt_8b_tsc(tsc, buffer->ref_timestamp);
+
+	intel_pt_log("Buffer 1st timestamp " x64_fmt " ref timestamp " x64_fmt "\n",
+		     tsc, buffer->ref_timestamp);
+
+	/*
+	 * If the buffer contains a timestamp earlier that the fast forward
+	 * timestamp, then record it, else stop.
+	 */
+	if (tsc < d->timestamp)
+		d->buf_timestamp = buffer->ref_timestamp;
+	else
+		return 1;
+
+	return 0;
+}
+
+/**
+ * intel_pt_fast_forward - reposition decoder forwards.
+ * @decoder: Intel PT decoder
+ * @timestamp: timestamp to fast forward towards
+ *
+ * Reposition decoder at the last PSB with a timestamp earlier than @timestamp.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int intel_pt_fast_forward(struct intel_pt_decoder *decoder, uint64_t timestamp)
+{
+	struct fast_forward_data d = { .timestamp = timestamp };
+	unsigned char *buf;
+	size_t len;
+	int err;
+
+	intel_pt_log("Fast forward towards timestamp " x64_fmt "\n", timestamp);
+
+	/* Find buffer timestamp of buffer to fast forward to */
+	err = decoder->lookahead(decoder->data, intel_pt_ff_cb, &d);
+	if (err < 0)
+		return err;
+
+	/* Walk to buffer with same buffer timestamp */
+	if (d.buf_timestamp) {
+		do {
+			decoder->pos += decoder->len;
+			decoder->len = 0;
+			err = intel_pt_get_next_data(decoder, true);
+			/* -ENOLINK means non-consecutive trace */
+			if (err && err != -ENOLINK)
+				return err;
+		} while (decoder->buf_timestamp != d.buf_timestamp);
+	}
+
+	if (!decoder->buf)
+		return 0;
+
+	buf = (unsigned char *)decoder->buf;
+	len = decoder->len;
+
+	if (!intel_pt_next_psb(&buf, &len))
+		return 0;
+
+	/*
+	 * Walk PSBs while the PSB timestamp is less than the fast forward
+	 * timestamp.
+	 */
+	do {
+		uint64_t tsc;
+		size_t rem;
+
+		if (!intel_pt_next_tsc(buf, len, &tsc, &rem))
+			break;
+		tsc = intel_pt_8b_tsc(tsc, decoder->buf_timestamp);
+		/*
+		 * A TSC packet can slip past MTC packets but, after fast
+		 * forward, decoding starts at the TSC timestamp. That means
+		 * the timestamps may not be exactly the same as the timestamps
+		 * that would have been decoded without fast forward.
+		 */
+		if (tsc < timestamp) {
+			intel_pt_log("Fast forward to next PSB timestamp " x64_fmt "\n", tsc);
+			decoder->pos += decoder->len - len;
+			decoder->buf = buf;
+			decoder->len = len;
+			intel_pt_reposition(decoder);
+		} else {
+			break;
+		}
+	} while (intel_pt_step_psb(&buf, &len));
+
+	return 0;
+}
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 51c18d6..e289e46 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel_pt_decoder.h: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__INTEL_PT_DECODER_H__
@@ -37,6 +28,9 @@
 	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,
+	INTEL_PT_BLK_ITEMS	= 1 << 11,
 };
 
 enum intel_pt_period_type {
@@ -68,6 +62,141 @@
 	INTEL_PT_FUP_WITH_NLIP	= 1 << 0,
 };
 
+enum intel_pt_blk_type {
+	INTEL_PT_GP_REGS	= 1,
+	INTEL_PT_PEBS_BASIC	= 4,
+	INTEL_PT_PEBS_MEM	= 5,
+	INTEL_PT_LBR_0		= 8,
+	INTEL_PT_LBR_1		= 9,
+	INTEL_PT_LBR_2		= 10,
+	INTEL_PT_XMM		= 16,
+	INTEL_PT_BLK_TYPE_MAX
+};
+
+/*
+ * The block type numbers are not sequential but here they are given sequential
+ * positions to avoid wasting space for array placement.
+ */
+enum intel_pt_blk_type_pos {
+	INTEL_PT_GP_REGS_POS,
+	INTEL_PT_PEBS_BASIC_POS,
+	INTEL_PT_PEBS_MEM_POS,
+	INTEL_PT_LBR_0_POS,
+	INTEL_PT_LBR_1_POS,
+	INTEL_PT_LBR_2_POS,
+	INTEL_PT_XMM_POS,
+	INTEL_PT_BLK_TYPE_CNT
+};
+
+/* Get the array position for a block type */
+static inline int intel_pt_blk_type_pos(enum intel_pt_blk_type blk_type)
+{
+#define BLK_TYPE(bt) [INTEL_PT_##bt] = INTEL_PT_##bt##_POS + 1
+	const int map[INTEL_PT_BLK_TYPE_MAX] = {
+		BLK_TYPE(GP_REGS),
+		BLK_TYPE(PEBS_BASIC),
+		BLK_TYPE(PEBS_MEM),
+		BLK_TYPE(LBR_0),
+		BLK_TYPE(LBR_1),
+		BLK_TYPE(LBR_2),
+		BLK_TYPE(XMM),
+	};
+#undef BLK_TYPE
+
+	return blk_type < INTEL_PT_BLK_TYPE_MAX ? map[blk_type] - 1 : -1;
+}
+
+#define INTEL_PT_BLK_ITEM_ID_CNT	32
+
+/*
+ * Use unions so that the block items can be accessed by name or by array index.
+ * There is an array of 32-bit masks for each block type, which indicate which
+ * values are present. Then arrays of 32 64-bit values for each block type.
+ */
+struct intel_pt_blk_items {
+	union {
+		uint32_t mask[INTEL_PT_BLK_TYPE_CNT];
+		struct {
+			uint32_t has_rflags:1;
+			uint32_t has_rip:1;
+			uint32_t has_rax:1;
+			uint32_t has_rcx:1;
+			uint32_t has_rdx:1;
+			uint32_t has_rbx:1;
+			uint32_t has_rsp:1;
+			uint32_t has_rbp:1;
+			uint32_t has_rsi:1;
+			uint32_t has_rdi:1;
+			uint32_t has_r8:1;
+			uint32_t has_r9:1;
+			uint32_t has_r10:1;
+			uint32_t has_r11:1;
+			uint32_t has_r12:1;
+			uint32_t has_r13:1;
+			uint32_t has_r14:1;
+			uint32_t has_r15:1;
+			uint32_t has_unused_0:14;
+			uint32_t has_ip:1;
+			uint32_t has_applicable_counters:1;
+			uint32_t has_timestamp:1;
+			uint32_t has_unused_1:29;
+			uint32_t has_mem_access_address:1;
+			uint32_t has_mem_aux_info:1;
+			uint32_t has_mem_access_latency:1;
+			uint32_t has_tsx_aux_info:1;
+			uint32_t has_unused_2:28;
+			uint32_t has_lbr_0;
+			uint32_t has_lbr_1;
+			uint32_t has_lbr_2;
+			uint32_t has_xmm;
+		};
+	};
+	union {
+		uint64_t val[INTEL_PT_BLK_TYPE_CNT][INTEL_PT_BLK_ITEM_ID_CNT];
+		struct {
+			struct {
+				uint64_t rflags;
+				uint64_t rip;
+				uint64_t rax;
+				uint64_t rcx;
+				uint64_t rdx;
+				uint64_t rbx;
+				uint64_t rsp;
+				uint64_t rbp;
+				uint64_t rsi;
+				uint64_t rdi;
+				uint64_t r8;
+				uint64_t r9;
+				uint64_t r10;
+				uint64_t r11;
+				uint64_t r12;
+				uint64_t r13;
+				uint64_t r14;
+				uint64_t r15;
+				uint64_t unused_0[INTEL_PT_BLK_ITEM_ID_CNT - 18];
+			};
+			struct {
+				uint64_t ip;
+				uint64_t applicable_counters;
+				uint64_t timestamp;
+				uint64_t unused_1[INTEL_PT_BLK_ITEM_ID_CNT - 3];
+			};
+			struct {
+				uint64_t mem_access_address;
+				uint64_t mem_aux_info;
+				uint64_t mem_access_latency;
+				uint64_t tsx_aux_info;
+				uint64_t unused_2[INTEL_PT_BLK_ITEM_ID_CNT - 4];
+			};
+			uint64_t lbr_0[INTEL_PT_BLK_ITEM_ID_CNT];
+			uint64_t lbr_1[INTEL_PT_BLK_ITEM_ID_CNT];
+			uint64_t lbr_2[INTEL_PT_BLK_ITEM_ID_CNT];
+			uint64_t xmm[INTEL_PT_BLK_ITEM_ID_CNT];
+		};
+	};
+	bool is_32_bit;
+};
+
 struct intel_pt_state {
 	enum intel_pt_sample_type type;
 	int err;
@@ -75,6 +204,7 @@
 	uint64_t to_ip;
 	uint64_t cr3;
 	uint64_t tot_insn_cnt;
+	uint64_t tot_cyc_cnt;
 	uint64_t timestamp;
 	uint64_t est_timestamp;
 	uint64_t trace_nr;
@@ -83,10 +213,12 @@
 	uint64_t pwre_payload;
 	uint64_t pwrx_payload;
 	uint64_t cbr_payload;
+	uint32_t cbr;
 	uint32_t flags;
 	enum intel_pt_insn_op insn_op;
 	int insn_len;
 	char insn[INTEL_PT_INSN_BUF_SZ];
+	struct intel_pt_blk_items items;
 };
 
 struct intel_pt_insn;
@@ -99,12 +231,15 @@
 	uint64_t trace_nr;
 };
 
+typedef int (*intel_pt_lookahead_cb_t)(struct intel_pt_buffer *, void *);
+
 struct intel_pt_params {
 	int (*get_trace)(struct intel_pt_buffer *buffer, void *data);
 	int (*walk_insn)(struct intel_pt_insn *intel_pt_insn,
 			 uint64_t *insn_cnt_ptr, uint64_t *ip, uint64_t to_ip,
 			 uint64_t max_insn_cnt, void *data);
 	bool (*pgd_ip)(uint64_t ip, void *data);
+	int (*lookahead)(void *data, intel_pt_lookahead_cb_t cb, void *cb_data);
 	void *data;
 	bool return_compression;
 	bool branch_enable;
@@ -124,6 +259,8 @@
 
 const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
 
+int intel_pt_fast_forward(struct intel_pt_decoder *decoder, uint64_t timestamp);
+
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
 				     bool have_tsc, bool *consecutive);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 5481882..fb8a355 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -1,30 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel_pt_insn_decoder.c: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
+#include <linux/kernel.h>
 #include <stdio.h>
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include "../../../arch/x86/include/asm/insn.h"
+
+#include "../../../arch/x86/lib/inat.c"
+#include "../../../arch/x86/lib/insn.c"
 
 #include "event.h"
 
-#include "insn.h"
-
-#include "inat.c"
-#include "insn.c"
-
 #include "intel-pt-insn-decoder.h"
 #include "dump-insn.h"
 
@@ -180,6 +171,14 @@
 	return 0;
 }
 
+int arch_is_branch(const unsigned char *buf, size_t len, int x86_64)
+{
+	struct intel_pt_insn in;
+	if (intel_pt_get_insn(buf, len, x86_64, &in) < 0)
+		return -1;
+	return in.branch != INTEL_PT_BR_NO_BRANCH;
+}
+
 const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 		      u8 *inbuf, int inlen, int *lenp)
 {
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
index 37ec562..95a1eb0 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel_pt_insn_decoder.h: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__INTEL_PT_INSN_DECODER_H__
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
index e02bc7b..09feb5b 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel_pt_log.c: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <stdio.h>
@@ -31,6 +22,11 @@
 static char log_name[MAX_LOG_NAME];
 bool intel_pt_enable_logging;
 
+void *intel_pt_log_fp(void)
+{
+	return f;
+}
+
 void intel_pt_log_enable(void)
 {
 	intel_pt_enable_logging = true;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
index 45b64f9..388661f 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel_pt_log.h: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__INTEL_PT_LOG_H__
@@ -22,6 +13,7 @@
 
 struct intel_pt_pkt;
 
+void *intel_pt_log_fp(void);
 void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index d426761..0ccf10a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel_pt_pkt_decoder.c: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <stdio.h>
@@ -71,6 +62,10 @@
 	[INTEL_PT_MWAIT]	= "MWAIT",
 	[INTEL_PT_PWRE]		= "PWRE",
 	[INTEL_PT_PWRX]		= "PWRX",
+	[INTEL_PT_BBP]		= "BBP",
+	[INTEL_PT_BIP]		= "BIP",
+	[INTEL_PT_BEP]		= "BEP",
+	[INTEL_PT_BEP_IP]	= "BEP",
 };
 
 const char *intel_pt_pkt_name(enum intel_pt_pkt_type type)
@@ -289,6 +284,55 @@
 	return 7;
 }
 
+static int intel_pt_get_bbp(const unsigned char *buf, size_t len,
+			    struct intel_pt_pkt *packet)
+{
+	if (len < 3)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_BBP;
+	packet->count = buf[2] >> 7;
+	packet->payload = buf[2] & 0x1f;
+	return 3;
+}
+
+static int intel_pt_get_bip_4(const unsigned char *buf, size_t len,
+			      struct intel_pt_pkt *packet)
+{
+	if (len < 5)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_BIP;
+	packet->count = buf[0] >> 3;
+	memcpy_le64(&packet->payload, buf + 1, 4);
+	return 5;
+}
+
+static int intel_pt_get_bip_8(const unsigned char *buf, size_t len,
+			      struct intel_pt_pkt *packet)
+{
+	if (len < 9)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_BIP;
+	packet->count = buf[0] >> 3;
+	memcpy_le64(&packet->payload, buf + 1, 8);
+	return 9;
+}
+
+static int intel_pt_get_bep(size_t len, struct intel_pt_pkt *packet)
+{
+	if (len < 2)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_BEP;
+	return 2;
+}
+
+static int intel_pt_get_bep_ip(size_t len, struct intel_pt_pkt *packet)
+{
+	if (len < 2)
+		return INTEL_PT_NEED_MORE_BYTES;
+	packet->type = INTEL_PT_BEP_IP;
+	return 2;
+}
+
 static int intel_pt_get_ext(const unsigned char *buf, size_t len,
 			    struct intel_pt_pkt *packet)
 {
@@ -329,6 +373,12 @@
 		return intel_pt_get_pwre(buf, len, packet);
 	case 0xA2: /* PWRX */
 		return intel_pt_get_pwrx(buf, len, packet);
+	case 0x63: /* BBP */
+		return intel_pt_get_bbp(buf, len, packet);
+	case 0x33: /* BEP no IP */
+		return intel_pt_get_bep(len, packet);
+	case 0xb3: /* BEP with IP */
+		return intel_pt_get_bep_ip(len, packet);
 	default:
 		return INTEL_PT_BAD_PACKET;
 	}
@@ -477,7 +527,8 @@
 }
 
 static int intel_pt_do_get_packet(const unsigned char *buf, size_t len,
-				  struct intel_pt_pkt *packet)
+				  struct intel_pt_pkt *packet,
+				  enum intel_pt_pkt_ctx ctx)
 {
 	unsigned int byte;
 
@@ -487,6 +538,22 @@
 		return INTEL_PT_NEED_MORE_BYTES;
 
 	byte = buf[0];
+
+	switch (ctx) {
+	case INTEL_PT_NO_CTX:
+		break;
+	case INTEL_PT_BLK_4_CTX:
+		if ((byte & 0x7) == 4)
+			return intel_pt_get_bip_4(buf, len, packet);
+		break;
+	case INTEL_PT_BLK_8_CTX:
+		if ((byte & 0x7) == 4)
+			return intel_pt_get_bip_8(buf, len, packet);
+		break;
+	default:
+		break;
+	};
+
 	if (!(byte & BIT(0))) {
 		if (byte == 0)
 			return intel_pt_get_pad(packet);
@@ -525,15 +592,65 @@
 	}
 }
 
+void intel_pt_upd_pkt_ctx(const struct intel_pt_pkt *packet,
+			  enum intel_pt_pkt_ctx *ctx)
+{
+	switch (packet->type) {
+	case INTEL_PT_BAD:
+	case INTEL_PT_PAD:
+	case INTEL_PT_TSC:
+	case INTEL_PT_TMA:
+	case INTEL_PT_MTC:
+	case INTEL_PT_FUP:
+	case INTEL_PT_CYC:
+	case INTEL_PT_CBR:
+	case INTEL_PT_MNT:
+	case INTEL_PT_EXSTOP:
+	case INTEL_PT_EXSTOP_IP:
+	case INTEL_PT_PWRE:
+	case INTEL_PT_PWRX:
+	case INTEL_PT_BIP:
+		break;
+	case INTEL_PT_TNT:
+	case INTEL_PT_TIP:
+	case INTEL_PT_TIP_PGD:
+	case INTEL_PT_TIP_PGE:
+	case INTEL_PT_MODE_EXEC:
+	case INTEL_PT_MODE_TSX:
+	case INTEL_PT_PIP:
+	case INTEL_PT_OVF:
+	case INTEL_PT_VMCS:
+	case INTEL_PT_TRACESTOP:
+	case INTEL_PT_PSB:
+	case INTEL_PT_PSBEND:
+	case INTEL_PT_PTWRITE:
+	case INTEL_PT_PTWRITE_IP:
+	case INTEL_PT_MWAIT:
+	case INTEL_PT_BEP:
+	case INTEL_PT_BEP_IP:
+		*ctx = INTEL_PT_NO_CTX;
+		break;
+	case INTEL_PT_BBP:
+		if (packet->count)
+			*ctx = INTEL_PT_BLK_4_CTX;
+		else
+			*ctx = INTEL_PT_BLK_8_CTX;
+		break;
+	default:
+		break;
+	}
+}
+
 int intel_pt_get_packet(const unsigned char *buf, size_t len,
-			struct intel_pt_pkt *packet)
+			struct intel_pt_pkt *packet, enum intel_pt_pkt_ctx *ctx)
 {
 	int ret;
 
-	ret = intel_pt_do_get_packet(buf, len, packet);
+	ret = intel_pt_do_get_packet(buf, len, packet, *ctx);
 	if (ret > 0) {
 		while (ret < 8 && len > (size_t)ret && !buf[ret])
 			ret += 1;
+		intel_pt_upd_pkt_ctx(packet, ctx);
 	}
 	return ret;
 }
@@ -611,8 +728,10 @@
 		return snprintf(buf, buf_len, "%s 0x%llx IP:0", name, payload);
 	case INTEL_PT_PTWRITE_IP:
 		return snprintf(buf, buf_len, "%s 0x%llx IP:1", name, payload);
+	case INTEL_PT_BEP:
 	case INTEL_PT_EXSTOP:
 		return snprintf(buf, buf_len, "%s IP:0", name);
+	case INTEL_PT_BEP_IP:
 	case INTEL_PT_EXSTOP_IP:
 		return snprintf(buf, buf_len, "%s IP:1", name);
 	case INTEL_PT_MWAIT:
@@ -630,6 +749,12 @@
 				(unsigned int)((payload >> 4) & 0xf),
 				(unsigned int)(payload & 0xf),
 				(unsigned int)((payload >> 8) & 0xf));
+	case INTEL_PT_BBP:
+		return snprintf(buf, buf_len, "%s SZ %s-byte Type 0x%llx",
+				name, packet->count ? "4" : "8", payload);
+	case INTEL_PT_BIP:
+		return snprintf(buf, buf_len, "%s ID 0x%02x Value 0x%llx",
+				name, packet->count, payload);
 	default:
 		break;
 	}
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
index 73ddc3a..17ca9b5 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel_pt_pkt_decoder.h: Intel Processor Trace support
  * Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__INTEL_PT_PKT_DECODER_H__
@@ -59,6 +50,10 @@
 	INTEL_PT_MWAIT,
 	INTEL_PT_PWRE,
 	INTEL_PT_PWRX,
+	INTEL_PT_BBP,
+	INTEL_PT_BIP,
+	INTEL_PT_BEP,
+	INTEL_PT_BEP_IP,
 };
 
 struct intel_pt_pkt {
@@ -67,10 +62,25 @@
 	uint64_t		payload;
 };
 
+/*
+ * Decoding of BIP packets conflicts with single-byte TNT packets. Since BIP
+ * packets only occur in the context of a block (i.e. between BBP and BEP), that
+ * context must be recorded and passed to the packet decoder.
+ */
+enum intel_pt_pkt_ctx {
+	INTEL_PT_NO_CTX,	/* BIP packets are invalid */
+	INTEL_PT_BLK_4_CTX,	/* 4-byte BIP packets */
+	INTEL_PT_BLK_8_CTX,	/* 8-byte BIP packets */
+};
+
 const char *intel_pt_pkt_name(enum intel_pt_pkt_type);
 
 int intel_pt_get_packet(const unsigned char *buf, size_t len,
-			struct intel_pt_pkt *packet);
+			struct intel_pt_pkt *packet,
+			enum intel_pt_pkt_ctx *ctx);
+
+void intel_pt_upd_pkt_ctx(const struct intel_pt_pkt *packet,
+			  enum intel_pt_pkt_ctx *ctx);
 
 int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, size_t len);
 
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
deleted file mode 100644
index e0b8593..0000000
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ /dev/null
@@ -1,1072 +0,0 @@
-# x86 Opcode Maps
-#
-# This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
-#   (#326018-047US, June 2013)
-#
-#<Opcode maps>
-# Table: table-name
-# Referrer: escaped-name
-# AVXcode: avx-code
-# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# (or)
-# opcode: escape # escaped-name
-# EndTable
-#
-# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
-# mnemonics that begin with lowercase 'k' accept a VEX prefix
-#
-#<group maps>
-# GrpTable: GrpXXX
-# reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
-# EndTable
-#
-# AVX Superscripts
-#  (ev): this opcode requires EVEX prefix.
-#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
-#  (v): this opcode requires VEX prefix.
-#  (v1): this opcode only supports 128bit VEX.
-#
-# Last Prefix Superscripts
-#  - (66): the last prefix is 0x66
-#  - (F3): the last prefix is 0xF3
-#  - (F2): the last prefix is 0xF2
-#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
-#  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
-
-Table: one byte opcode
-Referrer:
-AVXcode:
-# 0x00 - 0x0f
-00: ADD Eb,Gb
-01: ADD Ev,Gv
-02: ADD Gb,Eb
-03: ADD Gv,Ev
-04: ADD AL,Ib
-05: ADD rAX,Iz
-06: PUSH ES (i64)
-07: POP ES (i64)
-08: OR Eb,Gb
-09: OR Ev,Gv
-0a: OR Gb,Eb
-0b: OR Gv,Ev
-0c: OR AL,Ib
-0d: OR rAX,Iz
-0e: PUSH CS (i64)
-0f: escape # 2-byte escape
-# 0x10 - 0x1f
-10: ADC Eb,Gb
-11: ADC Ev,Gv
-12: ADC Gb,Eb
-13: ADC Gv,Ev
-14: ADC AL,Ib
-15: ADC rAX,Iz
-16: PUSH SS (i64)
-17: POP SS (i64)
-18: SBB Eb,Gb
-19: SBB Ev,Gv
-1a: SBB Gb,Eb
-1b: SBB Gv,Ev
-1c: SBB AL,Ib
-1d: SBB rAX,Iz
-1e: PUSH DS (i64)
-1f: POP DS (i64)
-# 0x20 - 0x2f
-20: AND Eb,Gb
-21: AND Ev,Gv
-22: AND Gb,Eb
-23: AND Gv,Ev
-24: AND AL,Ib
-25: AND rAx,Iz
-26: SEG=ES (Prefix)
-27: DAA (i64)
-28: SUB Eb,Gb
-29: SUB Ev,Gv
-2a: SUB Gb,Eb
-2b: SUB Gv,Ev
-2c: SUB AL,Ib
-2d: SUB rAX,Iz
-2e: SEG=CS (Prefix)
-2f: DAS (i64)
-# 0x30 - 0x3f
-30: XOR Eb,Gb
-31: XOR Ev,Gv
-32: XOR Gb,Eb
-33: XOR Gv,Ev
-34: XOR AL,Ib
-35: XOR rAX,Iz
-36: SEG=SS (Prefix)
-37: AAA (i64)
-38: CMP Eb,Gb
-39: CMP Ev,Gv
-3a: CMP Gb,Eb
-3b: CMP Gv,Ev
-3c: CMP AL,Ib
-3d: CMP rAX,Iz
-3e: SEG=DS (Prefix)
-3f: AAS (i64)
-# 0x40 - 0x4f
-40: INC eAX (i64) | REX (o64)
-41: INC eCX (i64) | REX.B (o64)
-42: INC eDX (i64) | REX.X (o64)
-43: INC eBX (i64) | REX.XB (o64)
-44: INC eSP (i64) | REX.R (o64)
-45: INC eBP (i64) | REX.RB (o64)
-46: INC eSI (i64) | REX.RX (o64)
-47: INC eDI (i64) | REX.RXB (o64)
-48: DEC eAX (i64) | REX.W (o64)
-49: DEC eCX (i64) | REX.WB (o64)
-4a: DEC eDX (i64) | REX.WX (o64)
-4b: DEC eBX (i64) | REX.WXB (o64)
-4c: DEC eSP (i64) | REX.WR (o64)
-4d: DEC eBP (i64) | REX.WRB (o64)
-4e: DEC eSI (i64) | REX.WRX (o64)
-4f: DEC eDI (i64) | REX.WRXB (o64)
-# 0x50 - 0x5f
-50: PUSH rAX/r8 (d64)
-51: PUSH rCX/r9 (d64)
-52: PUSH rDX/r10 (d64)
-53: PUSH rBX/r11 (d64)
-54: PUSH rSP/r12 (d64)
-55: PUSH rBP/r13 (d64)
-56: PUSH rSI/r14 (d64)
-57: PUSH rDI/r15 (d64)
-58: POP rAX/r8 (d64)
-59: POP rCX/r9 (d64)
-5a: POP rDX/r10 (d64)
-5b: POP rBX/r11 (d64)
-5c: POP rSP/r12 (d64)
-5d: POP rBP/r13 (d64)
-5e: POP rSI/r14 (d64)
-5f: POP rDI/r15 (d64)
-# 0x60 - 0x6f
-60: PUSHA/PUSHAD (i64)
-61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
-63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
-64: SEG=FS (Prefix)
-65: SEG=GS (Prefix)
-66: Operand-Size (Prefix)
-67: Address-Size (Prefix)
-68: PUSH Iz (d64)
-69: IMUL Gv,Ev,Iz
-6a: PUSH Ib (d64)
-6b: IMUL Gv,Ev,Ib
-6c: INS/INSB Yb,DX
-6d: INS/INSW/INSD Yz,DX
-6e: OUTS/OUTSB DX,Xb
-6f: OUTS/OUTSW/OUTSD DX,Xz
-# 0x70 - 0x7f
-70: JO Jb
-71: JNO Jb
-72: JB/JNAE/JC Jb
-73: JNB/JAE/JNC Jb
-74: JZ/JE Jb
-75: JNZ/JNE Jb
-76: JBE/JNA Jb
-77: JNBE/JA Jb
-78: JS Jb
-79: JNS Jb
-7a: JP/JPE Jb
-7b: JNP/JPO Jb
-7c: JL/JNGE Jb
-7d: JNL/JGE Jb
-7e: JLE/JNG Jb
-7f: JNLE/JG Jb
-# 0x80 - 0x8f
-80: Grp1 Eb,Ib (1A)
-81: Grp1 Ev,Iz (1A)
-82: Grp1 Eb,Ib (1A),(i64)
-83: Grp1 Ev,Ib (1A)
-84: TEST Eb,Gb
-85: TEST Ev,Gv
-86: XCHG Eb,Gb
-87: XCHG Ev,Gv
-88: MOV Eb,Gb
-89: MOV Ev,Gv
-8a: MOV Gb,Eb
-8b: MOV Gv,Ev
-8c: MOV Ev,Sw
-8d: LEA Gv,M
-8e: MOV Sw,Ew
-8f: Grp1A (1A) | POP Ev (d64)
-# 0x90 - 0x9f
-90: NOP | PAUSE (F3) | XCHG r8,rAX
-91: XCHG rCX/r9,rAX
-92: XCHG rDX/r10,rAX
-93: XCHG rBX/r11,rAX
-94: XCHG rSP/r12,rAX
-95: XCHG rBP/r13,rAX
-96: XCHG rSI/r14,rAX
-97: XCHG rDI/r15,rAX
-98: CBW/CWDE/CDQE
-99: CWD/CDQ/CQO
-9a: CALLF Ap (i64)
-9b: FWAIT/WAIT
-9c: PUSHF/D/Q Fv (d64)
-9d: POPF/D/Q Fv (d64)
-9e: SAHF
-9f: LAHF
-# 0xa0 - 0xaf
-a0: MOV AL,Ob
-a1: MOV rAX,Ov
-a2: MOV Ob,AL
-a3: MOV Ov,rAX
-a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Yv,Xv
-a6: CMPS/B Xb,Yb
-a7: CMPS/W/D Xv,Yv
-a8: TEST AL,Ib
-a9: TEST rAX,Iz
-aa: STOS/B Yb,AL
-ab: STOS/W/D/Q Yv,rAX
-ac: LODS/B AL,Xb
-ad: LODS/W/D/Q rAX,Xv
-ae: SCAS/B AL,Yb
-# Note: The May 2011 Intel manual shows Xv for the second parameter of the
-# next instruction but Yv is correct
-af: SCAS/W/D/Q rAX,Yv
-# 0xb0 - 0xbf
-b0: MOV AL/R8L,Ib
-b1: MOV CL/R9L,Ib
-b2: MOV DL/R10L,Ib
-b3: MOV BL/R11L,Ib
-b4: MOV AH/R12L,Ib
-b5: MOV CH/R13L,Ib
-b6: MOV DH/R14L,Ib
-b7: MOV BH/R15L,Ib
-b8: MOV rAX/r8,Iv
-b9: MOV rCX/r9,Iv
-ba: MOV rDX/r10,Iv
-bb: MOV rBX/r11,Iv
-bc: MOV rSP/r12,Iv
-bd: MOV rBP/r13,Iv
-be: MOV rSI/r14,Iv
-bf: MOV rDI/r15,Iv
-# 0xc0 - 0xcf
-c0: Grp2 Eb,Ib (1A)
-c1: Grp2 Ev,Ib (1A)
-c2: RETN Iw (f64)
-c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11A Eb,Ib (1A)
-c7: Grp11B Ev,Iz (1A)
-c8: ENTER Iw,Ib
-c9: LEAVE (d64)
-ca: RETF Iw
-cb: RETF
-cc: INT3
-cd: INT Ib
-ce: INTO (i64)
-cf: IRET/D/Q
-# 0xd0 - 0xdf
-d0: Grp2 Eb,1 (1A)
-d1: Grp2 Ev,1 (1A)
-d2: Grp2 Eb,CL (1A)
-d3: Grp2 Ev,CL (1A)
-d4: AAM Ib (i64)
-d5: AAD Ib (i64)
-d6:
-d7: XLAT/XLATB
-d8: ESC
-d9: ESC
-da: ESC
-db: ESC
-dc: ESC
-dd: ESC
-de: ESC
-df: ESC
-# 0xe0 - 0xef
-# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
-# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
-# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-e1: LOOPE/LOOPZ Jb (f64)
-e2: LOOP Jb (f64)
-e3: JrCXZ Jb (f64)
-e4: IN AL,Ib
-e5: IN eAX,Ib
-e6: OUT Ib,AL
-e7: OUT Ib,eAX
-# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
-# in "near" jumps and calls is 16-bit. For CALL,
-# push of return address is 16-bit wide, RSP is decremented by 2
-# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64)
-e9: JMP-near Jz (f64)
-ea: JMP-far Ap (i64)
-eb: JMP-short Jb (f64)
-ec: IN AL,DX
-ed: IN eAX,DX
-ee: OUT DX,AL
-ef: OUT DX,eAX
-# 0xf0 - 0xff
-f0: LOCK (Prefix)
-f1:
-f2: REPNE (Prefix) | XACQUIRE (Prefix)
-f3: REP/REPE (Prefix) | XRELEASE (Prefix)
-f4: HLT
-f5: CMC
-f6: Grp3_1 Eb (1A)
-f7: Grp3_2 Ev (1A)
-f8: CLC
-f9: STC
-fa: CLI
-fb: STI
-fc: CLD
-fd: STD
-fe: Grp4 (1A)
-ff: Grp5 (1A)
-EndTable
-
-Table: 2-byte opcode (0x0f)
-Referrer: 2-byte escape
-AVXcode: 1
-# 0x0f 0x00-0x0f
-00: Grp6 (1A)
-01: Grp7 (1A)
-02: LAR Gv,Ew
-03: LSL Gv,Ew
-04:
-05: SYSCALL (o64)
-06: CLTS
-07: SYSRET (o64)
-08: INVD
-09: WBINVD
-0a:
-0b: UD2 (1B)
-0c:
-# AMD's prefetch group. Intel supports prefetchw(/1) only.
-0d: GrpP
-0e: FEMMS
-# 3DNow! uses the last imm byte as opcode extension.
-0f: 3DNow! Pq,Qq,Ib
-# 0x0f 0x10-0x1f
-# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
-# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
-# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
-# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
-# Reference A.1
-10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
-11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
-12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
-13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
-14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
-15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
-16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
-17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
-18: Grp16 (1A)
-19:
-# Intel SDM opcode map does not list MPX instructions. For now using Gv for
-# bnd registers and Ev for everything else is OK because the instruction
-# decoder does not use the information except as an indication that there is
-# a ModR/M byte.
-1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
-1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
-1d:
-1e:
-1f: NOP Ev
-# 0x0f 0x20-0x2f
-20: MOV Rd,Cd
-21: MOV Rd,Dd
-22: MOV Cd,Rd
-23: MOV Dd,Rd
-24:
-25:
-26:
-27:
-28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
-29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
-2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
-2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
-2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
-2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
-2e: vucomiss Vss,Wss (v1) | vucomisd  Vsd,Wsd (66),(v1)
-2f: vcomiss Vss,Wss (v1) | vcomisd  Vsd,Wsd (66),(v1)
-# 0x0f 0x30-0x3f
-30: WRMSR
-31: RDTSC
-32: RDMSR
-33: RDPMC
-34: SYSENTER
-35: SYSEXIT
-36:
-37: GETSEC
-38: escape # 3-byte escape 1
-39:
-3a: escape # 3-byte escape 2
-3b:
-3c:
-3d:
-3e:
-3f:
-# 0x0f 0x40-0x4f
-40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
-42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
-43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
-45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
-46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
-47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
-48: CMOVS Gv,Ev
-49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
-4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
-4c: CMOVL/NGE Gv,Ev
-4d: CMOVNL/GE Gv,Ev
-4e: CMOVLE/NG Gv,Ev
-4f: CMOVNLE/G Gv,Ev
-# 0x0f 0x50-0x5f
-50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
-51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
-52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
-53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
-54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
-55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
-56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
-57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
-58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
-59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
-5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
-5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
-5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
-5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
-5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
-# 0x0f 0x60-0x6f
-60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
-61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
-62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
-63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
-64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
-65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
-66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
-67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
-68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
-69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
-6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
-6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
-6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
-6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
-6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
-# 0x0f 0x70-0x7f
-70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
-71: Grp12 (1A)
-72: Grp13 (1A)
-73: Grp14 (1A)
-74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
-75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
-76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
-# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
-77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
-79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
-7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
-7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
-7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
-7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
-7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
-# 0x0f 0x80-0x8f
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-81: JNO Jz (f64)
-82: JB/JC/JNAE Jz (f64)
-83: JAE/JNB/JNC Jz (f64)
-84: JE/JZ Jz (f64)
-85: JNE/JNZ Jz (f64)
-86: JBE/JNA Jz (f64)
-87: JA/JNBE Jz (f64)
-88: JS Jz (f64)
-89: JNS Jz (f64)
-8a: JP/JPE Jz (f64)
-8b: JNP/JPO Jz (f64)
-8c: JL/JNGE Jz (f64)
-8d: JNL/JGE Jz (f64)
-8e: JLE/JNG Jz (f64)
-8f: JNLE/JG Jz (f64)
-# 0x0f 0x90-0x9f
-90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
-91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
-92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
-93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
-94: SETE/Z Eb
-95: SETNE/NZ Eb
-96: SETBE/NA Eb
-97: SETA/NBE Eb
-98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
-99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
-9a: SETP/PE Eb
-9b: SETNP/PO Eb
-9c: SETL/NGE Eb
-9d: SETNL/GE Eb
-9e: SETLE/NG Eb
-9f: SETNLE/G Eb
-# 0x0f 0xa0-0xaf
-a0: PUSH FS (d64)
-a1: POP FS (d64)
-a2: CPUID
-a3: BT Ev,Gv
-a4: SHLD Ev,Gv,Ib
-a5: SHLD Ev,Gv,CL
-a6: GrpPDLK
-a7: GrpRNG
-a8: PUSH GS (d64)
-a9: POP GS (d64)
-aa: RSM
-ab: BTS Ev,Gv
-ac: SHRD Ev,Gv,Ib
-ad: SHRD Ev,Gv,CL
-ae: Grp15 (1A),(1C)
-af: IMUL Gv,Ev
-# 0x0f 0xb0-0xbf
-b0: CMPXCHG Eb,Gb
-b1: CMPXCHG Ev,Gv
-b2: LSS Gv,Mp
-b3: BTR Ev,Gv
-b4: LFS Gv,Mp
-b5: LGS Gv,Mp
-b6: MOVZX Gv,Eb
-b7: MOVZX Gv,Ew
-b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
-b9: Grp10 (1A)
-ba: Grp8 Ev,Ib (1A)
-bb: BTC Ev,Gv
-bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
-be: MOVSX Gv,Eb
-bf: MOVSX Gv,Ew
-# 0x0f 0xc0-0xcf
-c0: XADD Eb,Gb
-c1: XADD Ev,Gv
-c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
-c3: movnti My,Gy
-c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
-c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
-c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
-c7: Grp9 (1A)
-c8: BSWAP RAX/EAX/R8/R8D
-c9: BSWAP RCX/ECX/R9/R9D
-ca: BSWAP RDX/EDX/R10/R10D
-cb: BSWAP RBX/EBX/R11/R11D
-cc: BSWAP RSP/ESP/R12/R12D
-cd: BSWAP RBP/EBP/R13/R13D
-ce: BSWAP RSI/ESI/R14/R14D
-cf: BSWAP RDI/EDI/R15/R15D
-# 0x0f 0xd0-0xdf
-d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
-d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
-d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
-d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
-d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
-d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
-d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
-d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
-d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
-da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
-dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
-dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
-de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
-e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
-e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
-e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
-e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
-e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
-e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
-e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
-e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
-ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
-ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
-ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
-ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0xf0-0xff
-f0: vlddqu Vx,Mx (F2)
-f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
-f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
-f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
-f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
-f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
-f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
-f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
-f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
-f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
-fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
-fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
-fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
-fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
-fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff: UD0
-EndTable
-
-Table: 3-byte opcode 1 (0x0f 0x38)
-Referrer: 3-byte escape 1
-AVXcode: 2
-# 0x0f 0x38 0x00-0x0f
-00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
-01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
-02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
-03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
-04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
-05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
-06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
-07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
-08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
-09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
-0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
-0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
-0c: vpermilps Vx,Hx,Wx (66),(v)
-0d: vpermilpd Vx,Hx,Wx (66),(v)
-0e: vtestps Vx,Wx (66),(v)
-0f: vtestpd Vx,Wx (66),(v)
-# 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
-11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
-12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
-13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
-14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
-15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
-16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
-17: vptest Vx,Wx (66)
-18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
-1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
-1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
-1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
-1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
-1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f: vpabsq Vx,Wx (66),(ev)
-# 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
-21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
-24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
-26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
-27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
-28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
-2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
-2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
-2e: vmaskmovps Mx,Hx,Vx (66),(v)
-2f: vmaskmovpd Mx,Hx,Vx (66),(v)
-# 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
-31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
-34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
-36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
-37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
-39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
-3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
-3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
-3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
-3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
-# 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
-41: vphminposuw Vdq,Wdq (66),(v1)
-42: vgetexpps/d Vx,Wx (66),(ev)
-43: vgetexpss/d Vx,Hx,Wx (66),(ev)
-44: vplzcntd/q Vx,Wx (66),(ev)
-45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
-47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x4b
-4c: vrcp14ps/d Vpd,Wpd (66),(ev)
-4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
-4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
-4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-# Skip 0x50-0x57
-58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
-5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
-5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x63
-64: vpblendmd/q Vx,Hx,Wx (66),(ev)
-65: vblendmps/d Vx,Hx,Wx (66),(ev)
-66: vpblendmb/w Vx,Hx,Wx (66),(ev)
-# Skip 0x67-0x74
-75: vpermi2b/w Vx,Hx,Wx (66),(ev)
-76: vpermi2d/q Vx,Hx,Wx (66),(ev)
-77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
-78: vpbroadcastb Vx,Wx (66),(v)
-79: vpbroadcastw Vx,Wx (66),(v)
-7a: vpbroadcastb Vx,Rv (66),(ev)
-7b: vpbroadcastw Vx,Rv (66),(ev)
-7c: vpbroadcastd/q Vx,Rv (66),(ev)
-7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
-7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
-7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
-80: INVEPT Gy,Mdq (66)
-81: INVVPID Gy,Mdq (66)
-82: INVPCID Gy,Mdq (66)
-83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
-88: vexpandps/d Vpd,Wpd (66),(ev)
-89: vpexpandd/q Vx,Wx (66),(ev)
-8a: vcompressps/d Wx,Vx (66),(ev)
-8b: vpcompressd/q Wx,Vx (66),(ev)
-8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
-8d: vpermb/w Vx,Hx,Wx (66),(ev)
-8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
-# 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
-91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
-92: vgatherdps/d Vx,Hx,Wx (66),(v)
-93: vgatherqps/d Vx,Hx,Wx (66),(v)
-94:
-95:
-96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
-97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
-98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
-99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
-9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
-9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
-a0: vpscatterdd/q Wx,Vx (66),(ev)
-a1: vpscatterqd/q Wx,Vx (66),(ev)
-a2: vscatterdps/d Wx,Vx (66),(ev)
-a3: vscatterqps/d Wx,Vx (66),(ev)
-a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
-a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
-a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
-a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
-ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
-af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
-b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
-b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
-b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
-b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
-b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
-bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
-bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
-be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
-bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
-# 0x0f 0x38 0xc0-0xff
-c4: vpconflictd/q Vx,Wx (66),(ev)
-c6: Grp18 (1A)
-c7: Grp19 (1A)
-c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
-c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
-cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
-cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
-cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
-db: VAESIMC Vdq,Wdq (66),(v1)
-dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
-f2: ANDN Gy,By,Ey (v)
-f3: Grp17 (1A)
-f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
-f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
-EndTable
-
-Table: 3-byte opcode 2 (0x0f 0x3a)
-Referrer: 3-byte escape 2
-AVXcode: 3
-# 0x0f 0x3a 0x00-0xff
-00: vpermq Vqq,Wqq,Ib (66),(v)
-01: vpermpd Vqq,Wqq,Ib (66),(v)
-02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
-04: vpermilps Vx,Wx,Ib (66),(v)
-05: vpermilpd Vx,Wx,Ib (66),(v)
-06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
-07:
-08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
-09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
-0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
-0c: vblendps Vx,Hx,Wx,Ib (66)
-0d: vblendpd Vx,Hx,Wx,Ib (66)
-0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
-0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
-14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
-15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
-16: vpextrd/q Ey,Vdq,Ib (66),(v1)
-17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-1d: vcvtps2ph Wx,Vx,Ib (66),(v)
-1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
-1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
-20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
-21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
-22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
-26: vgetmantps/d Vx,Wx,Ib (66),(ev)
-27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
-30: kshiftrb/w Vk,Uk,Ib (66),(v)
-31: kshiftrd/q Vk,Uk,Ib (66),(v)
-32: kshiftlb/w Vk,Uk,Ib (66),(v)
-33: kshiftld/q Vk,Uk,Ib (66),(v)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
-39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
-3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
-3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
-3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
-3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
-40: vdpps Vx,Hx,Wx,Ib (66)
-41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
-43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
-46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
-4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
-4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
-4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
-50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
-51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
-54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
-55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
-56: vreduceps/d Vx,Wx,Ib (66),(ev)
-57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
-60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
-61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
-62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
-63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
-66: vfpclassps/d Vk,Wx,Ib (66),(ev)
-67: vfpclassss/d Vk,Wx,Ib (66),(ev)
-cc: sha1rnds4 Vdq,Wdq,Ib
-df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
-f0: RORX Gy,Ey,Ib (F2),(v)
-EndTable
-
-GrpTable: Grp1
-0: ADD
-1: OR
-2: ADC
-3: SBB
-4: AND
-5: SUB
-6: XOR
-7: CMP
-EndTable
-
-GrpTable: Grp1A
-0: POP
-EndTable
-
-GrpTable: Grp2
-0: ROL
-1: ROR
-2: RCL
-3: RCR
-4: SHL/SAL
-5: SHR
-6:
-7: SAR
-EndTable
-
-GrpTable: Grp3_1
-0: TEST Eb,Ib
-1: TEST Eb,Ib
-2: NOT Eb
-3: NEG Eb
-4: MUL AL,Eb
-5: IMUL AL,Eb
-6: DIV AL,Eb
-7: IDIV AL,Eb
-EndTable
-
-GrpTable: Grp3_2
-0: TEST Ev,Iz
-1:
-2: NOT Ev
-3: NEG Ev
-4: MUL rAX,Ev
-5: IMUL rAX,Ev
-6: DIV rAX,Ev
-7: IDIV rAX,Ev
-EndTable
-
-GrpTable: Grp4
-0: INC Eb
-1: DEC Eb
-EndTable
-
-GrpTable: Grp5
-0: INC Ev
-1: DEC Ev
-# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-2: CALLN Ev (f64)
-3: CALLF Ep
-4: JMPN Ev (f64)
-5: JMPF Mp
-6: PUSH Ev (d64)
-7:
-EndTable
-
-GrpTable: Grp6
-0: SLDT Rv/Mw
-1: STR Rv/Mw
-2: LLDT Ew
-3: LTR Ew
-4: VERR Ew
-5: VERW Ew
-EndTable
-
-GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
-3: LIDT Ms
-4: SMSW Mw/Rv
-5: rdpkru (110),(11B) | wrpkru (111),(11B)
-6: LMSW Ew
-7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
-EndTable
-
-GrpTable: Grp8
-4: BT
-5: BTS
-6: BTR
-7: BTC
-EndTable
-
-GrpTable: Grp9
-1: CMPXCHG8B/16B Mq/Mdq
-3: xrstors
-4: xsavec
-5: xsaves
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
-EndTable
-
-GrpTable: Grp10
-# all are UD1
-0: UD1
-1: UD1
-2: UD1
-3: UD1
-4: UD1
-5: UD1
-6: UD1
-7: UD1
-EndTable
-
-# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
-GrpTable: Grp11A
-0: MOV Eb,Ib
-7: XABORT Ib (000),(11B)
-EndTable
-
-GrpTable: Grp11B
-0: MOV Eb,Iz
-7: XBEGIN Jz (000),(11B)
-EndTable
-
-GrpTable: Grp12
-2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
-4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
-6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp13
-0: vprord/q Hx,Wx,Ib (66),(ev)
-1: vprold/q Hx,Wx,Ib (66),(ev)
-2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
-6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp14
-2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
-3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
-6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
-7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
-EndTable
-
-GrpTable: Grp15
-0: fxsave | RDFSBASE Ry (F3),(11B)
-1: fxstor | RDGSBASE Ry (F3),(11B)
-2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
-3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
-4: XSAVE | ptwrite Ey (F3),(11B)
-5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
-7: clflush | clflushopt (66) | sfence (11B)
-EndTable
-
-GrpTable: Grp16
-0: prefetch NTA
-1: prefetch T0
-2: prefetch T1
-3: prefetch T2
-EndTable
-
-GrpTable: Grp17
-1: BLSR By,Ey (v)
-2: BLSMSK By,Ey (v)
-3: BLSI By,Ey (v)
-EndTable
-
-GrpTable: Grp18
-1: vgatherpf0dps/d Wx (66),(ev)
-2: vgatherpf1dps/d Wx (66),(ev)
-5: vscatterpf0dps/d Wx (66),(ev)
-6: vscatterpf1dps/d Wx (66),(ev)
-EndTable
-
-GrpTable: Grp19
-1: vgatherpf0qps/d Wx (66),(ev)
-2: vgatherpf1qps/d Wx (66),(ev)
-5: vscatterpf0qps/d Wx (66),(ev)
-6: vscatterpf1qps/d Wx (66),(ev)
-EndTable
-
-# AMD's Prefetch Group
-GrpTable: GrpP
-0: PREFETCH
-1: PREFETCHW
-EndTable
-
-GrpTable: GrpPDLK
-0: MONTMUL
-1: XSHA1
-2: XSHA2
-EndTable
-
-GrpTable: GrpRNG
-0: xstore-rng
-1: xcrypt-ecb
-2: xcrypt-cbc
-4: xcrypt-cfb
-5: xcrypt-ofb
-EndTable
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4f48bc1..a1c9eb6 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * intel_pt.c: Intel Processor Trace support
  * Copyright (c) 2013-2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <inttypes.h>
@@ -18,9 +9,10 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 
-#include "../perf.h"
 #include "session.h"
 #include "machine.h"
 #include "memswap.h"
@@ -31,7 +23,6 @@
 #include "evsel.h"
 #include "map.h"
 #include "color.h"
-#include "util.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "symbol.h"
@@ -42,6 +33,10 @@
 #include "tsc.h"
 #include "intel-pt.h"
 #include "config.h"
+#include "util/synthetic-events.h"
+#include "time-utils.h"
+
+#include "../arch/x86/include/uapi/asm/perf_regs.h"
 
 #include "intel-pt-decoder/intel-pt-log.h"
 #include "intel-pt-decoder/intel-pt-decoder.h"
@@ -50,6 +45,11 @@
 
 #define MAX_TIMESTAMP (~0ULL)
 
+struct range {
+	u64 start;
+	u64 end;
+};
+
 struct intel_pt {
 	struct auxtrace auxtrace;
 	struct auxtrace_queues queues;
@@ -57,7 +57,7 @@
 	u32 auxtrace_type;
 	struct perf_session *session;
 	struct machine *machine;
-	struct perf_evsel *switch_evsel;
+	struct evsel *switch_evsel;
 	struct thread *unknown_thread;
 	bool timeless_decoding;
 	bool sampling_mode;
@@ -104,6 +104,9 @@
 	u64 pwrx_id;
 	u64 cbr_id;
 
+	bool sample_pebs;
+	struct evsel *pebs_evsel;
+
 	u64 tsc_bit;
 	u64 mtc_bit;
 	u64 mtc_freq_bits;
@@ -118,6 +121,9 @@
 
 	char *filter;
 	struct addr_filters filts;
+
+	struct range *time_ranges;
+	unsigned int range_cnt;
 };
 
 enum switch_state {
@@ -154,9 +160,19 @@
 	bool have_sample;
 	u64 time;
 	u64 timestamp;
+	u64 sel_timestamp;
+	bool sel_start;
+	unsigned int sel_idx;
 	u32 flags;
 	u16 insn_len;
 	u64 last_insn_cnt;
+	u64 ipc_insn_cnt;
+	u64 ipc_cyc_cnt;
+	u64 last_in_insn_cnt;
+	u64 last_in_cyc_cnt;
+	u64 last_br_insn_cnt;
+	u64 last_br_cyc_cnt;
+	unsigned int cbr_seen;
 	char insn[INTEL_PT_INSN_BUF_SZ];
 };
 
@@ -168,13 +184,14 @@
 	int ret, pkt_len, i;
 	char desc[INTEL_PT_PKT_DESC_MAX];
 	const char *color = PERF_COLOR_BLUE;
+	enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
 
 	color_fprintf(stdout, color,
 		      ". ... Intel Processor Trace data: size %zu bytes\n",
 		      len);
 
 	while (len) {
-		ret = intel_pt_get_packet(buf, len, &packet);
+		ret = intel_pt_get_packet(buf, len, &packet, &ctx);
 		if (ret > 0)
 			pkt_len = ret;
 		else
@@ -206,6 +223,16 @@
 	intel_pt_dump(pt, buf, len);
 }
 
+static void intel_pt_log_event(union perf_event *event)
+{
+	FILE *f = intel_pt_log_fp();
+
+	if (!intel_pt_enable_logging || !f)
+		return;
+
+	perf_event__fprintf(event, f);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -223,32 +250,13 @@
 	return 0;
 }
 
-/* This function assumes data is processed sequentially only */
-static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+static int intel_pt_get_buffer(struct intel_pt_queue *ptq,
+			       struct auxtrace_buffer *buffer,
+			       struct auxtrace_buffer *old_buffer,
+			       struct intel_pt_buffer *b)
 {
-	struct intel_pt_queue *ptq = data;
-	struct auxtrace_buffer *buffer = ptq->buffer;
-	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
-	struct auxtrace_queue *queue;
 	bool might_overlap;
 
-	if (ptq->stop) {
-		b->len = 0;
-		return 0;
-	}
-
-	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-
-	buffer = auxtrace_buffer__next(queue, buffer);
-	if (!buffer) {
-		if (old_buffer)
-			auxtrace_buffer__drop_data(old_buffer);
-		b->len = 0;
-		return 0;
-	}
-
-	ptq->buffer = buffer;
-
 	if (!buffer->data) {
 		int fd = perf_data__fd(ptq->pt->session->data);
 
@@ -278,6 +286,95 @@
 		b->consecutive = true;
 	}
 
+	return 0;
+}
+
+/* Do not drop buffers with references - refer intel_pt_get_trace() */
+static void intel_pt_lookahead_drop_buffer(struct intel_pt_queue *ptq,
+					   struct auxtrace_buffer *buffer)
+{
+	if (!buffer || buffer == ptq->buffer || buffer == ptq->old_buffer)
+		return;
+
+	auxtrace_buffer__drop_data(buffer);
+}
+
+/* Must be serialized with respect to intel_pt_get_trace() */
+static int intel_pt_lookahead(void *data, intel_pt_lookahead_cb_t cb,
+			      void *cb_data)
+{
+	struct intel_pt_queue *ptq = data;
+	struct auxtrace_buffer *buffer = ptq->buffer;
+	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+	struct auxtrace_queue *queue;
+	int err = 0;
+
+	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+	while (1) {
+		struct intel_pt_buffer b = { .len = 0 };
+
+		buffer = auxtrace_buffer__next(queue, buffer);
+		if (!buffer)
+			break;
+
+		err = intel_pt_get_buffer(ptq, buffer, old_buffer, &b);
+		if (err)
+			break;
+
+		if (b.len) {
+			intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+			old_buffer = buffer;
+		} else {
+			intel_pt_lookahead_drop_buffer(ptq, buffer);
+			continue;
+		}
+
+		err = cb(&b, cb_data);
+		if (err)
+			break;
+	}
+
+	if (buffer != old_buffer)
+		intel_pt_lookahead_drop_buffer(ptq, buffer);
+	intel_pt_lookahead_drop_buffer(ptq, old_buffer);
+
+	return err;
+}
+
+/*
+ * This function assumes data is processed sequentially only.
+ * Must be serialized with respect to intel_pt_lookahead()
+ */
+static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+{
+	struct intel_pt_queue *ptq = data;
+	struct auxtrace_buffer *buffer = ptq->buffer;
+	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
+	struct auxtrace_queue *queue;
+	int err;
+
+	if (ptq->stop) {
+		b->len = 0;
+		return 0;
+	}
+
+	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+	buffer = auxtrace_buffer__next(queue, buffer);
+	if (!buffer) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		b->len = 0;
+		return 0;
+	}
+
+	ptq->buffer = buffer;
+
+	err = intel_pt_get_buffer(ptq, buffer, old_buffer, b);
+	if (err)
+		return err;
+
 	if (ptq->step_through_buffers)
 		ptq->stop = true;
 
@@ -627,11 +724,11 @@
 
 static bool intel_pt_exclude_kernel(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
-		    !evsel->attr.exclude_kernel)
+		if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
+		    !evsel->core.attr.exclude_kernel)
 			return false;
 	}
 	return true;
@@ -639,14 +736,14 @@
 
 static bool intel_pt_return_compression(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	u64 config;
 
 	if (!pt->noretcomp_bit)
 		return true;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
 		    (config & pt->noretcomp_bit))
 			return false;
 	}
@@ -655,11 +752,11 @@
 
 static bool intel_pt_branch_enable(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	u64 config;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
 		    (config & 1) && !(config & 0x2000))
 			return false;
 	}
@@ -668,7 +765,7 @@
 
 static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	unsigned int shift;
 	u64 config;
 
@@ -679,7 +776,7 @@
 		config >>= 1;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, &config))
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config))
 			return (config & pt->mtc_freq_bits) >> shift;
 	}
 	return 0;
@@ -687,7 +784,7 @@
 
 static bool intel_pt_timeless_decoding(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	bool timeless_decoding = true;
 	u64 config;
 
@@ -695,9 +792,9 @@
 		return true;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_TIME))
 			return true;
-		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
 			if (config & pt->tsc_bit)
 				timeless_decoding = false;
 			else
@@ -709,11 +806,11 @@
 
 static bool intel_pt_tracing_kernel(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
-		    !evsel->attr.exclude_kernel)
+		if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
+		    !evsel->core.attr.exclude_kernel)
 			return true;
 	}
 	return false;
@@ -721,7 +818,7 @@
 
 static bool intel_pt_have_tsc(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	bool have_tsc = false;
 	u64 config;
 
@@ -729,7 +826,7 @@
 		return false;
 
 	evlist__for_each_entry(pt->session->evlist, evsel) {
-		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+		if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
 			if (config & pt->tsc_bit)
 				have_tsc = true;
 			else
@@ -797,6 +894,7 @@
 
 	params.get_trace = intel_pt_get_trace;
 	params.walk_insn = intel_pt_walk_next_insn;
+	params.lookahead = intel_pt_lookahead;
 	params.data = ptq;
 	params.return_compression = intel_pt_return_compression(pt);
 	params.branch_enable = intel_pt_branch_enable(pt);
@@ -913,6 +1011,28 @@
 		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 void intel_pt_setup_time_range(struct intel_pt *pt,
+				      struct intel_pt_queue *ptq)
+{
+	if (!pt->range_cnt)
+		return;
+
+	ptq->sel_timestamp = pt->time_ranges[0].start;
+	ptq->sel_idx = 0;
+
+	if (ptq->sel_timestamp) {
+		ptq->sel_start = true;
+	} else {
+		ptq->sel_timestamp = pt->time_ranges[0].end;
+		ptq->sel_start = false;
+	}
 }
 
 static int intel_pt_setup_queue(struct intel_pt *pt,
@@ -934,11 +1054,15 @@
 			ptq->cpu = queue->cpu;
 		ptq->tid = queue->tid;
 
+		ptq->cbr_seen = UINT_MAX;
+
 		if (pt->sampling_mode && !pt->snapshot_mode &&
 		    pt->timeless_decoding)
 			ptq->step_through_buffers = true;
 
 		ptq->sync_switch = pt->sync_switch;
+
+		intel_pt_setup_time_range(pt, ptq);
 	}
 
 	if (!ptq->on_heap &&
@@ -953,6 +1077,14 @@
 		intel_pt_log("queue %u getting timestamp\n", queue_nr);
 		intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
 			     queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+
+		if (ptq->sel_start && ptq->sel_timestamp) {
+			ret = intel_pt_fast_forward(ptq->decoder,
+						    ptq->sel_timestamp);
+			if (ret)
+				return ret;
+		}
+
 		while (1) {
 			state = intel_pt_decode(ptq->decoder);
 			if (state->err) {
@@ -972,6 +1104,9 @@
 			     queue_nr, ptq->timestamp);
 		ptq->state = state;
 		ptq->have_sample = true;
+		if (ptq->sel_start && ptq->sel_timestamp &&
+		    ptq->timestamp < ptq->sel_timestamp)
+			ptq->have_sample = false;
 		intel_pt_sample_flags(ptq);
 		ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
 		if (ret)
@@ -1053,28 +1188,48 @@
 	       pt->num_events++ < pt->synth_opts.initial_skip;
 }
 
+/*
+ * Cannot count CBR as skipped because it won't go away until cbr == cbr_seen.
+ * Also ensure CBR is first non-skipped event by allowing for 4 more samples
+ * from this decoder state.
+ */
+static inline bool intel_pt_skip_cbr_event(struct intel_pt *pt)
+{
+	return pt->synth_opts.initial_skip &&
+	       pt->num_events + 4 < pt->synth_opts.initial_skip;
+}
+
+static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
+				   union perf_event *event,
+				   struct perf_sample *sample)
+{
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	sample->pid = ptq->pid;
+	sample->tid = ptq->tid;
+	sample->cpu = ptq->cpu;
+	sample->insn_len = ptq->insn_len;
+	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+}
+
 static void intel_pt_prep_b_sample(struct intel_pt *pt,
 				   struct intel_pt_queue *ptq,
 				   union perf_event *event,
 				   struct perf_sample *sample)
 {
+	intel_pt_prep_a_sample(ptq, event, sample);
+
 	if (!pt->timeless_decoding)
 		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
 	sample->ip = ptq->state->from_ip;
 	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
-	sample->pid = ptq->pid;
-	sample->tid = ptq->tid;
 	sample->addr = ptq->state->to_ip;
 	sample->period = 1;
-	sample->cpu = ptq->cpu;
 	sample->flags = ptq->flags;
-	sample->insn_len = ptq->insn_len;
-	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
 
-	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = sample->cpumode;
-	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
@@ -1147,6 +1302,13 @@
 		sample.branch_stack = (struct branch_stack *)&dummy_bs;
 	}
 
+	sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt;
+	if (sample.cyc_cnt) {
+		sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt;
+		ptq->last_br_insn_cnt = ptq->ipc_insn_cnt;
+		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
+	}
+
 	return intel_pt_deliver_synth_b_event(pt, event, &sample,
 					      pt->branches_sample_type);
 }
@@ -1159,7 +1321,7 @@
 	intel_pt_prep_b_sample(pt, ptq, event, sample);
 
 	if (pt->synth_opts.callchain) {
-		thread_stack__sample(ptq->thread, ptq->chain,
+		thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
 				     pt->synth_opts.callchain_sz + 1,
 				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
@@ -1202,6 +1364,13 @@
 	sample.stream_id = ptq->pt->instructions_id;
 	sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
 
+	sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt;
+	if (sample.cyc_cnt) {
+		sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt;
+		ptq->last_in_insn_cnt = ptq->ipc_insn_cnt;
+		ptq->last_in_cyc_cnt = ptq->ipc_cyc_cnt;
+	}
+
 	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
 
 	return intel_pt_deliver_synth_event(pt, ptq, event, &sample,
@@ -1275,9 +1444,11 @@
 	struct perf_synth_intel_cbr raw;
 	u32 flags;
 
-	if (intel_pt_skip_event(pt))
+	if (intel_pt_skip_cbr_event(pt))
 		return 0;
 
+	ptq->cbr_seen = ptq->state->cbr;
+
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->cbr_id;
@@ -1395,8 +1566,263 @@
 					    pt->pwr_events_sample_type);
 }
 
+/*
+ * PEBS gp_regs array indexes plus 1 so that 0 means not present. Refer
+ * intel_pt_add_gp_regs().
+ */
+static const int pebs_gp_regs[] = {
+	[PERF_REG_X86_FLAGS]	= 1,
+	[PERF_REG_X86_IP]	= 2,
+	[PERF_REG_X86_AX]	= 3,
+	[PERF_REG_X86_CX]	= 4,
+	[PERF_REG_X86_DX]	= 5,
+	[PERF_REG_X86_BX]	= 6,
+	[PERF_REG_X86_SP]	= 7,
+	[PERF_REG_X86_BP]	= 8,
+	[PERF_REG_X86_SI]	= 9,
+	[PERF_REG_X86_DI]	= 10,
+	[PERF_REG_X86_R8]	= 11,
+	[PERF_REG_X86_R9]	= 12,
+	[PERF_REG_X86_R10]	= 13,
+	[PERF_REG_X86_R11]	= 14,
+	[PERF_REG_X86_R12]	= 15,
+	[PERF_REG_X86_R13]	= 16,
+	[PERF_REG_X86_R14]	= 17,
+	[PERF_REG_X86_R15]	= 18,
+};
+
+static u64 *intel_pt_add_gp_regs(struct regs_dump *intr_regs, u64 *pos,
+				 const struct intel_pt_blk_items *items,
+				 u64 regs_mask)
+{
+	const u64 *gp_regs = items->val[INTEL_PT_GP_REGS_POS];
+	u32 mask = items->mask[INTEL_PT_GP_REGS_POS];
+	u32 bit;
+	int i;
+
+	for (i = 0, bit = 1; i < PERF_REG_X86_64_MAX; i++, bit <<= 1) {
+		/* Get the PEBS gp_regs array index */
+		int n = pebs_gp_regs[i] - 1;
+
+		if (n < 0)
+			continue;
+		/*
+		 * Add only registers that were requested (i.e. 'regs_mask') and
+		 * that were provided (i.e. 'mask'), and update the resulting
+		 * mask (i.e. 'intr_regs->mask') accordingly.
+		 */
+		if (mask & 1 << n && regs_mask & bit) {
+			intr_regs->mask |= bit;
+			*pos++ = gp_regs[n];
+		}
+	}
+
+	return pos;
+}
+
+#ifndef PERF_REG_X86_XMM0
+#define PERF_REG_X86_XMM0 32
+#endif
+
+static void intel_pt_add_xmm(struct regs_dump *intr_regs, u64 *pos,
+			     const struct intel_pt_blk_items *items,
+			     u64 regs_mask)
+{
+	u32 mask = items->has_xmm & (regs_mask >> PERF_REG_X86_XMM0);
+	const u64 *xmm = items->xmm;
+
+	/*
+	 * If there are any XMM registers, then there should be all of them.
+	 * Nevertheless, follow the logic to add only registers that were
+	 * requested (i.e. 'regs_mask') and that were provided (i.e. 'mask'),
+	 * and update the resulting mask (i.e. 'intr_regs->mask') accordingly.
+	 */
+	intr_regs->mask |= (u64)mask << PERF_REG_X86_XMM0;
+
+	for (; mask; mask >>= 1, xmm++) {
+		if (mask & 1)
+			*pos++ = *xmm;
+	}
+}
+
+#define LBR_INFO_MISPRED	(1ULL << 63)
+#define LBR_INFO_IN_TX		(1ULL << 62)
+#define LBR_INFO_ABORT		(1ULL << 61)
+#define LBR_INFO_CYCLES		0xffff
+
+/* Refer kernel's intel_pmu_store_pebs_lbrs() */
+static u64 intel_pt_lbr_flags(u64 info)
+{
+	union {
+		struct branch_flags flags;
+		u64 result;
+	} u = {
+		.flags = {
+			.mispred	= !!(info & LBR_INFO_MISPRED),
+			.predicted	= !(info & LBR_INFO_MISPRED),
+			.in_tx		= !!(info & LBR_INFO_IN_TX),
+			.abort		= !!(info & LBR_INFO_ABORT),
+			.cycles		= info & LBR_INFO_CYCLES,
+		}
+	};
+
+	return u.result;
+}
+
+static void intel_pt_add_lbrs(struct branch_stack *br_stack,
+			      const struct intel_pt_blk_items *items)
+{
+	u64 *to;
+	int i;
+
+	br_stack->nr = 0;
+
+	to = &br_stack->entries[0].from;
+
+	for (i = INTEL_PT_LBR_0_POS; i <= INTEL_PT_LBR_2_POS; i++) {
+		u32 mask = items->mask[i];
+		const u64 *from = items->val[i];
+
+		for (; mask; mask >>= 3, from += 3) {
+			if ((mask & 7) == 7) {
+				*to++ = from[0];
+				*to++ = from[1];
+				*to++ = intel_pt_lbr_flags(from[2]);
+				br_stack->nr += 1;
+			}
+		}
+	}
+}
+
+/* INTEL_PT_LBR_0, INTEL_PT_LBR_1 and INTEL_PT_LBR_2 */
+#define LBRS_MAX (INTEL_PT_BLK_ITEM_ID_CNT * 3)
+
+static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
+{
+	const struct intel_pt_blk_items *items = &ptq->state->items;
+	struct perf_sample sample = { .ip = 0, };
+	union perf_event *event = ptq->event_buf;
+	struct intel_pt *pt = ptq->pt;
+	struct evsel *evsel = pt->pebs_evsel;
+	u64 sample_type = evsel->core.attr.sample_type;
+	u64 id = evsel->core.id[0];
+	u8 cpumode;
+
+	if (intel_pt_skip_event(pt))
+		return 0;
+
+	intel_pt_prep_a_sample(ptq, event, &sample);
+
+	sample.id = id;
+	sample.stream_id = id;
+
+	if (!evsel->core.attr.freq)
+		sample.period = evsel->core.attr.sample_period;
+
+	/* No support for non-zero CS base */
+	if (items->has_ip)
+		sample.ip = items->ip;
+	else if (items->has_rip)
+		sample.ip = items->rip;
+	else
+		sample.ip = ptq->state->from_ip;
+
+	/* No support for guest mode at this time */
+	cpumode = sample.ip < ptq->pt->kernel_start ?
+		  PERF_RECORD_MISC_USER :
+		  PERF_RECORD_MISC_KERNEL;
+
+	event->sample.header.misc = cpumode | PERF_RECORD_MISC_EXACT_IP;
+
+	sample.cpumode = cpumode;
+
+	if (sample_type & PERF_SAMPLE_TIME) {
+		u64 timestamp = 0;
+
+		if (items->has_timestamp)
+			timestamp = items->timestamp;
+		else if (!pt->timeless_decoding)
+			timestamp = ptq->timestamp;
+		if (timestamp)
+			sample.time = tsc_to_perf_time(timestamp, &pt->tc);
+	}
+
+	if (sample_type & PERF_SAMPLE_CALLCHAIN &&
+	    pt->synth_opts.callchain) {
+		thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
+				     pt->synth_opts.callchain_sz, sample.ip,
+				     pt->kernel_start);
+		sample.callchain = ptq->chain;
+	}
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR &&
+	    items->mask[INTEL_PT_GP_REGS_POS]) {
+		u64 regs[sizeof(sample.intr_regs.mask)];
+		u64 regs_mask = evsel->core.attr.sample_regs_intr;
+		u64 *pos;
+
+		sample.intr_regs.abi = items->is_32_bit ?
+				       PERF_SAMPLE_REGS_ABI_32 :
+				       PERF_SAMPLE_REGS_ABI_64;
+		sample.intr_regs.regs = regs;
+
+		pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask);
+
+		intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
+	}
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		struct {
+			struct branch_stack br_stack;
+			struct branch_entry entries[LBRS_MAX];
+		} br;
+
+		if (items->mask[INTEL_PT_LBR_0_POS] ||
+		    items->mask[INTEL_PT_LBR_1_POS] ||
+		    items->mask[INTEL_PT_LBR_2_POS]) {
+			intel_pt_add_lbrs(&br.br_stack, items);
+			sample.branch_stack = &br.br_stack;
+		} else if (pt->synth_opts.last_branch) {
+			intel_pt_copy_last_branch_rb(ptq);
+			sample.branch_stack = ptq->last_branch;
+		} else {
+			br.br_stack.nr = 0;
+			sample.branch_stack = &br.br_stack;
+		}
+	}
+
+	if (sample_type & PERF_SAMPLE_ADDR && items->has_mem_access_address)
+		sample.addr = items->mem_access_address;
+
+	if (sample_type & PERF_SAMPLE_WEIGHT) {
+		/*
+		 * Refer kernel's setup_pebs_adaptive_sample_data() and
+		 * intel_hsw_weight().
+		 */
+		if (items->has_mem_access_latency)
+			sample.weight = items->mem_access_latency;
+		if (!sample.weight && items->has_tsx_aux_info) {
+			/* Cycles last block */
+			sample.weight = (u32)items->tsx_aux_info;
+		}
+	}
+
+	if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
+		u64 ax = items->has_rax ? items->rax : 0;
+		/* Refer kernel's intel_hsw_transaction() */
+		u64 txn = (u8)(items->tsx_aux_info >> 32);
+
+		/* For RTM XABORTs also log the abort code from AX */
+		if (txn & PERF_TXN_TRANSACTION && ax & 1)
+			txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+		sample.transaction = txn;
+	}
+
+	return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
+}
+
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
-				pid_t pid, pid_t tid, u64 ip)
+				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
 	union perf_event event;
 	char msg[MAX_AUXTRACE_ERROR_MSG];
@@ -1405,7 +1831,7 @@
 	intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
 
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
-			     code, cpu, pid, tid, ip, msg);
+			     code, cpu, pid, tid, ip, msg, timestamp);
 
 	err = perf_session__deliver_synth_event(pt->session, &event, NULL);
 	if (err)
@@ -1415,6 +1841,18 @@
 	return err;
 }
 
+static int intel_ptq_synth_error(struct intel_pt_queue *ptq,
+				 const struct intel_pt_state *state)
+{
+	struct intel_pt *pt = ptq->pt;
+	u64 tm = ptq->timestamp;
+
+	tm = pt->timeless_decoding ? 0 : tsc_to_perf_time(tm, &pt->tc);
+
+	return intel_pt_synth_error(pt, state->err, ptq->cpu, ptq->pid,
+				    ptq->tid, state->from_ip, tm);
+}
+
 static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
 {
 	struct auxtrace_queue *queue;
@@ -1447,8 +1885,7 @@
 }
 
 #define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \
-			  INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \
-			  INTEL_PT_CBR_CHG)
+			  INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT)
 
 static int intel_pt_sample(struct intel_pt_queue *ptq)
 {
@@ -1461,31 +1898,52 @@
 
 	ptq->have_sample = false;
 
-	if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) {
-		if (state->type & INTEL_PT_CBR_CHG) {
+	if (ptq->state->tot_cyc_cnt > ptq->ipc_cyc_cnt) {
+		/*
+		 * Cycle count and instruction count only go together to create
+		 * a valid IPC ratio when the cycle count changes.
+		 */
+		ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt;
+		ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt;
+	}
+
+	/*
+	 * Do PEBS first to allow for the possibility that the PEBS timestamp
+	 * precedes the current timestamp.
+	 */
+	if (pt->sample_pebs && state->type & INTEL_PT_BLK_ITEMS) {
+		err = intel_pt_synth_pebs_sample(ptq);
+		if (err)
+			return err;
+	}
+
+	if (pt->sample_pwr_events) {
+		if (ptq->state->cbr != ptq->cbr_seen) {
 			err = intel_pt_synth_cbr_sample(ptq);
 			if (err)
 				return err;
 		}
-		if (state->type & INTEL_PT_MWAIT_OP) {
-			err = intel_pt_synth_mwait_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_PWR_ENTRY) {
-			err = intel_pt_synth_pwre_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_EX_STOP) {
-			err = intel_pt_synth_exstop_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_PWR_EXIT) {
-			err = intel_pt_synth_pwrx_sample(ptq);
-			if (err)
-				return err;
+		if (state->type & INTEL_PT_PWR_EVT) {
+			if (state->type & INTEL_PT_MWAIT_OP) {
+				err = intel_pt_synth_mwait_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_PWR_ENTRY) {
+				err = intel_pt_synth_pwre_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_EX_STOP) {
+				err = intel_pt_synth_exstop_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_PWR_EXIT) {
+				err = intel_pt_synth_pwrx_sample(ptq);
+				if (err)
+					return err;
+			}
 		}
 	}
 
@@ -1511,11 +1969,11 @@
 		return 0;
 
 	if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
-		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
+		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
 	else
-		thread_stack__set_trace_nr(ptq->thread, state->trace_nr);
+		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);
@@ -1623,10 +2081,83 @@
 	}
 }
 
+/*
+ * To filter against time ranges, it is only necessary to look at the next start
+ * or end time.
+ */
+static bool intel_pt_next_time(struct intel_pt_queue *ptq)
+{
+	struct intel_pt *pt = ptq->pt;
+
+	if (ptq->sel_start) {
+		/* Next time is an end time */
+		ptq->sel_start = false;
+		ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].end;
+		return true;
+	} else if (ptq->sel_idx + 1 < pt->range_cnt) {
+		/* Next time is a start time */
+		ptq->sel_start = true;
+		ptq->sel_idx += 1;
+		ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].start;
+		return true;
+	}
+
+	/* No next time */
+	return false;
+}
+
+static int intel_pt_time_filter(struct intel_pt_queue *ptq, u64 *ff_timestamp)
+{
+	int err;
+
+	while (1) {
+		if (ptq->sel_start) {
+			if (ptq->timestamp >= ptq->sel_timestamp) {
+				/* After start time, so consider next time */
+				intel_pt_next_time(ptq);
+				if (!ptq->sel_timestamp) {
+					/* No end time */
+					return 0;
+				}
+				/* Check against end time */
+				continue;
+			}
+			/* Before start time, so fast forward */
+			ptq->have_sample = false;
+			if (ptq->sel_timestamp > *ff_timestamp) {
+				if (ptq->sync_switch) {
+					intel_pt_next_tid(ptq->pt, ptq);
+					ptq->switch_state = INTEL_PT_SS_UNKNOWN;
+				}
+				*ff_timestamp = ptq->sel_timestamp;
+				err = intel_pt_fast_forward(ptq->decoder,
+							    ptq->sel_timestamp);
+				if (err)
+					return err;
+			}
+			return 0;
+		} else if (ptq->timestamp > ptq->sel_timestamp) {
+			/* After end time, so consider next time */
+			if (!intel_pt_next_time(ptq)) {
+				/* No next time range, so stop decoding */
+				ptq->have_sample = false;
+				ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
+				return 1;
+			}
+			/* Check against next start time */
+			continue;
+		} else {
+			/* Before end time */
+			return 0;
+		}
+	}
+}
+
 static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 {
 	const struct intel_pt_state *state = ptq->state;
 	struct intel_pt *pt = ptq->pt;
+	u64 ff_timestamp = 0;
 	int err;
 
 	if (!pt->kernel_start) {
@@ -1661,10 +2192,7 @@
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {
-				err = intel_pt_synth_error(pt, state->err,
-							   ptq->cpu, ptq->pid,
-							   ptq->tid,
-							   state->from_ip);
+				err = intel_ptq_synth_error(ptq, state);
 				if (err)
 					return err;
 			}
@@ -1694,6 +2222,12 @@
 			ptq->timestamp = state->timestamp;
 		}
 
+		if (ptq->sel_timestamp) {
+			err = intel_pt_time_filter(ptq, &ff_timestamp);
+			if (err)
+				return err;
+		}
+
 		if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
 			*timestamp = ptq->timestamp;
 			return 0;
@@ -1789,7 +2323,7 @@
 static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
 {
 	return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
-				    sample->pid, sample->tid, 0);
+				    sample->pid, sample->tid, 0, sample->time);
 }
 
 static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
@@ -1835,7 +2369,6 @@
 
 	switch (ptq->switch_state) {
 	case INTEL_PT_SS_NOT_TRACING:
-		ptq->next_tid = -1;
 		break;
 	case INTEL_PT_SS_UNKNOWN:
 	case INTEL_PT_SS_TRACING:
@@ -1855,20 +2388,21 @@
 		ptq->switch_state = INTEL_PT_SS_TRACING;
 		break;
 	case INTEL_PT_SS_EXPECTING_SWITCH_IP:
-		ptq->next_tid = tid;
 		intel_pt_log("ERROR: cpu %d expecting switch ip\n", cpu);
 		break;
 	default:
 		break;
 	}
 
+	ptq->next_tid = -1;
+
 	return 1;
 }
 
 static int intel_pt_process_switch(struct intel_pt *pt,
 				   struct perf_sample *sample)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	pid_t tid;
 	int cpu, ret;
 
@@ -1890,6 +2424,44 @@
 	return machine__set_current_tid(pt->machine, cpu, -1, tid);
 }
 
+static int intel_pt_context_switch_in(struct intel_pt *pt,
+				      struct perf_sample *sample)
+{
+	pid_t pid = sample->pid;
+	pid_t tid = sample->tid;
+	int cpu = sample->cpu;
+
+	if (pt->sync_switch) {
+		struct intel_pt_queue *ptq;
+
+		ptq = intel_pt_cpu_to_ptq(pt, cpu);
+		if (ptq && ptq->sync_switch) {
+			ptq->next_tid = -1;
+			switch (ptq->switch_state) {
+			case INTEL_PT_SS_NOT_TRACING:
+			case INTEL_PT_SS_UNKNOWN:
+			case INTEL_PT_SS_TRACING:
+				break;
+			case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
+			case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+				ptq->switch_state = INTEL_PT_SS_TRACING;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If the current tid has not been updated yet, ensure it is now that
+	 * a "switch in" event has occurred.
+	 */
+	if (machine__get_current_tid(pt->machine, cpu) == tid)
+		return 0;
+
+	return machine__set_current_tid(pt->machine, cpu, pid, tid);
+}
+
 static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
 				   struct perf_sample *sample)
 {
@@ -1901,7 +2473,7 @@
 
 	if (pt->have_sched_switch == 3) {
 		if (!out)
-			return 0;
+			return intel_pt_context_switch_in(pt, sample);
 		if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
 			pr_err("Expecting CPU-wide context switch event\n");
 			return -EINVAL;
@@ -2005,9 +2577,9 @@
 		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
 		err = intel_pt_context_switch(pt, event, sample);
 
-	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     perf_event__name(event->header.type), event->header.type,
-		     sample->cpu, sample->time, timestamp);
+	intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+		     event->header.type, sample->cpu, sample->time, timestamp);
+	intel_pt_log_event(event);
 
 	return err;
 }
@@ -2061,6 +2633,7 @@
 	thread__put(pt->unknown_thread);
 	addr_filters__exit(&pt->filts);
 	zfree(&pt->filter);
+	zfree(&pt->time_ranges);
 	free(pt);
 }
 
@@ -2141,13 +2714,13 @@
 	return err;
 }
 
-static void intel_pt_set_event_name(struct perf_evlist *evlist, u64 id,
+static void intel_pt_set_event_name(struct evlist *evlist, u64 id,
 				    const char *name)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->id && evsel->id[0] == id) {
+		if (evsel->core.id && evsel->core.id[0] == id) {
 			if (evsel->name)
 				zfree(&evsel->name);
 			evsel->name = strdup(name);
@@ -2156,13 +2729,13 @@
 	}
 }
 
-static struct perf_evsel *intel_pt_evsel(struct intel_pt *pt,
-					 struct perf_evlist *evlist)
+static struct evsel *intel_pt_evsel(struct intel_pt *pt,
+					 struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type == pt->pmu_type && evsel->ids)
+		if (evsel->core.attr.type == pt->pmu_type && evsel->core.ids)
 			return evsel;
 	}
 
@@ -2172,8 +2745,8 @@
 static int intel_pt_synth_events(struct intel_pt *pt,
 				 struct perf_session *session)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct perf_evsel *evsel = intel_pt_evsel(pt, evlist);
+	struct evlist *evlist = session->evlist;
+	struct evsel *evsel = intel_pt_evsel(pt, evlist);
 	struct perf_event_attr attr;
 	u64 id;
 	int err;
@@ -2186,7 +2759,7 @@
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD;
 	if (pt->timeless_decoding)
@@ -2195,15 +2768,15 @@
 		attr.sample_type |= PERF_SAMPLE_TIME;
 	if (!pt->per_cpu_mmaps)
 		attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
-	attr.exclude_user = evsel->attr.exclude_user;
-	attr.exclude_kernel = evsel->attr.exclude_kernel;
-	attr.exclude_hv = evsel->attr.exclude_hv;
-	attr.exclude_host = evsel->attr.exclude_host;
-	attr.exclude_guest = evsel->attr.exclude_guest;
-	attr.sample_id_all = evsel->attr.sample_id_all;
-	attr.read_format = evsel->attr.read_format;
+	attr.exclude_user = evsel->core.attr.exclude_user;
+	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
+	attr.exclude_hv = evsel->core.attr.exclude_hv;
+	attr.exclude_host = evsel->core.attr.exclude_host;
+	attr.exclude_guest = evsel->core.attr.exclude_guest;
+	attr.sample_id_all = evsel->core.attr.sample_id_all;
+	attr.read_format = evsel->core.attr.read_format;
 
-	id = evsel->id[0] + 1000000000;
+	id = evsel->core.id[0] + 1000000000;
 	if (!id)
 		id = 1;
 
@@ -2285,7 +2858,7 @@
 		id += 1;
 	}
 
-	if (pt->synth_opts.pwr_events && (evsel->attr.config & 0x10)) {
+	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) {
 		attr.config = PERF_SYNTH_INTEL_MWAIT;
 		err = intel_pt_synth_event(session, "mwait", &attr, id);
 		if (err)
@@ -2322,9 +2895,25 @@
 	return 0;
 }
 
-static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
+static void intel_pt_setup_pebs_events(struct intel_pt *pt)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
+
+	if (!pt->synth_opts.other_events)
+		return;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (evsel->core.attr.aux_output && evsel->core.id) {
+			pt->sample_pebs = true;
+			pt->pebs_evsel = evsel;
+			return;
+		}
+	}
+}
+
+static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
+{
+	struct evsel *evsel;
 
 	evlist__for_each_entry_reverse(evlist, evsel) {
 		const char *name = perf_evsel__name(evsel);
@@ -2336,12 +2925,12 @@
 	return NULL;
 }
 
-static bool intel_pt_find_switch(struct perf_evlist *evlist)
+static bool intel_pt_find_switch(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.context_switch)
+		if (evsel->core.attr.context_switch)
 			return true;
 	}
 
@@ -2358,6 +2947,85 @@
 	return 0;
 }
 
+/* Find least TSC which converts to ns or later */
+static u64 intel_pt_tsc_start(u64 ns, struct intel_pt *pt)
+{
+	u64 tsc, tm;
+
+	tsc = perf_time_to_tsc(ns, &pt->tc);
+
+	while (1) {
+		tm = tsc_to_perf_time(tsc, &pt->tc);
+		if (tm < ns)
+			break;
+		tsc -= 1;
+	}
+
+	while (tm < ns)
+		tm = tsc_to_perf_time(++tsc, &pt->tc);
+
+	return tsc;
+}
+
+/* Find greatest TSC which converts to ns or earlier */
+static u64 intel_pt_tsc_end(u64 ns, struct intel_pt *pt)
+{
+	u64 tsc, tm;
+
+	tsc = perf_time_to_tsc(ns, &pt->tc);
+
+	while (1) {
+		tm = tsc_to_perf_time(tsc, &pt->tc);
+		if (tm > ns)
+			break;
+		tsc += 1;
+	}
+
+	while (tm > ns)
+		tm = tsc_to_perf_time(--tsc, &pt->tc);
+
+	return tsc;
+}
+
+static int intel_pt_setup_time_ranges(struct intel_pt *pt,
+				      struct itrace_synth_opts *opts)
+{
+	struct perf_time_interval *p = opts->ptime_range;
+	int n = opts->range_num;
+	int i;
+
+	if (!n || !p || pt->timeless_decoding)
+		return 0;
+
+	pt->time_ranges = calloc(n, sizeof(struct range));
+	if (!pt->time_ranges)
+		return -ENOMEM;
+
+	pt->range_cnt = n;
+
+	intel_pt_log("%s: %u range(s)\n", __func__, n);
+
+	for (i = 0; i < n; i++) {
+		struct range *r = &pt->time_ranges[i];
+		u64 ts = p[i].start;
+		u64 te = p[i].end;
+
+		/*
+		 * Take care to ensure the TSC range matches the perf-time range
+		 * when converted back to perf-time.
+		 */
+		r->start = ts ? intel_pt_tsc_start(ts, pt) : 0;
+		r->end   = te ? intel_pt_tsc_end(te, pt) : 0;
+
+		intel_pt_log("range %d: perf time interval: %"PRIu64" to %"PRIu64"\n",
+			     i, ts, te);
+		intel_pt_log("range %d: TSC time interval: %#"PRIx64" to %#"PRIx64"\n",
+			     i, r->start, r->end);
+	}
+
+	return 0;
+}
+
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
@@ -2377,7 +3045,7 @@
 	[INTEL_PT_FILTER_STR_LEN]	= "  Filter string len.  %"PRIu64"\n",
 };
 
-static void intel_pt_print_info(u64 *arr, int start, int finish)
+static void intel_pt_print_info(__u64 *arr, int start, int finish)
 {
 	int i;
 
@@ -2396,23 +3064,23 @@
 	fprintf(stdout, "  %-20s%s\n", name, str ? str : "");
 }
 
-static bool intel_pt_has(struct auxtrace_info_event *auxtrace_info, int pos)
+static bool intel_pt_has(struct perf_record_auxtrace_info *auxtrace_info, int pos)
 {
 	return auxtrace_info->header.size >=
-		sizeof(struct auxtrace_info_event) + (sizeof(u64) * (pos + 1));
+		sizeof(struct perf_record_auxtrace_info) + (sizeof(u64) * (pos + 1));
 }
 
 int intel_pt_process_auxtrace_info(union perf_event *event,
 				   struct perf_session *session)
 {
-	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
 	struct intel_pt *pt;
 	void *info_end;
-	u64 *info;
+	__u64 *info;
 	int err;
 
-	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
 					min_sz)
 		return -EINVAL;
 
@@ -2507,6 +3175,8 @@
 	}
 
 	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
+	if (pt->timeless_decoding && !pt->tc.time_mult)
+		pt->tc.time_mult = 1;
 	pt->have_tsc = intel_pt_have_tsc(pt);
 	pt->sampling_mode = false;
 	pt->est_tsc = !pt->timeless_decoding;
@@ -2557,16 +3227,17 @@
 		goto err_delete_thread;
 	}
 
-	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+	if (session->itrace_synth_opts->set) {
 		pt->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&pt->synth_opts);
-		if (use_browser != -1) {
+		itrace_synth_opts__set_default(&pt->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
+		if (!session->itrace_synth_opts->default_no_sample &&
+		    !session->itrace_synth_opts->inject) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
 		}
-		if (session->itrace_synth_opts)
-			pt->synth_opts.thread_stack =
+		pt->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
 	}
 
@@ -2586,6 +3257,10 @@
 		pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000;
 	}
 
+	err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
+	if (err)
+		goto err_delete_thread;
+
 	if (pt->synth_opts.calls)
 		pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
 				       PERF_IP_FLAG_TRACE_END;
@@ -2605,6 +3280,8 @@
 	if (err)
 		goto err_delete_thread;
 
+	intel_pt_setup_pebs_events(pt);
+
 	err = auxtrace_queues__process_index(&pt->queues, session);
 	if (err)
 		goto err_delete_thread;
@@ -2626,6 +3303,7 @@
 err_free:
 	addr_filters__exit(&pt->filts);
 	zfree(&pt->filter);
+	zfree(&pt->time_ranges);
 	free(pt);
 	return err;
 }
diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h
index e13b14e..c7d6068 100644
--- a/tools/perf/util/intel-pt.h
+++ b/tools/perf/util/intel-pt.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * intel_pt.h: Intel Processor Trace support
  * Copyright (c) 2013-2015, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef INCLUDE__PERF_INTEL_PT_H__
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
index 89715b6..84e5304 100644
--- a/tools/perf/util/intlist.c
+++ b/tools/perf/util/intlist.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on intlist.c by:
  * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Licensed under the GPLv2.
  */
 
 #include <errno.h>
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 85bab87..5c19ee0 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -45,7 +45,7 @@
 /* For intlist iteration */
 static inline struct int_node *intlist__first(struct intlist *ilist)
 {
-	struct rb_node *rn = rb_first(&ilist->rblist.entries);
+	struct rb_node *rn = rb_first_cached(&ilist->rblist.entries);
 	return rn ? rb_entry(rn, struct int_node, rb_node) : NULL;
 }
 static inline struct int_node *intlist__next(struct int_node *in)
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index a186300..e3ccb0c 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -2,6 +2,7 @@
 #include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <errno.h>
+#include <libgen.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -13,7 +14,7 @@
 #include <sys/mman.h>
 #include <linux/stringify.h>
 
-#include "util.h"
+#include "build-id.h"
 #include "event.h"
 #include "debug.h"
 #include "evlist.h"
@@ -25,9 +26,9 @@
 #include "jit.h"
 #include "jitdump.h"
 #include "genelf.h"
-#include "../builtin.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 struct jit_buf_desc {
 	struct perf_data *output;
@@ -38,7 +39,7 @@
 	uint64_t	 sample_type;
 	size_t           bufsize;
 	FILE             *in;
-	bool		 needs_bswap; /* handles cross-endianess */
+	bool		 needs_bswap; /* handles cross-endianness */
 	bool		 use_arch_timestamp;
 	void		 *debug_data;
 	void		 *unwinding_data;
@@ -116,13 +117,13 @@
 static int
 jit_validate_events(struct perf_session *session)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	/*
 	 * check that all events use CLOCK_MONOTONIC
 	 */
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+		if (evsel->core.attr.use_clockid == 0 || evsel->core.attr.clockid != CLOCK_MONOTONIC)
 			return -1;
 	}
 	return 0;
@@ -394,7 +395,7 @@
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -417,7 +418,7 @@
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -430,14 +431,12 @@
 			   jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size);
 
 	if (jd->debug_data && jd->nr_debug_entries) {
-		free(jd->debug_data);
-		jd->debug_data = NULL;
+		zfree(&jd->debug_data);
 		jd->nr_debug_entries = 0;
 	}
 
 	if (jd->unwinding_data && jd->eh_frame_hdr_size) {
-		free(jd->unwinding_data);
-		jd->unwinding_data = NULL;
+		zfree(&jd->unwinding_data);
 		jd->eh_frame_hdr_size = 0;
 		jd->unwinding_mapped_size = 0;
 		jd->unwinding_size = 0;
@@ -530,7 +529,7 @@
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
@@ -758,7 +757,7 @@
 	    pid_t pid,
 	    u64 *nbytes)
 {
-	struct perf_evsel *first;
+	struct evsel *first;
 	struct jit_buf_desc jd;
 	int ret;
 
@@ -778,8 +777,8 @@
 	 * track sample_type to compute id_all layout
 	 * perf sets the same sample type to all events as of now
 	 */
-	first = perf_evlist__first(session->evlist);
-	jd.sample_type = first->attr.sample_type;
+	first = evlist__first(session->evlist);
+	jd.sample_type = first->core.attr.sample_type;
 
 	*nbytes = 0;
 
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
index c6b9b67..f2c3823 100644
--- a/tools/perf/util/jitdump.h
+++ b/tools/perf/util/jitdump.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * jitdump.h: jitted code info encapsulation file format
  *
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 7b1f065..6f0fa05 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -2,12 +2,15 @@
 #ifndef __PERF_KVM_STAT_H
 #define __PERF_KVM_STAT_H
 
-#include "../perf.h"
-#include "evsel.h"
-#include "evlist.h"
-#include "session.h"
+#ifdef HAVE_KVM_STAT_SUPPORT
+
 #include "tool.h"
 #include "stat.h"
+#include "record.h"
+
+struct evsel;
+struct evlist;
+struct perf_session;
 
 struct event_key {
 	#define INVALID_KEY     (~0ULL)
@@ -44,17 +47,17 @@
 struct perf_kvm_stat;
 
 struct child_event_ops {
-	void (*get_key)(struct perf_evsel *evsel,
+	void (*get_key)(struct evsel *evsel,
 			struct perf_sample *sample,
 			struct event_key *key);
 	const char *name;
 };
 
 struct kvm_events_ops {
-	bool (*is_begin_event)(struct perf_evsel *evsel,
+	bool (*is_begin_event)(struct evsel *evsel,
 			       struct perf_sample *sample,
 			       struct event_key *key);
-	bool (*is_end_event)(struct perf_evsel *evsel,
+	bool (*is_end_event)(struct evsel *evsel,
 			     struct perf_sample *sample, struct event_key *key);
 	struct child_event_ops *child_ops;
 	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
@@ -73,7 +76,7 @@
 struct perf_kvm_stat {
 	struct perf_tool    tool;
 	struct record_opts  opts;
-	struct perf_evlist  *evlist;
+	struct evlist  *evlist;
 	struct perf_session *session;
 
 	const char *file_name;
@@ -108,21 +111,21 @@
 	struct kvm_events_ops *ops;
 };
 
-void exit_event_get_key(struct perf_evsel *evsel,
+void exit_event_get_key(struct evsel *evsel,
 			struct perf_sample *sample,
 			struct event_key *key);
-bool exit_event_begin(struct perf_evsel *evsel,
+bool exit_event_begin(struct evsel *evsel,
 		      struct perf_sample *sample,
 		      struct event_key *key);
-bool exit_event_end(struct perf_evsel *evsel,
+bool exit_event_end(struct evsel *evsel,
 		    struct perf_sample *sample,
 		    struct event_key *key);
 void exit_event_decode_key(struct perf_kvm_stat *kvm,
 			   struct event_key *key,
 			   char *decode);
 
-bool kvm_exit_event(struct perf_evsel *evsel);
-bool kvm_entry_event(struct perf_evsel *evsel);
+bool kvm_exit_event(struct evsel *evsel);
+bool kvm_entry_event(struct evsel *evsel);
 int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)	\
@@ -143,5 +146,7 @@
 extern const char *kvm_exit_reason;
 extern const char *kvm_entry_trace;
 extern const char *kvm_exit_trace;
+#endif /* HAVE_KVM_STAT_SUPPORT */
 
+extern int kvm_add_default_arch_event(int *argc, const char **argv);
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 66756e6..6b4e5a0 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -22,7 +22,6 @@
 #define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
 
 #include "unwind.h"
-#include "debug.h"
 #include "libunwind-aarch64.h"
 #include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
 #include "../../arch/arm64/util/unwind-libunwind.c"
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index c5e5681..21c216c 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -22,7 +22,6 @@
 #define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
 #include "unwind.h"
-#include "debug.h"
 #include "libunwind-x86.h"
 #include <../../../../arch/x86/include/uapi/asm/perf_regs.h>
 
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 19262f9..8b14e4a 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -8,7 +8,10 @@
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <unistd.h>
 #include <linux/err.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include "debug.h"
 #include "llvm-utils.h"
 #include "config.h"
@@ -19,7 +22,7 @@
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
+		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
@@ -230,14 +233,14 @@
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
@@ -352,8 +355,7 @@
 "     \toption in [llvm] to \"\" to suppress this detection.\n\n",
 			*kbuild_dir);
 
-		free(*kbuild_dir);
-		*kbuild_dir = NULL;
+		zfree(kbuild_dir);
 		goto errout;
 	}
 
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index bf3f3f4..7878a0e 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -6,7 +6,7 @@
 #ifndef __LLVM_UTILS_H
 #define __LLVM_UTILS_H
 
-#include "debug.h"
+#include <stdbool.h>
 
 struct llvm_param {
 	/* Path of clang executable */
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index b1dd29a..39062df 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -7,9 +7,10 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include "compress.h"
-#include "util.h"
 #include "debug.h"
+#include <string.h>
 #include <unistd.h>
+#include <internal/lib.h>
 
 #define BUFSIZE 8192
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8ee8ab3..70a9f87 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -3,16 +3,26 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include <stdlib.h>
 #include "callchain.h"
 #include "debug.h"
+#include "dso.h"
+#include "env.h"
 #include "event.h"
 #include "evsel.h"
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "map_symbol.h"
+#include "branch.h"
+#include "mem-events.h"
+#include "srcline.h"
+#include "symbol.h"
 #include "sort.h"
 #include "strlist.h"
+#include "target.h"
 #include "thread.h"
+#include "util.h"
 #include "vdso.h"
 #include <stdbool.h>
 #include <sys/types.h>
@@ -21,10 +31,14 @@
 #include "unwind.h"
 #include "linux/hash.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
+#include <internal/lib.h> // page_size
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 #include <symbol/kallsyms.h>
 #include <linux/mman.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -41,7 +55,7 @@
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
-		threads->entries = RB_ROOT;
+		threads->entries = RB_ROOT_CACHED;
 		init_rwsem(&threads->lock);
 		threads->nr = 0;
 		INIT_LIST_HEAD(&threads->dead);
@@ -137,7 +151,7 @@
 	struct machine *machine = machine__new_host();
 	/*
 	 * FIXME:
-	 * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely
+	 * 1) We should switch to machine__load_kallsyms(), i.e. not explicitly
 	 *    ask for not using the kcore parsing code, once this one is fixed
 	 *    to create a map per module.
 	 */
@@ -179,7 +193,7 @@
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
 		down_write(&threads->lock);
-		nd = rb_first(&threads->entries);
+		nd = rb_first_cached(&threads->entries);
 		while (nd) {
 			struct thread *t = rb_entry(nd, struct thread, rb_node);
 
@@ -207,6 +221,18 @@
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		struct threads *threads = &machine->threads[i];
+		struct thread *thread, *n;
+		/*
+		 * Forget about the dead, at this point whatever threads were
+		 * left in the dead lists better have a reference count taken
+		 * by who is using them, and then, when they drop those references
+		 * and it finally hits zero, thread__put() will check and see that
+		 * its not in the dead threads list and will not try to remove it
+		 * from there, just calling thread__delete() straight away.
+		 */
+		list_for_each_entry_safe(thread, n, &threads->dead, node)
+			list_del_init(&thread->node);
+
 		exit_rwsem(&threads->lock);
 	}
 }
@@ -222,7 +248,7 @@
 void machines__init(struct machines *machines)
 {
 	machine__init(&machines->host, "", HOST_KERNEL_ID);
-	machines->guests = RB_ROOT;
+	machines->guests = RB_ROOT_CACHED;
 }
 
 void machines__exit(struct machines *machines)
@@ -234,9 +260,10 @@
 struct machine *machines__add(struct machines *machines, pid_t pid,
 			      const char *root_dir)
 {
-	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node **p = &machines->guests.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *pos, *machine = malloc(sizeof(*machine));
+	bool leftmost = true;
 
 	if (machine == NULL)
 		return NULL;
@@ -251,12 +278,14 @@
 		pos = rb_entry(parent, struct machine, rb_node);
 		if (pid < pos->pid)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&machine->rb_node, parent, p);
-	rb_insert_color(&machine->rb_node, &machines->guests);
+	rb_insert_color_cached(&machine->rb_node, &machines->guests, leftmost);
 
 	return machine;
 }
@@ -267,7 +296,7 @@
 
 	machines->host.comm_exec = comm_exec;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *machine = rb_entry(nd, struct machine, rb_node);
 
 		machine->comm_exec = comm_exec;
@@ -276,7 +305,7 @@
 
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
-	struct rb_node **p = &machines->guests.rb_node;
+	struct rb_node **p = &machines->guests.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *machine;
 	struct machine *default_machine = NULL;
@@ -339,7 +368,7 @@
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		process(pos, data);
 	}
@@ -352,7 +381,8 @@
 
 	machines->host.id_hdr_size = id_hdr_size;
 
-	for (node = rb_first(&machines->guests); node; node = rb_next(node)) {
+	for (node = rb_first_cached(&machines->guests); node;
+	     node = rb_next(node)) {
 		machine = rb_entry(node, struct machine, rb_node);
 		machine->id_hdr_size = id_hdr_size;
 	}
@@ -465,9 +495,10 @@
 						  pid_t pid, pid_t tid,
 						  bool create)
 {
-	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node **p = &threads->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct thread *th;
+	bool leftmost = true;
 
 	th = threads__get_last_match(threads, machine, pid, tid);
 	if (th)
@@ -485,8 +516,10 @@
 
 		if (tid < th->tid)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	if (!create)
@@ -495,7 +528,7 @@
 	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
-		rb_insert_color(&th->rb_node, &threads->entries);
+		rb_insert_color_cached(&th->rb_node, &threads->entries, leftmost);
 
 		/*
 		 * We have to initialize map_groups separately
@@ -506,7 +539,7 @@
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase_init(&th->rb_node, &threads->entries);
+			rb_erase_cached(&th->rb_node, &threads->entries);
 			RB_CLEAR_NODE(&th->rb_node);
 			thread__put(th);
 			return NULL;
@@ -620,7 +653,7 @@
 int machine__process_lost_event(struct machine *machine __maybe_unused,
 				union perf_event *event, struct perf_sample *sample __maybe_unused)
 {
-	dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+	dump_printf(": id:%" PRI_lu64 ": lost:%" PRI_lu64 "\n",
 		    event->lost.id, event->lost.lost);
 	return 0;
 }
@@ -628,7 +661,7 @@
 int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 					union perf_event *event, struct perf_sample *sample)
 {
-	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRI_lu64 "\n",
 		    sample->id, event->lost_samples.lost);
 	return 0;
 }
@@ -681,6 +714,59 @@
 	return 0;
 }
 
+static int machine__process_ksymbol_register(struct machine *machine,
+					     union perf_event *event,
+					     struct perf_sample *sample __maybe_unused)
+{
+	struct symbol *sym;
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
+	if (!map) {
+		map = dso__new_map(event->ksymbol.name);
+		if (!map)
+			return -ENOMEM;
+
+		map->start = event->ksymbol.addr;
+		map->end = map->start + event->ksymbol.len;
+		map_groups__insert(&machine->kmaps, map);
+	}
+
+	sym = symbol__new(map->map_ip(map, map->start),
+			  event->ksymbol.len,
+			  0, 0, event->ksymbol.name);
+	if (!sym)
+		return -ENOMEM;
+	dso__insert_symbol(map->dso, sym);
+	return 0;
+}
+
+static int machine__process_ksymbol_unregister(struct machine *machine,
+					       union perf_event *event,
+					       struct perf_sample *sample __maybe_unused)
+{
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol.addr);
+	if (map)
+		map_groups__remove(&machine->kmaps, map);
+
+	return 0;
+}
+
+int machine__process_ksymbol(struct machine *machine __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample)
+{
+	if (dump_trace)
+		perf_event__fprintf_ksymbol(event, stdout);
+
+	if (event->ksymbol.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
+		return machine__process_ksymbol_unregister(machine, event,
+							   sample);
+	return machine__process_ksymbol_register(machine, event, sample);
+}
+
 static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
 {
 	const char *dup_filename;
@@ -735,7 +821,7 @@
 out:
 	/* put the dso here, corresponding to  machine__findnew_module_dso */
 	dso__put(dso);
-	free(m.name);
+	zfree(&m.name);
 	return map;
 }
 
@@ -744,7 +830,7 @@
 	struct rb_node *nd;
 	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += __dsos__fprintf(&pos->dsos.head, fp);
 	}
@@ -764,7 +850,7 @@
 	struct rb_node *nd;
 	size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm);
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm);
 	}
@@ -804,7 +890,8 @@
 
 		ret = fprintf(fp, "Threads: %u\n", threads->nr);
 
-		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+		for (nd = rb_first_cached(&threads->entries); nd;
+		     nd = rb_next(nd)) {
 			struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 			ret += thread__fprintf(pos, fp);
@@ -861,7 +948,8 @@
  * symbol_name if it's not that important.
  */
 static int machine__get_running_kernel_start(struct machine *machine,
-					     const char **symbol_name, u64 *start)
+					     const char **symbol_name,
+					     u64 *start, u64 *end)
 {
 	char filename[PATH_MAX];
 	int i, err = -1;
@@ -886,6 +974,11 @@
 		*symbol_name = name;
 
 	*start = addr;
+
+	err = kallsyms__get_function_start(filename, "_etext", &addr);
+	if (!err)
+		*end = addr;
+
 	return 0;
 }
 
@@ -1107,7 +1200,7 @@
 
 void machines__destroy_kernel_maps(struct machines *machines)
 {
-	struct rb_node *next = rb_first(&machines->guests);
+	struct rb_node *next = rb_first_cached(&machines->guests);
 
 	machine__destroy_kernel_maps(&machines->host);
 
@@ -1115,7 +1208,7 @@
 		struct machine *pos = rb_entry(next, struct machine, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, &machines->guests);
+		rb_erase_cached(&pos->rb_node, &machines->guests);
 		machine__delete(pos);
 	}
 }
@@ -1171,9 +1264,10 @@
 	if (!file)
 		return NULL;
 
-	version[0] = '\0';
 	tmp = fgets(version, sizeof(version), file);
 	fclose(file);
+	if (!tmp)
+		return NULL;
 
 	name = strstr(version, prefix);
 	if (!name)
@@ -1267,7 +1361,7 @@
 			if (m.kmod)
 				ret = map_groups__set_module_path(mg, path, &m);
 
-			free(m.name);
+			zfree(&m.name);
 
 			if (ret)
 				goto out;
@@ -1295,6 +1389,7 @@
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1306,7 +1401,7 @@
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
@@ -1358,12 +1453,26 @@
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name = NULL;
 	struct map *map;
-	u64 addr = 0;
+	u64 start = 0, end = ~0ULL;
 	int ret;
 
 	if (kernel == NULL)
@@ -1382,34 +1491,31 @@
 				 "continuing anyway...\n", machine->pid);
 	}
 
-	if (!machine__get_running_kernel_start(machine, &name, &addr)) {
+	if (!machine__get_running_kernel_start(machine, &name, &start, &end)) {
 		if (name &&
-		    map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) {
+		    map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, start)) {
 			machine__destroy_kernel_maps(machine);
 			ret = -1;
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, start, end);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
 		pr_debug("Problems creating extra kernel maps, continuing anyway...\n");
 
-	/* update end address of the kernel map using adjacent module address */
-	map = map__next(machine__kernel_map(machine));
-	if (map)
-		machine__set_kernel_mmap(machine, addr, map->start);
+	if (end == ~0ULL) {
+		/* update end address of the kernel map using adjacent module address */
+		map = map__next(machine__kernel_map(machine));
+		if (map)
+			machine__set_kernel_mmap(machine, start, map->start);
+	}
+
 out_put:
 	dso__put(kernel);
 	return ret;
@@ -1536,7 +1642,7 @@
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*
@@ -1677,10 +1783,12 @@
 	if (threads->last_match == th)
 		threads__set_last_match(threads, NULL);
 
-	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
 		down_write(&threads->lock);
-	rb_erase_init(&th->rb_node, &threads->entries);
+
+	BUG_ON(refcount_read(&th->refcnt) == 0);
+
+	rb_erase_cached(&th->rb_node, &threads->entries);
 	RB_CLEAR_NODE(&th->rb_node);
 	--threads->nr;
 	/*
@@ -1689,9 +1797,16 @@
 	 * will be called and we will remove it from the dead_threads list.
 	 */
 	list_add_tail(&th->node, &threads->dead);
+
+	/*
+	 * We need to do the put here because if this is the last refcount,
+	 * then we will be touching the threads->dead head when removing the
+	 * thread.
+	 */
+	thread__put(th);
+
 	if (lock)
 		up_write(&threads->lock);
-	thread__put(th);
 }
 
 void machine__remove_thread(struct machine *machine, struct thread *th)
@@ -1708,6 +1823,7 @@
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1852,25 @@
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
@@ -1795,6 +1927,10 @@
 	case PERF_RECORD_SWITCH:
 	case PERF_RECORD_SWITCH_CPU_WIDE:
 		ret = machine__process_switch_event(machine, event); break;
+	case PERF_RECORD_KSYMBOL:
+		ret = machine__process_ksymbol(machine, event, sample); break;
+	case PERF_RECORD_BPF_EVENT:
+		ret = machine__process_bpf(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
@@ -1988,7 +2124,7 @@
 {
 	int i;
 
-	iter->nr_loop_iter = nr;
+	iter->nr_loop_iter++;
 	iter->cycles = 0;
 
 	for (i = 0; i < nr; i++)
@@ -2163,7 +2299,7 @@
 
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
-					    struct perf_evsel *evsel,
+					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    struct symbol **parent,
 					    struct addr_location *root_al,
@@ -2369,13 +2505,13 @@
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
 					    struct callchain_cursor *cursor,
-					    struct perf_evsel *evsel,
+					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    int max_stack)
 {
 	/* Can we do dwarf post unwind? */
-	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
-	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+	if (!((evsel->core.attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->core.attr.sample_type & PERF_SAMPLE_STACK_USER)))
 		return 0;
 
 	/* Bail out if nothing was captured. */
@@ -2389,7 +2525,7 @@
 
 int thread__resolve_callchain(struct thread *thread,
 			      struct callchain_cursor *cursor,
-			      struct perf_evsel *evsel,
+			      struct evsel *evsel,
 			      struct perf_sample *sample,
 			      struct symbol **parent,
 			      struct addr_location *root_al,
@@ -2436,7 +2572,8 @@
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
 		threads = &machine->threads[i];
-		for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+		for (nd = rb_first_cached(&threads->entries); nd;
+		     nd = rb_next(nd)) {
 			thread = rb_entry(nd, struct thread, rb_node);
 			rc = fn(thread, priv);
 			if (rc != 0)
@@ -2463,7 +2600,7 @@
 	if (rc != 0)
 		return rc;
 
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *machine = rb_entry(nd, struct machine, rb_node);
 
 		rc = machine__for_each_thread(machine, fn, priv);
@@ -2473,26 +2610,11 @@
 	return rc;
 }
 
-int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout,
-				  unsigned int nr_threads_synthesize)
-{
-	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
-	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process,
-						      machine, data_mmap,
-						      proc_map_timeout,
-						      nr_threads_synthesize);
-	/* command specified */
-	return 0;
-}
-
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+
+	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
 		return -1;
 
 	return machine->current_tid[cpu];
@@ -2502,6 +2624,7 @@
 			     pid_t tid)
 {
 	struct thread *thread;
+	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
 
 	if (cpu < 0)
 		return -EINVAL;
@@ -2509,14 +2632,14 @@
 	if (!machine->current_tid) {
 		int i;
 
-		machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+		machine->current_tid = calloc(nr_cpus, sizeof(pid_t));
 		if (!machine->current_tid)
 			return -ENOMEM;
-		for (i = 0; i < MAX_NR_CPUS; i++)
+		for (i = 0; i < nr_cpus; i++)
 			machine->current_tid[i] = -1;
 	}
 
-	if (cpu >= MAX_NR_CPUS) {
+	if (cpu >= nr_cpus) {
 		pr_err("Requested CPU %d too large. ", cpu);
 		pr_err("Consider raising MAX_NR_CPUS\n");
 		return -EINVAL;
@@ -2575,6 +2698,33 @@
 	return err;
 }
 
+u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr)
+{
+	u8 addr_cpumode = cpumode;
+	bool kernel_ip;
+
+	if (!machine->single_address_space)
+		goto out;
+
+	kernel_ip = machine__kernel_ip(machine, addr);
+	switch (cpumode) {
+	case PERF_RECORD_MISC_KERNEL:
+	case PERF_RECORD_MISC_USER:
+		addr_cpumode = kernel_ip ? PERF_RECORD_MISC_KERNEL :
+					   PERF_RECORD_MISC_USER;
+		break;
+	case PERF_RECORD_MISC_GUEST_KERNEL:
+	case PERF_RECORD_MISC_GUEST_USER:
+		addr_cpumode = kernel_ip ? PERF_RECORD_MISC_GUEST_KERNEL :
+					   PERF_RECORD_MISC_GUEST_USER;
+		break;
+	default:
+		break;
+	}
+out:
+	return addr_cpumode;
+}
+
 struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
 {
 	return dsos__findnew(&machine->dsos, filename);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index d856b85..18e13c0 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,16 +4,17 @@
 
 #include <sys/types.h>
 #include <linux/rbtree.h>
-#include "map.h"
-#include "dso.h"
-#include "event.h"
+#include "map_groups.h"
+#include "dsos.h"
 #include "rwsem.h"
 
 struct addr_location;
 struct branch_stack;
-struct perf_evsel;
+struct dso;
+struct evsel;
 struct perf_sample;
 struct symbol;
+struct target;
 struct thread;
 union perf_event;
 
@@ -29,11 +30,11 @@
 #define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
 
 struct threads {
-	struct rb_root	  entries;
-	struct rw_semaphore lock;
-	unsigned int	  nr;
-	struct list_head  dead;
-	struct thread	  *last_match;
+	struct rb_root_cached  entries;
+	struct rw_semaphore    lock;
+	unsigned int	       nr;
+	struct list_head       dead;
+	struct thread	       *last_match;
 };
 
 struct machine {
@@ -42,6 +43,7 @@
 	u16		  id_hdr_size;
 	bool		  comm_exec;
 	bool		  kptr_restrict_warned;
+	bool		  single_address_space;
 	char		  *root_dir;
 	char		  *mmap_name;
 	struct threads    threads[THREADS__TABLE_SIZE];
@@ -99,6 +101,8 @@
 	return ip >= kernel_start;
 }
 
+u8 machine__addr_cpumode(struct machine *machine, u8 cpumode, u64 addr);
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
 struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -127,6 +131,9 @@
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
 				 struct perf_sample *sample);
+int machine__process_ksymbol(struct machine *machine,
+			     union perf_event *event,
+			     struct perf_sample *sample);
 int machine__process_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 
@@ -134,7 +141,7 @@
 
 struct machines {
 	struct machine host;
-	struct rb_root guests;
+	struct rb_root_cached guests;
 };
 
 void machines__init(struct machines *machines);
@@ -169,7 +176,7 @@
 
 int thread__resolve_callchain(struct thread *thread,
 			      struct callchain_cursor *cursor,
-			      struct perf_evsel *evsel,
+			      struct evsel *evsel,
 			      struct perf_sample *sample,
 			      struct symbol **parent,
 			      struct addr_location *root_al,
@@ -216,7 +223,7 @@
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
@@ -244,23 +251,6 @@
 			      int (*fn)(struct thread *thread, void *p),
 			      void *priv);
 
-int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap,
-				  unsigned int proc_map_timeout,
-				  unsigned int nr_threads_synthesize);
-static inline
-int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct thread_map *threads, bool data_mmap,
-				unsigned int proc_map_timeout,
-				unsigned int nr_threads_synthesize)
-{
-	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap,
-					     proc_map_timeout,
-					     nr_threads_synthesize);
-}
-
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6a6929f..eec9b28 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -8,19 +9,24 @@
 #include <stdio.h>
 #include <unistd.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include "dso.h"
 #include "map.h"
+#include "map_symbol.h"
 #include "thread.h"
 #include "vdso.h"
 #include "build-id.h"
-#include "util.h"
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include "srcline.h"
 #include "namespaces.h"
 #include "unwind.h"
+#include "srccode.h"
+#include "ui/ui.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
+static void __maps__insert_name(struct maps *maps, struct map *map);
 
 static inline int is_anon_memory(const char *filename, u32 flags)
 {
@@ -259,6 +265,22 @@
 	return kmap && kmap->name[0];
 }
 
+bool __map__is_bpf_prog(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return true;
+
+	/*
+	 * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && (strstr(name, "bpf_prog_") == name);
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
@@ -284,8 +306,8 @@
 
 void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols;
-	struct rb_node *nd = rb_first(symbols);
+	struct rb_root_cached *symbols = &map->dso->symbols;
+	struct rb_node *nd = rb_first_cached(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 		map->start = sym->start;
@@ -294,8 +316,8 @@
 
 void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols;
-	struct rb_node *nd = rb_last(symbols);
+	struct rb_root_cached *symbols = &map->dso->symbols;
+	struct rb_node *nd = rb_last(&symbols->rb_root);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
 		map->end = sym->end;
@@ -320,12 +342,11 @@
 			build_id__sprintf(map->dso->build_id,
 					  sizeof(map->dso->build_id),
 					  sbuild_id);
-			pr_warning("%s with build id %s not found",
-				   name, sbuild_id);
+			pr_debug("%s with build id %s not found", name, sbuild_id);
 		} else
-			pr_warning("Failed to open %s", name);
+			pr_debug("Failed to open %s", name);
 
-		pr_warning(", continuing without symbols\n");
+		pr_debug(", continuing without symbols\n");
 		return -1;
 	} else if (nr == 0) {
 #ifdef HAVE_LIBELF_SUPPORT
@@ -334,12 +355,11 @@
 
 		if (len > sizeof(DSO__DELETED) &&
 		    strcmp(name + real_len + 1, DSO__DELETED) == 0) {
-			pr_warning("%.*s was updated (is prelink enabled?). "
+			pr_debug("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
 		} else {
-			pr_warning("no symbols found in %s, maybe install "
-				   "a debug package?\n", name);
+			pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
 		}
 #endif
 		return -1;
@@ -389,6 +409,7 @@
 
 size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 {
+	char buf[symbol_conf.pad_output_len_dso + 1];
 	const char *dsoname = "[unknown]";
 
 	if (map && map->dso) {
@@ -398,6 +419,11 @@
 			dsoname = map->dso->name;
 	}
 
+	if (symbol_conf.pad_output_len_dso) {
+		scnprintf_pad(buf, symbol_conf.pad_output_len_dso, "%s", dsoname);
+		dsoname = buf;
+	}
+
 	return fprintf(fp, "%s", dsoname);
 }
 
@@ -422,6 +448,57 @@
 	return ret;
 }
 
+int map__fprintf_srccode(struct map *map, u64 addr,
+			 FILE *fp,
+			 struct srccode_state *state)
+{
+	char *srcfile;
+	int ret = 0;
+	unsigned line;
+	int len;
+	char *srccode;
+
+	if (!map || !map->dso)
+		return 0;
+	srcfile = get_srcline_split(map->dso,
+				    map__rip_2objdump(map, addr),
+				    &line);
+	if (!srcfile)
+		return 0;
+
+	/* Avoid redundant printing */
+	if (state &&
+	    state->srcfile &&
+	    !strcmp(state->srcfile, srcfile) &&
+	    state->line == line) {
+		free(srcfile);
+		return 0;
+	}
+
+	srccode = find_sourceline(srcfile, line, &len);
+	if (!srccode)
+		goto out_free_line;
+
+	ret = fprintf(fp, "|%-8d %.*s", line, len, srccode);
+
+	if (state) {
+		state->srcfile = srcfile;
+		state->line = line;
+	}
+	return ret;
+
+out_free_line:
+	free(srcfile);
+	return ret;
+}
+
+
+void srccode_state_free(struct srccode_state *state)
+{
+	zfree(&state->srcfile);
+	state->line = 0;
+}
+
 /**
  * map__rip_2objdump - convert symbol start address to objdump address.
  * @map: memory map
@@ -498,6 +575,7 @@
 static void maps__init(struct maps *maps)
 {
 	maps->entries = RB_ROOT;
+	maps->names = RB_ROOT;
 	init_rwsem(&maps->lock);
 }
 
@@ -508,6 +586,12 @@
 	refcount_set(&mg->refcnt, 1);
 }
 
+void map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	maps__insert(&mg->maps, map);
+	map->groups = mg;
+}
+
 static void __maps__purge(struct maps *maps)
 {
 	struct rb_root *root = &maps->entries;
@@ -522,10 +606,25 @@
 	}
 }
 
+static void __maps__purge_names(struct maps *maps)
+{
+	struct rb_root *root = &maps->names;
+	struct rb_node *next = rb_first(root);
+
+	while (next) {
+		struct map *pos = rb_entry(next, struct map, rb_node_name);
+
+		next = rb_next(&pos->rb_node_name);
+		rb_erase_init(&pos->rb_node_name, root);
+		map__put(pos);
+	}
+}
+
 static void maps__exit(struct maps *maps)
 {
 	down_write(&maps->lock);
 	__maps__purge(maps);
+	__maps__purge_names(maps);
 	up_write(&maps->lock);
 }
 
@@ -541,7 +640,7 @@
 
 struct map_groups *map_groups__new(struct machine *machine)
 {
-	struct map_groups *mg = malloc(sizeof(*mg));
+	struct map_groups *mg = zalloc(sizeof(*mg));
 
 	if (mg != NULL)
 		map_groups__init(mg, machine);
@@ -552,6 +651,7 @@
 void map_groups__delete(struct map_groups *mg)
 {
 	map_groups__exit(mg);
+	unwind__finish_access(mg);
 	free(mg);
 }
 
@@ -666,6 +766,7 @@
 static void __map_groups__insert(struct map_groups *mg, struct map *map)
 {
 	__maps__insert(&mg->maps, map);
+	__maps__insert_name(&mg->maps, map);
 	map->groups = mg;
 }
 
@@ -712,8 +813,7 @@
 		if (verbose >= 2) {
 
 			if (use_browser) {
-				pr_warning("overlapping maps in %s "
-					   "(disable tui for more info)\n",
+				pr_debug("overlapping maps in %s (disable tui for more info)\n",
 					   map->dso->name);
 			} else {
 				fputs("overlapping maps:\n", fp);
@@ -751,6 +851,8 @@
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
@@ -792,7 +894,7 @@
 		if (new == NULL)
 			goto out_unlock;
 
-		err = unwind__prepare_access(thread, new, NULL);
+		err = unwind__prepare_access(mg, new, NULL);
 		if (err)
 			goto out_unlock;
 
@@ -827,10 +929,32 @@
 	map__get(map);
 }
 
+static void __maps__insert_name(struct maps *maps, struct map *map)
+{
+	struct rb_node **p = &maps->names.rb_node;
+	struct rb_node *parent = NULL;
+	struct map *m;
+	int rc;
+
+	while (*p != NULL) {
+		parent = *p;
+		m = rb_entry(parent, struct map, rb_node_name);
+		rc = strcmp(m->dso->short_name, map->dso->short_name);
+		if (rc < 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&map->rb_node_name, parent, p);
+	rb_insert_color(&map->rb_node_name, &maps->names);
+	map__get(map);
+}
+
 void maps__insert(struct maps *maps, struct map *map)
 {
 	down_write(&maps->lock);
 	__maps__insert(maps, map);
+	__maps__insert_name(maps, map);
 	up_write(&maps->lock);
 }
 
@@ -838,6 +962,9 @@
 {
 	rb_erase_init(&map->rb_node, &maps->entries);
 	map__put(map);
+
+	rb_erase_init(&map->rb_node_name, &maps->names);
+	map__put(map);
 }
 
 void maps__remove(struct maps *maps, struct map *map)
@@ -849,19 +976,18 @@
 
 struct map *maps__find(struct maps *maps, u64 ip)
 {
-	struct rb_node **p, *parent = NULL;
+	struct rb_node *p;
 	struct map *m;
 
 	down_read(&maps->lock);
 
-	p = &maps->entries.rb_node;
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map, rb_node);
+	p = maps->entries.rb_node;
+	while (p != NULL) {
+		m = rb_entry(p, struct map, rb_node);
 		if (ip < m->start)
-			p = &(*p)->rb_left;
+			p = p->rb_left;
 		else if (ip >= m->end)
-			p = &(*p)->rb_right;
+			p = p->rb_right;
 		else
 			goto out;
 	}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index e0f327b..c361419 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,25 +6,24 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
-#include <pthread.h>
 #include <stdio.h>
 #include <string.h>
 #include <stdbool.h>
 #include <linux/types.h>
-#include "rwsem.h"
 
 struct dso;
 struct ip_callchain;
 struct ref_reloc_sym;
 struct map_groups;
 struct machine;
-struct perf_evsel;
+struct evsel;
 
 struct map {
 	union {
 		struct rb_node	rb_node;
 		struct list_head node;
 	};
+	struct rb_node          rb_node_name;
 	u64			start;
 	u64			end;
 	bool			erange_warned;
@@ -47,37 +46,7 @@
 	refcount_t		refcnt;
 };
 
-#define KMAP_NAME_LEN 256
-
-struct kmap {
-	struct ref_reloc_sym	*ref_reloc_sym;
-	struct map_groups	*kmaps;
-	char			name[KMAP_NAME_LEN];
-};
-
-struct maps {
-	struct rb_root	 entries;
-	struct rw_semaphore lock;
-};
-
-struct map_groups {
-	struct maps	 maps;
-	struct machine	 *machine;
-	refcount_t	 refcnt;
-};
-
-struct map_groups *map_groups__new(struct machine *machine);
-void map_groups__delete(struct map_groups *mg);
-bool map_groups__empty(struct map_groups *mg);
-
-static inline struct map_groups *map_groups__get(struct map_groups *mg)
-{
-	if (mg)
-		refcount_inc(&mg->refcnt);
-	return mg;
-}
-
-void map_groups__put(struct map_groups *mg);
+struct kmap;
 
 struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
@@ -172,6 +141,11 @@
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
+struct srccode_state;
+
+int map__fprintf_srccode(struct map *map, u64 addr,
+			 FILE *fp, struct srccode_state *state);
+
 int map__load(struct map *map);
 struct symbol *map__find_symbol(struct map *map, u64 addr);
 struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
@@ -180,67 +154,17 @@
 
 void map__reloc_vmlinux(struct map *map);
 
-void maps__insert(struct maps *maps, struct map *map);
-void maps__remove(struct maps *maps, struct map *map);
-struct map *maps__find(struct maps *maps, u64 addr);
-struct map *maps__first(struct maps *maps);
-struct map *map__next(struct map *map);
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-                                         struct map **mapp);
-void map_groups__init(struct map_groups *mg, struct machine *machine);
-void map_groups__exit(struct map_groups *mg);
-int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent);
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
-
 int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 				    u64 addr);
 
-static inline void map_groups__insert(struct map_groups *mg, struct map *map)
-{
-	maps__insert(&mg->maps, map);
-	map->groups = mg;
-}
-
-static inline void map_groups__remove(struct map_groups *mg, struct map *map)
-{
-	maps__remove(&mg->maps, map);
-}
-
-static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
-{
-	return maps__find(&mg->maps, addr);
-}
-
-struct map *map_groups__first(struct map_groups *mg);
-
-static inline struct map *map_groups__next(struct map *map)
-{
-	return map__next(map);
-}
-
-struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       u64 addr, struct map **mapp);
-
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       const char *name,
-					       struct map **mapp);
-
-struct addr_map_symbol;
-
-int map_groups__find_ams(struct addr_map_symbol *ams);
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   FILE *fp);
-
-struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
-
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map);
 }
 
 bool map__has_symbols(const struct map *map);
diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h
new file mode 100644
index 0000000..77252e1
--- /dev/null
+++ b/tools/perf/util/map_groups.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_MAP_GROUPS_H
+#define __PERF_MAP_GROUPS_H
+
+#include <linux/refcount.h>
+#include <linux/rbtree.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include "rwsem.h"
+
+struct ref_reloc_sym;
+struct machine;
+struct map;
+struct thread;
+
+struct maps {
+	struct rb_root      entries;
+	struct rb_root	    names;
+	struct rw_semaphore lock;
+};
+
+void maps__insert(struct maps *maps, struct map *map);
+void maps__remove(struct maps *maps, struct map *map);
+struct map *maps__find(struct maps *maps, u64 addr);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp);
+
+struct map_groups {
+	struct maps	 maps;
+	struct machine	 *machine;
+	refcount_t	 refcnt;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	void				*addr_space;
+	struct unwind_libunwind_ops	*unwind_libunwind_ops;
+#endif
+};
+
+#define KMAP_NAME_LEN 256
+
+struct kmap {
+	struct ref_reloc_sym *ref_reloc_sym;
+	struct map_groups    *kmaps;
+	char		     name[KMAP_NAME_LEN];
+};
+
+struct map_groups *map_groups__new(struct machine *machine);
+void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
+
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
+{
+	if (mg)
+		refcount_inc(&mg->refcnt);
+	return mg;
+}
+
+void map_groups__put(struct map_groups *mg);
+void map_groups__init(struct map_groups *mg, struct machine *machine);
+void map_groups__exit(struct map_groups *mg);
+int map_groups__clone(struct thread *thread, struct map_groups *parent);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
+
+void map_groups__insert(struct map_groups *mg, struct map *map);
+
+static inline void map_groups__remove(struct map_groups *mg, struct map *map)
+{
+	maps__remove(&mg->maps, map);
+}
+
+static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
+{
+	return maps__find(&mg->maps, addr);
+}
+
+struct map *map_groups__first(struct map_groups *mg);
+
+static inline struct map *map_groups__next(struct map *map)
+{
+	return map__next(map);
+}
+
+struct symbol *map_groups__find_symbol(struct map_groups *mg, u64 addr, struct map **mapp);
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg, const char *name, struct map **mapp);
+
+struct addr_map_symbol;
+
+int map_groups__find_ams(struct addr_map_symbol *ams);
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, FILE *fp);
+
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
+
+int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map);
+
+#endif // __PERF_MAP_GROUPS_H
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
new file mode 100644
index 0000000..5a1aed9
--- /dev/null
+++ b/tools/perf/util/map_symbol.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_MAP_SYMBOL
+#define __PERF_MAP_SYMBOL 1
+
+#include <linux/types.h>
+
+struct map;
+struct symbol;
+
+struct map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+};
+
+struct addr_map_symbol {
+	struct map    *map;
+	struct symbol *sym;
+	u64	      addr;
+	u64	      al_addr;
+	u64	      phys_addr;
+};
+#endif // __PERF_MAP_SYMBOL
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8..3d39158 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -8,10 +8,10 @@
 #include <unistd.h>
 #include <api/fs/fs.h>
 #include <linux/kernel.h>
+#include "map_symbol.h"
 #include "mem-events.h"
 #include "debug.h"
 #include "symbol.h"
-#include "sort.h"
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 
@@ -28,7 +28,7 @@
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index a889ec2..f1389bd 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -6,6 +6,8 @@
 #include <stdint.h>
 #include <stdio.h>
 #include <linux/types.h>
+#include <linux/refcount.h>
+#include <linux/perf_event.h>
 #include "stat.h"
 
 struct perf_mem_event {
@@ -16,6 +18,13 @@
 	const char	*sysfs_name;
 };
 
+struct mem_info {
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
+};
+
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index c6fd81c..797d86a 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -1,8 +1,11 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitmap.h>
+#include <linux/kernel.h>
+#include <linux/zalloc.h>
+#include "debug.h"
+#include "env.h"
 #include "mem2node.h"
-#include "util.h"
 
 struct phys_entry {
 	struct rb_node	rb_node;
diff --git a/tools/perf/util/mem2node.h b/tools/perf/util/mem2node.h
index 59c4752..8dfa2b5 100644
--- a/tools/perf/util/mem2node.h
+++ b/tools/perf/util/mem2node.h
@@ -2,8 +2,9 @@
 #define __MEM2NODE_H
 
 #include <linux/rbtree.h>
-#include "env.h"
+#include <linux/types.h>
 
+struct perf_env;
 struct phys_entry;
 
 struct mem2node {
diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h
index 1e29ff9..2c38e8c 100644
--- a/tools/perf/util/memswap.h
+++ b/tools/perf/util/memswap.h
@@ -2,6 +2,13 @@
 #ifndef PERF_MEMSWAP_H_
 #define PERF_MEMSWAP_H_
 
+#include <linux/types.h>
+
+union u64_swap {
+	u64 val64;
+	u32 val32[2];
+};
+
 void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index a28f9b5..a7c0424 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1,35 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2017, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 /* Manage metrics and groups of metrics from JSON files */
 
 #include "metricgroup.h"
+#include "debug.h"
 #include "evlist.h"
+#include "evsel.h"
 #include "strbuf.h"
 #include "pmu.h"
 #include "expr.h"
 #include "rblist.h"
 #include <string.h>
-#include <stdbool.h>
 #include <errno.h>
 #include "pmu-events/pmu-events.h"
 #include "strlist.h"
 #include <assert.h>
-#include <ctype.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <subcmd/parse-options.h>
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 bool create)
 {
 	struct rb_node *nd;
@@ -92,40 +87,68 @@
 	const char **ids;
 	const char *metric_name;
 	const char *metric_expr;
+	const char *metric_unit;
 };
 
-static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
-				     const char **ids,
-				     int idnum,
-				     struct perf_evsel **metric_events)
+static struct evsel *find_evsel_group(struct evlist *perf_evlist,
+				      const char **ids,
+				      int idnum,
+				      struct evsel **metric_events)
 {
-	struct perf_evsel *ev, *start = NULL;
-	int ind = 0;
+	struct evsel *ev;
+	int i = 0;
+	bool leader_found;
 
 	evlist__for_each_entry (perf_evlist, ev) {
-		if (!strcmp(ev->name, ids[ind])) {
-			metric_events[ind] = ev;
-			if (ind == 0)
-				start = ev;
-			if (++ind == idnum) {
-				metric_events[ind] = NULL;
-				return start;
-			}
+		if (!strcmp(ev->name, ids[i])) {
+			if (!metric_events[i])
+				metric_events[i] = ev;
 		} else {
-			ind = 0;
-			start = NULL;
+			if (++i == idnum) {
+				/* Discard the whole match and start again */
+				i = 0;
+				memset(metric_events, 0,
+				       sizeof(struct evsel *) * idnum);
+				continue;
+			}
+
+			if (!strcmp(ev->name, ids[i]))
+				metric_events[i] = ev;
+			else {
+				/* Discard the whole match and start again */
+				i = 0;
+				memset(metric_events, 0,
+				       sizeof(struct evsel *) * idnum);
+				continue;
+			}
 		}
 	}
-	/*
-	 * This can happen when an alias expands to multiple
-	 * events, like for uncore events.
-	 * We don't support this case for now.
-	 */
-	return NULL;
+
+	if (i != idnum - 1) {
+		/* Not whole match */
+		return NULL;
+	}
+
+	metric_events[idnum] = NULL;
+
+	for (i = 0; i < idnum; i++) {
+		leader_found = false;
+		evlist__for_each_entry(perf_evlist, ev) {
+			if (!leader_found && (ev == metric_events[i]))
+				leader_found = true;
+
+			if (leader_found &&
+			    !strcmp(ev->name, metric_events[i]->name)) {
+				ev->metric_leader = metric_events[i];
+			}
+		}
+	}
+
+	return metric_events[0];
 }
 
 static int metricgroup__setup_events(struct list_head *groups,
-				     struct perf_evlist *perf_evlist,
+				     struct evlist *perf_evlist,
 				     struct rblist *metric_events_list)
 {
 	struct metric_event *me;
@@ -133,18 +156,18 @@
 	int i = 0;
 	int ret = 0;
 	struct egroup *eg;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	list_for_each_entry (eg, groups, nd) {
-		struct perf_evsel **metric_events;
+		struct evsel **metric_events;
 
 		metric_events = calloc(sizeof(void *), eg->idnum + 1);
 		if (!metric_events) {
 			ret = -ENOMEM;
 			break;
 		}
-		evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
-				   metric_events);
+		evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
+					 metric_events);
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
@@ -164,6 +187,7 @@
 		}
 		expr->metric_expr = eg->metric_expr;
 		expr->metric_name = eg->metric_name;
+		expr->metric_unit = eg->metric_unit;
 		expr->metric_events = metric_events;
 		list_add(&expr->nd, &me->head);
 	}
@@ -221,7 +245,7 @@
 		goto out_name;
 	return &me->nd;
 out_name:
-	free((char *)me->name);
+	zfree(&me->name);
 out_me:
 	free(me);
 	return NULL;
@@ -249,7 +273,7 @@
 	struct mep *me = container_of(nd, struct mep, nd);
 
 	strlist__delete(me->metrics);
-	free((void *)me->name);
+	zfree(&me->name);
 	free(me);
 }
 
@@ -270,7 +294,7 @@
 }
 
 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;
@@ -317,10 +341,9 @@
 				struct mep *me;
 				char *s;
 
+				g = skip_spaces(g);
 				if (*g == 0)
 					g = "No_group";
-				while (isspace(*g))
-					g++;
 				if (filter && !strstr(g, filter))
 					continue;
 				if (raw)
@@ -329,6 +352,12 @@
 					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)
@@ -352,11 +381,11 @@
 	else if (metrics && !raw)
 		printf("\nMetrics:\n\n");
 
-	for (node = rb_first(&groups.entries); node; node = next) {
+	for (node = rb_first_cached(&groups.entries); node; node = next) {
 		struct mep *me = container_of(node, struct mep, nd);
 
 		if (metricgroups)
-			printf("%s%s%s", me->name, metrics ? ":" : "", raw ? " " : "\n");
+			printf("%s%s%s", me->name, metrics && !raw ? ":" : "", raw ? " " : "\n");
 		if (metrics)
 			metricgroup__print_strlist(me->metrics, raw);
 		next = rb_next(node);
@@ -390,6 +419,7 @@
 			const char **ids;
 			int idnum;
 			struct egroup *eg;
+			bool no_group = false;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
@@ -400,11 +430,25 @@
 				strbuf_addf(events, ",");
 			for (j = 0; j < idnum; j++) {
 				pr_debug("found event %s\n", ids[j]);
+				/*
+				 * Duration time maps to a software event and can make
+				 * groups not count. Always use it outside a
+				 * group.
+				 */
+				if (!strcmp(ids[j], "duration_time")) {
+					if (j > 0)
+						strbuf_addf(events, "}:W,");
+					strbuf_addf(events, "duration_time");
+					no_group = true;
+					continue;
+				}
 				strbuf_addf(events, "%s%s",
-					j == 0 ? "{" : ",",
+					j == 0 || no_group ? "{" : ",",
 					ids[j]);
+				no_group = false;
 			}
-			strbuf_addf(events, "}:W");
+			if (!no_group)
+				strbuf_addf(events, "}:W");
 
 			eg = malloc(sizeof(struct egroup));
 			if (!eg) {
@@ -415,6 +459,7 @@
 			eg->idnum = idnum;
 			eg->metric_name = pe->metric_name;
 			eg->metric_expr = pe->metric_expr;
+			eg->metric_unit = pe->unit;
 			list_add_tail(&eg->nd, group_list);
 			ret = 0;
 		}
@@ -455,8 +500,9 @@
 
 	list_for_each_entry_safe (eg, egtmp, group_list, nd) {
 		for (i = 0; i < eg->idnum; i++)
-			free((char *)eg->ids[i]);
-		free(eg->ids);
+			zfree(&eg->ids[i]);
+		zfree(&eg->ids);
+		list_del_init(&eg->nd);
 		free(eg);
 	}
 }
@@ -466,7 +512,7 @@
 			   struct rblist *metric_events)
 {
 	struct parse_events_error parse_error;
-	struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+	struct evlist *perf_evlist = *(struct evlist **)opt->value;
 	struct strbuf extra_events;
 	LIST_HEAD(group_list);
 	int ret;
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 8a155db..475c7f9 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -1,15 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
 #ifndef METRICGROUP_H
 #define METRICGROUP_H 1
 
-#include "linux/list.h"
-#include "rblist.h"
-#include <subcmd/parse-options.h>
-#include "evlist.h"
-#include "strbuf.h"
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <stdbool.h>
+
+struct evsel;
+struct option;
+struct rblist;
 
 struct metric_event {
 	struct rb_node nd;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct list_head head; /* list of metric_expr */
 };
 
@@ -17,16 +20,18 @@
 	struct list_head nd;
 	const char *metric_expr;
 	const char *metric_name;
-	struct perf_evsel **metric_events;
+	const char *metric_unit;
+	struct evsel **metric_events;
 };
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 bool create);
 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/mmap.c b/tools/perf/util/mmap.c
index 215f69f..a35dc57 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -1,37 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
  * copyright notes.
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include <sys/mman.h>
 #include <inttypes.h>
 #include <asm/bug.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h> // sysconf()
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
+#include "cpumap.h"
 #include "debug.h"
 #include "event.h"
 #include "mmap.h"
-#include "util.h" /* page_size */
+#include "../perf.h"
+#include <internal/lib.h> /* page_size */
 
-size_t perf_mmap__mmap_len(struct perf_mmap *map)
+size_t perf_mmap__mmap_len(struct mmap *map)
 {
-	return map->mask + 1 + page_size;
+	return map->core.mask + 1 + page_size;
 }
 
 /* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct perf_mmap *map,
+static union perf_event *perf_mmap__read(struct mmap *map,
 					 u64 *startp, u64 end)
 {
-	unsigned char *data = map->base + page_size;
+	unsigned char *data = map->core.base + page_size;
 	union perf_event *event = NULL;
 	int diff = end - *startp;
 
 	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
-		event = (union perf_event *)&data[*startp & map->mask];
+		event = (union perf_event *)&data[*startp & map->core.mask];
 		size = event->header.size;
 
 		if (size < sizeof(event->header) || diff < (int)size)
@@ -41,20 +49,20 @@
 		 * Event straddles the mmap boundary -- header should always
 		 * be inside due to u64 alignment of output.
 		 */
-		if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
+		if ((*startp & map->core.mask) + size != ((*startp + size) & map->core.mask)) {
 			unsigned int offset = *startp;
 			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = map->event_copy;
+			void *dst = map->core.event_copy;
 
 			do {
-				cpy = min(map->mask + 1 - (offset & map->mask), len);
-				memcpy(dst, &data[offset & map->mask], cpy);
+				cpy = min(map->core.mask + 1 - (offset & map->core.mask), len);
+				memcpy(dst, &data[offset & map->core.mask], cpy);
 				offset += cpy;
 				dst += cpy;
 				len -= cpy;
 			} while (len);
 
-			event = (union perf_event *)map->event_copy;
+			event = (union perf_event *)map->core.event_copy;
 		}
 
 		*startp += size;
@@ -75,55 +83,55 @@
  * }
  * perf_mmap__read_done()
  */
-union perf_event *perf_mmap__read_event(struct perf_mmap *map)
+union perf_event *perf_mmap__read_event(struct mmap *map)
 {
 	union perf_event *event;
 
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!refcount_read(&map->refcnt))
+	if (!refcount_read(&map->core.refcnt))
 		return NULL;
 
 	/* non-overwirte doesn't pause the ringbuffer */
-	if (!map->overwrite)
-		map->end = perf_mmap__read_head(map);
+	if (!map->core.overwrite)
+		map->core.end = perf_mmap__read_head(map);
 
-	event = perf_mmap__read(map, &map->start, map->end);
+	event = perf_mmap__read(map, &map->core.start, map->core.end);
 
-	if (!map->overwrite)
-		map->prev = map->start;
+	if (!map->core.overwrite)
+		map->core.prev = map->core.start;
 
 	return event;
 }
 
-static bool perf_mmap__empty(struct perf_mmap *map)
+static bool perf_mmap__empty(struct mmap *map)
 {
-	return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
+	return perf_mmap__read_head(map) == map->core.prev && !map->auxtrace_mmap.base;
 }
 
-void perf_mmap__get(struct perf_mmap *map)
+void perf_mmap__get(struct mmap *map)
 {
-	refcount_inc(&map->refcnt);
+	refcount_inc(&map->core.refcnt);
 }
 
-void perf_mmap__put(struct perf_mmap *map)
+void perf_mmap__put(struct mmap *map)
 {
-	BUG_ON(map->base && refcount_read(&map->refcnt) == 0);
+	BUG_ON(map->core.base && refcount_read(&map->core.refcnt) == 0);
 
-	if (refcount_dec_and_test(&map->refcnt))
+	if (refcount_dec_and_test(&map->core.refcnt))
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map)
+void perf_mmap__consume(struct mmap *map)
 {
-	if (!map->overwrite) {
-		u64 old = map->prev;
+	if (!map->core.overwrite) {
+		u64 old = map->core.prev;
 
 		perf_mmap__write_tail(map, old);
 	}
 
-	if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
+	if (refcount_read(&map->core.refcnt) == 1 && perf_mmap__empty(map))
 		perf_mmap__put(map);
 }
 
@@ -147,24 +155,205 @@
 }
 
 void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
-					  struct perf_evlist *evlist __maybe_unused,
+					  struct evlist *evlist __maybe_unused,
 					  int idx __maybe_unused,
 					  bool per_cpu __maybe_unused)
 {
 }
 
-void perf_mmap__munmap(struct perf_mmap *map)
+#ifdef HAVE_AIO_SUPPORT
+static int perf_mmap__aio_enabled(struct mmap *map)
 {
-	if (map->base != NULL) {
-		munmap(map->base, perf_mmap__mmap_len(map));
-		map->base = NULL;
-		map->fd = -1;
-		refcount_set(&map->refcnt, 0);
+	return map->aio.nr_cblocks > 0;
+}
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_alloc(struct mmap *map, int idx)
+{
+	map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+				  MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+	if (map->aio.data[idx] == MAP_FAILED) {
+		map->aio.data[idx] = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct mmap *map, int idx)
+{
+	if (map->aio.data[idx]) {
+		munmap(map->aio.data[idx], perf_mmap__mmap_len(map));
+		map->aio.data[idx] = NULL;
+	}
+}
+
+static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
+{
+	void *data;
+	size_t mmap_len;
+	unsigned long node_mask;
+
+	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+		data = map->aio.data[idx];
+		mmap_len = perf_mmap__mmap_len(map);
+		node_mask = 1UL << cpu__get_node(cpu);
+		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
+				data, data + mmap_len, cpu__get_node(cpu));
+			return -1;
+		}
+	}
+
+	return 0;
+}
+#else /* !HAVE_LIBNUMA_SUPPORT */
+static int perf_mmap__aio_alloc(struct mmap *map, int idx)
+{
+	map->aio.data[idx] = malloc(perf_mmap__mmap_len(map));
+	if (map->aio.data[idx] == NULL)
+		return -1;
+
+	return 0;
+}
+
+static void perf_mmap__aio_free(struct mmap *map, int idx)
+{
+	zfree(&(map->aio.data[idx]));
+}
+
+static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused,
+		int cpu __maybe_unused, int affinity __maybe_unused)
+{
+	return 0;
+}
+#endif
+
+static int perf_mmap__aio_mmap(struct mmap *map, struct mmap_params *mp)
+{
+	int delta_max, i, prio, ret;
+
+	map->aio.nr_cblocks = mp->nr_cblocks;
+	if (map->aio.nr_cblocks) {
+		map->aio.aiocb = calloc(map->aio.nr_cblocks, sizeof(struct aiocb *));
+		if (!map->aio.aiocb) {
+			pr_debug2("failed to allocate aiocb for data buffer, error %m\n");
+			return -1;
+		}
+		map->aio.cblocks = calloc(map->aio.nr_cblocks, sizeof(struct aiocb));
+		if (!map->aio.cblocks) {
+			pr_debug2("failed to allocate cblocks for data buffer, error %m\n");
+			return -1;
+		}
+		map->aio.data = calloc(map->aio.nr_cblocks, sizeof(void *));
+		if (!map->aio.data) {
+			pr_debug2("failed to allocate data buffer, error %m\n");
+			return -1;
+		}
+		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
+		for (i = 0; i < map->aio.nr_cblocks; ++i) {
+			ret = perf_mmap__aio_alloc(map, i);
+			if (ret == -1) {
+				pr_debug2("failed to allocate data buffer area, error %m");
+				return -1;
+			}
+			ret = perf_mmap__aio_bind(map, i, map->core.cpu, mp->affinity);
+			if (ret == -1)
+				return -1;
+			/*
+			 * Use cblock.aio_fildes value different from -1
+			 * to denote started aio write operation on the
+			 * cblock so it requires explicit record__aio_sync()
+			 * call prior the cblock may be reused again.
+			 */
+			map->aio.cblocks[i].aio_fildes = -1;
+			/*
+			 * Allocate cblocks with priority delta to have
+			 * faster aio write system calls because queued requests
+			 * are kept in separate per-prio queues and adding
+			 * a new request will iterate thru shorter per-prio
+			 * list. Blocks with numbers higher than
+			 *  _SC_AIO_PRIO_DELTA_MAX go with priority 0.
+			 */
+			prio = delta_max - i;
+			map->aio.cblocks[i].aio_reqprio = prio >= 0 ? prio : 0;
+		}
+	}
+
+	return 0;
+}
+
+static void perf_mmap__aio_munmap(struct mmap *map)
+{
+	int i;
+
+	for (i = 0; i < map->aio.nr_cblocks; ++i)
+		perf_mmap__aio_free(map, i);
+	if (map->aio.data)
+		zfree(&map->aio.data);
+	zfree(&map->aio.cblocks);
+	zfree(&map->aio.aiocb);
+}
+#else /* !HAVE_AIO_SUPPORT */
+static int perf_mmap__aio_enabled(struct mmap *map __maybe_unused)
+{
+	return 0;
+}
+
+static int perf_mmap__aio_mmap(struct mmap *map __maybe_unused,
+			       struct mmap_params *mp __maybe_unused)
+{
+	return 0;
+}
+
+static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused)
+{
+}
+#endif
+
+void perf_mmap__munmap(struct mmap *map)
+{
+	perf_mmap__aio_munmap(map);
+	if (map->data != NULL) {
+		munmap(map->data, perf_mmap__mmap_len(map));
+		map->data = NULL;
+	}
+	if (map->core.base != NULL) {
+		munmap(map->core.base, perf_mmap__mmap_len(map));
+		map->core.base = NULL;
+		map->core.fd = -1;
+		refcount_set(&map->core.refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
+static void build_node_mask(int node, cpu_set_t *mask)
+{
+	int c, cpu, nr_cpus;
+	const struct perf_cpu_map *cpu_map = NULL;
+
+	cpu_map = cpu_map__online();
+	if (!cpu_map)
+		return;
+
+	nr_cpus = perf_cpu_map__nr(cpu_map);
+	for (c = 0; c < nr_cpus; c++) {
+		cpu = cpu_map->map[c]; /* map c index to online cpu index */
+		if (cpu__get_node(cpu) == node)
+			CPU_SET(cpu, mask);
+	}
+}
+
+static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
+{
+	CPU_ZERO(&map->affinity_mask);
+	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
+		build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
+	else if (mp->affinity == PERF_AFFINITY_CPU)
+		CPU_SET(map->core.cpu, &map->affinity_mask);
+}
+
+int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
 	/*
 	 * The last one will be done at perf_mmap__consume(), so that we
@@ -179,25 +368,42 @@
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	refcount_set(&map->refcnt, 2);
-	map->prev = 0;
-	map->mask = mp->mask;
-	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+	refcount_set(&map->core.refcnt, 2);
+	map->core.prev = 0;
+	map->core.mask = mp->mask;
+	map->core.base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
 			 MAP_SHARED, fd, 0);
-	if (map->base == MAP_FAILED) {
+	if (map->core.base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
 			  errno);
-		map->base = NULL;
+		map->core.base = NULL;
 		return -1;
 	}
-	map->fd = fd;
-	map->cpu = cpu;
+	map->core.fd = fd;
+	map->core.cpu = cpu;
+
+	perf_mmap__setup_affinity_mask(map, mp);
+
+	map->core.flush = mp->flush;
+
+	map->comp_level = mp->comp_level;
+
+	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+		map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+		if (map->data == MAP_FAILED) {
+			pr_debug2("failed to mmap data buffer, error %d\n",
+					errno);
+			map->data = NULL;
+			return -1;
+		}
+	}
 
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
-				&mp->auxtrace_mp, map->base, fd))
+				&mp->auxtrace_mp, map->core.base, fd))
 		return -1;
 
-	return 0;
+	return perf_mmap__aio_mmap(map, mp);
 }
 
 static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end)
@@ -235,25 +441,25 @@
 /*
  * Report the start and end of the available data in ringbuffer
  */
-static int __perf_mmap__read_init(struct perf_mmap *md)
+static int __perf_mmap__read_init(struct mmap *md)
 {
 	u64 head = perf_mmap__read_head(md);
-	u64 old = md->prev;
-	unsigned char *data = md->base + page_size;
+	u64 old = md->core.prev;
+	unsigned char *data = md->core.base + page_size;
 	unsigned long size;
 
-	md->start = md->overwrite ? head : old;
-	md->end = md->overwrite ? old : head;
+	md->core.start = md->core.overwrite ? head : old;
+	md->core.end = md->core.overwrite ? old : head;
 
-	if (md->start == md->end)
+	if ((md->core.end - md->core.start) < md->core.flush)
 		return -EAGAIN;
 
-	size = md->end - md->start;
-	if (size > (unsigned long)(md->mask) + 1) {
-		if (!md->overwrite) {
+	size = md->core.end - md->core.start;
+	if (size > (unsigned long)(md->core.mask) + 1) {
+		if (!md->core.overwrite) {
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
-			md->prev = head;
+			md->core.prev = head;
 			perf_mmap__consume(md);
 			return -EAGAIN;
 		}
@@ -262,60 +468,60 @@
 		 * Backward ring buffer is full. We still have a chance to read
 		 * most of data from it.
 		 */
-		if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end))
+		if (overwrite_rb_find_range(data, md->core.mask, &md->core.start, &md->core.end))
 			return -EINVAL;
 	}
 
 	return 0;
 }
 
-int perf_mmap__read_init(struct perf_mmap *map)
+int perf_mmap__read_init(struct mmap *map)
 {
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!refcount_read(&map->refcnt))
+	if (!refcount_read(&map->core.refcnt))
 		return -ENOENT;
 
 	return __perf_mmap__read_init(map);
 }
 
-int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size))
+int perf_mmap__push(struct mmap *md, void *to,
+		    int push(struct mmap *map, void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
-	unsigned char *data = md->base + page_size;
+	unsigned char *data = md->core.base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
 	rc = perf_mmap__read_init(md);
 	if (rc < 0)
-		return (rc == -EAGAIN) ? 0 : -1;
+		return (rc == -EAGAIN) ? 1 : -1;
 
-	size = md->end - md->start;
+	size = md->core.end - md->core.start;
 
-	if ((md->start & md->mask) + size != (md->end & md->mask)) {
-		buf = &data[md->start & md->mask];
-		size = md->mask + 1 - (md->start & md->mask);
-		md->start += size;
+	if ((md->core.start & md->core.mask) + size != (md->core.end & md->core.mask)) {
+		buf = &data[md->core.start & md->core.mask];
+		size = md->core.mask + 1 - (md->core.start & md->core.mask);
+		md->core.start += size;
 
-		if (push(to, buf, size) < 0) {
+		if (push(md, to, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
 	}
 
-	buf = &data[md->start & md->mask];
-	size = md->end - md->start;
-	md->start += size;
+	buf = &data[md->core.start & md->core.mask];
+	size = md->core.end - md->core.start;
+	md->core.start += size;
 
-	if (push(to, buf, size) < 0) {
+	if (push(md, to, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
 
-	md->prev = head;
+	md->core.prev = head;
 	perf_mmap__consume(md);
 out:
 	return rc;
@@ -324,16 +530,16 @@
 /*
  * Mandatory for overwrite mode
  * The direction of overwrite mode is backward.
- * The last perf_mmap__read() will set tail to map->prev.
- * Need to correct the map->prev to head which is the end of next read.
+ * The last perf_mmap__read() will set tail to map->core.prev.
+ * Need to correct the map->core.prev to head which is the end of next read.
  */
-void perf_mmap__read_done(struct perf_mmap *map)
+void perf_mmap__read_done(struct mmap *map)
 {
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
 	 */
-	if (!refcount_read(&map->refcnt))
+	if (!refcount_read(&map->core.refcnt))
 		return;
 
-	map->prev = perf_mmap__read_head(map);
+	map->core.prev = perf_mmap__read_head(map);
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 05a6d47..e567c1c 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -1,102 +1,73 @@
 #ifndef __PERF_MMAP_H
 #define __PERF_MMAP_H 1
 
+#include <internal/mmap.h>
 #include <linux/compiler.h>
 #include <linux/refcount.h>
 #include <linux/types.h>
-#include <asm/barrier.h>
+#include <linux/ring_buffer.h>
 #include <stdbool.h>
+#include <pthread.h> // for cpu_set_t
+#ifdef HAVE_AIO_SUPPORT
+#include <aio.h>
+#endif
 #include "auxtrace.h"
 #include "event.h"
 
+struct aiocb;
 /**
- * struct perf_mmap - perf's ring buffer mmap details
+ * struct mmap - perf's ring buffer mmap details
  *
  * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
  */
-struct perf_mmap {
-	void		 *base;
-	int		 mask;
-	int		 fd;
-	int		 cpu;
-	refcount_t	 refcnt;
-	u64		 prev;
-	u64		 start;
-	u64		 end;
-	bool		 overwrite;
+struct mmap {
+	struct perf_mmap	core;
 	struct auxtrace_mmap auxtrace_mmap;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
-};
-
-/*
- * State machine of bkw_mmap_state:
- *
- *                     .________________(forbid)_____________.
- *                     |                                     V
- * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
- *                     ^  ^              |   ^               |
- *                     |  |__(forbid)____/   |___(forbid)___/|
- *                     |                                     |
- *                      \_________________(3)_______________/
- *
- * NOTREADY     : Backward ring buffers are not ready
- * RUNNING      : Backward ring buffers are recording
- * DATA_PENDING : We are required to collect data from backward ring buffers
- * EMPTY        : We have collected data from backward ring buffers.
- *
- * (0): Setup backward ring buffer
- * (1): Pause ring buffers for reading
- * (2): Read from ring buffers
- * (3): Resume ring buffers for recording
- */
-enum bkw_mmap_state {
-	BKW_MMAP_NOTREADY,
-	BKW_MMAP_RUNNING,
-	BKW_MMAP_DATA_PENDING,
-	BKW_MMAP_EMPTY,
+#ifdef HAVE_AIO_SUPPORT
+	struct {
+		void		 **data;
+		struct aiocb	 *cblocks;
+		struct aiocb	 **aiocb;
+		int		 nr_cblocks;
+	} aio;
+#endif
+	cpu_set_t	affinity_mask;
+	void		*data;
+	int		comp_level;
 };
 
 struct mmap_params {
-	int			    prot, mask;
+	int prot, mask, nr_cblocks, affinity, flush, comp_level;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu);
-void perf_mmap__munmap(struct perf_mmap *map);
+int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
+void perf_mmap__munmap(struct mmap *map);
 
-void perf_mmap__get(struct perf_mmap *map);
-void perf_mmap__put(struct perf_mmap *map);
+void perf_mmap__get(struct mmap *map);
+void perf_mmap__put(struct mmap *map);
 
-void perf_mmap__consume(struct perf_mmap *map);
+void perf_mmap__consume(struct mmap *map);
 
-static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
+static inline u64 perf_mmap__read_head(struct mmap *mm)
 {
-	struct perf_event_mmap_page *pc = mm->base;
-	u64 head = READ_ONCE(pc->data_head);
-	rmb();
-	return head;
+	return ring_buffer_read_head(mm->core.base);
 }
 
-static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
+static inline void perf_mmap__write_tail(struct mmap *md, u64 tail)
 {
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	mb();
-	pc->data_tail = tail;
+	ring_buffer_write_tail(md->core.base, tail);
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
+union perf_event *perf_mmap__read_forward(struct mmap *map);
 
-union perf_event *perf_mmap__read_event(struct perf_mmap *map);
+union perf_event *perf_mmap__read_event(struct mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, void *to,
-		    int push(void *to, void *buf, size_t size));
+int perf_mmap__push(struct mmap *md, void *to,
+		    int push(struct mmap *map, void *to, void *buf, size_t size));
 
-size_t perf_mmap__mmap_len(struct perf_mmap *map);
+size_t perf_mmap__mmap_len(struct mmap *map);
 
-int perf_mmap__read_init(struct perf_mmap *md);
-void perf_mmap__read_done(struct perf_mmap *map);
+int perf_mmap__read_init(struct mmap *md);
+void perf_mmap__read_done(struct mmap *map);
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index aed170b..285d6f3 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -1,14 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  *
  * Copyright (C) 2017 Hari Bathini, IBM Corporation
  */
 
 #include "namespaces.h"
-#include "util.h"
 #include "event.h"
+#include "get_current_dir_name.h"
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -19,8 +17,27 @@
 #include <string.h>
 #include <unistd.h>
 #include <asm/bug.h>
+#include <linux/kernel.h>
+#include <linux/zalloc.h>
 
-struct namespaces *namespaces__new(struct namespaces_event *event)
+static const char *perf_ns__names[] = {
+	[NET_NS_INDEX]		= "net",
+	[UTS_NS_INDEX]		= "uts",
+	[IPC_NS_INDEX]		= "ipc",
+	[PID_NS_INDEX]		= "pid",
+	[USER_NS_INDEX]		= "user",
+	[MNT_NS_INDEX]		= "mnt",
+	[CGROUP_NS_INDEX]	= "cgroup",
+};
+
+const char *perf_ns__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_ns__names))
+		return "UNKNOWN";
+	return perf_ns__names[id];
+}
+
+struct namespaces *namespaces__new(struct perf_record_namespaces *event)
 {
 	struct namespaces *namespaces;
 	u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index d5f46c0..4b33f68 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -1,7 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
  *
  * Copyright (C) 2017 Hari Bathini, IBM Corporation
  */
@@ -15,7 +13,11 @@
 #include <linux/refcount.h>
 #include <linux/types.h>
 
-struct namespaces_event;
+#ifndef HAVE_SETNS_SUPPORT
+int setns(int fd, int nstype);
+#endif
+
+struct perf_record_namespaces;
 
 struct namespaces {
 	struct list_head list;
@@ -23,7 +25,7 @@
 	struct perf_ns_link_info link_info[];
 };
 
-struct namespaces *namespaces__new(struct namespaces_event *event);
+struct namespaces *namespaces__new(struct perf_record_namespaces *event);
 void namespaces__free(struct namespaces *namespaces);
 
 struct nsinfo {
@@ -64,4 +66,6 @@
 
 #define nsinfo__zput(nsi) __nsinfo__zput(&nsi)
 
+const char *perf_ns__name(unsigned int id);
+
 #endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index bad9e02..359db2b 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -8,6 +8,7 @@
 #include "session.h"
 #include "asm/bug.h"
 #include "debug.h"
+#include "ui/progress.h"
 
 #define pr_N(n, fmt, ...) \
 	eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
@@ -80,14 +81,20 @@
 	return oe->copy_on_queue ? __dup_event(oe, event) : event;
 }
 
-static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+static void __free_dup_event(struct ordered_events *oe, union perf_event *event)
 {
-	if (event && oe->copy_on_queue) {
+	if (event) {
 		oe->cur_alloc_size -= event->header.size;
 		free(event);
 	}
 }
 
+static void free_dup_event(struct ordered_events *oe, union perf_event *event)
+{
+	if (oe->copy_on_queue)
+		__free_dup_event(oe, event);
+}
+
 #define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
 static struct ordered_event *alloc_event(struct ordered_events *oe,
 					 union perf_event *event)
@@ -95,21 +102,49 @@
 	struct list_head *cache = &oe->cache;
 	struct ordered_event *new = NULL;
 	union perf_event *new_event;
+	size_t size;
 
 	new_event = dup_event(oe, event);
 	if (!new_event)
 		return NULL;
 
+	/*
+	 * We maintain the following scheme of buffers for ordered
+	 * event allocation:
+	 *
+	 *   to_free list -> buffer1 (64K)
+	 *                   buffer2 (64K)
+	 *                   ...
+	 *
+	 * Each buffer keeps an array of ordered events objects:
+	 *    buffer -> event[0]
+	 *              event[1]
+	 *              ...
+	 *
+	 * Each allocated ordered event is linked to one of
+	 * following lists:
+	 *   - time ordered list 'events'
+	 *   - list of currently removed events 'cache'
+	 *
+	 * Allocation of the ordered event uses the following order
+	 * to get the memory:
+	 *   - use recently removed object from 'cache' list
+	 *   - use available object in current allocation buffer
+	 *   - allocate new buffer if the current buffer is full
+	 *
+	 * Removal of ordered event object moves it from events to
+	 * the cache list.
+	 */
+	size = sizeof(*oe->buffer) + MAX_SAMPLE_BUFFER * sizeof(*new);
+
 	if (!list_empty(cache)) {
 		new = list_entry(cache->next, struct ordered_event, list);
-		list_del(&new->list);
+		list_del_init(&new->list);
 	} else if (oe->buffer) {
-		new = oe->buffer + oe->buffer_idx;
+		new = &oe->buffer->event[oe->buffer_idx];
 		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
 			oe->buffer = NULL;
-	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
-		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
-
+	} else if ((oe->cur_alloc_size + size) < oe->max_alloc_size) {
 		oe->buffer = malloc(size);
 		if (!oe->buffer) {
 			free_dup_event(oe, new_event);
@@ -122,11 +157,11 @@
 		oe->cur_alloc_size += size;
 		list_add(&oe->buffer->list, &oe->to_free);
 
-		/* First entry is abused to maintain the to_free list. */
-		oe->buffer_idx = 2;
-		new = oe->buffer + 1;
+		oe->buffer_idx = 1;
+		new = &oe->buffer->event[0];
 	} else {
 		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+		return NULL;
 	}
 
 	new->event = new_event;
@@ -185,13 +220,12 @@
 	return 0;
 }
 
-static int __ordered_events__flush(struct ordered_events *oe)
+static int do_flush(struct ordered_events *oe, bool show_progress)
 {
 	struct list_head *head = &oe->events;
 	struct ordered_event *tmp, *iter;
 	u64 limit = oe->next_flush;
 	u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
-	bool show_progress = limit == ULLONG_MAX;
 	struct ui_progress prog;
 	int ret;
 
@@ -229,21 +263,28 @@
 	return 0;
 }
 
-int ordered_events__flush(struct ordered_events *oe, enum oe_flush how)
+static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how,
+				   u64 timestamp)
 {
 	static const char * const str[] = {
 		"NONE",
 		"FINAL",
 		"ROUND",
 		"HALF ",
+		"TOP  ",
+		"TIME ",
 	};
 	int err;
+	bool show_progress = false;
 
 	if (oe->nr_events == 0)
 		return 0;
 
 	switch (how) {
 	case OE_FLUSH__FINAL:
+		show_progress = true;
+		__fallthrough;
+	case OE_FLUSH__TOP:
 		oe->next_flush = ULLONG_MAX;
 		break;
 
@@ -264,6 +305,11 @@
 		break;
 	}
 
+	case OE_FLUSH__TIME:
+		oe->next_flush = timestamp;
+		show_progress = false;
+		break;
+
 	case OE_FLUSH__ROUND:
 	case OE_FLUSH__NONE:
 	default:
@@ -274,7 +320,7 @@
 		   str[how], oe->nr_events);
 	pr_oe_time(oe->max_timestamp, "max_timestamp\n");
 
-	err = __ordered_events__flush(oe);
+	err = do_flush(oe, show_progress);
 
 	if (!err) {
 		if (how == OE_FLUSH__ROUND)
@@ -290,7 +336,29 @@
 	return err;
 }
 
-void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver)
+int ordered_events__flush(struct ordered_events *oe, enum oe_flush how)
+{
+	return __ordered_events__flush(oe, how, 0);
+}
+
+int ordered_events__flush_time(struct ordered_events *oe, u64 timestamp)
+{
+	return __ordered_events__flush(oe, OE_FLUSH__TIME, timestamp);
+}
+
+u64 ordered_events__first_time(struct ordered_events *oe)
+{
+	struct ordered_event *event;
+
+	if (list_empty(&oe->events))
+		return 0;
+
+	event = list_first_entry(&oe->events, struct ordered_event, list);
+	return event->timestamp;
+}
+
+void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver,
+			  void *data)
 {
 	INIT_LIST_HEAD(&oe->events);
 	INIT_LIST_HEAD(&oe->cache);
@@ -298,17 +366,43 @@
 	oe->max_alloc_size = (u64) -1;
 	oe->cur_alloc_size = 0;
 	oe->deliver	   = deliver;
+	oe->data	   = data;
+}
+
+static void
+ordered_events_buffer__free(struct ordered_events_buffer *buffer,
+			    unsigned int max, struct ordered_events *oe)
+{
+	if (oe->copy_on_queue) {
+		unsigned int i;
+
+		for (i = 0; i < max; i++)
+			__free_dup_event(oe, buffer->event[i].event);
+	}
+
+	free(buffer);
 }
 
 void ordered_events__free(struct ordered_events *oe)
 {
-	while (!list_empty(&oe->to_free)) {
-		struct ordered_event *event;
+	struct ordered_events_buffer *buffer, *tmp;
 
-		event = list_entry(oe->to_free.next, struct ordered_event, list);
-		list_del(&event->list);
-		free_dup_event(oe, event->event);
-		free(event);
+	if (list_empty(&oe->to_free))
+		return;
+
+	/*
+	 * Current buffer might not have all the events allocated
+	 * yet, we need to free only allocated ones ...
+	 */
+	if (oe->buffer) {
+		list_del_init(&oe->buffer->list);
+		ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+	}
+
+	/* ... and continue with the rest */
+	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
+		list_del_init(&buffer->list);
+		ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
 	}
 }
 
@@ -318,5 +412,5 @@
 
 	ordered_events__free(oe);
 	memset(oe, '\0', sizeof(*oe));
-	ordered_events__init(oe, old_deliver);
+	ordered_events__init(oe, old_deliver, oe->data);
 }
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 8c7a294..0920fb0 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -18,6 +18,8 @@
 	OE_FLUSH__FINAL,
 	OE_FLUSH__ROUND,
 	OE_FLUSH__HALF,
+	OE_FLUSH__TOP,
+	OE_FLUSH__TIME,
 };
 
 struct ordered_events;
@@ -25,32 +27,41 @@
 typedef int (*ordered_events__deliver_t)(struct ordered_events *oe,
 					 struct ordered_event *event);
 
+struct ordered_events_buffer {
+	struct list_head	list;
+	struct ordered_event	event[0];
+};
+
 struct ordered_events {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	u64			max_alloc_size;
-	u64			cur_alloc_size;
-	struct list_head	events;
-	struct list_head	cache;
-	struct list_head	to_free;
-	struct ordered_event	*buffer;
-	struct ordered_event	*last;
-	ordered_events__deliver_t deliver;
-	int			buffer_idx;
-	unsigned int		nr_events;
-	enum oe_flush		last_flush_type;
-	u32			nr_unordered_events;
-	bool                    copy_on_queue;
+	u64				 last_flush;
+	u64				 next_flush;
+	u64				 max_timestamp;
+	u64				 max_alloc_size;
+	u64				 cur_alloc_size;
+	struct list_head		 events;
+	struct list_head		 cache;
+	struct list_head		 to_free;
+	struct ordered_events_buffer	*buffer;
+	struct ordered_event		*last;
+	ordered_events__deliver_t	 deliver;
+	int				 buffer_idx;
+	unsigned int			 nr_events;
+	enum oe_flush			 last_flush_type;
+	u32				 nr_unordered_events;
+	bool				 copy_on_queue;
+	void				*data;
 };
 
 int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
 			  u64 timestamp, u64 file_offset);
 void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
 int ordered_events__flush(struct ordered_events *oe, enum oe_flush how);
-void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver);
+int ordered_events__flush_time(struct ordered_events *oe, u64 timestamp);
+void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver,
+			  void *data);
 void ordered_events__free(struct ordered_events *oe);
 void ordered_events__reinit(struct ordered_events *oe);
+u64 ordered_events__first_time(struct ordered_events *oe);
 
 static inline
 void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index bd779d9..bb4aa88 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
-#include "util/util.h"
 #include "util/debug.h"
+#include "util/event.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
+#include <stdlib.h>
+#include <string.h>
 
 #define BRANCH_OPT(n, m) \
 	{ .name = n, .mode = (m) }
@@ -30,6 +31,7 @@
 	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
 	BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
 	BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
+	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7..b5e2ade 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/hw_breakpoint.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
@@ -9,30 +10,32 @@
 #include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
-#include "../perf.h"
+#include "build-id.h"
 #include "evlist.h"
 #include "evsel.h"
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include <subcmd/exec-cmd.h>
 #include "string2.h"
 #include "strlist.h"
 #include "symbol.h"
-#include "cache.h"
 #include "header.h"
 #include "bpf-loader.h"
 #include "debug.h"
 #include <api/fs/tracing_path.h>
+#include <perf/cpumap.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
 #include "metricgroup.h"
+#include "util/evsel_config.h"
+#include "util/event.h"
 
 #define MAX_NAME_LEN 100
 
@@ -313,14 +316,16 @@
 	return NULL;
 }
 
-static struct perf_evsel *
+static struct evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
 	    char *name, struct perf_pmu *pmu,
-	    struct list_head *config_terms, bool auto_merge_stats)
+	    struct list_head *config_terms, bool auto_merge_stats,
+	    const char *cpu_list)
 {
-	struct perf_evsel *evsel;
-	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
+	struct evsel *evsel;
+	struct perf_cpu_map *cpus = pmu ? pmu->cpus :
+			       cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
 
 	event_attr_init(attr);
 
@@ -329,9 +334,9 @@
 		return NULL;
 
 	(*idx)++;
-	evsel->cpus        = cpu_map__get(cpus);
-	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = pmu ? pmu->is_uncore : false;
+	evsel->core.cpus   = perf_cpu_map__get(cpus);
+	evsel->core.own_cpus = perf_cpu_map__get(cpus);
+	evsel->core.system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -340,7 +345,7 @@
 	if (config_terms)
 		list_splice(config_terms, &evsel->config_terms);
 
-	list_add_tail(&evsel->node, list);
+	list_add_tail(&evsel->core.node, list);
 	return evsel;
 }
 
@@ -348,7 +353,25 @@
 		     struct perf_event_attr *attr, char *name,
 		     struct list_head *config_terms)
 {
-	return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
+	return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM;
+}
+
+static int add_event_tool(struct list_head *list, int *idx,
+			  enum perf_tool_event tool_event)
+{
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+	};
+
+	evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0");
+	if (!evsel)
+		return -ENOMEM;
+	evsel->tool_event = tool_event;
+	if (tool_event == PERF_TOOL_DURATION_TIME)
+		evsel->unit = strdup("ns");
+	return 0;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -489,7 +512,7 @@
 			  struct parse_events_error *err,
 			  struct list_head *head_config)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++);
 	if (IS_ERR(evsel)) {
@@ -505,7 +528,7 @@
 		list_splice(&config_terms, &evsel->config_terms);
 	}
 
-	list_add_tail(&evsel->node, list);
+	list_add_tail(&evsel->core.node, list);
 	return 0;
 }
 
@@ -609,15 +632,24 @@
 	struct list_head *head_config;
 };
 
-static int add_bpf_event(const char *group, const char *event, int fd,
+static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj,
 			 void *_param)
 {
 	LIST_HEAD(new_evsels);
 	struct __add_bpf_event_param *param = _param;
 	struct parse_events_state *parse_state = param->parse_state;
 	struct list_head *list = param->list;
-	struct perf_evsel *pos;
+	struct evsel *pos;
 	int err;
+	/*
+	 * Check if we should add the event, i.e. if it is a TP but starts with a '!',
+	 * then don't add the tracepoint, this will be used for something else, like
+	 * adding to a BPF_MAP_TYPE_PROG_ARRAY.
+	 *
+	 * See tools/perf/examples/bpf/augmented_raw_syscalls.c
+	 */
+	if (group[0] == '!')
+		return 0;
 
 	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
 		 group, event, fd);
@@ -626,22 +658,23 @@
 					  event, parse_state->error,
 					  param->head_config);
 	if (err) {
-		struct perf_evsel *evsel, *tmp;
+		struct evsel *evsel, *tmp;
 
 		pr_debug("Failed to add BPF event %s:%s\n",
 			 group, event);
-		list_for_each_entry_safe(evsel, tmp, &new_evsels, node) {
-			list_del(&evsel->node);
-			perf_evsel__delete(evsel);
+		list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) {
+			list_del_init(&evsel->core.node);
+			evsel__delete(evsel);
 		}
 		return err;
 	}
 	pr_debug("adding %s:%s\n", group, event);
 
-	list_for_each_entry(pos, &new_evsels, node) {
+	list_for_each_entry(pos, &new_evsels, core.node) {
 		pr_debug("adding %s:%s to %p\n",
 			 group, event, pos);
 		pos->bpf_fd = fd;
+		pos->bpf_obj = obj;
 	}
 	list_splice(&new_evsels, list);
 	return 0;
@@ -926,9 +959,12 @@
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
+	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
 };
 
 static bool config_term_shrinked;
@@ -949,6 +985,7 @@
 	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_PERCORE:
 		return true;
 	default:
 		if (!err)
@@ -1037,6 +1074,20 @@
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		CHECK_TYPE_VAL(NUM);
+		break;
+	case PARSE_EVENTS__TERM_TYPE_PERCORE:
+		CHECK_TYPE_VAL(NUM);
+		if ((unsigned int)term->val.num > 1) {
+			err->str = strdup("expected 0 or 1");
+			err->idx = term->err_val;
+			return -EINVAL;
+		}
+		break;
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1084,8 +1135,10 @@
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1162,6 +1215,9 @@
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+			ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
 			break;
@@ -1171,6 +1227,13 @@
 		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
 			ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_PERCORE:
+			ADD_CONFIG_TERM(PERCORE, percore,
+					term->val.num ? true : false);
+			break;
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+			ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0);
+			break;
 		default:
 			break;
 		}
@@ -1225,6 +1288,25 @@
 			 get_config_name(head_config), &config_terms);
 }
 
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event)
+{
+	return add_event_tool(list, &parse_state->idx, tool_event);
+}
+
+static bool config_term_percore(struct list_head *config_terms)
+{
+	struct perf_evsel_config_term *term;
+
+	list_for_each_entry(term, config_terms, list) {
+		if (term->type == PERF_EVSEL__CONFIG_TERM_PERCORE)
+			return term->val.percore;
+	}
+
+	return false;
+}
+
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,
@@ -1234,7 +1316,7 @@
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
 	bool use_uncore_alias;
 	LIST_HEAD(config_terms);
@@ -1259,7 +1341,8 @@
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
+				    auto_merge_stats, NULL);
 		if (evsel) {
 			evsel->pmu_name = name;
 			evsel->use_uncore_alias = use_uncore_alias;
@@ -1287,7 +1370,7 @@
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
 			    get_config_name(head_config), pmu,
-			    &config_terms, auto_merge_stats);
+			    &config_terms, auto_merge_stats, NULL);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -1297,6 +1380,7 @@
 		evsel->metric_name = info.metric_name;
 		evsel->pmu_name = name;
 		evsel->use_uncore_alias = use_uncore_alias;
+		evsel->percore = config_term_percore(&evsel->config_terms);
 	}
 
 	return evsel ? 0 : -ENOMEM;
@@ -1379,13 +1463,13 @@
 parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
 					   struct parse_events_state *parse_state)
 {
-	struct perf_evsel *evsel, *leader;
+	struct evsel *evsel, *leader;
 	uintptr_t *leaders;
 	bool is_leader = true;
 	int i, nr_pmu = 0, total_members, ret = 0;
 
-	leader = list_first_entry(list, struct perf_evsel, node);
-	evsel = list_last_entry(list, struct perf_evsel, node);
+	leader = list_first_entry(list, struct evsel, core.node);
+	evsel = list_last_entry(list, struct evsel, core.node);
 	total_members = evsel->idx - leader->idx + 1;
 
 	leaders = calloc(total_members, sizeof(uintptr_t));
@@ -1447,13 +1531,13 @@
 	__evlist__for_each_entry(list, evsel) {
 		if (i >= nr_pmu)
 			i = 0;
-		evsel->leader = (struct perf_evsel *) leaders[i++];
+		evsel->leader = (struct evsel *) leaders[i++];
 	}
 
 	/* The number of members and group name are same for each group */
 	for (i = 0; i < nr_pmu; i++) {
-		evsel = (struct perf_evsel *) leaders[i];
-		evsel->nr_members = total_members / nr_pmu;
+		evsel = (struct evsel *) leaders[i];
+		evsel->core.nr_members = total_members / nr_pmu;
 		evsel->group_name = name ? strdup(name) : NULL;
 	}
 
@@ -1470,7 +1554,7 @@
 void parse_events__set_leader(char *name, struct list_head *list,
 			      struct parse_events_state *parse_state)
 {
-	struct perf_evsel *leader;
+	struct evsel *leader;
 
 	if (list_empty(list)) {
 		WARN_ONCE(true, "WARNING: failed to set leader: empty list");
@@ -1481,7 +1565,7 @@
 		return;
 
 	__perf_evlist__set_leader(list);
-	leader = list_entry(list->next, struct perf_evsel, node);
+	leader = list_entry(list->next, struct evsel, core.node);
 	leader->group_name = name ? strdup(name) : NULL;
 }
 
@@ -1514,18 +1598,18 @@
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
-			       struct perf_evsel *evsel)
+			       struct evsel *evsel)
 {
-	int eu = evsel ? evsel->attr.exclude_user : 0;
-	int ek = evsel ? evsel->attr.exclude_kernel : 0;
-	int eh = evsel ? evsel->attr.exclude_hv : 0;
-	int eH = evsel ? evsel->attr.exclude_host : 0;
-	int eG = evsel ? evsel->attr.exclude_guest : 0;
-	int eI = evsel ? evsel->attr.exclude_idle : 0;
-	int precise = evsel ? evsel->attr.precise_ip : 0;
+	int eu = evsel ? evsel->core.attr.exclude_user : 0;
+	int ek = evsel ? evsel->core.attr.exclude_kernel : 0;
+	int eh = evsel ? evsel->core.attr.exclude_hv : 0;
+	int eH = evsel ? evsel->core.attr.exclude_host : 0;
+	int eG = evsel ? evsel->core.attr.exclude_guest : 0;
+	int eI = evsel ? evsel->core.attr.exclude_idle : 0;
+	int precise = evsel ? evsel->core.attr.precise_ip : 0;
 	int precise_max = 0;
 	int sample_read = 0;
-	int pinned = evsel ? evsel->attr.pinned : 0;
+	int pinned = evsel ? evsel->core.attr.pinned : 0;
 
 	int exclude = eu | ek | eh;
 	int exclude_GH = evsel ? evsel->exclude_GH : 0;
@@ -1627,7 +1711,7 @@
 
 int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct event_modifier mod;
 
 	if (str == NULL)
@@ -1643,20 +1727,20 @@
 		if (add && get_event_modifier(&mod, str, evsel))
 			return -EINVAL;
 
-		evsel->attr.exclude_user   = mod.eu;
-		evsel->attr.exclude_kernel = mod.ek;
-		evsel->attr.exclude_hv     = mod.eh;
-		evsel->attr.precise_ip     = mod.precise;
-		evsel->attr.exclude_host   = mod.eH;
-		evsel->attr.exclude_guest  = mod.eG;
-		evsel->attr.exclude_idle   = mod.eI;
+		evsel->core.attr.exclude_user   = mod.eu;
+		evsel->core.attr.exclude_kernel = mod.ek;
+		evsel->core.attr.exclude_hv     = mod.eh;
+		evsel->core.attr.precise_ip     = mod.precise;
+		evsel->core.attr.exclude_host   = mod.eH;
+		evsel->core.attr.exclude_guest  = mod.eG;
+		evsel->core.attr.exclude_idle   = mod.eI;
 		evsel->exclude_GH          = mod.exclude_GH;
 		evsel->sample_read         = mod.sample_read;
 		evsel->precise_max         = mod.precise_max;
 		evsel->weak_group	   = mod.weak;
 
 		if (perf_evsel__is_group_leader(evsel))
-			evsel->attr.pinned = mod.pinned;
+			evsel->core.attr.pinned = mod.pinned;
 	}
 
 	return 0;
@@ -1664,7 +1748,7 @@
 
 int parse_events_name(struct list_head *list, char *name)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	__evlist__for_each_entry(list, evsel) {
 		if (!evsel->name)
@@ -1830,12 +1914,12 @@
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str,
+int parse_events(struct evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_state parse_state = {
 		.list   = LIST_HEAD_INIT(parse_state.list),
-		.idx    = evlist->nr_entries,
+		.idx    = evlist->core.nr_entries,
 		.error  = err,
 		.evlist = evlist,
 	};
@@ -1844,7 +1928,7 @@
 	ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS);
 	perf_pmu__parse_cleanup();
 	if (!ret) {
-		struct perf_evsel *last;
+		struct evsel *last;
 
 		if (list_empty(&parse_state.list)) {
 			WARN_ONCE(true, "WARNING: event parser found nothing\n");
@@ -1853,7 +1937,7 @@
 
 		perf_evlist__splice_list_tail(evlist, &parse_state.list);
 		evlist->nr_groups += parse_state.nr_groups;
-		last = perf_evlist__last(evlist);
+		last = evlist__last(evlist);
 		last->cmdline_group_boundary = true;
 
 		return 0;
@@ -1861,7 +1945,7 @@
 
 	/*
 	 * There are 2 users - builtin-record and builtin-test objects.
-	 * Both call perf_evlist__delete in case of error, so we dont
+	 * Both call evlist__delete in case of error, so we dont
 	 * need to bother.
 	 */
 	return ret;
@@ -1939,7 +2023,7 @@
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
-	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	struct evlist *evlist = *(struct evlist **)opt->value;
 	struct parse_events_error err = { .idx = 0, };
 	int ret = parse_events(evlist, str, &err);
 
@@ -1952,12 +2036,12 @@
 }
 
 static int
-foreach_evsel_in_last_glob(struct perf_evlist *evlist,
-			   int (*func)(struct perf_evsel *evsel,
+foreach_evsel_in_last_glob(struct evlist *evlist,
+			   int (*func)(struct evsel *evsel,
 				       const void *arg),
 			   const void *arg)
 {
-	struct perf_evsel *last = NULL;
+	struct evsel *last = NULL;
 	int err;
 
 	/*
@@ -1966,8 +2050,8 @@
 	 *
 	 * So no need to WARN here, let *func do this.
 	 */
-	if (evlist->nr_entries > 0)
-		last = perf_evlist__last(evlist);
+	if (evlist->core.nr_entries > 0)
+		last = evlist__last(evlist);
 
 	do {
 		err = (*func)(last, arg);
@@ -1976,15 +2060,15 @@
 		if (!last)
 			return 0;
 
-		if (last->node.prev == &evlist->entries)
+		if (last->core.node.prev == &evlist->core.entries)
 			return 0;
-		last = list_entry(last->node.prev, struct perf_evsel, node);
+		last = list_entry(last->core.node.prev, struct evsel, core.node);
 	} while (!last->cmdline_group_boundary);
 
 	return 0;
 }
 
-static int set_filter(struct perf_evsel *evsel, const void *arg)
+static int set_filter(struct evsel *evsel, const void *arg)
 {
 	const char *str = arg;
 	bool found = false;
@@ -1997,7 +2081,7 @@
 		return -1;
 	}
 
-	if (evsel->attr.type == PERF_TYPE_TRACEPOINT) {
+	if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
 		if (perf_evsel__append_tp_filter(evsel, str) < 0) {
 			fprintf(stderr,
 				"not enough memory to hold filter string\n");
@@ -2008,7 +2092,7 @@
 	}
 
 	while ((pmu = perf_pmu__scan(pmu)) != NULL)
-		if (pmu->type == evsel->attr.type) {
+		if (pmu->type == evsel->core.attr.type) {
 			found = true;
 			break;
 		}
@@ -2035,18 +2119,18 @@
 int parse_filter(const struct option *opt, const char *str,
 		 int unset __maybe_unused)
 {
-	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	struct evlist *evlist = *(struct evlist **)opt->value;
 
 	return foreach_evsel_in_last_glob(evlist, set_filter,
 					  (const void *)str);
 }
 
-static int add_exclude_perf_filter(struct perf_evsel *evsel,
+static int add_exclude_perf_filter(struct evsel *evsel,
 				   const void *arg __maybe_unused)
 {
 	char new_filter[64];
 
-	if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+	if (evsel == NULL || evsel->core.attr.type != PERF_TYPE_TRACEPOINT) {
 		fprintf(stderr,
 			"--exclude-perf option should follow a -e tracepoint option\n");
 		return -1;
@@ -2067,7 +2151,7 @@
 		 const char *arg __maybe_unused,
 		 int unset __maybe_unused)
 {
-	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	struct evlist *evlist = *(struct evlist **)opt->value;
 
 	return foreach_evsel_in_last_glob(evlist, add_exclude_perf_filter,
 					  NULL);
@@ -2233,20 +2317,20 @@
 {
 	bool ret = true;
 	int open_return;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct perf_event_attr attr = {
 		.type = type,
 		.config = config,
 		.disabled = 1,
 	};
-	struct thread_map *tmap = thread_map__new_by_tid(0);
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
 
 	if (tmap == NULL)
 		return false;
 
-	evsel = perf_evsel__new(&attr);
+	evsel = evsel__new(&attr);
 	if (evsel) {
-		open_return = perf_evsel__open(evsel, NULL, tmap);
+		open_return = evsel__open(evsel, NULL, tmap);
 		ret = open_return >= 0;
 
 		if (open_return == -EACCES) {
@@ -2257,12 +2341,13 @@
 			 * by default as some ARM machines do not support it.
 			 *
 			 */
-			evsel->attr.exclude_kernel = 1;
-			ret = perf_evsel__open(evsel, NULL, tmap) >= 0;
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
 		}
-		perf_evsel__delete(evsel);
+		evsel__delete(evsel);
 	}
 
+	perf_thread_map__put(tmap);
 	return ret;
 }
 
@@ -2333,6 +2418,7 @@
 				printf("  %-50s [%s]\n", buf, "SDT event");
 				free(buf);
 			}
+			free(path);
 		} else
 			printf("  %-50s [%s]\n", nd->s, "SDT event");
 		if (nd2) {
@@ -2419,6 +2505,25 @@
 	return evt_num;
 }
 
+static void print_tool_event(const char *name, const char *event_glob,
+			     bool name_only)
+{
+	if (event_glob && !strglobmatch(name, event_glob))
+		return;
+	if (name_only)
+		printf("%s ", name);
+	else
+		printf("  %-50s [%s]\n", name, "Tool event");
+
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+	print_tool_event("duration_time", event_glob, name_only);
+	if (pager_in_use())
+		printf("\n");
+}
+
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only)
@@ -2454,7 +2559,7 @@
 		if (!name_only && strlen(syms->alias))
 			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
 		else
-			strncpy(name, syms->symbol, MAX_NAME_LEN);
+			strlcpy(name, syms->symbol, MAX_NAME_LEN);
 
 		evt_list[evt_i] = strdup(name);
 		if (evt_list[evt_i] == NULL)
@@ -2502,6 +2607,7 @@
 
 	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
 			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+	print_tool_events(event_glob, name_only);
 
 	print_hwcache_events(event_glob, name_only);
 
@@ -2532,7 +2638,7 @@
 
 	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.h b/tools/perf/util/parse-events.h
index 4473dac..616ca1e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -12,8 +12,8 @@
 #include <string.h>
 
 struct list_head;
-struct perf_evsel;
-struct perf_evlist;
+struct evsel;
+struct evlist;
 struct parse_events_error;
 
 struct option;
@@ -31,7 +31,7 @@
 const char *event_type(int type);
 
 int parse_events_option(const struct option *opt, const char *str, int unset);
-int parse_events(struct perf_evlist *evlist, const char *str,
+int parse_events(struct evlist *evlist, const char *str,
 		 struct parse_events_error *error);
 int parse_events_terms(struct list_head *terms, const char *str);
 int parse_filter(const struct option *opt, const char *str, int unset);
@@ -71,9 +71,12 @@
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
+	PARSE_EVENTS__TERM_TYPE_PERCORE,
+	PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
@@ -117,7 +120,7 @@
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
-	struct perf_evlist	  *evlist;
+	struct evlist	  *evlist;
 	struct list_head	  *terms;
 };
 
@@ -159,6 +162,10 @@
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
+enum perf_tool_event;
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2,
 			   struct parse_events_error *error,
@@ -199,6 +206,7 @@
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3..7469497 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -15,6 +15,7 @@
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
+#include "evsel.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -154,6 +155,14 @@
 	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
+static int tool(yyscan_t scanner, enum perf_tool_event event)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = event;
+	return PE_VALUE_SYM_TOOL;
+}
+
 static int term(yyscan_t scanner, int type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -269,10 +278,13 @@
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
 no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
+percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
+aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
@@ -321,7 +333,7 @@
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-duration_time					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index da8fe57..48126ae 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -9,12 +9,11 @@
 #define YYDEBUG 1
 
 #include <fnmatch.h>
+#include <stdio.h>
 #include <linux/compiler.h>
-#include <linux/list.h>
 #include <linux/types.h>
-#include "util.h"
 #include "pmu.h"
-#include "debug.h"
+#include "evsel.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
@@ -45,6 +44,7 @@
 
 %token PE_START_EVENTS PE_START_TERMS
 %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_NAME
 %token PE_BPF_OBJECT PE_BPF_SOURCE
@@ -58,6 +58,7 @@
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
+%type <num> PE_VALUE_SYM_TOOL
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
@@ -311,7 +312,7 @@
 	$$ = list;
 }
 |
-value_sym sep_slash_dc
+value_sym sep_slash_slash_dc
 {
 	struct list_head *list;
 	int type = $1 >> 16;
@@ -321,6 +322,15 @@
 	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
 	$$ = list;
 }
+|
+PE_VALUE_SYM_TOOL sep_slash_slash_dc
+{
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+	$$ = list;
+}
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
@@ -468,7 +478,6 @@
 PE_BPF_OBJECT opt_event_config
 {
 	struct parse_events_state *parse_state = _parse_state;
-	struct parse_events_error *error = parse_state->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
@@ -614,7 +623,6 @@
 PE_NAME array '=' PE_NAME
 {
 	struct parse_events_term *term;
-	int i;
 
 	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
 					$1, $4, &@1, &@4));
@@ -702,7 +710,7 @@
 
 sep_dc: ':' |
 
-sep_slash_dc: '/' | ':' |
+sep_slash_slash_dc: '/' '/' | ':' |
 
 %%
 
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index e6599e2..ef46c28 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,17 +1,22 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
-#include "util/util.h"
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <stdio.h>
 #include "util/debug.h"
 #include <subcmd/parse-options.h>
+#include "util/perf_regs.h"
 #include "util/parse-regs-options.h"
 
-int
-parse_regs(const struct option *opt, const char *str, int unset)
+static int
+__parse_regs(const struct option *opt, const char *str, int unset, bool intr)
 {
 	uint64_t *mode = (uint64_t *)opt->value;
 	const struct sample_reg *r;
 	char *s, *os = NULL, *p;
 	int ret = -1;
+	uint64_t mask;
 
 	if (unset)
 		return 0;
@@ -22,6 +27,11 @@
 	if (*mode)
 		return -1;
 
+	if (intr)
+		mask = arch__intr_reg_mask();
+	else
+		mask = arch__user_reg_mask();
+
 	/* str may be NULL in case no arg is passed to -I */
 	if (str) {
 		/* because str is read-only */
@@ -37,19 +47,20 @@
 			if (!strcmp(s, "?")) {
 				fprintf(stderr, "available registers: ");
 				for (r = sample_reg_masks; r->name; r++) {
-					fprintf(stderr, "%s ", r->name);
+					if (r->mask & mask)
+						fprintf(stderr, "%s ", r->name);
 				}
 				fputc('\n', stderr);
 				/* just printing available regs */
 				return -1;
 			}
 			for (r = sample_reg_masks; r->name; r++) {
-				if (!strcasecmp(s, r->name))
+				if ((r->mask & mask) && !strcasecmp(s, r->name))
 					break;
 			}
 			if (!r->name) {
-				ui__warning("unknown register %s,"
-					    " check man page\n", s);
+				ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n",
+					    s, intr ? "-I" : "--user-regs=");
 				goto error;
 			}
 
@@ -65,8 +76,20 @@
 
 	/* default to all possible regs */
 	if (*mode == 0)
-		*mode = PERF_REGS_MASK;
+		*mode = mask;
 error:
 	free(os);
 	return ret;
 }
+
+int
+parse_user_regs(const struct option *opt, const char *str, int unset)
+{
+	return __parse_regs(opt, str, unset, false);
+}
+
+int
+parse_intr_regs(const struct option *opt, const char *str, int unset)
+{
+	return __parse_regs(opt, str, unset, true);
+}
diff --git a/tools/perf/util/parse-regs-options.h b/tools/perf/util/parse-regs-options.h
index cdefb1a..2b23d25 100644
--- a/tools/perf/util/parse-regs-options.h
+++ b/tools/perf/util/parse-regs-options.h
@@ -2,5 +2,6 @@
 #ifndef _PERF_PARSE_REGS_OPTIONS_H
 #define _PERF_PARSE_REGS_OPTIONS_H 1
 struct option;
-int parse_regs(const struct option *opt, const char *str, int unset);
+int parse_user_regs(const struct option *opt, const char *str, int unset);
+int parse_intr_regs(const struct option *opt, const char *str, int unset);
 #endif /* _PERF_PARSE_REGS_OPTIONS_H */
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index ca56ba2..caed033 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,11 +11,12 @@
  *
  * which is what it's designed for.
  */
-#include "cache.h"
 #include "path.h"
+#include "cache.h"
 #include <linux/kernel.h>
 #include <limits.h>
 #include <stdio.h>
+#include <string.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <dirent.h>
diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h
index f014f90..083429b 100644
--- a/tools/perf/util/path.h
+++ b/tools/perf/util/path.h
@@ -2,6 +2,9 @@
 #ifndef _PERF_PATH_H
 #define _PERF_PATH_H
 
+#include <stddef.h>
+#include <stdbool.h>
+
 struct dirent;
 
 int path__join(char *bf, size_t size, const char *path1, const char *path2);
diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c
index 4f3aa8d..7a0ab35 100644
--- a/tools/perf/util/perf-hooks.c
+++ b/tools/perf/util/perf-hooks.c
@@ -8,10 +8,10 @@
 
 #include <errno.h>
 #include <stdlib.h>
+#include <string.h>
 #include <setjmp.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/perf-hooks.h"
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
new file mode 100644
index 0000000..d4ad3f0
--- /dev/null
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
+#include "util/evsel_fprintf.h"
+
+struct bit_names {
+	int bit;
+	const char *name;
+};
+
+static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
+{
+	bool first_bit = true;
+	int i = 0;
+
+	do {
+		if (value & bits[i].bit) {
+			buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
+			first_bit = false;
+		}
+	} while (bits[++i].name != NULL);
+}
+
+static void __p_sample_type(char *buf, size_t size, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
+		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
+		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
+		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
+		bit_name(WEIGHT), bit_name(PHYS_ADDR),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	__p_bits(buf, size, value, bits);
+}
+
+static void __p_branch_sample_type(char *buf, size_t size, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
+		bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
+		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
+		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
+		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	__p_bits(buf, size, value, bits);
+}
+
+static void __p_read_format(char *buf, size_t size, u64 value)
+{
+#define bit_name(n) { PERF_FORMAT_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
+		bit_name(ID), bit_name(GROUP),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	__p_bits(buf, size, value, bits);
+}
+
+#define BUF_SIZE		1024
+
+#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
+#define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
+#define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
+#define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
+#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
+#define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
+
+#define PRINT_ATTRn(_n, _f, _p)				\
+do {							\
+	if (attr->_f) {					\
+		_p(attr->_f);				\
+		ret += attr__fprintf(fp, _n, buf, priv);\
+	}						\
+} while (0)
+
+#define PRINT_ATTRf(_f, _p)	PRINT_ATTRn(#_f, _f, _p)
+
+int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
+			     attr__fprintf_f attr__fprintf, void *priv)
+{
+	char buf[BUF_SIZE];
+	int ret = 0;
+
+	PRINT_ATTRf(type, p_unsigned);
+	PRINT_ATTRf(size, p_unsigned);
+	PRINT_ATTRf(config, p_hex);
+	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
+	PRINT_ATTRf(sample_type, p_sample_type);
+	PRINT_ATTRf(read_format, p_read_format);
+
+	PRINT_ATTRf(disabled, p_unsigned);
+	PRINT_ATTRf(inherit, p_unsigned);
+	PRINT_ATTRf(pinned, p_unsigned);
+	PRINT_ATTRf(exclusive, p_unsigned);
+	PRINT_ATTRf(exclude_user, p_unsigned);
+	PRINT_ATTRf(exclude_kernel, p_unsigned);
+	PRINT_ATTRf(exclude_hv, p_unsigned);
+	PRINT_ATTRf(exclude_idle, p_unsigned);
+	PRINT_ATTRf(mmap, p_unsigned);
+	PRINT_ATTRf(comm, p_unsigned);
+	PRINT_ATTRf(freq, p_unsigned);
+	PRINT_ATTRf(inherit_stat, p_unsigned);
+	PRINT_ATTRf(enable_on_exec, p_unsigned);
+	PRINT_ATTRf(task, p_unsigned);
+	PRINT_ATTRf(watermark, p_unsigned);
+	PRINT_ATTRf(precise_ip, p_unsigned);
+	PRINT_ATTRf(mmap_data, p_unsigned);
+	PRINT_ATTRf(sample_id_all, p_unsigned);
+	PRINT_ATTRf(exclude_host, p_unsigned);
+	PRINT_ATTRf(exclude_guest, p_unsigned);
+	PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
+	PRINT_ATTRf(exclude_callchain_user, p_unsigned);
+	PRINT_ATTRf(mmap2, p_unsigned);
+	PRINT_ATTRf(comm_exec, p_unsigned);
+	PRINT_ATTRf(use_clockid, p_unsigned);
+	PRINT_ATTRf(context_switch, p_unsigned);
+	PRINT_ATTRf(write_backward, p_unsigned);
+	PRINT_ATTRf(namespaces, p_unsigned);
+	PRINT_ATTRf(ksymbol, p_unsigned);
+	PRINT_ATTRf(bpf_event, p_unsigned);
+	PRINT_ATTRf(aux_output, p_unsigned);
+
+	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
+	PRINT_ATTRf(bp_type, p_unsigned);
+	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
+	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
+	PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
+	PRINT_ATTRf(sample_regs_user, p_hex);
+	PRINT_ATTRf(sample_stack_user, p_unsigned);
+	PRINT_ATTRf(clockid, p_signed);
+	PRINT_ATTRf(sample_regs_intr, p_hex);
+	PRINT_ATTRf(aux_watermark, p_unsigned);
+	PRINT_ATTRf(sample_max_stack, p_unsigned);
+
+	return ret;
+}
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 2acfcc5..2774cec 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -13,6 +13,16 @@
 	return SDT_ARG_SKIP;
 }
 
+uint64_t __weak arch__intr_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
+uint64_t __weak arch__user_reg_mask(void)
+{
+	return PERF_REGS_MASK;
+}
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index c9319f8..47fe34e 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -12,6 +12,7 @@
 	uint64_t mask;
 };
 #define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
+#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
 #define SMPL_REG_END { .name = NULL }
 
 extern const struct sample_reg sample_reg_masks[];
@@ -22,16 +23,22 @@
 };
 
 int arch_sdt_arg_parse_op(char *old_op, char **new_op);
+uint64_t arch__intr_reg_mask(void);
+uint64_t arch__user_reg_mask(void);
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
 
+#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
+
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK	0
 #define PERF_REGS_MAX	0
 
+#define DWARF_MINIMAL_REGS PERF_REGS_MASK
+
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
 	return NULL;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7e49baa..5608da8 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/list.h>
 #include <linux/compiler.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <subcmd/pager.h>
 #include <sys/types.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -13,14 +16,14 @@
 #include <api/fs/fs.h>
 #include <locale.h>
 #include <regex.h>
-#include "util.h"
+#include <perf/cpumap.h>
+#include "debug.h"
 #include "pmu.h"
 #include "parse-events.h"
-#include "cpumap.h"
 #include "header.h"
 #include "pmu-events/pmu-events.h"
-#include "cache.h"
 #include "string2.h"
+#include "strbuf.h"
 
 struct perf_pmu_format {
 	char *name;
@@ -29,8 +32,6 @@
 	struct list_head list;
 };
 
-#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
-
 int perf_pmu_parse(struct list_head *list, char *name);
 extern FILE *perf_pmu_in;
 
@@ -100,7 +101,7 @@
 	return 0;
 }
 
-static int convert_scale(const char *scale, char **end, double *sval)
+int perf_pmu__convert_scale(const char *scale, char **end, double *sval)
 {
 	char *lc;
 	int ret = 0;
@@ -145,7 +146,7 @@
 	int fd, ret = -1;
 	char path[PATH_MAX];
 
-	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -163,7 +164,7 @@
 	else
 		scale[sret] = '\0';
 
-	ret = convert_scale(scale, NULL, &alias->scale);
+	ret = perf_pmu__convert_scale(scale, NULL, &alias->scale);
 error:
 	close(fd);
 	return ret;
@@ -175,7 +176,7 @@
 	ssize_t sret;
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -205,7 +206,7 @@
 	char path[PATH_MAX];
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -223,7 +224,7 @@
 	char path[PATH_MAX];
 	int fd;
 
-	snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+	scnprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -371,7 +372,7 @@
 				desc ? strdup(desc) : NULL;
 	alias->topic = topic ? strdup(topic) : NULL;
 	if (unit) {
-		if (convert_scale(unit, &unit, &alias->scale) < 0)
+		if (perf_pmu__convert_scale(unit, &unit, &alias->scale) < 0)
 			return -1;
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
@@ -396,7 +397,7 @@
 	buf[ret] = 0;
 
 	/* Remove trailing newline from sysfs file */
-	rtrim(buf);
+	strim(buf);
 
 	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
 				     NULL, NULL, NULL);
@@ -573,16 +574,16 @@
 	closedir(dir);
 }
 
-static struct cpu_map *__pmu_cpumask(const char *path)
+static struct perf_cpu_map *__pmu_cpumask(const char *path)
 {
 	FILE *file;
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 
 	file = fopen(path, "r");
 	if (!file)
 		return NULL;
 
-	cpus = cpu_map__read(file);
+	cpus = perf_cpu_map__read(file);
 	fclose(file);
 	return cpus;
 }
@@ -594,10 +595,10 @@
 #define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
 #define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
 
-static struct cpu_map *pmu_cpumask(const char *name)
+static struct perf_cpu_map *pmu_cpumask(const char *name)
 {
 	char path[PATH_MAX];
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 	const char *templates[] = {
 		CPUS_TEMPLATE_UNCORE,
@@ -622,12 +623,12 @@
 static bool pmu_is_uncore(const char *name)
 {
 	char path[PATH_MAX];
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 
 	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
 	cpus = __pmu_cpumask(path);
-	cpu_map__put(cpus);
+	perf_cpu_map__put(cpus);
 
 	return !!cpus;
 }
@@ -655,45 +656,6 @@
 	return 0;
 }
 
-/*
- * Return the CPU id as a raw string.
- *
- * Each architecture should provide a more precise id string that
- * can be use to match the architecture's "mapfile".
- */
-char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
-{
-	return NULL;
-}
-
-/* Return zero when the cpuid from the mapfile.csv matches the
- * cpuid string generated on this platform.
- * Otherwise return non-zero.
- */
-int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
-{
-	regex_t re;
-	regmatch_t pmatch[1];
-	int match;
-
-	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
-		/* Warn unable to generate match particular string. */
-		pr_info("Invalid regular expression %s\n", mapcpuid);
-		return 1;
-	}
-
-	match = !regexec(&re, cpuid, 1, pmatch, 0);
-	regfree(&re);
-	if (match) {
-		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
-
-		/* Verify the entire string matched. */
-		if (match_len == strlen(cpuid))
-			return 0;
-	}
-	return 1;
-}
-
 static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;
@@ -741,6 +703,46 @@
 	return map;
 }
 
+static bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
+{
+	char *tmp = NULL, *tok, *str;
+	bool res;
+
+	str = strdup(pmu_name);
+	if (!str)
+		return false;
+
+	/*
+	 * uncore alias may be from different PMU with common prefix
+	 */
+	tok = strtok_r(str, ",", &tmp);
+	if (strncmp(pmu_name, tok, strlen(tok))) {
+		res = false;
+		goto out;
+	}
+
+	/*
+	 * Match more complex aliases where the alias name is a comma-delimited
+	 * list of tokens, orderly contained in the matching PMU name.
+	 *
+	 * Example: For alias "socket,pmuname" and PMU "socketX_pmunameY", we
+	 *	    match "socket" in "socketX_pmunameY" and then "pmuname" in
+	 *	    "pmunameY".
+	 */
+	for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+		name = strstr(name, tok);
+		if (!name) {
+			res = false;
+			goto out;
+		}
+	}
+
+	res = true;
+out:
+	free(str);
+	return res;
+}
+
 /*
  * From the pmu_events_map, find the table of PMU events that corresponds
  * to the current running CPU. Then, add all PMU events from that table
@@ -750,9 +752,7 @@
 {
 	int i;
 	struct pmu_events_map *map;
-	struct pmu_event *pe;
 	const char *name = pmu->name;
-	const char *pname;
 
 	map = perf_pmu__find_map(pmu);
 	if (!map)
@@ -763,20 +763,24 @@
 	 */
 	i = 0;
 	while (1) {
+		const char *cpu_name = is_arm_pmu_core(name) ? name : "cpu";
+		struct pmu_event *pe = &map->table[i++];
+		const char *pname = pe->pmu ? pe->pmu : cpu_name;
 
-		pe = &map->table[i++];
 		if (!pe->name) {
 			if (pe->metric_group || pe->metric_name)
 				continue;
 			break;
 		}
 
-		if (!is_arm_pmu_core(name)) {
-			pname = pe->pmu ? pe->pmu : "cpu";
-			if (strcmp(pname, name))
-				continue;
-		}
+		if (pmu_is_uncore(name) &&
+		    pmu_uncore_alias_match(pname, name))
+			goto new_alias;
 
+		if (strcmp(pname, name))
+			continue;
+
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
@@ -793,6 +797,19 @@
 	return NULL;
 }
 
+static int pmu_max_precise(const char *name)
+{
+	char path[PATH_MAX];
+	int max_precise = -1;
+
+	scnprintf(path, PATH_MAX,
+		 "bus/event_source/devices/%s/caps/max_precise",
+		 name);
+
+	sysfs__read_int(path, &max_precise);
+	return max_precise;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -825,6 +842,7 @@
 	pmu->name = strdup(name);
 	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(name);
+	pmu->max_precise = pmu_max_precise(name);
 	pmu_add_cpu_aliases(&aliases, pmu);
 
 	INIT_LIST_HEAD(&pmu->format);
@@ -1229,7 +1247,7 @@
 		info->metric_expr = alias->metric_expr;
 		info->metric_name = alias->metric_name;
 
-		list_del(&term->list);
+		list_del_init(&term->list);
 		free(term);
 	}
 
@@ -1360,7 +1378,7 @@
 			break;
 		s += wlen;
 		column += n;
-		s = ltrim(s);
+		s = skip_spaces(s);
 	}
 }
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 76fecec..f36ade6 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -6,9 +6,10 @@
 #include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
-#include "evsel.h"
 #include "parse-events.h"
 
+struct perf_evsel_config_term;
+
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
 	PERF_PMU_FORMAT_VALUE_CONFIG1,
@@ -16,6 +17,7 @@
 };
 
 #define PERF_PMU_FORMAT_BITS 64
+#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
 
 struct perf_event_attr;
 
@@ -24,12 +26,12 @@
 	__u32 type;
 	bool selectable;
 	bool is_uncore;
+	int max_precise;
 	struct perf_event_attr *default_config;
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
 	struct list_head list;    /* ELEM */
-	int (*set_drv_config)	(struct perf_evsel_config_term *term);
 };
 
 struct perf_pmu_info {
@@ -94,4 +96,6 @@
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 
+int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
index 23e3670..599a154 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "print_binary.h"
 #include <linux/log2.h>
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 int binary__fprintf(unsigned char *data, size_t len,
 		    size_t bytes_per_line, binary__fprintf_t printer,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index f119eb6..91cab5f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1,22 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * probe-event.c : perf-probe definition to probe_events format converter
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  */
 
 #include <inttypes.h>
@@ -33,15 +19,17 @@
 #include <limits.h>
 #include <elf.h>
 
-#include "util.h"
+#include "build-id.h"
 #include "event.h"
+#include "namespaces.h"
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
-#include "cache.h"
+#include "dso.h"
 #include "color.h"
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
-#include "thread.h"
 #include <api/fs/fs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
@@ -49,8 +37,11 @@
 #include "probe-file.h"
 #include "session.h"
 #include "string2.h"
+#include "strbuf.h"
 
-#include "sane_ctype.h"
+#include <subcmd/pager.h>
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 #define PERFPROBE_GROUP "probe"
 
@@ -157,8 +148,10 @@
 	if (module && strchr(module, '/'))
 		return dso__new_map(module);
 
-	if (!module)
-		module = "kernel";
+	if (!module) {
+		pos = machine__kernel_map(host_machine);
+		return map__get(pos);
+	}
 
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		/* short_name is "[module]" */
@@ -223,9 +216,9 @@
 
 static void clear_perf_probe_point(struct perf_probe_point *pp)
 {
-	free(pp->file);
-	free(pp->function);
-	free(pp->lazy_line);
+	zfree(&pp->file);
+	zfree(&pp->function);
+	zfree(&pp->lazy_line);
 }
 
 static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
@@ -469,9 +462,12 @@
 					strcpy(reason, "(unknown)");
 			} else
 				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
-			if (!silent)
-				pr_err("Failed to find the path for %s: %s\n",
-					module ?: "kernel", reason);
+			if (!silent) {
+				if (module)
+					pr_err("Module %s is not loaded, please specify its full path name.\n", module);
+				else
+					pr_err("Failed to find the path for the kernel: %s\n", reason);
+			}
 			return NULL;
 		}
 		path = dso->long_name;
@@ -692,7 +688,7 @@
 		return ret;
 
 	for (i = 0; i < ntevs && ret >= 0; i++) {
-		/* point.address is the addres of point.symbol + point.offset */
+		/* point.address is the address of point.symbol + point.offset */
 		tevs[i].point.address -= stext;
 		tevs[i].point.module = strdup(exec);
 		if (!tevs[i].point.module) {
@@ -1181,12 +1177,11 @@
 
 void line_range__clear(struct line_range *lr)
 {
-	free(lr->function);
-	free(lr->file);
-	free(lr->path);
-	free(lr->comp_dir);
+	zfree(&lr->function);
+	zfree(&lr->file);
+	zfree(&lr->path);
+	zfree(&lr->comp_dir);
 	intlist__delete(lr->line_list);
-	memset(lr, 0, sizeof(*lr));
 }
 
 int line_range__init(struct line_range *lr)
@@ -1569,6 +1564,17 @@
 		str = tmp + 1;
 	}
 
+	tmp = strchr(str, '@');
+	if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
+		if (!user_access_is_supported()) {
+			semantic_error("ftrace does not support user access\n");
+			return -EINVAL;
+		}
+		*tmp = '\0';
+		arg->user_access = true;
+		pr_debug("user_access ");
+	}
+
 	tmp = strchr(str, ':');
 	if (tmp) {	/* Type setting */
 		*tmp = '\0';
@@ -1819,6 +1825,12 @@
 			tp->offset = strtoul(fmt2_str, NULL, 10);
 	}
 
+	if (tev->uprobes) {
+		fmt2_str = strchr(p, '(');
+		if (fmt2_str)
+			tp->ref_ctr_offset = strtoul(fmt2_str + 1, NULL, 0);
+	}
+
 	tev->nargs = argc - 2;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
 	if (tev->args == NULL) {
@@ -2012,6 +2024,22 @@
 	return err;
 }
 
+static int
+synthesize_uprobe_trace_def(struct probe_trace_event *tev, struct strbuf *buf)
+{
+	struct probe_trace_point *tp = &tev->point;
+	int err;
+
+	err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address);
+
+	if (err >= 0 && tp->ref_ctr_offset) {
+		if (!uprobe_ref_ctr_is_supported())
+			return -1;
+		err = strbuf_addf(buf, "(0x%lx)", tp->ref_ctr_offset);
+	}
+	return err >= 0 ? 0 : -1;
+}
+
 char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 {
 	struct probe_trace_point *tp = &tev->point;
@@ -2041,15 +2069,17 @@
 	}
 
 	/* Use the tp->address for uprobes */
-	if (tev->uprobes)
-		err = strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address);
-	else if (!strncmp(tp->symbol, "0x", 2))
+	if (tev->uprobes) {
+		err = synthesize_uprobe_trace_def(tev, &buf);
+	} else if (!strncmp(tp->symbol, "0x", 2)) {
 		/* Absolute address. See try_to_find_absolute_address() */
 		err = strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "",
 				  tp->module ? ":" : "", tp->address);
-	else
+	} else {
 		err = strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "",
 				tp->module ? ":" : "", tp->symbol, tp->offset);
+	}
+
 	if (err)
 		goto error;
 
@@ -2185,15 +2215,15 @@
 	struct perf_probe_arg_field *field, *next;
 	int i;
 
-	free(pev->event);
-	free(pev->group);
-	free(pev->target);
+	zfree(&pev->event);
+	zfree(&pev->group);
+	zfree(&pev->target);
 	clear_perf_probe_point(&pev->point);
 
 	for (i = 0; i < pev->nargs; i++) {
-		free(pev->args[i].name);
-		free(pev->args[i].var);
-		free(pev->args[i].type);
+		zfree(&pev->args[i].name);
+		zfree(&pev->args[i].var);
+		zfree(&pev->args[i].type);
 		field = pev->args[i].field;
 		while (field) {
 			next = field->next;
@@ -2202,8 +2232,8 @@
 			field = next;
 		}
 	}
-	free(pev->args);
-	memset(pev, 0, sizeof(*pev));
+	pev->nargs = 0;
+	zfree(&pev->args);
 }
 
 #define strdup_or_goto(str, label)	\
@@ -2284,15 +2314,15 @@
 	struct probe_trace_arg_ref *ref, *next;
 	int i;
 
-	free(tev->event);
-	free(tev->group);
-	free(tev->point.symbol);
-	free(tev->point.realname);
-	free(tev->point.module);
+	zfree(&tev->event);
+	zfree(&tev->group);
+	zfree(&tev->point.symbol);
+	zfree(&tev->point.realname);
+	zfree(&tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
-		free(tev->args[i].name);
-		free(tev->args[i].value);
-		free(tev->args[i].type);
+		zfree(&tev->args[i].name);
+		zfree(&tev->args[i].value);
+		zfree(&tev->args[i].type);
 		ref = tev->args[i].ref;
 		while (ref) {
 			next = ref->next;
@@ -2300,8 +2330,8 @@
 			ref = next;
 		}
 	}
-	free(tev->args);
-	memset(tev, 0, sizeof(*tev));
+	zfree(&tev->args);
+	tev->nargs = 0;
 }
 
 struct kprobe_blacklist_node {
@@ -2318,8 +2348,8 @@
 	while (!list_empty(blacklist)) {
 		node = list_first_entry(blacklist,
 					struct kprobe_blacklist_node, list);
-		list_del(&node->list);
-		free(node->symbol);
+		list_del_init(&node->list);
+		zfree(&node->symbol);
 		free(node);
 	}
 }
@@ -2633,6 +2663,13 @@
 {
 	int i;
 	char *buf = synthesize_probe_trace_command(tev);
+	struct probe_trace_point *tp = &tev->point;
+
+	if (tp->ref_ctr_offset && !uprobe_ref_ctr_is_supported()) {
+		pr_warning("A semaphore is associated with %s:%s and "
+			   "seems your kernel doesn't support it.\n",
+			   tev->group, tev->event);
+	}
 
 	/* Old uprobe event doesn't support memory dereference */
 	if (!tev->uprobes || tev->nargs == 0 || !buf)
@@ -3031,7 +3068,7 @@
 	/*
 	 * Give it a '0x' leading symbol name.
 	 * In __add_probe_trace_events, a NULL symbol is interpreted as
-	 * invalud.
+	 * invalid.
 	 */
 	if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0)
 		goto errout;
@@ -3497,7 +3534,8 @@
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-	for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&map->dso->symbol_names); nd;
+	     nd = rb_next(nd)) {
 		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 
 		if (strfilter__compare(_filter, pos->sym.name))
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 45b14f0..96a319c 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -4,8 +4,9 @@
 
 #include <linux/compiler.h>
 #include <stdbool.h>
-#include "intlist.h"
-#include "namespaces.h"
+
+struct intlist;
+struct nsinfo;
 
 /* Probe related configurations */
 struct probe_conf {
@@ -27,6 +28,7 @@
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
+	unsigned long	ref_ctr_offset;	/* SDT reference counter offset */
 	unsigned long	address;	/* Actual address of the trace point */
 	bool		retprobe;	/* Return probe flag */
 };
@@ -35,6 +37,7 @@
 struct probe_trace_arg_ref {
 	struct probe_trace_arg_ref	*next;	/* Next reference */
 	long				offset;	/* Offset value */
+	bool				user_access;	/* User-memory access */
 };
 
 /* kprobe-tracer and uprobe-tracer tracing argument */
@@ -80,6 +83,7 @@
 	char				*var;	/* Variable name */
 	char				*type;	/* Type name */
 	struct perf_probe_arg_field	*field;	/* Structure fields */
+	bool				user_access;	/* User-memory access */
 };
 
 /* Perf probe probing event (point + arg) */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index b76088f..b659466 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -1,18 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * probe-file.c : operate ftrace k/uprobe events files
  *
  * Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  */
 #include <errno.h>
 #include <fcntl.h>
@@ -20,15 +10,17 @@
 #include <sys/types.h>
 #include <sys/uio.h>
 #include <unistd.h>
-#include "util.h"
+#include <linux/zalloc.h>
+#include "namespaces.h"
 #include "event.h"
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
-#include "cache.h"
+#include "build-id.h"
+#include "dso.h"
 #include "color.h"
 #include "symbol.h"
-#include "thread.h"
+#include "strbuf.h"
 #include <api/fs/tracing_path.h>
 #include "probe-event.h"
 #include "probe-file.h"
@@ -424,7 +416,7 @@
 
 	if (target && build_id_cache__cached(target)) {
 		/* This is a cached buildid */
-		strncpy(sbuildid, target, SBUILD_ID_SIZE);
+		strlcpy(sbuildid, target, SBUILD_ID_SIZE);
 		dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
 		goto found;
 	}
@@ -696,8 +688,16 @@
 #ifdef HAVE_GELF_GETNOTE_SUPPORT
 static unsigned long long sdt_note__get_addr(struct sdt_note *note)
 {
-	return note->bit32 ? (unsigned long long)note->addr.a32[0]
-		 : (unsigned long long)note->addr.a64[0];
+	return note->bit32 ?
+		(unsigned long long)note->addr.a32[SDT_NOTE_IDX_LOC] :
+		(unsigned long long)note->addr.a64[SDT_NOTE_IDX_LOC];
+}
+
+static unsigned long long sdt_note__get_ref_ctr_offset(struct sdt_note *note)
+{
+	return note->bit32 ?
+		(unsigned long long)note->addr.a32[SDT_NOTE_IDX_REFCTR] :
+		(unsigned long long)note->addr.a64[SDT_NOTE_IDX_REFCTR];
 }
 
 static const char * const type_to_suffix[] = {
@@ -775,14 +775,21 @@
 {
 	struct strbuf buf;
 	char *ret = NULL, **args;
-	int i, args_count;
+	int i, args_count, err;
+	unsigned long long ref_ctr_offset;
 
 	if (strbuf_init(&buf, 32) < 0)
 		return NULL;
 
-	if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
-				sdtgrp, note->name, pathname,
-				sdt_note__get_addr(note)) < 0)
+	err = strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
+			sdtgrp, note->name, pathname,
+			sdt_note__get_addr(note));
+
+	ref_ctr_offset = sdt_note__get_ref_ctr_offset(note);
+	if (ref_ctr_offset && err >= 0)
+		err = strbuf_addf(&buf, "(0x%llx)", ref_ctr_offset);
+
+	if (err < 0)
 		goto error;
 
 	if (!note->args)
@@ -998,6 +1005,8 @@
 enum ftrace_readme {
 	FTRACE_README_PROBE_TYPE_X = 0,
 	FTRACE_README_KRETPROBE_OFFSET,
+	FTRACE_README_UPROBE_REF_CTR,
+	FTRACE_README_USER_ACCESS,
 	FTRACE_README_END,
 };
 
@@ -1009,6 +1018,8 @@
 	[idx] = {.pattern = pat, .avail = false}
 	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
 	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
+	DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
+	DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
 };
 
 static bool scan_ftrace_readme(enum ftrace_readme type)
@@ -1064,3 +1075,13 @@
 {
 	return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
 }
+
+bool uprobe_ref_ctr_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR);
+}
+
+bool user_access_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_USER_ACCESS);
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 63f29b1..986c1c9 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -69,6 +69,8 @@
 int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
+bool uprobe_ref_ctr_is_supported(void);
+bool user_access_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c37fbef..cd9f95e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1,22 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * probe-finder.c : C expression to kprobe event converter
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
  */
 
 #include <inttypes.h>
@@ -33,11 +19,12 @@
 #include <dwarf-regs.h>
 
 #include <linux/bitops.h>
+#include <linux/zalloc.h>
 #include "event.h"
 #include "dso.h"
 #include "debug.h"
 #include "intlist.h"
-#include "util.h"
+#include "strbuf.h"
 #include "strlist.h"
 #include "symbol.h"
 #include "probe-finder.h"
@@ -294,7 +281,7 @@
 
 static int convert_variable_type(Dwarf_Die *vr_die,
 				 struct probe_trace_arg *tvar,
-				 const char *cast)
+				 const char *cast, bool user_access)
 {
 	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
@@ -334,7 +321,8 @@
 	pr_debug("%s type is %s.\n",
 		 dwarf_diename(vr_die), dwarf_diename(&type));
 
-	if (cast && strcmp(cast, "string") == 0) {	/* String type */
+	if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
+		/* String type */
 		ret = dwarf_tag(&type);
 		if (ret != DW_TAG_pointer_type &&
 		    ret != DW_TAG_array_type) {
@@ -357,6 +345,7 @@
 				pr_warning("Out of memory error\n");
 				return -ENOMEM;
 			}
+			(*ref_ptr)->user_access = user_access;
 		}
 		if (!die_compare_name(&type, "char") &&
 		    !die_compare_name(&type, "unsigned char")) {
@@ -411,7 +400,7 @@
 static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				    struct perf_probe_arg_field *field,
 				    struct probe_trace_arg_ref **ref_ptr,
-				    Dwarf_Die *die_mem)
+				    Dwarf_Die *die_mem, bool user_access)
 {
 	struct probe_trace_arg_ref *ref = *ref_ptr;
 	Dwarf_Die type;
@@ -448,6 +437,7 @@
 				*ref_ptr = ref;
 		}
 		ref->offset += dwarf_bytesize(&type) * field->index;
+		ref->user_access = user_access;
 		goto next;
 	} else if (tag == DW_TAG_pointer_type) {
 		/* Check the pointer and dereference */
@@ -519,17 +509,18 @@
 		}
 	}
 	ref->offset += (long)offs;
+	ref->user_access = user_access;
 
 	/* If this member is unnamed, we need to reuse this field */
 	if (!dwarf_diename(die_mem))
 		return convert_variable_fields(die_mem, varname, field,
-						&ref, die_mem);
+						&ref, die_mem, user_access);
 
 next:
 	/* Converting next field */
 	if (field->next)
 		return convert_variable_fields(die_mem, field->name,
-					field->next, &ref, die_mem);
+				field->next, &ref, die_mem, user_access);
 	else
 		return 0;
 }
@@ -555,11 +546,12 @@
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
 					      pf->pvar->field, &pf->tvar->ref,
-					      &die_mem);
+					      &die_mem, pf->pvar->user_access);
 		vr_die = &die_mem;
 	}
 	if (ret == 0)
-		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type);
+		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type,
+					    pf->pvar->user_access);
 	/* *expr will be cached in libdw. Don't free it. */
 	return ret;
 }
@@ -1253,6 +1245,17 @@
 	return n;
 }
 
+static bool trace_event_finder_overlap(struct trace_event_finder *tf)
+{
+	int i;
+
+	for (i = 0; i < tf->ntevs; i++) {
+		if (tf->pf.addr == tf->tevs[i].point.address)
+			return true;
+	}
+	return false;
+}
+
 /* Add a found probe point into trace event list */
 static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
@@ -1263,6 +1266,14 @@
 	struct perf_probe_arg *args = NULL;
 	int ret, i;
 
+	/*
+	 * For some reason (e.g. different column assigned to same address)
+	 * This callback can be called with the address which already passed.
+	 * Ignore it first.
+	 */
+	if (trace_event_finder_overlap(tf))
+		return 0;
+
 	/* Check number of tevs */
 	if (tf->ntevs == tf->max_tevs) {
 		pr_warning("Too many( > %d) probe point found.\n",
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 1625298..670c477 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -5,7 +5,7 @@
 #include <stdbool.h>
 #include "intlist.h"
 #include "probe-event.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 #define MAX_PROBE_BUFFER	1024
 #define MAX_PROBES		 128
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index 797fe1a..80ff41f 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -5,11 +5,12 @@
  * (c) 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 
-#include "util.h"
 #include "pstack.h"
 #include "debug.h"
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <stdlib.h>
+#include <string.h>
 
 struct pstack {
 	unsigned short	top;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 7aa0ea6..9af1838 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -6,9 +6,11 @@
 #
 
 util/python.c
-util/ctype.c
+../lib/ctype.c
+util/cap.c
 util/evlist.c
 util/evsel.c
+util/perf_event_attr_fprintf.c
 util/cpumap.c
 util/memswap.c
 util/mmap.c
@@ -16,10 +18,10 @@
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
+../lib/string.c
 ../lib/vsprintf.c
 util/thread_map.c
 util/util.c
-util/xyarray.c
 util/cgroup.c
 util/parse-branch-options.c
 util/rblist.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ce501ba..0246036 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -4,14 +4,19 @@
 #include <inttypes.h>
 #include <poll.h>
 #include <linux/err.h>
+#include <perf/cpumap.h>
+#include <traceevent/event-parse.h>
 #include "evlist.h"
 #include "callchain.h"
 #include "evsel.h"
 #include "event.h"
-#include "cpumap.h"
 #include "print_binary.h"
 #include "thread_map.h"
+#include "trace-event.h"
 #include "mmap.h"
+#include "util/env.h"
+#include <internal/lib.h>
+#include "../perf-sys.h"
 
 #if PY_MAJOR_VERSION < 3
 #define _PyUnicode_FromString(arg) \
@@ -50,11 +55,18 @@
 }
 
 /*
+ * Add this one here not to drag util/env.c
+ */
+struct perf_env perf_env;
+
+/*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.
  */
 int verbose;
 
+int eprintf(int level, int var, const char *fmt, ...);
+
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
@@ -92,7 +104,7 @@
 
 struct pyrf_event {
 	PyObject_HEAD
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct perf_sample sample;
 	union perf_event   event;
 };
@@ -114,12 +126,12 @@
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
 	member_def(perf_event_header, misc, T_UINT, "event misc"),
-	member_def(mmap_event, pid, T_UINT, "event pid"),
-	member_def(mmap_event, tid, T_UINT, "event tid"),
-	member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
-	member_def(mmap_event, len, T_ULONGLONG, "map length"),
-	member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
-	member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+	member_def(perf_record_mmap, pid, T_UINT, "event pid"),
+	member_def(perf_record_mmap, tid, T_UINT, "event tid"),
+	member_def(perf_record_mmap, start, T_ULONGLONG, "start of the map"),
+	member_def(perf_record_mmap, len, T_ULONGLONG, "map length"),
+	member_def(perf_record_mmap, pgoff, T_ULONGLONG, "page offset"),
+	member_def(perf_record_mmap, filename, T_STRING_INPLACE, "backing store"),
 	{ .name = NULL, },
 };
 
@@ -128,8 +140,8 @@
 	PyObject *ret;
 	char *s;
 
-	if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
-			 "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+	if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRI_lx64 ", "
+			 "length: %#" PRI_lx64 ", offset: %#" PRI_lx64 ", "
 			 "filename: %s }",
 		     pevent->event.mmap.pid, pevent->event.mmap.tid,
 		     pevent->event.mmap.start, pevent->event.mmap.len,
@@ -157,18 +169,18 @@
 static PyMemberDef pyrf_task_event__members[] = {
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
-	member_def(fork_event, pid, T_UINT, "event pid"),
-	member_def(fork_event, ppid, T_UINT, "event ppid"),
-	member_def(fork_event, tid, T_UINT, "event tid"),
-	member_def(fork_event, ptid, T_UINT, "event ptid"),
-	member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+	member_def(perf_record_fork, pid, T_UINT, "event pid"),
+	member_def(perf_record_fork, ppid, T_UINT, "event ppid"),
+	member_def(perf_record_fork, tid, T_UINT, "event tid"),
+	member_def(perf_record_fork, ptid, T_UINT, "event ptid"),
+	member_def(perf_record_fork, time, T_ULONGLONG, "timestamp"),
 	{ .name = NULL, },
 };
 
 static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
 {
 	return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
-				   "ptid: %u, time: %" PRIu64 "}",
+				   "ptid: %u, time: %" PRI_lu64 "}",
 				   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
 				   pevent->event.fork.pid,
 				   pevent->event.fork.ppid,
@@ -192,9 +204,9 @@
 static PyMemberDef pyrf_comm_event__members[] = {
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
-	member_def(comm_event, pid, T_UINT, "event pid"),
-	member_def(comm_event, tid, T_UINT, "event tid"),
-	member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+	member_def(perf_record_comm, pid, T_UINT, "event pid"),
+	member_def(perf_record_comm, tid, T_UINT, "event tid"),
+	member_def(perf_record_comm, comm, T_STRING_INPLACE, "process name"),
 	{ .name = NULL, },
 };
 
@@ -221,18 +233,18 @@
 static PyMemberDef pyrf_throttle_event__members[] = {
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
-	member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
-	member_def(throttle_event, id, T_ULONGLONG, "event id"),
-	member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+	member_def(perf_record_throttle, time, T_ULONGLONG, "timestamp"),
+	member_def(perf_record_throttle, id, T_ULONGLONG, "event id"),
+	member_def(perf_record_throttle, stream_id, T_ULONGLONG, "event stream id"),
 	{ .name = NULL, },
 };
 
 static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
 {
-	struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+	struct perf_record_throttle *te = (struct perf_record_throttle *)(&pevent->event.header + 1);
 
-	return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
-				   ", stream_id: %" PRIu64 " }",
+	return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRI_lu64 ", id: %" PRI_lu64
+				   ", stream_id: %" PRI_lu64 " }",
 				   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
 				   te->time, te->id, te->stream_id);
 }
@@ -251,8 +263,8 @@
 
 static PyMemberDef pyrf_lost_event__members[] = {
 	sample_members
-	member_def(lost_event, id, T_ULONGLONG, "event id"),
-	member_def(lost_event, lost, T_ULONGLONG, "number of lost events"),
+	member_def(perf_record_lost, id, T_ULONGLONG, "event id"),
+	member_def(perf_record_lost, lost, T_ULONGLONG, "number of lost events"),
 	{ .name = NULL, },
 };
 
@@ -261,8 +273,8 @@
 	PyObject *ret;
 	char *s;
 
-	if (asprintf(&s, "{ type: lost, id: %#" PRIx64 ", "
-			 "lost: %#" PRIx64 " }",
+	if (asprintf(&s, "{ type: lost, id: %#" PRI_lx64 ", "
+			 "lost: %#" PRI_lx64 " }",
 		     pevent->event.lost.id, pevent->event.lost.lost) < 0) {
 		ret = PyErr_NoMemory();
 	} else {
@@ -286,8 +298,8 @@
 
 static PyMemberDef pyrf_read_event__members[] = {
 	sample_members
-	member_def(read_event, pid, T_UINT, "event pid"),
-	member_def(read_event, tid, T_UINT, "event tid"),
+	member_def(perf_record_read, pid, T_UINT, "event pid"),
+	member_def(perf_record_read, tid, T_UINT, "event tid"),
 	{ .name = NULL, },
 };
 
@@ -336,40 +348,40 @@
 
 static bool is_tracepoint(struct pyrf_event *pevent)
 {
-	return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT;
+	return pevent->evsel->core.attr.type == PERF_TYPE_TRACEPOINT;
 }
 
 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;
+	struct tep_handle *pevent = field->event->tep;
 	void *data = pe->sample.raw_data;
 	PyObject *ret = NULL;
 	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);
@@ -382,13 +394,13 @@
 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 evsel *evsel = pevent->evsel;
+	struct tep_format_field *field;
 
 	if (!evsel->tp_format) {
-		struct event_format *tp_format;
+		struct tep_event *tp_format;
 
-		tp_format = trace_event__tp_format_id(evsel->attr.config);
+		tp_format = trace_event__tp_format_id(evsel->core.attr.config);
 		if (!tp_format)
 			return NULL;
 
@@ -429,8 +441,8 @@
 static PyMemberDef pyrf_context_switch_event__members[] = {
 	sample_members
 	member_def(perf_event_header, type, T_UINT, "event type"),
-	member_def(context_switch_event, next_prev_pid, T_UINT, "next/prev pid"),
-	member_def(context_switch_event, next_prev_tid, T_UINT, "next/prev tid"),
+	member_def(perf_record_switch, next_prev_pid, T_UINT, "next/prev pid"),
+	member_def(perf_record_switch, next_prev_tid, T_UINT, "next/prev tid"),
 	{ .name = NULL, },
 };
 
@@ -535,7 +547,7 @@
 struct pyrf_cpu_map {
 	PyObject_HEAD
 
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 };
 
 static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
@@ -548,7 +560,7 @@
 					 kwlist, &cpustr))
 		return -1;
 
-	pcpus->cpus = cpu_map__new(cpustr);
+	pcpus->cpus = perf_cpu_map__new(cpustr);
 	if (pcpus->cpus == NULL)
 		return -1;
 	return 0;
@@ -556,7 +568,7 @@
 
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
-	cpu_map__put(pcpus->cpus);
+	perf_cpu_map__put(pcpus->cpus);
 	Py_TYPE(pcpus)->tp_free((PyObject*)pcpus);
 }
 
@@ -604,7 +616,7 @@
 struct pyrf_thread_map {
 	PyObject_HEAD
 
-	struct thread_map *threads;
+	struct perf_thread_map *threads;
 };
 
 static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
@@ -625,7 +637,7 @@
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__put(pthreads->threads);
+	perf_thread_map__put(pthreads->threads);
 	Py_TYPE(pthreads)->tp_free((PyObject*)pthreads);
 }
 
@@ -673,7 +685,7 @@
 struct pyrf_evsel {
 	PyObject_HEAD
 
-	struct perf_evsel evsel;
+	struct evsel evsel;
 };
 
 static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
@@ -781,7 +793,7 @@
 	attr.sample_id_all  = sample_id_all;
 	attr.size	    = sizeof(attr);
 
-	perf_evsel__init(&pevsel->evsel, &attr, idx);
+	evsel__init(&pevsel->evsel, &attr, idx);
 	return 0;
 }
 
@@ -794,9 +806,9 @@
 static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct perf_evsel *evsel = &pevsel->evsel;
-	struct cpu_map *cpus = NULL;
-	struct thread_map *threads = NULL;
+	struct evsel *evsel = &pevsel->evsel;
+	struct perf_cpu_map *cpus = NULL;
+	struct perf_thread_map *threads = NULL;
 	PyObject *pcpus = NULL, *pthreads = NULL;
 	int group = 0, inherit = 0;
 	static char *kwlist[] = { "cpus", "threads", "group", "inherit", NULL };
@@ -811,12 +823,12 @@
 	if (pcpus != NULL)
 		cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-	evsel->attr.inherit = inherit;
+	evsel->core.attr.inherit = inherit;
 	/*
 	 * This will group just the fds for this single evsel, to group
 	 * multiple events, use evlist.open().
 	 */
-	if (perf_evsel__open(evsel, cpus, threads) < 0) {
+	if (evsel__open(evsel, cpus, threads) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -857,35 +869,35 @@
 struct pyrf_evlist {
 	PyObject_HEAD
 
-	struct perf_evlist evlist;
+	struct evlist evlist;
 };
 
 static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
 			     PyObject *args, PyObject *kwargs __maybe_unused)
 {
 	PyObject *pcpus = NULL, *pthreads = NULL;
-	struct cpu_map *cpus;
-	struct thread_map *threads;
+	struct perf_cpu_map *cpus;
+	struct perf_thread_map *threads;
 
 	if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
 		return -1;
 
 	threads = ((struct pyrf_thread_map *)pthreads)->threads;
 	cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
-	perf_evlist__init(&pevlist->evlist, cpus, threads);
+	evlist__init(&pevlist->evlist, cpus, threads);
 	return 0;
 }
 
 static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
 {
-	perf_evlist__exit(&pevlist->evlist);
+	evlist__exit(&pevlist->evlist);
 	Py_TYPE(pevlist)->tp_free((PyObject*)pevlist);
 }
 
 static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
 				   PyObject *args, PyObject *kwargs)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
 	static char *kwlist[] = { "pages", "overwrite", NULL };
 	int pages = 128, overwrite = false;
 
@@ -893,7 +905,7 @@
 					 &pages, &overwrite))
 		return NULL;
 
-	if (perf_evlist__mmap(evlist, pages) < 0) {
+	if (evlist__mmap(evlist, pages) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -905,14 +917,14 @@
 static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
 				   PyObject *args, PyObject *kwargs)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
 	static char *kwlist[] = { "timeout", NULL };
 	int timeout = -1, n;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
 		return NULL;
 
-	n = perf_evlist__poll(evlist, timeout);
+	n = evlist__poll(evlist, timeout);
 	if (n < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
@@ -925,21 +937,22 @@
 					 PyObject *args __maybe_unused,
 					 PyObject *kwargs __maybe_unused)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
         PyObject *list = PyList_New(0);
 	int i;
 
-	for (i = 0; i < evlist->pollfd.nr; ++i) {
+	for (i = 0; i < evlist->core.pollfd.nr; ++i) {
 		PyObject *file;
 #if PY_MAJOR_VERSION < 3
-		FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
+		FILE *fp = fdopen(evlist->core.pollfd.entries[i].fd, "r");
 
 		if (fp == NULL)
 			goto free_list;
 
 		file = PyFile_FromFile(fp, "perf", "r", NULL);
 #else
-		file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1);
+		file = PyFile_FromFd(evlist->core.pollfd.entries[i].fd, "perf", "r", -1,
+				     NULL, NULL, NULL, 0);
 #endif
 		if (file == NULL)
 			goto free_list;
@@ -962,29 +975,29 @@
 				  PyObject *args,
 				  PyObject *kwargs __maybe_unused)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
 	PyObject *pevsel;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	if (!PyArg_ParseTuple(args, "O", &pevsel))
 		return NULL;
 
 	Py_INCREF(pevsel);
 	evsel = &((struct pyrf_evsel *)pevsel)->evsel;
-	evsel->idx = evlist->nr_entries;
-	perf_evlist__add(evlist, evsel);
+	evsel->idx = evlist->core.nr_entries;
+	evlist__add(evlist, evsel);
 
-	return Py_BuildValue("i", evlist->nr_entries);
+	return Py_BuildValue("i", evlist->core.nr_entries);
 }
 
-static struct perf_mmap *get_md(struct perf_evlist *evlist, int cpu)
+static struct mmap *get_md(struct evlist *evlist, int cpu)
 {
 	int i;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		struct perf_mmap *md = &evlist->mmap[i];
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
+		struct mmap *md = &evlist->mmap[i];
 
-		if (md->cpu == cpu)
+		if (md->core.cpu == cpu)
 			return md;
 	}
 
@@ -994,11 +1007,11 @@
 static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 					  PyObject *args, PyObject *kwargs)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
-	struct perf_mmap *md;
+	struct mmap *md;
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -1016,7 +1029,7 @@
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
-		struct perf_evsel *evsel;
+		struct evsel *evsel;
 
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
@@ -1047,7 +1060,7 @@
 static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
 				   PyObject *args, PyObject *kwargs)
 {
-	struct perf_evlist *evlist = &pevlist->evlist;
+	struct evlist *evlist = &pevlist->evlist;
 	int group = 0;
 	static char *kwlist[] = { "group", NULL };
 
@@ -1057,7 +1070,7 @@
 	if (group)
 		perf_evlist__set_leader(evlist);
 
-	if (perf_evlist__open(evlist) < 0) {
+	if (evlist__open(evlist) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
 	}
@@ -1110,15 +1123,15 @@
 {
 	struct pyrf_evlist *pevlist = (void *)obj;
 
-	return pevlist->evlist.nr_entries;
+	return pevlist->evlist.core.nr_entries;
 }
 
 static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
 {
 	struct pyrf_evlist *pevlist = (void *)obj;
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
-	if (i >= pevlist->evlist.nr_entries)
+	if (i >= pevlist->evlist.core.nr_entries)
 		return NULL;
 
 	evlist__for_each_entry(&pevlist->evlist, pos) {
@@ -1240,7 +1253,7 @@
 static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 				  PyObject *args, PyObject *kwargs)
 {
-	struct event_format *tp_format;
+	struct tep_event *tp_format;
 	static char *kwlist[] = { "sys", "name", NULL };
 	char *sys  = NULL;
 	char *name = NULL;
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index a920f70..376e86c 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -140,12 +140,12 @@
 
 /* For 'struct intlist' */
 #define DECLARE_RESORT_RB_INTLIST(__name, __ilist)				\
-	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries,			\
+	DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries.rb_root,		\
 				  __ilist->rblist.nr_entries)
 
 /* For 'struct machine->threads' */
-#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)	\
-	DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries,	\
-				  __machine->threads[hash_bucket].nr)
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine, hash_bucket)    \
+ DECLARE_RESORT_RB(__name)(&__machine->threads[hash_bucket].entries.rb_root, \
+			   __machine->threads[hash_bucket].nr)
 
 #endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/rblist.c b/tools/perf/util/rblist.c
index 0efc325..f399b7e 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Based on strlist.c by:
  * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Licensed under the GPLv2.
  */
 
 #include <errno.h>
@@ -13,8 +12,9 @@
 
 int rblist__add_node(struct rblist *rblist, const void *new_entry)
 {
-	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node **p = &rblist->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL, *new_node;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		int rc;
@@ -24,8 +24,10 @@
 		rc = rblist->node_cmp(parent, new_entry);
 		if (rc > 0)
 			p = &(*p)->rb_left;
-		else if (rc < 0)
+		else if (rc < 0) {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 		else
 			return -EEXIST;
 	}
@@ -35,7 +37,7 @@
 		return -ENOMEM;
 
 	rb_link_node(new_node, parent, p);
-	rb_insert_color(new_node, &rblist->entries);
+	rb_insert_color_cached(new_node, &rblist->entries, leftmost);
 	++rblist->nr_entries;
 
 	return 0;
@@ -43,7 +45,7 @@
 
 void rblist__remove_node(struct rblist *rblist, struct rb_node *rb_node)
 {
-	rb_erase(rb_node, &rblist->entries);
+	rb_erase_cached(rb_node, &rblist->entries);
 	--rblist->nr_entries;
 	rblist->node_delete(rblist, rb_node);
 }
@@ -52,8 +54,9 @@
 					 const void *entry,
 					 bool create)
 {
-	struct rb_node **p = &rblist->entries.rb_node;
+	struct rb_node **p = &rblist->entries.rb_root.rb_node;
 	struct rb_node *parent = NULL, *new_node = NULL;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		int rc;
@@ -63,8 +66,10 @@
 		rc = rblist->node_cmp(parent, entry);
 		if (rc > 0)
 			p = &(*p)->rb_left;
-		else if (rc < 0)
+		else if (rc < 0) {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 		else
 			return parent;
 	}
@@ -73,7 +78,8 @@
 		new_node = rblist->node_new(rblist, entry);
 		if (new_node) {
 			rb_link_node(new_node, parent, p);
-			rb_insert_color(new_node, &rblist->entries);
+			rb_insert_color_cached(new_node,
+					       &rblist->entries, leftmost);
 			++rblist->nr_entries;
 		}
 	}
@@ -94,7 +100,7 @@
 void rblist__init(struct rblist *rblist)
 {
 	if (rblist != NULL) {
-		rblist->entries	 = RB_ROOT;
+		rblist->entries	 = RB_ROOT_CACHED;
 		rblist->nr_entries = 0;
 	}
 
@@ -103,7 +109,7 @@
 
 void rblist__exit(struct rblist *rblist)
 {
-	struct rb_node *pos, *next = rb_first(&rblist->entries);
+	struct rb_node *pos, *next = rb_first_cached(&rblist->entries);
 
 	while (next) {
 		pos = next;
@@ -124,7 +130,8 @@
 {
 	struct rb_node *node;
 
-	for (node = rb_first(&rblist->entries); node; node = rb_next(node)) {
+	for (node = rb_first_cached(&rblist->entries); node;
+	     node = rb_next(node)) {
 		if (!idx--)
 			return node;
 	}
diff --git a/tools/perf/util/rblist.h b/tools/perf/util/rblist.h
index 76df15c..14b232a 100644
--- a/tools/perf/util/rblist.h
+++ b/tools/perf/util/rblist.h
@@ -20,7 +20,7 @@
  */
 
 struct rblist {
-	struct rb_root entries;
+	struct rb_root_cached entries;
 	unsigned int   nr_entries;
 
 	int (*node_cmp)(struct rb_node *rbn, const void *entry);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 9cfc7bf..8579505 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -1,35 +1,39 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "cpumap.h"
 #include "parse-events.h"
 #include <errno.h>
+#include <limits.h>
+#include <stdlib.h>
 #include <api/fs/fs.h>
 #include <subcmd/parse-options.h>
-#include "util.h"
+#include <perf/cpumap.h>
 #include "cloexec.h"
+#include "record.h"
+#include "../perf-sys.h"
 
-typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
+typedef void (*setup_probe_fn_t)(struct evsel *evsel);
 
 static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 {
-	struct perf_evlist *evlist;
-	struct perf_evsel *evsel;
+	struct evlist *evlist;
+	struct evsel *evsel;
 	unsigned long flags = perf_event_open_cloexec_flag();
 	int err = -EAGAIN, fd;
 	static pid_t pid = -1;
 
-	evlist = perf_evlist__new();
+	evlist = evlist__new();
 	if (!evlist)
 		return -ENOMEM;
 
 	if (parse_events(evlist, str, NULL))
 		goto out_delete;
 
-	evsel = perf_evlist__first(evlist);
+	evsel = evlist__first(evlist);
 
 	while (1) {
-		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
 		if (fd < 0) {
 			if (pid == -1 && errno == EACCES) {
 				pid = 0;
@@ -43,7 +47,7 @@
 
 	fn(evsel);
 
-	fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+	fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
 	if (fd < 0) {
 		if (errno == EINVAL)
 			err = -EINVAL;
@@ -53,21 +57,21 @@
 	err = 0;
 
 out_delete:
-	perf_evlist__delete(evlist);
+	evlist__delete(evlist);
 	return err;
 }
 
 static bool perf_probe_api(setup_probe_fn_t fn)
 {
 	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 	int cpu, ret, i = 0;
 
-	cpus = cpu_map__new(NULL);
+	cpus = perf_cpu_map__new(NULL);
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__put(cpus);
+	perf_cpu_map__put(cpus);
 
 	do {
 		ret = perf_do_probe_api(fn, cpu, try[i++]);
@@ -78,19 +82,19 @@
 	return false;
 }
 
-static void perf_probe_sample_identifier(struct perf_evsel *evsel)
+static void perf_probe_sample_identifier(struct evsel *evsel)
 {
-	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+	evsel->core.attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
 }
 
-static void perf_probe_comm_exec(struct perf_evsel *evsel)
+static void perf_probe_comm_exec(struct evsel *evsel)
 {
-	evsel->attr.comm_exec = 1;
+	evsel->core.attr.comm_exec = 1;
 }
 
-static void perf_probe_context_switch(struct perf_evsel *evsel)
+static void perf_probe_context_switch(struct evsel *evsel)
 {
-	evsel->attr.context_switch = 1;
+	evsel->core.attr.context_switch = 1;
 }
 
 bool perf_can_sample_identifier(void)
@@ -115,14 +119,14 @@
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 		.exclude_kernel = 1,
 	};
-	struct cpu_map *cpus;
+	struct perf_cpu_map *cpus;
 	int cpu, fd;
 
-	cpus = cpu_map__new(NULL);
+	cpus = perf_cpu_map__new(NULL);
 	if (!cpus)
 		return false;
 	cpu = cpus->map[0];
-	cpu_map__put(cpus);
+	perf_cpu_map__put(cpus);
 
 	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
 	if (fd < 0)
@@ -132,10 +136,10 @@
 	return true;
 }
 
-void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
+void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 			 struct callchain_param *callchain)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	bool use_sample_identifier = false;
 	bool use_comm_exec;
 	bool sample_id = opts->sample_id;
@@ -147,7 +151,7 @@
 	if (opts->group)
 		perf_evlist__set_leader(evlist);
 
-	if (evlist->cpus->map[0] < 0)
+	if (evlist->core.cpus->map[0] < 0)
 		opts->no_inherit = true;
 
 	use_comm_exec = perf_can_comm_exec();
@@ -155,7 +159,7 @@
 	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__config(evsel, opts, callchain);
 		if (evsel->tracking && use_comm_exec)
-			evsel->attr.comm_exec = 1;
+			evsel->core.attr.comm_exec = 1;
 	}
 
 	if (opts->full_auxtrace) {
@@ -166,11 +170,11 @@
 		 */
 		use_sample_identifier = perf_can_sample_identifier();
 		sample_id = true;
-	} else if (evlist->nr_entries > 1) {
-		struct perf_evsel *first = perf_evlist__first(evlist);
+	} else if (evlist->core.nr_entries > 1) {
+		struct evsel *first = evlist__first(evlist);
 
 		evlist__for_each_entry(evlist, evsel) {
-			if (evsel->attr.sample_type == first->attr.sample_type)
+			if (evsel->core.attr.sample_type == first->core.attr.sample_type)
 				continue;
 			use_sample_identifier = perf_can_sample_identifier();
 			break;
@@ -256,15 +260,15 @@
 	return record_opts__config_freq(opts);
 }
 
-bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
+bool perf_evlist__can_select_event(struct evlist *evlist, const char *str)
 {
-	struct perf_evlist *temp_evlist;
-	struct perf_evsel *evsel;
+	struct evlist *temp_evlist;
+	struct evsel *evsel;
 	int err, fd, cpu;
 	bool ret = false;
 	pid_t pid = -1;
 
-	temp_evlist = perf_evlist__new();
+	temp_evlist = evlist__new();
 	if (!temp_evlist)
 		return false;
 
@@ -272,19 +276,19 @@
 	if (err)
 		goto out_delete;
 
-	evsel = perf_evlist__last(temp_evlist);
+	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || cpu_map__empty(evlist->cpus)) {
-		struct cpu_map *cpus = cpu_map__new(NULL);
+	if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
+		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
 
 		cpu =  cpus ? cpus->map[0] : 0;
-		cpu_map__put(cpus);
+		perf_cpu_map__put(cpus);
 	} else {
-		cpu = evlist->cpus->map[0];
+		cpu = evlist->core.cpus->map[0];
 	}
 
 	while (1) {
-		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1,
 					 perf_event_open_cloexec_flag());
 		if (fd < 0) {
 			if (pid == -1 && errno == EACCES) {
@@ -299,7 +303,7 @@
 	ret = true;
 
 out_delete:
-	perf_evlist__delete(temp_evlist);
+	evlist__delete(temp_evlist);
 	return ret;
 }
 
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
new file mode 100644
index 0000000..00275af
--- /dev/null
+++ b/tools/perf/util/record.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_RECORD_H
+#define _PERF_RECORD_H
+
+#include <time.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include "util/target.h"
+
+struct option;
+
+struct record_opts {
+	struct target target;
+	bool	      group;
+	bool	      inherit_stat;
+	bool	      no_buffering;
+	bool	      no_inherit;
+	bool	      no_inherit_set;
+	bool	      no_samples;
+	bool	      raw_samples;
+	bool	      sample_address;
+	bool	      sample_phys_addr;
+	bool	      sample_weight;
+	bool	      sample_time;
+	bool	      sample_time_set;
+	bool	      sample_cpu;
+	bool	      period;
+	bool	      period_set;
+	bool	      running_time;
+	bool	      full_auxtrace;
+	bool	      auxtrace_snapshot_mode;
+	bool	      auxtrace_snapshot_on_exit;
+	bool	      record_namespaces;
+	bool	      record_switch_events;
+	bool	      all_kernel;
+	bool	      all_user;
+	bool	      kernel_callchains;
+	bool	      user_callchains;
+	bool	      tail_synthesize;
+	bool	      overwrite;
+	bool	      ignore_missing_thread;
+	bool	      strict_freq;
+	bool	      sample_id;
+	bool	      no_bpf_event;
+	unsigned int  freq;
+	unsigned int  mmap_pages;
+	unsigned int  auxtrace_mmap_pages;
+	unsigned int  user_freq;
+	u64	      branch_stack;
+	u64	      sample_intr_regs;
+	u64	      sample_user_regs;
+	u64	      default_interval;
+	u64	      user_interval;
+	size_t	      auxtrace_snapshot_size;
+	const char    *auxtrace_snapshot_opts;
+	bool	      sample_transaction;
+	unsigned      initial_delay;
+	bool	      use_clockid;
+	clockid_t     clockid;
+	u64	      clockid_res_ns;
+	int	      nr_cblocks;
+	int	      affinity;
+	int	      mmap_flush;
+	unsigned int  comp_level;
+};
+
+extern const char * const *record_usage;
+extern struct option *record_options;
+
+int record__parse_freq(const struct option *opt, const char *str, int unset);
+
+#endif // _PERF_RECORD_H
diff --git a/tools/perf/util/rlimit.c b/tools/perf/util/rlimit.c
new file mode 100644
index 0000000..13521d3
--- /dev/null
+++ b/tools/perf/util/rlimit.c
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+#include "util/debug.h"
+#include "util/rlimit.h"
+#include <sys/time.h>
+#include <sys/resource.h>
+
+/*
+ * Bump the memlock so that we can get bpf maps of a reasonable size,
+ * like the ones used with 'perf trace' and with 'perf test bpf',
+ * improve this to some specific request if needed.
+ */
+void rlimit__bump_memlock(void)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &rlim) == 0) {
+		rlim.rlim_cur *= 4;
+		rlim.rlim_max *= 4;
+
+		if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0) {
+			rlim.rlim_cur /= 2;
+			rlim.rlim_max /= 2;
+
+			if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0)
+				pr_debug("Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc\n");
+		}
+	}
+}
diff --git a/tools/perf/util/rlimit.h b/tools/perf/util/rlimit.h
new file mode 100644
index 0000000..9f59d8e
--- /dev/null
+++ b/tools/perf/util/rlimit.h
@@ -0,0 +1,6 @@
+#ifndef __PERF_RLIMIT_H_
+#define __PERF_RLIMIT_H_
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+void rlimit__bump_memlock(void);
+#endif // __PERF_RLIMIT_H_
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
index 5e52e7b..f3d29d8 100644
--- a/tools/perf/util/rwsem.c
+++ b/tools/perf/util/rwsem.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "util.h"
 #include "rwsem.h"
 
diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
new file mode 100644
index 0000000..d435603
--- /dev/null
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Support for s390 CPU measurement counter set diagnostic facility
+ *
+ * Copyright IBM Corp. 2019
+   Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ *		Thomas Richter <tmricht@linux.ibm.com>
+ */
+#ifndef S390_CPUMCF_KERNEL_H
+#define S390_CPUMCF_KERNEL_H
+
+#define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
+#define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
+
+struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
+	unsigned int def:16;	/* 0-15  Data Entry Format */
+	unsigned int set:16;	/* 16-23 Counter set identifier */
+	unsigned int ctr:16;	/* 24-39 Number of stored counters */
+	unsigned int res1:16;	/* 40-63 Reserved */
+};
+
+struct cf_trailer_entry {	/* CPU-M CF trailer for raw traces (64 byte) */
+	/* 0 - 7 */
+	union {
+		struct {
+			unsigned int clock_base:1;	/* TOD clock base */
+			unsigned int speed:1;		/* CPU speed */
+			/* Measurement alerts */
+			unsigned int mtda:1;	/* Loss of MT ctr. data alert */
+			unsigned int caca:1;	/* Counter auth. change alert */
+			unsigned int lcda:1;	/* Loss of counter data alert */
+		};
+		unsigned long flags;		/* 0-63    All indicators */
+	};
+	/* 8 - 15 */
+	unsigned int cfvn:16;			/* 64-79   Ctr First Version */
+	unsigned int csvn:16;			/* 80-95   Ctr Second Version */
+	unsigned int cpu_speed:32;		/* 96-127  CPU speed */
+	/* 16 - 23 */
+	unsigned long timestamp;		/* 128-191 Timestamp (TOD) */
+	/* 24 - 55 */
+	union {
+		struct {
+			unsigned long progusage1;
+			unsigned long progusage2;
+			unsigned long progusage3;
+			unsigned long tod_base;
+		};
+		unsigned long progusage[4];
+	};
+	/* 56 - 63 */
+	unsigned int mach_type:16;		/* Machine type */
+	unsigned int res1:16;			/* Reserved */
+	unsigned int res2:32;			/* Reserved */
+};
+
+#define	CPUMF_CTR_SET_BASIC	0	/* Basic Counter Set */
+#define	CPUMF_CTR_SET_USER	1	/* Problem-State Counter Set */
+#define	CPUMF_CTR_SET_CRYPTO	2	/* Crypto-Activity Counter Set */
+#define	CPUMF_CTR_SET_EXT	3	/* Extended Counter Set */
+#define	CPUMF_CTR_SET_MT_DIAG	4	/* MT-diagnostic Counter Set */
+#endif
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index d2c78ff..6785cd8 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -17,8 +17,8 @@
  *	see Documentation/perf.data-file-format.txt.
  * PERF_RECORD_AUXTRACE_INFO:
  *	Defines a table of contains for PERF_RECORD_AUXTRACE records. This
- *	record is generated during 'perf record' command. Each record contains up
- *	to 256 entries describing offset and size of the AUXTRACE data in the
+ *	record is generated during 'perf record' command. Each record contains
+ *	up to 256 entries describing offset and size of the AUXTRACE data in the
  *	perf.data file.
  * PERF_RECORD_AUXTRACE_ERROR:
  *	Indicates an error during AUXTRACE collection such as buffer overflow.
@@ -146,19 +146,23 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
-#include "cpumap.h"
+#include <sys/stat.h>
+#include <sys/types.h>
+
 #include "color.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "util.h"
-#include "thread.h"
+#include "tool.h"
 #include "debug.h"
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "s390-cpumcf-kernel.h"
+#include "config.h"
 
 struct s390_cpumsf {
 	struct auxtrace		auxtrace;
@@ -170,6 +174,8 @@
 	u32			pmu_type;
 	u16			machine_type;
 	bool			data_queued;
+	bool			use_logfile;
+	char			*logdir;
 };
 
 struct s390_cpumsf_queue {
@@ -177,12 +183,86 @@
 	unsigned int		queue_nr;
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
+	FILE			*logfile;
+	FILE			*logfile_ctr;
 };
 
-/* Display s390 CPU measurement facility basic-sampling data entry */
-static bool s390_cpumsf_basic_show(const char *color, size_t pos,
-				   struct hws_basic_entry *basic)
+/* Check if the raw data should be dumped to file. If this is the case and
+ * the file to dump to has not been opened for writing, do so.
+ *
+ * Return 0 on success and greater zero on error so processing continues.
+ */
+static int s390_cpumcf_dumpctr(struct s390_cpumsf *sf,
+			       struct perf_sample *sample)
 {
+	struct s390_cpumsf_queue *sfq;
+	struct auxtrace_queue *q;
+	int rc = 0;
+
+	if (!sf->use_logfile || sf->queues.nr_queues <= sample->cpu)
+		return rc;
+
+	q = &sf->queues.queue_array[sample->cpu];
+	sfq = q->priv;
+	if (!sfq)		/* Queue not yet allocated */
+		return rc;
+
+	if (!sfq->logfile_ctr) {
+		char *name;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.ctr.%02x",
+				 sf->logdir, sample->cpu)
+			: asprintf(&name, "aux.ctr.%02x", sample->cpu);
+		if (rc > 0)
+			sfq->logfile_ctr = fopen(name, "w");
+		if (sfq->logfile_ctr == NULL) {
+			pr_err("Failed to open counter set log file %s, "
+			       "continue...\n", name);
+			rc = 1;
+		}
+		free(name);
+	}
+
+	if (sfq->logfile_ctr) {
+		/* See comment above for -4 */
+		size_t n = fwrite(sample->raw_data, sample->raw_size - 4, 1,
+				  sfq->logfile_ctr);
+		if (n != 1) {
+			pr_err("Failed to write counter set data\n");
+			rc = 1;
+		}
+	}
+	return rc;
+}
+
+/* Display s390 CPU measurement facility basic-sampling data entry
+ * Data written on s390 in big endian byte order and contains bit
+ * fields across byte boundaries.
+ */
+static bool s390_cpumsf_basic_show(const char *color, size_t pos,
+				   struct hws_basic_entry *basicp)
+{
+	struct hws_basic_entry *basic = basicp;
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	struct hws_basic_entry local;
+	unsigned long long word = be64toh(*(unsigned long long *)basicp);
+
+	memset(&local, 0, sizeof(local));
+	local.def = be16toh(basicp->def);
+	local.prim_asn = word & 0xffff;
+	local.CL = word >> 30 & 0x3;
+	local.I = word >> 32 & 0x1;
+	local.AS = word >> 33 & 0x3;
+	local.P = word >> 35 & 0x1;
+	local.W = word >> 36 & 0x1;
+	local.T = word >> 37 & 0x1;
+	local.U = word >> 40 & 0xf;
+	local.ia = be64toh(basicp->ia);
+	local.gpp = be64toh(basicp->gpp);
+	local.hpp = be64toh(basicp->hpp);
+	basic = &local;
+#endif
 	if (basic->def != 1) {
 		pr_err("Invalid AUX trace basic entry [%#08zx]\n", pos);
 		return false;
@@ -200,10 +280,22 @@
 	return true;
 }
 
-/* Display s390 CPU measurement facility diagnostic-sampling data entry */
+/* Display s390 CPU measurement facility diagnostic-sampling data entry.
+ * Data written on s390 in big endian byte order and contains bit
+ * fields across byte boundaries.
+ */
 static bool s390_cpumsf_diag_show(const char *color, size_t pos,
-				  struct hws_diag_entry *diag)
+				  struct hws_diag_entry *diagp)
 {
+	struct hws_diag_entry *diag = diagp;
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	struct hws_diag_entry local;
+	unsigned long long word = be64toh(*(unsigned long long *)diagp);
+
+	local.def = be16toh(diagp->def);
+	local.I = word >> 32 & 0x1;
+	diag = &local;
+#endif
 	if (diag->def < S390_CPUMSF_DIAG_DEF_FIRST) {
 		pr_err("Invalid AUX trace diagnostic entry [%#08zx]\n", pos);
 		return false;
@@ -214,35 +306,52 @@
 }
 
 /* Return TOD timestamp contained in an trailer entry */
-static unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
+static unsigned long long trailer_timestamp(struct hws_trailer_entry *te,
+					    int idx)
 {
 	/* te->t set: TOD in STCKE format, bytes 8-15
 	 * to->t not set: TOD in STCK format, bytes 0-7
 	 */
 	unsigned long long ts;
 
-	memcpy(&ts, &te->timestamp[te->t], sizeof(ts));
-	return ts;
+	memcpy(&ts, &te->timestamp[idx], sizeof(ts));
+	return be64toh(ts);
 }
 
 /* Display s390 CPU measurement facility trailer entry */
 static bool s390_cpumsf_trailer_show(const char *color, size_t pos,
 				     struct hws_trailer_entry *te)
 {
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	struct hws_trailer_entry local;
+	const unsigned long long flags = be64toh(te->flags);
+
+	memset(&local, 0, sizeof(local));
+	local.f = flags >> 63 & 0x1;
+	local.a = flags >> 62 & 0x1;
+	local.t = flags >> 61 & 0x1;
+	local.bsdes = be16toh((flags >> 16 & 0xffff));
+	local.dsdes = be16toh((flags & 0xffff));
+	memcpy(&local.timestamp, te->timestamp, sizeof(te->timestamp));
+	local.overflow = be64toh(te->overflow);
+	local.clock_base = be64toh(te->progusage[0]) >> 63 & 1;
+	local.progusage2 = be64toh(te->progusage2);
+	te = &local;
+#endif
 	if (te->bsdes != sizeof(struct hws_basic_entry)) {
 		pr_err("Invalid AUX trace trailer entry [%#08zx]\n", pos);
 		return false;
 	}
 	color_fprintf(stdout, color, "    [%#08zx] Trailer %c%c%c bsdes:%d"
 		      " dsdes:%d Overflow:%lld Time:%#llx\n"
-		      "\t\tC:%d TOD:%#lx 1:%#llx 2:%#llx\n",
+		      "\t\tC:%d TOD:%#lx\n",
 		      pos,
 		      te->f ? 'F' : ' ',
 		      te->a ? 'A' : ' ',
 		      te->t ? 'T' : ' ',
 		      te->bsdes, te->dsdes, te->overflow,
-		      trailer_timestamp(te), te->clock_base, te->progusage2,
-		      te->progusage[0], te->progusage[1]);
+		      trailer_timestamp(te, te->clock_base),
+		      te->clock_base, te->progusage2);
 	return true;
 }
 
@@ -269,13 +378,13 @@
 	*dsdes = *bsdes = 0;
 	if (len & (S390_CPUMSF_PAGESZ - 1))	/* Illegal size */
 		return false;
-	if (basic->def != 1)		/* No basic set entry, must be first */
+	if (be16toh(basic->def) != 1)	/* No basic set entry, must be first */
 		return false;
 	/* Check for trailer entry at end of SDB */
 	te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
 					      - sizeof(*te));
-	*bsdes = te->bsdes;
-	*dsdes = te->dsdes;
+	*bsdes = be16toh(te->bsdes);
+	*dsdes = be16toh(te->dsdes);
 	if (!te->bsdes && !te->dsdes) {
 		/* Very old hardware, use CPUID */
 		switch (machine_type) {
@@ -294,6 +403,11 @@
 			*dsdes = 85;
 			*bsdes = 32;
 			break;
+		case 2964:
+		case 2965:
+			*dsdes = 112;
+			*bsdes = 32;
+			break;
 		default:
 			/* Illegal trailer entry */
 			return false;
@@ -432,19 +546,27 @@
 static unsigned long long get_trailer_time(const unsigned char *buf)
 {
 	struct hws_trailer_entry *te;
-	unsigned long long aux_time;
+	unsigned long long aux_time, progusage2;
+	bool clock_base;
 
 	te = (struct hws_trailer_entry *)(buf + S390_CPUMSF_PAGESZ
 					      - sizeof(*te));
 
-	if (!te->clock_base)	/* TOD_CLOCK_BASE value missing */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	clock_base = be64toh(te->progusage[0]) >> 63 & 0x1;
+	progusage2 = be64toh(te->progusage[1]);
+#else
+	clock_base = te->clock_base;
+	progusage2 = te->progusage2;
+#endif
+	if (!clock_base)	/* TOD_CLOCK_BASE value missing */
 		return 0;
 
 	/* Correct calculation to convert time stamp in trailer entry to
 	 * nano seconds (taken from arch/s390 function tod_to_ns()).
 	 * TOD_CLOCK_BASE is stored in trailer entry member progusage2.
 	 */
-	aux_time = trailer_timestamp(te) - te->progusage2;
+	aux_time = trailer_timestamp(te, clock_base) - progusage2;
 	aux_time = (aux_time >> 9) * 125 + (((aux_time & 0x1ff) * 125) >> 9);
 	return aux_time;
 }
@@ -499,7 +621,7 @@
 	aux_ts = get_trailer_time(buf);
 	if (!aux_ts) {
 		pr_err("[%#08" PRIx64 "] Invalid AUX trailer entry TOD clock base\n",
-		       sfq->buffer->data_offset);
+		       (s64)sfq->buffer->data_offset);
 		aux_ts = ~0ULL;
 		goto out;
 	}
@@ -595,6 +717,12 @@
 			buffer->use_size = buffer->size;
 			buffer->use_data = buffer->data;
 		}
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	} else
 		buffer = sfq->buffer;
 
@@ -606,6 +734,13 @@
 			return -ENOMEM;
 		buffer->use_size = buffer->size;
 		buffer->use_data = buffer->data;
+
+		if (sfq->logfile) {	/* Write into log file */
+			size_t rc = fwrite(buffer->data, buffer->size, 1,
+					   sfq->logfile);
+			if (rc != 1)
+				pr_err("Failed to write auxiliary data\n");
+		}
 	}
 	pr_debug4("%s queue_nr:%d buffer:%" PRId64 " offset:%#" PRIx64 " size:%#zx rest:%#zx\n",
 		  __func__, sfq->queue_nr, buffer->buffer_nr, buffer->offset,
@@ -620,7 +755,7 @@
 	 */
 	if (err) {
 		sfq->buffer = NULL;
-		list_del(&buffer->list);
+		list_del_init(&buffer->list);
 		auxtrace_buffer__free(buffer);
 		if (err > 0)		/* Buffer done, no error */
 			err = 0;
@@ -640,6 +775,23 @@
 	sfq->sf = sf;
 	sfq->queue_nr = queue_nr;
 	sfq->cpu = -1;
+	if (sf->use_logfile) {
+		char *name;
+		int rc;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.smp.%02x",
+				 sf->logdir, queue_nr)
+			: asprintf(&name, "aux.smp.%02x", queue_nr);
+		if (rc > 0)
+			sfq->logfile = fopen(name, "w");
+		if (sfq->logfile == NULL) {
+			pr_err("Failed to open auxiliary log file %s,"
+			       "continue...\n", name);
+			sf->use_logfile = false;
+		}
+		free(name);
+	}
 	return sfq;
 }
 
@@ -731,7 +883,7 @@
 }
 
 static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
-				   pid_t pid, pid_t tid, u64 ip)
+				   pid_t pid, pid_t tid, u64 ip, u64 timestamp)
 {
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 	union perf_event event;
@@ -739,7 +891,7 @@
 
 	strncpy(msg, "Lost Auxiliary Trace Buffer", sizeof(msg) - 1);
 	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
-			     code, cpu, pid, tid, ip, msg);
+			     code, cpu, pid, tid, ip, msg, timestamp);
 
 	err = perf_session__deliver_synth_event(sf->session, &event, NULL);
 	if (err)
@@ -751,11 +903,12 @@
 static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample)
 {
 	return s390_cpumsf_synth_error(sf, 1, sample->cpu,
-				       sample->pid, sample->tid, 0);
+				       sample->pid, sample->tid, 0,
+				       sample->time);
 }
 
 static int
-s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
+s390_cpumsf_process_event(struct perf_session *session,
 			  union perf_event *event,
 			  struct perf_sample *sample,
 			  struct perf_tool *tool)
@@ -764,6 +917,8 @@
 					      struct s390_cpumsf,
 					      auxtrace);
 	u64 timestamp = sample->time;
+	struct evsel *ev_bc000;
+
 	int err = 0;
 
 	if (dump_trace)
@@ -774,6 +929,16 @@
 		return -EINVAL;
 	}
 
+	if (event->header.type == PERF_RECORD_SAMPLE &&
+	    sample->raw_size) {
+		/* Handle event with raw data */
+		ev_bc000 = perf_evlist__event2evsel(session->evlist, event);
+		if (ev_bc000 &&
+		    ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG)
+			err = s390_cpumcf_dumpctr(sf, sample);
+		return err;
+	}
+
 	if (event->header.type == PERF_RECORD_AUX &&
 	    event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
 		return s390_cpumsf_lost(sf, sample);
@@ -850,8 +1015,22 @@
 	struct auxtrace_queues *queues = &sf->queues;
 	unsigned int i;
 
-	for (i = 0; i < queues->nr_queues; i++)
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
+						queues->queue_array[i].priv;
+
+		if (sfq != NULL) {
+			if (sfq->logfile) {
+				fclose(sfq->logfile);
+				sfq->logfile = NULL;
+			}
+			if (sfq->logfile_ctr) {
+				fclose(sfq->logfile_ctr);
+				sfq->logfile_ctr = NULL;
+			}
+		}
 		zfree(&queues->queue_array[i].priv);
+	}
 	auxtrace_queues__free(queues);
 }
 
@@ -864,6 +1043,7 @@
 	auxtrace_heap__free(&sf->heap);
 	s390_cpumsf_free_queues(session);
 	session->auxtrace = NULL;
+	zfree(&sf->logdir);
 	free(sf);
 }
 
@@ -877,25 +1057,62 @@
 
 /* Check itrace options set on perf report command.
  * Return true, if none are set or all options specified can be
- * handled on s390.
+ * handled on s390 (currently only option 'd' for logging.
  * Return false otherwise.
  */
 static bool check_auxtrace_itrace(struct itrace_synth_opts *itops)
 {
+	bool ison = false;
+
 	if (!itops || !itops->set)
 		return true;
-	pr_err("No --itrace options supported\n");
+	ison = itops->inject || itops->instructions || itops->branches ||
+		itops->transactions || itops->ptwrites ||
+		itops->pwr_events || itops->errors ||
+		itops->dont_decode || itops->calls || itops->returns ||
+		itops->callchain || itops->thread_stack ||
+		itops->last_branch;
+	if (!ison)
+		return true;
+	pr_err("Unsupported --itrace options specified\n");
 	return false;
 }
 
+/* Check for AUXTRACE dump directory if it is needed.
+ * On failure print an error message but continue.
+ * Return 0 on wrong keyword in config file and 1 otherwise.
+ */
+static int s390_cpumsf__config(const char *var, const char *value, void *cb)
+{
+	struct s390_cpumsf *sf = cb;
+	struct stat stbuf;
+	int rc;
+
+	if (strcmp(var, "auxtrace.dumpdir"))
+		return 0;
+	sf->logdir = strdup(value);
+	if (sf->logdir == NULL) {
+		pr_err("Failed to find auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		return 1;
+	}
+	rc = stat(sf->logdir, &stbuf);
+	if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
+		pr_err("Missing auxtrace log directory %s,"
+		       " continue with current directory...\n", value);
+		zfree(&sf->logdir);
+	}
+	return 1;
+}
+
 int s390_cpumsf_process_auxtrace_info(union perf_event *event,
 				      struct perf_session *session)
 {
-	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
 	struct s390_cpumsf *sf;
 	int err;
 
-	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event))
+	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info))
 		return -EINVAL;
 
 	sf = zalloc(sizeof(struct s390_cpumsf));
@@ -906,6 +1123,9 @@
 		err = -EINVAL;
 		goto err_free;
 	}
+	sf->use_logfile = session->itrace_synth_opts->log;
+	if (sf->use_logfile)
+		perf_config(s390_cpumsf__config, sf);
 
 	err = auxtrace_queues__init(&sf->queues);
 	if (err)
@@ -940,6 +1160,7 @@
 	auxtrace_queues__free(&sf->queues);
 	session->auxtrace = NULL;
 err_free:
+	zfree(&sf->logdir);
 	free(sf);
 	return err;
 }
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
new file mode 100644
index 0000000..05b43ab
--- /dev/null
+++ b/tools/perf/util/s390-sample-raw.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ * Author(s): Thomas Richter <tmricht@linux.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Architecture specific trace_event function. Save event's bc000 raw data
+ * to file. File name is aux.ctr.## where ## stands for the CPU number the
+ * sample was taken from.
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+
+#include <sys/stat.h>
+#include <linux/compiler.h>
+#include <asm/byteorder.h>
+
+#include "debug.h"
+#include "session.h"
+#include "evlist.h"
+#include "color.h"
+#include "sample-raw.h"
+#include "s390-cpumcf-kernel.h"
+#include "pmu-events/pmu-events.h"
+
+static size_t ctrset_size(struct cf_ctrset_entry *set)
+{
+	return sizeof(*set) + set->ctr * sizeof(u64);
+}
+
+static bool ctrset_valid(struct cf_ctrset_entry *set)
+{
+	return set->def == S390_CPUMCF_DIAG_DEF;
+}
+
+/* CPU Measurement Counter Facility raw data is a byte stream. It is 8 byte
+ * aligned and might have trailing padding bytes.
+ * Display the raw data on screen.
+ */
+static bool s390_cpumcfdg_testctr(struct perf_sample *sample)
+{
+	size_t len = sample->raw_size, offset = 0;
+	unsigned char *buf = sample->raw_data;
+	struct cf_trailer_entry *te;
+	struct cf_ctrset_entry *cep, ce;
+
+	if (!len)
+		return false;
+	while (offset < len) {
+		cep = (struct cf_ctrset_entry *)(buf + offset);
+		ce.def = be16_to_cpu(cep->def);
+		ce.set = be16_to_cpu(cep->set);
+		ce.ctr = be16_to_cpu(cep->ctr);
+		ce.res1 = be16_to_cpu(cep->res1);
+
+		if (!ctrset_valid(&ce) || offset + ctrset_size(&ce) > len) {
+			/* Raw data for counter sets are always multiple of 8
+			 * bytes. Prepending a 4 bytes size field to the
+			 * raw data block in the sample causes the perf tool
+			 * to append 4 padding bytes to make the raw data part
+			 * of the sample a multiple of eight bytes again.
+			 *
+			 * If the last entry (trailer) is 4 bytes off the raw
+			 * area data end, all is good.
+			 */
+			if (len - offset - sizeof(*te) == 4)
+				break;
+			pr_err("Invalid counter set entry at %zd\n", offset);
+			return false;
+		}
+		offset += ctrset_size(&ce);
+	}
+	return true;
+}
+
+/* Dump event bc000 on screen, already tested on correctness. */
+static void s390_cpumcfdg_dumptrail(const char *color, size_t offset,
+				    struct cf_trailer_entry *tep)
+{
+	struct cf_trailer_entry  te;
+
+	te.flags = be64_to_cpu(tep->flags);
+	te.cfvn = be16_to_cpu(tep->cfvn);
+	te.csvn = be16_to_cpu(tep->csvn);
+	te.cpu_speed = be32_to_cpu(tep->cpu_speed);
+	te.timestamp = be64_to_cpu(tep->timestamp);
+	te.progusage1 = be64_to_cpu(tep->progusage1);
+	te.progusage2 = be64_to_cpu(tep->progusage2);
+	te.progusage3 = be64_to_cpu(tep->progusage3);
+	te.tod_base = be64_to_cpu(tep->tod_base);
+	te.mach_type = be16_to_cpu(tep->mach_type);
+	te.res1 = be16_to_cpu(tep->res1);
+	te.res2 = be32_to_cpu(tep->res2);
+
+	color_fprintf(stdout, color, "    [%#08zx] Trailer:%c%c%c%c%c"
+		      " Cfvn:%d Csvn:%d Speed:%d TOD:%#llx\n",
+		      offset, te.clock_base ? 'T' : ' ',
+		      te.speed ? 'S' : ' ', te.mtda ? 'M' : ' ',
+		      te.caca ? 'C' : ' ', te.lcda ? 'L' : ' ',
+		      te.cfvn, te.csvn, te.cpu_speed, te.timestamp);
+	color_fprintf(stdout, color, "\t\t1:%lx 2:%lx 3:%lx TOD-Base:%#llx"
+		      " Type:%x\n\n",
+		      te.progusage1, te.progusage2, te.progusage3,
+		      te.tod_base, te.mach_type);
+}
+
+/* Return starting number of a counter set */
+static int get_counterset_start(int setnr)
+{
+	switch (setnr) {
+	case CPUMF_CTR_SET_BASIC:		/* Basic counter set */
+		return 0;
+	case CPUMF_CTR_SET_USER:		/* Problem state counter set */
+		return 32;
+	case CPUMF_CTR_SET_CRYPTO:		/* Crypto counter set */
+		return 64;
+	case CPUMF_CTR_SET_EXT:			/* Extended counter set */
+		return 128;
+	case CPUMF_CTR_SET_MT_DIAG:		/* Diagnostic counter set */
+		return 448;
+	default:
+		return -1;
+	}
+}
+
+/* Scan the PMU table and extract the logical name of a counter from the
+ * PMU events table. Input is the counter set and counter number with in the
+ * set. Construct the event number and use this as key. If they match return
+ * the name of this counter.
+ * If no match is found a NULL pointer is returned.
+ */
+static const char *get_counter_name(int set, int nr, struct pmu_events_map *map)
+{
+	int rc, event_nr, wanted = get_counterset_start(set) + nr;
+
+	if (map) {
+		struct pmu_event *evp = map->table;
+
+		for (; evp->name || evp->event || evp->desc; ++evp) {
+			if (evp->name == NULL || evp->event == NULL)
+				continue;
+			rc = sscanf(evp->event, "event=%x", &event_nr);
+			if (rc == 1 && event_nr == wanted)
+				return evp->name;
+		}
+	}
+	return NULL;
+}
+
+static void s390_cpumcfdg_dump(struct perf_sample *sample)
+{
+	size_t i, len = sample->raw_size, offset = 0;
+	unsigned char *buf = sample->raw_data;
+	const char *color = PERF_COLOR_BLUE;
+	struct cf_ctrset_entry *cep, ce;
+	struct pmu_events_map *map;
+	struct perf_pmu pmu;
+	u64 *p;
+
+	memset(&pmu, 0, sizeof(pmu));
+	map = perf_pmu__find_map(&pmu);
+	while (offset < len) {
+		cep = (struct cf_ctrset_entry *)(buf + offset);
+
+		ce.def = be16_to_cpu(cep->def);
+		ce.set = be16_to_cpu(cep->set);
+		ce.ctr = be16_to_cpu(cep->ctr);
+		ce.res1 = be16_to_cpu(cep->res1);
+
+		if (!ctrset_valid(&ce)) {	/* Print trailer */
+			s390_cpumcfdg_dumptrail(color, offset,
+						(struct cf_trailer_entry *)cep);
+			return;
+		}
+
+		color_fprintf(stdout, color, "    [%#08zx] Counterset:%d"
+			      " Counters:%d\n", offset, ce.set, ce.ctr);
+		for (i = 0, p = (u64 *)(cep + 1); i < ce.ctr; ++i, ++p) {
+			const char *ev_name = get_counter_name(ce.set, i, map);
+
+			color_fprintf(stdout, color,
+				      "\tCounter:%03d %s Value:%#018lx\n", i,
+				      ev_name ?: "<unknown>", be64_to_cpu(*p));
+		}
+		offset += ctrset_size(&ce);
+	}
+}
+
+/* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events
+ * and if the event was triggered by a counter set diagnostic event display
+ * its raw data.
+ * The function is only invoked when the dump flag -D is set.
+ */
+void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
+				  struct perf_sample *sample)
+{
+	struct evsel *ev_bc000;
+
+	if (event->header.type != PERF_RECORD_SAMPLE)
+		return;
+
+	ev_bc000 = perf_evlist__event2evsel(evlist, event);
+	if (ev_bc000 == NULL ||
+	    ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
+		return;
+
+	/* Display raw data on screen */
+	if (!s390_cpumcfdg_testctr(sample)) {
+		pr_err("Invalid counter set data encountered\n");
+		return;
+	}
+	s390_cpumcfdg_dump(sample);
+}
diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c
new file mode 100644
index 0000000..e84bbe0
--- /dev/null
+++ b/tools/perf/util/sample-raw.c
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <string.h>
+#include "evlist.h"
+#include "env.h"
+#include "sample-raw.h"
+
+/*
+ * Check platform the perf data file was created on and perform platform
+ * specific interpretation.
+ */
+void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist)
+{
+	const char *arch_pf = perf_env__arch(evlist->env);
+
+	if (arch_pf && !strcmp("s390", arch_pf))
+		evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw;
+}
diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h
new file mode 100644
index 0000000..afe1491
--- /dev/null
+++ b/tools/perf/util/sample-raw.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __SAMPLE_RAW_H
+#define __SAMPLE_RAW_H 1
+
+struct evlist;
+union perf_event;
+struct perf_sample;
+
+void perf_evlist__s390_sample_raw(struct evlist *evlist,
+				  union perf_event *event,
+				  struct perf_sample *sample);
+
+void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist);
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h
deleted file mode 100644
index c2b42ff..0000000
--- a/tools/perf/util/sane_ctype.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_SANE_CTYPE_H
-#define _PERF_SANE_CTYPE_H
-
-extern const char *graph_line;
-extern const char *graph_dotted_line;
-extern const char *spaces;
-extern const char *dots;
-
-/* Sane ctype - no locale, and works with signed chars */
-#undef isascii
-#undef isspace
-#undef isdigit
-#undef isxdigit
-#undef isalpha
-#undef isprint
-#undef isalnum
-#undef islower
-#undef isupper
-#undef tolower
-#undef toupper
-
-extern unsigned char sane_ctype[256];
-#define GIT_SPACE		0x01
-#define GIT_DIGIT		0x02
-#define GIT_ALPHA		0x04
-#define GIT_GLOB_SPECIAL	0x08
-#define GIT_REGEX_SPECIAL	0x10
-#define GIT_PRINT_EXTRA		0x20
-#define GIT_PRINT		0x3E
-#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
-#define isascii(x) (((x) & ~0x7f) == 0)
-#define isspace(x) sane_istest(x,GIT_SPACE)
-#define isdigit(x) sane_istest(x,GIT_DIGIT)
-#define isxdigit(x)	\
-	(sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
-#define isalpha(x) sane_istest(x,GIT_ALPHA)
-#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
-#define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
-#define tolower(x) sane_case((unsigned char)(x), 0x20)
-#define toupper(x) sane_case((unsigned char)(x), 0)
-
-static inline int sane_case(int x, int high)
-{
-	if (sane_istest(x, GIT_ALPHA))
-		x = (x & ~0x20) | high;
-	return x;
-}
-
-#endif /* _PERF_SANE_CTYPE_H */
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 82d28c6..7b342ce 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
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 45484f0..741f040 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,9 +34,11 @@
 #include <EXTERN.h>
 #include <perl.h>
 
-#include "../../perf.h"
 #include "../callchain.h"
+#include "../dso.h"
 #include "../machine.h"
+#include "../map.h"
+#include "../symbol.h"
 #include "../thread.h"
 #include "../event.h"
 #include "../trace-event.h"
@@ -99,7 +101,7 @@
 	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 +159,7 @@
 	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 +191,62 @@
 	LEAVE;
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event *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... */
@@ -256,7 +258,7 @@
 }
 
 static SV *perl_process_callchain(struct perf_sample *sample,
-				  struct perf_evsel *evsel,
+				  struct evsel *evsel,
 				  struct addr_location *al)
 {
 	AV *list;
@@ -334,12 +336,12 @@
 }
 
 static void perl_process_tracepoint(struct perf_sample *sample,
-				    struct perf_evsel *evsel,
+				    struct evsel *evsel,
 				    struct addr_location *al)
 {
 	struct thread *thread = al->thread;
-	struct event_format *event = evsel->tp_format;
-	struct format_field *field;
+	struct tep_event *event = evsel->tp_format;
+	struct tep_format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
@@ -351,11 +353,11 @@
 
 	dSP;
 
-	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+	if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
 	if (!event) {
-		pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+		pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config);
 		return;
 	}
 
@@ -370,7 +372,7 @@
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	ENTER;
 	SAVETMPS;
@@ -388,9 +390,9 @@
 	/* 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 +401,7 @@
 		} 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)));
@@ -429,7 +431,7 @@
 
 static void perl_process_event_generic(union perf_event *event,
 				       struct perf_sample *sample,
-				       struct perf_evsel *evsel)
+				       struct evsel *evsel)
 {
 	dSP;
 
@@ -440,7 +442,7 @@
 	SAVETMPS;
 	PUSHMARK(SP);
 	XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size)));
-	XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr))));
+	XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->core.attr, sizeof(evsel->core.attr))));
 	XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample))));
 	XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size)));
 	PUTBACK;
@@ -453,7 +455,7 @@
 
 static void perl_process_event(union perf_event *event,
 			       struct perf_sample *sample,
-			       struct perf_evsel *evsel,
+			       struct evsel *evsel,
 			       struct addr_location *al)
 {
 	perl_process_tracepoint(sample, evsel, al);
@@ -537,10 +539,11 @@
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
+	struct tep_event *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.pl", outfile);
@@ -601,8 +604,11 @@
 }\n\n\
 ");
 
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
@@ -646,11 +652,11 @@
 			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 +674,7 @@
 			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 +684,7 @@
 					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 dfc6093..93c03b3 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -31,11 +31,12 @@
 #include <linux/compiler.h>
 #include <linux/time64.h>
 
-#include "../../perf.h"
+#include "../build-id.h"
+#include "../counts.h"
 #include "../debug.h"
+#include "../dso.h"
 #include "../callchain.h"
 #include "../evsel.h"
-#include "../util.h"
 #include "../event.h"
 #include "../thread.h"
 #include "../comm.h"
@@ -44,8 +45,9 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../call-path.h"
+#include "map.h"
+#include "symbol.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "print_binary.h"
 #include "stat.h"
 #include "mem-events.h"
@@ -110,6 +112,8 @@
 	PyObject		*sample_handler;
 	PyObject		*call_path_handler;
 	PyObject		*call_return_handler;
+	PyObject		*synth_handler;
+	PyObject		*context_switch_handler;
 	bool			db_export_mode;
 };
 
@@ -193,7 +197,7 @@
 		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 +208,7 @@
 	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 +227,8 @@
 	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 +239,7 @@
 		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 +248,10 @@
 	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 +260,7 @@
 
 	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 +268,54 @@
 	Py_DECREF(t);
 }
 
-static void define_event_symbols(struct event_format *event,
+static void define_event_symbols(struct tep_event *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 +323,11 @@
 		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 +336,10 @@
 		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 *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 +357,7 @@
 
 		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);
@@ -388,7 +392,7 @@
 }
 
 static PyObject *python_process_callchain(struct perf_sample *sample,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 struct addr_location *al)
 {
 	PyObject *pylist;
@@ -494,14 +498,14 @@
 		pydict_set_item_string_decref(pyelem, "cycles",
 		    PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
 
-		thread__find_map(thread, sample->cpumode,
-				 br->entries[i].from, &al);
+		thread__find_map_fb(thread, sample->cpumode,
+				    br->entries[i].from, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "from_dsoname",
 					      _PyUnicode_FromString(dsoname));
 
-		thread__find_map(thread, sample->cpumode,
-				 br->entries[i].to, &al);
+		thread__find_map_fb(thread, sample->cpumode,
+				    br->entries[i].to, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "to_dsoname",
 					      _PyUnicode_FromString(dsoname));
@@ -576,14 +580,14 @@
 		if (!pyelem)
 			Py_FatalError("couldn't create Python dictionary");
 
-		thread__find_symbol(thread, sample->cpumode,
-				    br->entries[i].from, &al);
+		thread__find_symbol_fb(thread, sample->cpumode,
+				       br->entries[i].from, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "from",
 					      _PyUnicode_FromString(bf));
 
-		thread__find_symbol(thread, sample->cpumode,
-				    br->entries[i].to, &al);
+		thread__find_symbol_fb(thread, sample->cpumode,
+				       br->entries[i].to, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "to",
 					      _PyUnicode_FromString(bf));
@@ -630,9 +634,9 @@
 
 static void set_sample_read_in_dict(PyObject *dict_sample,
 					 struct perf_sample *sample,
-					 struct perf_evsel *evsel)
+					 struct evsel *evsel)
 {
-	u64 read_format = evsel->attr.read_format;
+	u64 read_format = evsel->core.attr.read_format;
 	PyObject *values;
 	unsigned int i;
 
@@ -701,9 +705,9 @@
 
 static void set_regs_in_dict(PyObject *dict,
 			     struct perf_sample *sample,
-			     struct perf_evsel *evsel)
+			     struct evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	struct perf_event_attr *attr = &evsel->core.attr;
 	char bf[512];
 
 	regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
@@ -718,7 +722,7 @@
 }
 
 static PyObject *get_perf_sample_dict(struct perf_sample *sample,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 struct addr_location *al,
 					 PyObject *callchain)
 {
@@ -733,8 +737,7 @@
 		Py_FatalError("couldn't create Python dictionary");
 
 	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
-	pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize(
-			(const char *)&evsel->attr, sizeof(evsel->attr)));
+	pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr)));
 
 	pydict_set_item_string_decref(dict_sample, "pid",
 			_PyLong_FromLong(sample->pid));
@@ -787,14 +790,14 @@
 }
 
 static void python_process_tracepoint(struct perf_sample *sample,
-				      struct perf_evsel *evsel,
+				      struct evsel *evsel,
 				      struct addr_location *al)
 {
-	struct event_format *event = evsel->tp_format;
+	struct tep_event *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;
@@ -806,7 +809,7 @@
 
 	if (!event) {
 		snprintf(handler_name, sizeof(handler_name),
-			 "ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+			 "ug! no event found for type %" PRIu64, (u64)evsel->core.attr.config);
 		Py_FatalError(handler_name);
 	}
 
@@ -836,7 +839,7 @@
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	context = _PyCapsule_New(scripting_context, NULL, NULL);
 
@@ -867,22 +870,22 @@
 		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);
@@ -946,7 +949,13 @@
 	return PyTuple_SetItem(t, pos, _PyUnicode_FromString(s));
 }
 
-static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
+static int tuple_set_bytes(PyObject *t, unsigned int pos, void *bytes,
+			   unsigned int sz)
+{
+	return PyTuple_SetItem(t, pos, _PyBytes_FromStringAndSize(bytes, sz));
+}
+
+static int python_export_evsel(struct db_export *dbe, struct evsel *evsel)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
@@ -1003,15 +1012,19 @@
 	return 0;
 }
 
-static int python_export_comm(struct db_export *dbe, struct comm *comm)
+static int python_export_comm(struct db_export *dbe, struct comm *comm,
+			      struct thread *thread)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(2);
+	t = tuple_new(5);
 
 	tuple_set_u64(t, 0, comm->db_id);
 	tuple_set_string(t, 1, comm__str(comm));
+	tuple_set_u64(t, 2, thread->db_id);
+	tuple_set_u64(t, 3, comm->start);
+	tuple_set_s32(t, 4, comm->exec);
 
 	call_object(tables->comm_handler, t, "comm_table");
 
@@ -1104,13 +1117,13 @@
 	return 0;
 }
 
-static int python_export_sample(struct db_export *dbe,
-				struct export_sample *es)
+static void python_export_sample_table(struct db_export *dbe,
+				       struct export_sample *es)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(22);
+	t = tuple_new(24);
 
 	tuple_set_u64(t, 0, es->db_id);
 	tuple_set_u64(t, 1, es->evsel->db_id);
@@ -1134,10 +1147,39 @@
 	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
 	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
 	tuple_set_u64(t, 21, es->call_path_id);
+	tuple_set_u64(t, 22, es->sample->insn_cnt);
+	tuple_set_u64(t, 23, es->sample->cyc_cnt);
 
 	call_object(tables->sample_handler, t, "sample_table");
 
 	Py_DECREF(t);
+}
+
+static void python_export_synth(struct db_export *dbe, struct export_sample *es)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, es->db_id);
+	tuple_set_u64(t, 1, es->evsel->core.attr.config);
+	tuple_set_bytes(t, 2, es->sample->raw_data, es->sample->raw_size);
+
+	call_object(tables->synth_handler, t, "synth_data");
+
+	Py_DECREF(t);
+}
+
+static int python_export_sample(struct db_export *dbe,
+				struct export_sample *es)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+
+	python_export_sample_table(dbe, es);
+
+	if (es->evsel->core.attr.type == PERF_TYPE_SYNTH && tables->synth_handler)
+		python_export_synth(dbe, es);
 
 	return 0;
 }
@@ -1172,7 +1214,7 @@
 	u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
 	PyObject *t;
 
-	t = tuple_new(11);
+	t = tuple_new(14);
 
 	tuple_set_u64(t, 0, cr->db_id);
 	tuple_set_u64(t, 1, cr->thread->db_id);
@@ -1185,6 +1227,9 @@
 	tuple_set_u64(t, 8, cr->return_ref);
 	tuple_set_u64(t, 9, cr->cp->parent->db_id);
 	tuple_set_s32(t, 10, cr->flags);
+	tuple_set_u64(t, 11, cr->parent_db_id);
+	tuple_set_u64(t, 12, cr->insn_count);
+	tuple_set_u64(t, 13, cr->cyc_count);
 
 	call_object(tables->call_return_handler, t, "call_return_table");
 
@@ -1193,15 +1238,44 @@
 	return 0;
 }
 
-static int python_process_call_return(struct call_return *cr, void *data)
+static int python_export_context_switch(struct db_export *dbe, u64 db_id,
+					struct machine *machine,
+					struct perf_sample *sample,
+					u64 th_out_id, u64 comm_out_id,
+					u64 th_in_id, u64 comm_in_id, int flags)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(9);
+
+	tuple_set_u64(t, 0, db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_u64(t, 2, sample->time);
+	tuple_set_s32(t, 3, sample->cpu);
+	tuple_set_u64(t, 4, th_out_id);
+	tuple_set_u64(t, 5, comm_out_id);
+	tuple_set_u64(t, 6, th_in_id);
+	tuple_set_u64(t, 7, comm_in_id);
+	tuple_set_s32(t, 8, flags);
+
+	call_object(tables->context_switch_handler, t, "context_switch");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, u64 *parent_db_id,
+				      void *data)
 {
 	struct db_export *dbe = data;
 
-	return db_export__call_return(dbe, cr);
+	return db_export__call_return(dbe, cr, parent_db_id);
 }
 
 static void python_process_general_event(struct perf_sample *sample,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 struct addr_location *al)
 {
 	PyObject *handler, *t, *dict, *callchain;
@@ -1237,12 +1311,12 @@
 
 static void python_process_event(union perf_event *event,
 				 struct perf_sample *sample,
-				 struct perf_evsel *evsel,
+				 struct evsel *evsel,
 				 struct addr_location *al)
 {
 	struct tables *tables = &tables_global;
 
-	switch (evsel->attr.type) {
+	switch (evsel->core.attr.type) {
 	case PERF_TYPE_TRACEPOINT:
 		python_process_tracepoint(sample, evsel, al);
 		break;
@@ -1255,8 +1329,18 @@
 	}
 }
 
+static void python_process_switch(union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine)
+{
+	struct tables *tables = &tables_global;
+
+	if (tables->db_export_mode)
+		db_export__switch(&tables->dbe, event, sample, machine);
+}
+
 static void get_handler_name(char *str, size_t size,
-			     struct perf_evsel *evsel)
+			     struct evsel *evsel)
 {
 	char *p = str;
 
@@ -1269,7 +1353,7 @@
 }
 
 static void
-process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
+process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
 	     struct perf_counts_values *count)
 {
 	PyObject *handler, *t;
@@ -1306,10 +1390,10 @@
 }
 
 static void python_process_stat(struct perf_stat_config *config,
-				struct perf_evsel *counter, u64 tstamp)
+				struct evsel *counter, u64 tstamp)
 {
-	struct thread_map *threads = counter->threads;
-	struct cpu_map *cpus = counter->cpus;
+	struct perf_thread_map *threads = counter->core.threads;
+	struct perf_cpu_map *cpus = counter->core.cpus;
 	int cpu, thread;
 
 	if (config->aggr_mode == AGGR_GLOBAL) {
@@ -1321,7 +1405,7 @@
 	for (thread = 0; thread < threads->nr; thread++) {
 		for (cpu = 0; cpu < cpus->nr; cpu++) {
 			process_stat(counter, cpus->map[cpu],
-				     thread_map__pid(threads, thread), tstamp,
+				     perf_thread_map__pid(threads, thread), tstamp,
 				     perf_counts(counter->counts, cpu, thread));
 		}
 	}
@@ -1470,6 +1554,15 @@
 	SET_TABLE_HANDLER(sample);
 	SET_TABLE_HANDLER(call_path);
 	SET_TABLE_HANDLER(call_return);
+	SET_TABLE_HANDLER(context_switch);
+
+	/*
+	 * Synthesized events are samples but with architecture-specific data
+	 * stored in sample->raw_data. They are exported via
+	 * python_export_sample() and consequently do not need a separate export
+	 * callback.
+	 */
+	tables->synth_handler = get_handler("synth_data");
 }
 
 #if PY_MAJOR_VERSION < 3
@@ -1494,34 +1587,40 @@
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
+	PyMODINIT_FUNC (*initfunc)(void);
 #if PY_MAJOR_VERSION < 3
 	const char **command_line;
 #else
 	wchar_t **command_line;
 #endif
-	char buf[PATH_MAX];
+	/*
+	 * Use a non-const name variable to cope with python 2.6's
+	 * PyImport_AppendInittab prototype
+	 */
+	char buf[PATH_MAX], name[19] = "perf_trace_context";
 	int i, err = 0;
 	FILE *fp;
 
 #if PY_MAJOR_VERSION < 3
+	initfunc = initperf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
 #else
+	initfunc = PyInit_perf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
 #endif
 
+	PyImport_AppendInittab(name, initfunc);
 	Py_Initialize();
 
 #if PY_MAJOR_VERSION < 3
-	initperf_trace_context();
 	PySys_SetArgv(argc + 1, (char **)command_line);
 #else
-	PyInit_perf_trace_context();
 	PySys_SetArgv(argc + 1, command_line);
 #endif
 
@@ -1565,9 +1664,7 @@
 
 static int python_flush_script(void)
 {
-	struct tables *tables = &tables_global;
-
-	return db_export__flush(&tables->dbe);
+	return 0;
 }
 
 /*
@@ -1590,10 +1687,11 @@
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
-	struct event_format *event = NULL;
-	struct format_field *f;
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
+	struct tep_event *event = NULL;
+	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.py", outfile);
@@ -1638,7 +1736,11 @@
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
+
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
@@ -1686,12 +1788,12 @@
 			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 +1811,7 @@
 			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 +1821,7 @@
 					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;
@@ -1776,6 +1878,7 @@
 	.flush_script		= python_flush_script,
 	.stop_script		= python_stop_script,
 	.process_event		= python_process_event,
+	.process_switch		= python_process_switch,
 	.process_stat		= python_process_stat,
 	.process_stat_interval	= python_process_stat_interval,
 	.generate_script	= python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8b93693..061bb4d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,29 +1,100 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
-#include <traceevent/event-parse.h>
+#include <linux/zalloc.h>
 #include <api/fs/fs.h>
 
 #include <byteswap.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/mman.h>
+#include <perf/cpumap.h>
 
+#include "map_symbol.h"
+#include "branch.h"
+#include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "memswap.h"
+#include "map.h"
+#include "symbol.h"
 #include "session.h"
 #include "tool.h"
-#include "sort.h"
-#include "util.h"
-#include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
 #include "thread.h"
 #include "thread-stack.h"
+#include "sample-raw.h"
 #include "stat.h"
+#include "ui/progress.h"
+#include "../perf.h"
+#include "arch/common.h"
+#include <internal/lib.h>
+#include <linux/err.h>
+
+#ifdef HAVE_ZSTD_SUPPORT
+static int perf_session__process_compressed_event(struct perf_session *session,
+						  union perf_event *event, u64 file_offset)
+{
+	void *src;
+	size_t decomp_size, src_size;
+	u64 decomp_last_rem = 0;
+	size_t mmap_len, decomp_len = session->header.env.comp_mmap_len;
+	struct decomp *decomp, *decomp_last = session->decomp_last;
+
+	if (decomp_last) {
+		decomp_last_rem = decomp_last->size - decomp_last->head;
+		decomp_len += decomp_last_rem;
+	}
+
+	mmap_len = sizeof(struct decomp) + decomp_len;
+	decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE,
+		      MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	if (decomp == MAP_FAILED) {
+		pr_err("Couldn't allocate memory for decompression\n");
+		return -1;
+	}
+
+	decomp->file_pos = file_offset;
+	decomp->mmap_len = mmap_len;
+	decomp->head = 0;
+
+	if (decomp_last_rem) {
+		memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem);
+		decomp->size = decomp_last_rem;
+	}
+
+	src = (void *)event + sizeof(struct perf_record_compressed);
+	src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
+
+	decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size,
+				&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
+	if (!decomp_size) {
+		munmap(decomp, mmap_len);
+		pr_err("Couldn't decompress data\n");
+		return -1;
+	}
+
+	decomp->size += decomp_size;
+
+	if (session->decomp == NULL) {
+		session->decomp = decomp;
+		session->decomp_last = decomp;
+	} else {
+		session->decomp_last->next = decomp;
+		session->decomp_last = decomp;
+	}
+
+	pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size);
+
+	return 0;
+}
+#else /* !HAVE_ZSTD_SUPPORT */
+#define perf_session__process_compressed_event perf_session__process_compressed_event_stub
+#endif
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
@@ -86,10 +157,10 @@
 
 static bool perf_session__has_comm_exec(struct perf_session *session)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (evsel->attr.comm_exec)
+		if (evsel->core.attr.comm_exec)
 			return true;
 	}
 
@@ -116,6 +187,7 @@
 struct perf_session *perf_session__new(struct perf_data *data,
 				       bool repipe, struct perf_tool *tool)
 {
+	int ret = -ENOMEM;
 	struct perf_session *session = zalloc(sizeof(*session));
 
 	if (!session)
@@ -125,17 +197,21 @@
 	session->tool   = tool;
 	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
-	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
+	ordered_events__init(&session->ordered_events,
+			     ordered_events__deliver_event, NULL);
 
+	perf_env__init(&session->header.env);
 	if (data) {
-		if (perf_data__open(data))
+		ret = perf_data__open(data);
+		if (ret < 0)
 			goto out_delete;
 
 		session->data = data;
 
 		if (perf_data__is_read(data)) {
-			if (perf_session__open(session) < 0)
-				goto out_close;
+			ret = perf_session__open(session);
+			if (ret < 0)
+				goto out_delete;
 
 			/*
 			 * set session attributes that are present in perf.data
@@ -145,11 +221,23 @@
 				perf_session__set_id_hdr_size(session);
 				perf_session__set_comm_exec(session);
 			}
+
+			perf_evlist__init_trace_event_sample_raw(session->evlist);
+
+			/* Open the directory data. */
+			if (data->is_dir) {
+				ret = perf_data__open_dir(data);
+			if (ret)
+				goto out_delete;
+			}
 		}
 	} else  {
 		session->machines.host.env = &perf_env;
 	}
 
+	session->machines.host.single_address_space =
+		perf_env__single_address_space(session->machines.host.env);
+
 	if (!data || perf_data__is_write(data)) {
 		/*
 		 * In O_RDONLY mode this will be performed when reading the
@@ -171,12 +259,10 @@
 
 	return session;
 
- out_close:
-	perf_data__close(data);
  out_delete:
 	perf_session__delete(session);
  out:
-	return NULL;
+	return ERR_PTR(ret);
 }
 
 static void perf_session__delete_threads(struct perf_session *session)
@@ -184,6 +270,21 @@
 	machine__delete_threads(&session->machines.host);
 }
 
+static void perf_session__release_decomp_events(struct perf_session *session)
+{
+	struct decomp *next, *decomp;
+	size_t mmap_len;
+	next = session->decomp;
+	do {
+		decomp = next;
+		if (decomp == NULL)
+			break;
+		next = decomp->next;
+		mmap_len = decomp->mmap_len;
+		munmap(decomp, mmap_len);
+	} while (1);
+}
+
 void perf_session__delete(struct perf_session *session)
 {
 	if (session == NULL)
@@ -192,6 +293,7 @@
 	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
+	perf_session__release_decomp_events(session);
 	perf_env__exit(&session->header.env);
 	machines__exit(&session->machines);
 	if (session->data)
@@ -199,12 +301,10 @@
 	free(session);
 }
 
-static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+static int process_event_synth_tracing_data_stub(struct perf_session *session
 						 __maybe_unused,
 						 union perf_event *event
-						 __maybe_unused,
-						 struct perf_session *session
-						__maybe_unused)
+						 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -212,7 +312,7 @@
 
 static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
 					 union perf_event *event __maybe_unused,
-					 struct perf_evlist **pevlist
+					 struct evlist **pevlist
 					 __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
@@ -221,7 +321,7 @@
 
 static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
 						 union perf_event *event __maybe_unused,
-						 struct perf_evlist **pevlist
+						 struct evlist **pevlist
 						 __maybe_unused)
 {
 	if (dump_trace)
@@ -234,7 +334,7 @@
 static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample __maybe_unused,
-				     struct perf_evsel *evsel __maybe_unused,
+				     struct evsel *evsel __maybe_unused,
 				     struct machine *machine __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
@@ -277,10 +377,8 @@
 	return 0;
 }
 
-static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
-				       union perf_event *event,
-				       struct perf_session *session
-				       __maybe_unused)
+static s64 process_event_auxtrace_stub(struct perf_session *session __maybe_unused,
+				       union perf_event *event)
 {
 	dump_printf(": unhandled!\n");
 	if (perf_data__is_pipe(session->data))
@@ -288,9 +386,8 @@
 	return event->auxtrace.size;
 }
 
-static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -298,9 +395,8 @@
 
 
 static
-int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct perf_session *session __maybe_unused)
+int process_event_thread_map_stub(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_thread_map(event, stdout);
@@ -310,9 +406,8 @@
 }
 
 static
-int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
-			       union perf_event *event __maybe_unused,
-			       struct perf_session *session __maybe_unused)
+int process_event_cpu_map_stub(struct perf_session *session __maybe_unused,
+			       union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_cpu_map(event, stdout);
@@ -322,9 +417,8 @@
 }
 
 static
-int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *session __maybe_unused)
+int process_event_stat_config_stub(struct perf_session *session __maybe_unused,
+				   union perf_event *event __maybe_unused)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_config(event, stdout);
@@ -333,10 +427,8 @@
 	return 0;
 }
 
-static int process_stat_stub(struct perf_tool *tool __maybe_unused,
-			     union perf_event *event __maybe_unused,
-			     struct perf_session *perf_session
-			     __maybe_unused)
+static int process_stat_stub(struct perf_session *perf_session __maybe_unused,
+			     union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat(event, stdout);
@@ -345,10 +437,8 @@
 	return 0;
 }
 
-static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event __maybe_unused,
-				   struct perf_session *perf_session
-				   __maybe_unused)
+static int process_stat_round_stub(struct perf_session *perf_session __maybe_unused,
+				   union perf_event *event)
 {
 	if (dump_trace)
 		perf_event__fprintf_stat_round(event, stdout);
@@ -357,6 +447,14 @@
 	return 0;
 }
 
+static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused,
+						       union perf_event *event __maybe_unused,
+						       u64 file_offset __maybe_unused)
+{
+       dump_printf(": unhandled!\n");
+       return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -383,6 +481,10 @@
 		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->context_switch == NULL)
 		tool->context_switch = perf_event__process_switch;
+	if (tool->ksymbol == NULL)
+		tool->ksymbol = perf_event__process_ksymbol;
+	if (tool->bpf == NULL)
+		tool->bpf = perf_event__process_bpf;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -425,6 +527,8 @@
 		tool->time_conv = process_event_op2_stub;
 	if (tool->feature == NULL)
 		tool->feature = process_event_op2_stub;
+	if (tool->compressed == NULL)
+		tool->compressed = perf_session__process_compressed_event;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -561,6 +665,26 @@
 		swap_sample_id_all(event, &event->throttle + 1);
 }
 
+static void perf_event__namespaces_swap(union perf_event *event,
+					bool sample_id_all)
+{
+	u64 i;
+
+	event->namespaces.pid		= bswap_32(event->namespaces.pid);
+	event->namespaces.tid		= bswap_32(event->namespaces.tid);
+	event->namespaces.nr_namespaces	= bswap_64(event->namespaces.nr_namespaces);
+
+	for (i = 0; i < event->namespaces.nr_namespaces; i++) {
+		struct perf_ns_link_info *ns = &event->namespaces.link_info[i];
+
+		ns->dev = bswap_64(ns->dev);
+		ns->ino = bswap_64(ns->ino);
+	}
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->namespaces.link_info[i]);
+}
+
 static u8 revbyte(u8 b)
 {
 	int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -701,7 +825,10 @@
 	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
 	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
 	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.fmt  = bswap_32(event->auxtrace_error.fmt);
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+	if (event->auxtrace_error.fmt)
+		event->auxtrace_error.time = bswap_64(event->auxtrace_error.time);
 }
 
 static void perf_event__thread_map_swap(union perf_event *event,
@@ -718,9 +845,9 @@
 static void perf_event__cpu_map_swap(union perf_event *event,
 				     bool sample_id_all __maybe_unused)
 {
-	struct cpu_map_data *data = &event->cpu_map.data;
+	struct perf_record_cpu_map_data *data = &event->cpu_map.data;
 	struct cpu_map_entries *cpus;
-	struct cpu_map_mask *mask;
+	struct perf_record_record_cpu_map *mask;
 	unsigned i;
 
 	data->type = bswap_64(data->type);
@@ -735,7 +862,7 @@
 			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
 		break;
 	case PERF_CPU_MAP__MASK:
-		mask = (struct cpu_map_mask *) data->data;
+		mask = (struct perf_record_record_cpu_map *)data->data;
 
 		mask->nr = bswap_16(mask->nr);
 		mask->long_size = bswap_16(mask->long_size);
@@ -798,6 +925,7 @@
 	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
 	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
 	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
+	[PERF_RECORD_NAMESPACES]	  = perf_event__namespaces_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
@@ -917,7 +1045,7 @@
 	}
 }
 
-static void callchain__printf(struct perf_evsel *evsel,
+static void callchain__printf(struct evsel *evsel,
 			      struct perf_sample *sample)
 {
 	unsigned int i;
@@ -933,23 +1061,30 @@
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample)
+static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 {
 	uint64_t i;
 
-	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+	printf("%s: nr:%" PRIu64 "\n",
+		!callstack ? "... branch stack" : "... branch callstack",
+		sample->branch_stack->nr);
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &sample->branch_stack->entries[i];
 
-		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
-			i, e->from, e->to,
-			(unsigned short)e->flags.cycles,
-			e->flags.mispred ? "M" : " ",
-			e->flags.predicted ? "P" : " ",
-			e->flags.abort ? "A" : " ",
-			e->flags.in_tx ? "T" : " ",
-			(unsigned)e->flags.reserved);
+		if (!callstack) {
+			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+				i, e->from, e->to,
+				(unsigned short)e->flags.cycles,
+				e->flags.mispred ? "M" : " ",
+				e->flags.predicted ? "P" : " ",
+				e->flags.abort ? "A" : " ",
+				e->flags.in_tx ? "T" : " ",
+				(unsigned)e->flags.reserved);
+		} else {
+			printf("..... %2"PRIu64": %016" PRIx64 "\n",
+				i, i > 0 ? e->from : e->to);
+		}
 	}
 }
 
@@ -1013,7 +1148,7 @@
 	       dump->size, dump->offset);
 }
 
-static void perf_evlist__print_tstamp(struct perf_evlist *evlist,
+static void perf_evlist__print_tstamp(struct evlist *evlist,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
@@ -1062,7 +1197,7 @@
 			sample->read.one.id, sample->read.one.value);
 }
 
-static void dump_event(struct perf_evlist *evlist, union perf_event *event,
+static void dump_event(struct evlist *evlist, union perf_event *event,
 		       u64 file_offset, struct perf_sample *sample)
 {
 	if (!dump_trace)
@@ -1072,6 +1207,8 @@
 	       file_offset, event->header.size, event->header.type);
 
 	trace_event(event);
+	if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw)
+		evlist->trace_event_sample_raw(evlist, event, sample);
 
 	if (sample)
 		perf_evlist__print_tstamp(evlist, event, sample);
@@ -1080,7 +1217,7 @@
 	       event->header.size, perf_event__name(event->header.type));
 }
 
-static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
+static void dump_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *sample)
 {
 	u64 sample_type;
@@ -1092,13 +1229,13 @@
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
-	sample_type = evsel->attr.sample_type;
+	sample_type = evsel->core.attr.sample_type;
 
 	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
-	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
-		branch_stack__printf(sample);
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample);
@@ -1122,31 +1259,34 @@
 		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
 	if (sample_type & PERF_SAMPLE_READ)
-		sample_read__printf(sample, evsel->attr.read_format);
+		sample_read__printf(sample, evsel->core.attr.read_format);
 }
 
-static void dump_read(struct perf_evsel *evsel, union perf_event *event)
+static void dump_read(struct evsel *evsel, union perf_event *event)
 {
-	struct read_event *read_event = &event->read;
+	struct perf_record_read *read_event = &event->read;
 	u64 read_format;
 
 	if (!dump_trace)
 		return;
 
-	printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-	       evsel ? perf_evsel__name(evsel) : "FAIL",
+	printf(": %d %d %s %" PRI_lu64 "\n", event->read.pid, event->read.tid,
+	       perf_evsel__name(evsel),
 	       event->read.value);
 
-	read_format = evsel->attr.read_format;
+	if (!evsel)
+		return;
+
+	read_format = evsel->core.attr.read_format;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-		printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled);
+		printf("... time enabled : %" PRI_lu64 "\n", read_event->time_enabled);
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-		printf("... time running : %" PRIu64 "\n", read_event->time_running);
+		printf("... time running : %" PRI_lu64 "\n", read_event->time_running);
 
 	if (read_format & PERF_FORMAT_ID)
-		printf("... id           : %" PRIu64 "\n", read_event->id);
+		printf("... id           : %" PRI_lu64 "\n", read_event->id);
 }
 
 static struct machine *machines__find_for_cpumode(struct machines *machines,
@@ -1175,7 +1315,7 @@
 	return &machines->host;
 }
 
-static int deliver_sample_value(struct perf_evlist *evlist,
+static int deliver_sample_value(struct evlist *evlist,
 				struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -1183,6 +1323,7 @@
 				struct machine *machine)
 {
 	struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
+	struct evsel *evsel;
 
 	if (sid) {
 		sample->id     = v->id;
@@ -1195,10 +1336,18 @@
 		return 0;
 	}
 
-	return tool->sample(tool, event, sample, sid->evsel, machine);
+	/*
+	 * There's no reason to deliver sample
+	 * for zero period, bail out.
+	 */
+	if (!sample->period)
+		return 0;
+
+	evsel = container_of(sid->evsel, struct evsel, core);
+	return tool->sample(tool, event, sample, evsel, machine);
 }
 
-static int deliver_sample_group(struct perf_evlist *evlist,
+static int deliver_sample_group(struct evlist *evlist,
 				struct perf_tool *tool,
 				union  perf_event *event,
 				struct perf_sample *sample,
@@ -1219,16 +1368,16 @@
 }
 
 static int
- perf_evlist__deliver_sample(struct perf_evlist *evlist,
+ perf_evlist__deliver_sample(struct evlist *evlist,
 			     struct perf_tool *tool,
 			     union  perf_event *event,
 			     struct perf_sample *sample,
-			     struct perf_evsel *evsel,
+			     struct evsel *evsel,
 			     struct machine *machine)
 {
 	/* We know evsel != NULL. */
-	u64 sample_type = evsel->attr.sample_type;
-	u64 read_format = evsel->attr.read_format;
+	u64 sample_type = evsel->core.attr.sample_type;
+	u64 read_format = evsel->core.attr.read_format;
 
 	/* Standard sample delivery. */
 	if (!(sample_type & PERF_SAMPLE_READ))
@@ -1244,12 +1393,12 @@
 }
 
 static int machines__deliver_event(struct machines *machines,
-				   struct perf_evlist *evlist,
+				   struct evlist *evlist,
 				   union perf_event *event,
 				   struct perf_sample *sample,
 				   struct perf_tool *tool, u64 file_offset)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct machine *machine;
 
 	dump_event(evlist, event, file_offset, sample);
@@ -1312,6 +1461,10 @@
 	case PERF_RECORD_SWITCH:
 	case PERF_RECORD_SWITCH_CPU_WIDE:
 		return tool->context_switch(tool, event, sample, machine);
+	case PERF_RECORD_KSYMBOL:
+		return tool->ksymbol(tool, event, sample, machine);
+	case PERF_RECORD_BPF_EVENT:
+		return tool->bpf(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
@@ -1352,7 +1505,9 @@
 	int fd = perf_data__fd(session->data);
 	int err;
 
-	dump_event(session->evlist, event, file_offset, &sample);
+	if (event->header.type != PERF_RECORD_COMPRESSED ||
+	    tool->compressed == perf_session__process_compressed_event_stub)
+		dump_event(session->evlist, event, file_offset, &sample);
 
 	/* These events are processed right away */
 	switch (event->header.type) {
@@ -1374,37 +1529,42 @@
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset, SEEK_SET);
-		return tool->tracing_data(tool, event, session);
+		return tool->tracing_data(session, event);
 	case PERF_RECORD_HEADER_BUILD_ID:
-		return tool->build_id(tool, event, session);
+		return tool->build_id(session, event);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
-		return tool->id_index(tool, event, session);
+		return tool->id_index(session, event);
 	case PERF_RECORD_AUXTRACE_INFO:
-		return tool->auxtrace_info(tool, event, session);
+		return tool->auxtrace_info(session, event);
 	case PERF_RECORD_AUXTRACE:
 		/* setup for reading amidst mmap */
 		lseek(fd, file_offset + event->header.size, SEEK_SET);
-		return tool->auxtrace(tool, event, session);
+		return tool->auxtrace(session, event);
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
-		return tool->auxtrace_error(tool, event, session);
+		return tool->auxtrace_error(session, event);
 	case PERF_RECORD_THREAD_MAP:
-		return tool->thread_map(tool, event, session);
+		return tool->thread_map(session, event);
 	case PERF_RECORD_CPU_MAP:
-		return tool->cpu_map(tool, event, session);
+		return tool->cpu_map(session, event);
 	case PERF_RECORD_STAT_CONFIG:
-		return tool->stat_config(tool, event, session);
+		return tool->stat_config(session, event);
 	case PERF_RECORD_STAT:
-		return tool->stat(tool, event, session);
+		return tool->stat(session, event);
 	case PERF_RECORD_STAT_ROUND:
-		return tool->stat_round(tool, event, session);
+		return tool->stat_round(session, event);
 	case PERF_RECORD_TIME_CONV:
 		session->time_conv = event->time_conv;
-		return tool->time_conv(tool, event, session);
+		return tool->time_conv(session, event);
 	case PERF_RECORD_HEADER_FEATURE:
-		return tool->feature(tool, event, session);
+		return tool->feature(session, event);
+	case PERF_RECORD_COMPRESSED:
+		err = tool->compressed(session, event, file_offset);
+		if (err)
+			dump_event(session->evlist, event, file_offset, &sample);
+		return err;
 	default:
 		return -EINVAL;
 	}
@@ -1414,7 +1574,7 @@
 				      union perf_event *event,
 				      struct perf_sample *sample)
 {
-	struct perf_evlist *evlist = session->evlist;
+	struct evlist *evlist = session->evlist;
 	struct perf_tool *tool = session->tool;
 
 	events_stats__inc(&evlist->stats, event->header.type);
@@ -1492,7 +1652,7 @@
 static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event, u64 file_offset)
 {
-	struct perf_evlist *evlist = session->evlist;
+	struct evlist *evlist = session->evlist;
 	struct perf_tool *tool = session->tool;
 	int ret;
 
@@ -1534,6 +1694,13 @@
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
+/*
+ * Threads are identified by pid and tid, and the idle task has pid == tid == 0.
+ * So here a single thread is created for that, but actually there is a separate
+ * idle task per cpu, so there should be one 'struct thread' per cpu, but there
+ * is only 1. That causes problems for some tools, requiring workarounds. For
+ * example get_idle_thread() in builtin-sched.c, or thread_stack__per_cpu().
+ */
 int perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;
@@ -1559,11 +1726,11 @@
 perf_session__warn_order(const struct perf_session *session)
 {
 	const struct ordered_events *oe = &session->ordered_events;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	bool should_warn = true;
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (evsel->attr.write_backward)
+		if (evsel->core.attr.write_backward)
 			should_warn = false;
 	}
 
@@ -1680,6 +1847,8 @@
 
 volatile int session_done;
 
+static int __perf_session__process_decomp_events(struct perf_session *session);
+
 static int __perf_session__process_pipe_events(struct perf_session *session)
 {
 	struct ordered_events *oe = &session->ordered_events;
@@ -1760,6 +1929,10 @@
 	if (skip > 0)
 		head += skip;
 
+	err = __perf_session__process_decomp_events(session);
+	if (err)
+		goto out_err;
+
 	if (!session_done())
 		goto more;
 done:
@@ -1802,12 +1975,50 @@
 		/* We're not fetching the event so swap back again */
 		if (session->header.needs_swap)
 			perf_event_header__bswap(&event->header);
-		return NULL;
+		pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx: fuzzed perf.data?\n",
+			 __func__, head, event->header.size, mmap_size);
+		return ERR_PTR(-EINVAL);
 	}
 
 	return event;
 }
 
+static int __perf_session__process_decomp_events(struct perf_session *session)
+{
+	s64 skip;
+	u64 size, file_pos = 0;
+	struct decomp *decomp = session->decomp_last;
+
+	if (!decomp)
+		return 0;
+
+	while (decomp->head < decomp->size && !session_done()) {
+		union perf_event *event = fetch_mmaped_event(session, decomp->head, decomp->size, decomp->data);
+
+		if (IS_ERR(event))
+			return PTR_ERR(event);
+
+		if (!event)
+			break;
+
+		size = event->header.size;
+
+		if (size < sizeof(struct perf_event_header) ||
+		    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
+			pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+				decomp->file_pos + decomp->head, event->header.size, event->header.type);
+			return -EINVAL;
+		}
+
+		if (skip)
+			size += skip;
+
+		decomp->head += size;
+	}
+
+	return 0;
+}
+
 /*
  * On 64bit we can mmap the data file in one go. No need for tiny mmap
  * slices. On 32bit we use 32MB.
@@ -1820,38 +2031,42 @@
 #define NUM_MMAPS 128
 #endif
 
-static int __perf_session__process_events(struct perf_session *session,
-					  u64 data_offset, u64 data_size,
-					  u64 file_size)
+struct reader;
+
+typedef s64 (*reader_cb_t)(struct perf_session *session,
+			   union perf_event *event,
+			   u64 file_offset);
+
+struct reader {
+	int		 fd;
+	u64		 data_size;
+	u64		 data_offset;
+	reader_cb_t	 process;
+};
+
+static int
+reader__process_events(struct reader *rd, struct perf_session *session,
+		       struct ui_progress *prog)
 {
-	struct ordered_events *oe = &session->ordered_events;
-	struct perf_tool *tool = session->tool;
-	int fd = perf_data__fd(session->data);
+	u64 data_size = rd->data_size;
 	u64 head, page_offset, file_offset, file_pos, size;
-	int err, mmap_prot, mmap_flags, map_idx = 0;
+	int err = 0, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
 	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
-	struct ui_progress prog;
 	s64 skip;
 
-	perf_tool__fill_defaults(tool);
-
-	page_offset = page_size * (data_offset / page_size);
+	page_offset = page_size * (rd->data_offset / page_size);
 	file_offset = page_offset;
-	head = data_offset - page_offset;
+	head = rd->data_offset - page_offset;
 
-	if (data_size == 0)
-		goto out;
+	ui_progress__init_size(prog, data_size, "Processing events...");
 
-	if (data_offset + data_size < file_size)
-		file_size = data_offset + data_size;
-
-	ui_progress__init_size(&prog, file_size, "Processing events...");
+	data_size += rd->data_offset;
 
 	mmap_size = MMAP_SIZE;
-	if (mmap_size > file_size) {
-		mmap_size = file_size;
+	if (mmap_size > data_size) {
+		mmap_size = data_size;
 		session->one_mmap = true;
 	}
 
@@ -1865,12 +2080,12 @@
 		mmap_flags = MAP_PRIVATE;
 	}
 remap:
-	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
+	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, rd->fd,
 		   file_offset);
 	if (buf == MAP_FAILED) {
 		pr_err("failed to mmap file\n");
 		err = -errno;
-		goto out_err;
+		goto out;
 	}
 	mmaps[map_idx] = buf;
 	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
@@ -1882,6 +2097,9 @@
 
 more:
 	event = fetch_mmaped_event(session, head, mmap_size, buf);
+	if (IS_ERR(event))
+		return PTR_ERR(event);
+
 	if (!event) {
 		if (mmaps[map_idx]) {
 			munmap(mmaps[map_idx], mmap_size);
@@ -1896,13 +2114,15 @@
 
 	size = event->header.size;
 
+	skip = -EINVAL;
+
 	if (size < sizeof(struct perf_event_header) ||
-	    (skip = perf_session__process_event(session, event, file_pos)) < 0) {
-		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+	    (skip = rd->process(session, event, file_pos)) < 0) {
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       file_offset + head, event->header.size,
-		       event->header.type);
-		err = -EINVAL;
-		goto out_err;
+		       event->header.type, strerror(-skip));
+		err = skip;
+		goto out;
 	}
 
 	if (skip)
@@ -1911,15 +2131,52 @@
 	head += size;
 	file_pos += size;
 
-	ui_progress__update(&prog, size);
+	err = __perf_session__process_decomp_events(session);
+	if (err)
+		goto out;
+
+	ui_progress__update(prog, size);
 
 	if (session_done())
 		goto out;
 
-	if (file_pos < file_size)
+	if (file_pos < data_size)
 		goto more;
 
 out:
+	return err;
+}
+
+static s64 process_simple(struct perf_session *session,
+			  union perf_event *event,
+			  u64 file_offset)
+{
+	return perf_session__process_event(session, event, file_offset);
+}
+
+static int __perf_session__process_events(struct perf_session *session)
+{
+	struct reader rd = {
+		.fd		= perf_data__fd(session->data),
+		.data_size	= session->header.data_size,
+		.data_offset	= session->header.data_offset,
+		.process	= process_simple,
+	};
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = session->tool;
+	struct ui_progress prog;
+	int err;
+
+	perf_tool__fill_defaults(tool);
+
+	if (rd.data_size == 0)
+		return -1;
+
+	ui_progress__init_size(&prog, rd.data_size, "Processing events...");
+
+	err = reader__process_events(&rd, session, &prog);
+	if (err)
+		goto out_err;
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
 	if (err)
@@ -1944,28 +2201,21 @@
 
 int perf_session__process_events(struct perf_session *session)
 {
-	u64 size = perf_data__size(session->data);
-	int err;
-
 	if (perf_session__register_idle_thread(session) < 0)
 		return -ENOMEM;
 
-	if (!perf_data__is_pipe(session->data))
-		err = __perf_session__process_events(session,
-						     session->header.data_offset,
-						     session->header.data_size, size);
-	else
-		err = __perf_session__process_pipe_events(session);
+	if (perf_data__is_pipe(session->data))
+		return __perf_session__process_pipe_events(session);
 
-	return err;
+	return __perf_session__process_events(session);
 }
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
+		if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 	}
 
@@ -2036,13 +2286,13 @@
 	return machine__fprintf(&session->machines.host, fp);
 }
 
-struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
 	evlist__for_each_entry(session->evlist, pos) {
-		if (pos->attr.type == type)
+		if (pos->core.attr.type == type)
 			return pos;
 	}
 	return NULL;
@@ -2052,23 +2302,24 @@
 			     const char *cpu_list, unsigned long *cpu_bitmap)
 {
 	int i, err = -1;
-	struct cpu_map *map;
+	struct perf_cpu_map *map;
+	int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
-		struct perf_evsel *evsel;
+		struct evsel *evsel;
 
 		evsel = perf_session__find_first_evtype(session, i);
 		if (!evsel)
 			continue;
 
-		if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) {
+		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CPU)) {
 			pr_err("File does not contain CPU events. "
 			       "Remove -C option to proceed.\n");
 			return -1;
 		}
 	}
 
-	map = cpu_map__new(cpu_list);
+	map = perf_cpu_map__new(cpu_list);
 	if (map == NULL) {
 		pr_err("Invalid cpu_list\n");
 		return -1;
@@ -2077,7 +2328,7 @@
 	for (i = 0; i < map->nr; i++) {
 		int cpu = map->map[i];
 
-		if (cpu >= MAX_NR_CPUS) {
+		if (cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu);
 			goto out_delete_map;
@@ -2089,7 +2340,7 @@
 	err = 0;
 
 out_delete_map:
-	cpu_map__put(map);
+	perf_cpu_map__put(map);
 	return err;
 }
 
@@ -2106,10 +2357,10 @@
 
 
 int __perf_session__set_tracepoints_handlers(struct perf_session *session,
-					     const struct perf_evsel_str_handler *assocs,
+					     const struct evsel_str_handler *assocs,
 					     size_t nr_assocs)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	size_t i;
 	int err;
 
@@ -2133,15 +2384,14 @@
 	return err;
 }
 
-int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event,
-				 struct perf_session *session)
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event)
 {
-	struct perf_evlist *evlist = session->evlist;
-	struct id_index_event *ie = &event->id_index;
+	struct evlist *evlist = session->evlist;
+	struct perf_record_id_index *ie = &event->id_index;
 	size_t i, nr, max_nr;
 
-	max_nr = (ie->header.size - sizeof(struct id_index_event)) /
+	max_nr = (ie->header.size - sizeof(struct perf_record_id_index)) /
 		 sizeof(struct id_index_entry);
 	nr = ie->nr;
 	if (nr > max_nr)
@@ -2155,10 +2405,10 @@
 		struct perf_sample_id *sid;
 
 		if (dump_trace) {
-			fprintf(stdout,	" ... id: %"PRIu64, e->id);
-			fprintf(stdout,	"  idx: %"PRIu64, e->idx);
-			fprintf(stdout,	"  cpu: %"PRId64, e->cpu);
-			fprintf(stdout,	"  tid: %"PRId64"\n", e->tid);
+			fprintf(stdout,	" ... id: %"PRI_lu64, e->id);
+			fprintf(stdout,	"  idx: %"PRI_lu64, e->idx);
+			fprintf(stdout,	"  cpu: %"PRI_ld64, e->cpu);
+			fprintf(stdout,	"  tid: %"PRI_ld64"\n", e->tid);
 		}
 
 		sid = perf_evlist__id2sid(evlist, e->id);
@@ -2170,73 +2420,3 @@
 	}
 	return 0;
 }
-
-int perf_event__synthesize_id_index(struct perf_tool *tool,
-				    perf_event__handler_t process,
-				    struct perf_evlist *evlist,
-				    struct machine *machine)
-{
-	union perf_event *ev;
-	struct perf_evsel *evsel;
-	size_t nr = 0, i = 0, sz, max_nr, n;
-	int err;
-
-	pr_debug2("Synthesizing id index\n");
-
-	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
-		 sizeof(struct id_index_entry);
-
-	evlist__for_each_entry(evlist, evsel)
-		nr += evsel->ids;
-
-	n = nr > max_nr ? max_nr : nr;
-	sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry);
-	ev = zalloc(sz);
-	if (!ev)
-		return -ENOMEM;
-
-	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
-	ev->id_index.header.size = sz;
-	ev->id_index.nr = n;
-
-	evlist__for_each_entry(evlist, evsel) {
-		u32 j;
-
-		for (j = 0; j < evsel->ids; j++) {
-			struct id_index_entry *e;
-			struct perf_sample_id *sid;
-
-			if (i >= n) {
-				err = process(tool, ev, NULL, machine);
-				if (err)
-					goto out_err;
-				nr -= n;
-				i = 0;
-			}
-
-			e = &ev->id_index.entries[i++];
-
-			e->id = evsel->id[j];
-
-			sid = perf_evlist__id2sid(evlist, e->id);
-			if (!sid) {
-				free(ev);
-				return -ENOENT;
-			}
-
-			e->idx = sid->idx;
-			e->cpu = sid->cpu;
-			e->tid = sid->tid;
-		}
-	}
-
-	sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry);
-	ev->id_index.header.size = sz;
-	ev->id_index.nr = nr;
-
-	err = process(tool, ev, NULL, machine);
-out_err:
-	free(ev);
-
-	return err;
-}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index da40b4b..b4c9428 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -8,6 +8,7 @@
 #include "machine.h"
 #include "data.h"
 #include "ordered-events.h"
+#include "util/compress.h"
 #include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
@@ -22,12 +23,12 @@
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
-	struct perf_evlist	*evlist;
+	struct evlist	*evlist;
 	struct auxtrace		*auxtrace;
 	struct itrace_synth_opts *itrace_synth_opts;
 	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
-	struct time_conv_event	time_conv;
+	struct perf_record_time_conv	time_conv;
 	bool			repipe;
 	bool			one_mmap;
 	void			*one_mmap_addr;
@@ -35,6 +36,20 @@
 	struct ordered_events	ordered_events;
 	struct perf_data	*data;
 	struct perf_tool	*tool;
+	u64			bytes_transferred;
+	u64			bytes_compressed;
+	struct zstd_data	zstd_data;
+	struct decomp		*decomp;
+	struct decomp		*decomp_last;
+};
+
+struct decomp {
+	struct decomp *next;
+	u64 file_pos;
+	size_t mmap_len;
+	u64 head;
+	size_t size;
+	char data[];
 };
 
 struct perf_tool;
@@ -58,7 +73,7 @@
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
 int perf_session__resolve_callchain(struct perf_session *session,
-				    struct perf_evsel *evsel,
+				    struct evsel *evsel,
 				    struct thread *thread,
 				    struct ip_callchain *chain,
 				    struct symbol **parent);
@@ -95,7 +110,7 @@
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 
-struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
@@ -103,10 +118,10 @@
 
 void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-struct perf_evsel_str_handler;
+struct evsel_str_handler;
 
 int __perf_session__set_tracepoints_handlers(struct perf_session *session,
-					     const struct perf_evsel_str_handler *assocs,
+					     const struct evsel_str_handler *assocs,
 					     size_t nr_assocs);
 
 #define perf_session__set_tracepoints_handlers(session, array) \
@@ -120,13 +135,7 @@
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
-int perf_event__process_id_index(struct perf_tool *tool,
-				 union perf_event *event,
-				 struct perf_session *session);
-
-int perf_event__synthesize_id_index(struct perf_tool *tool,
-				    perf_event__handler_t process,
-				    struct perf_evlist *evlist,
-				    struct machine *machine);
+int perf_event__process_id_index(struct perf_session *session,
+				 union perf_event *event);
 
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c
index ce8fc29..48f9c0a 100644
--- a/tools/perf/util/setns.c
+++ b/tools/perf/util/setns.c
@@ -1,4 +1,6 @@
-#include "util.h"
+// SPDX-License-Identifier: LGPL-2.1
+
+#include "namespaces.h"
 #include <unistd.h>
 #include <sys/syscall.h>
 
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1942f6d..aa344a1 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,20 +1,24 @@
-#!/usr/bin/python
-
 from os import getenv
 from subprocess import Popen, PIPE
 from re import sub
 
 def clang_has_option(option):
-    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if "unknown argument" in o] == [ ]
+    return [o for o in Popen(['clang', option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
 
 cc = getenv("CC")
 if cc == "clang":
-    from _sysconfigdata import build_time_vars
-    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-mcet"):
-        build_time_vars["CFLAGS"] = sub("-mcet", "", build_time_vars["CFLAGS"])
-    if not clang_has_option("-fcf-protection"):
-        build_time_vars["CFLAGS"] = sub("-fcf-protection", "", build_time_vars["CFLAGS"])
+    from distutils.sysconfig import get_config_vars
+    vars = get_config_vars()
+    for var in ('CFLAGS', 'OPT'):
+        vars[var] = sub("-specs=[^ ]+", "", vars[var])
+        if not clang_has_option("-mcet"):
+            vars[var] = sub("-mcet", "", vars[var])
+        if not clang_has_option("-fcf-protection"):
+            vars[var] = sub("-fcf-protection", "", vars[var])
+        if not clang_has_option("-fstack-clash-protection"):
+            vars[var] = sub("-fstack-clash-protection", "", vars[var])
+        if not clang_has_option("-fstack-protector-strong"):
+            vars[var] = sub("-fstack-protector-strong", "", vars[var])
 
 from distutils.core import setup, Extension
 
@@ -44,6 +48,7 @@
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
 libapikfs = getenv('LIBAPI')
+libperf = getenv('LIBPERF')
 
 ext_sources = [f.strip() for f in open('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -51,11 +56,18 @@
 # use full paths with source files
 ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
 
+extra_libraries = []
+if '-DHAVE_LIBNUMA_SUPPORT' in cflags:
+    extra_libraries = [ 'numa' ]
+if '-DHAVE_LIBCAP_SUPPORT' in cflags:
+    extra_libraries += [ 'cap' ]
+
 perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
+		  libraries = extra_libraries,
 		  extra_compile_args = cflags,
-		  extra_objects = [libtraceevent, libapikfs],
+		  extra_objects = [libtraceevent, libapikfs, libperf],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 453f6f6..3b791ef 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -23,8 +23,12 @@
 		char fn[256];
 
 		snprintf(fn, sizeof fn,
-			"devices/system/cpu/cpu%d/topology/thread_siblings",
-			cpu);
+			"devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+		if (access(fn, F_OK) == -1) {
+			snprintf(fn, sizeof fn,
+				"devices/system/cpu/cpu%d/topology/thread_siblings",
+				cpu);
+		}
 		if (sysfs__read_str(fn, &str, &strlen) < 0)
 			continue;
 		/* Entry is hex, but does not have 0x, so need custom parser */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b284276..43d1d41 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,18 +2,31 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
+#include <stdlib.h>
 #include <linux/mman.h>
+#include <linux/time64.h>
+#include "debug.h"
+#include "dso.h"
 #include "sort.h"
 #include "hist.h"
+#include "cacheline.h"
 #include "comm.h"
+#include "map.h"
 #include "symbol.h"
+#include "map_symbol.h"
+#include "branch.h"
 #include "thread.h"
 #include "evsel.h"
 #include "evlist.h"
+#include "srcline.h"
 #include "strlist.h"
+#include "strbuf.h"
 #include <traceevent/event-parse.h>
 #include "mem-events.h"
+#include "annotate.h"
+#include "time-utils.h"
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -36,7 +49,7 @@
  * -t, --field-separator
  *
  * option, that uses a special separator character and don't pad with spaces,
- * replacing all occurances of this separator in symbol names (and other
+ * replacing all occurrences of this separator in symbol names (and other
  * output) with a '.' character, that thus it's the only non valid separator.
 */
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
@@ -229,8 +242,14 @@
 	if (sym_l == sym_r)
 		return 0;
 
-	if (sym_l->inlined || sym_r->inlined)
-		return strcmp(sym_l->name, sym_r->name);
+	if (sym_l->inlined || sym_r->inlined) {
+		int ret = strcmp(sym_l->name, sym_r->name);
+
+		if (ret)
+			return ret;
+		if ((sym_l->start <= sym_r->end) && (sym_l->end >= sym_r->start))
+			return 0;
+	}
 
 	if (sym_l->start != sym_r->start)
 		return (int64_t)(sym_r->start - sym_l->start);
@@ -422,6 +441,57 @@
 	.se_width_idx	= HISTC_SRCLINE_TO,
 };
 
+static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+
+	struct symbol *sym = he->ms.sym;
+	struct annotation *notes;
+	double ipc = 0.0, coverage = 0.0;
+	char tmp[64];
+
+	if (!sym)
+		return repsep_snprintf(bf, size, "%-*s", width, "-");
+
+	notes = symbol__annotation(sym);
+
+	if (notes->hit_cycles)
+		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+
+	if (notes->total_insn) {
+		coverage = notes->cover_insn * 100.0 /
+			((double)notes->total_insn);
+	}
+
+	snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage);
+	return repsep_snprintf(bf, size, "%-*s", width, tmp);
+}
+
+struct sort_entry sort_sym_ipc = {
+	.se_header	= "IPC   [IPC Coverage]",
+	.se_cmp		= sort__sym_cmp,
+	.se_snprintf	= hist_entry__sym_ipc_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_IPC,
+};
+
+static int hist_entry__sym_ipc_null_snprintf(struct hist_entry *he
+					     __maybe_unused,
+					     char *bf, size_t size,
+					     unsigned int width)
+{
+	char tmp[64];
+
+	snprintf(tmp, sizeof(tmp), "%-5s %2s", "-", "-");
+	return repsep_snprintf(bf, size, "%-*s", width, tmp);
+}
+
+struct sort_entry sort_sym_ipc_null = {
+	.se_header	= "IPC   [IPC Coverage]",
+	.se_cmp		= sort__sym_cmp,
+	.se_snprintf	= hist_entry__sym_ipc_null_snprintf,
+	.se_width_idx	= HISTC_SYMBOL_IPC,
+};
+
 /* --sort srcfile */
 
 static char no_srcfile[1];
@@ -595,12 +665,42 @@
 	.se_width_idx	= HISTC_SOCKET,
 };
 
+/* --sort time */
+
+static int64_t
+sort__time_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return right->time - left->time;
+}
+
+static int hist_entry__time_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	char he_time[32];
+
+	if (symbol_conf.nanosecs)
+		timestamp__scnprintf_nsec(he->time, he_time,
+					  sizeof(he_time));
+	else
+		timestamp__scnprintf_usec(he->time, he_time,
+					  sizeof(he_time));
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he_time);
+}
+
+struct sort_entry sort_time = {
+	.se_header      = "Time",
+	.se_cmp	        = sort__time_cmp,
+	.se_snprintf    = hist_entry__time_snprintf,
+	.se_width_idx	= HISTC_TIME,
+};
+
 /* --sort trace */
 
 static char *get_trace_output(struct hist_entry *he)
 {
 	struct trace_seq seq;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct tep_record rec = {
 		.data = he->raw_data,
 		.size = he->raw_size,
@@ -613,7 +713,8 @@
 		tep_print_fields(&seq, he->raw_data, he->raw_size,
 				 evsel->tp_format);
 	} else {
-		tep_event_info(&seq, evsel->tp_format, &rec);
+		tep_print_event(evsel->tp_format->tep,
+				&seq, &rec, "%s", TEP_PRINT_INFO);
 	}
 	/*
 	 * Trim the buffer, it starts at 4KB and we're not going to
@@ -625,10 +726,10 @@
 static int64_t
 sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evsel = hists_to_evsel(left->hists);
-	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+	if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 		return 0;
 
 	if (left->trace_output == NULL)
@@ -642,10 +743,10 @@
 static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evsel = hists_to_evsel(he->hists);
-	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+	if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 		return scnprintf(bf, size, "%-.*s", width, "N/A");
 
 	if (he->trace_output == NULL)
@@ -1574,6 +1675,8 @@
 	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
 	DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
+	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
+	DIM(SORT_TIME, "time", sort_time),
 };
 
 #undef DIM
@@ -1591,6 +1694,7 @@
 	DIM(SORT_CYCLES, "cycles", sort_cycles),
 	DIM(SORT_SRCLINE_FROM, "srcline_from", sort_srcline_from),
 	DIM(SORT_SRCLINE_TO, "srcline_to", sort_srcline_to),
+	DIM(SORT_SYM_IPC, "ipc_lbr", sort_sym_ipc),
 };
 
 #undef DIM
@@ -1883,8 +1987,8 @@
 
 struct hpp_dynamic_entry {
 	struct perf_hpp_fmt hpp;
-	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct evsel *evsel;
+	struct tep_format_field *field;
 	unsigned dynamic_len;
 	bool raw_trace;
 };
@@ -1899,7 +2003,7 @@
 		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 +2019,7 @@
 			       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 +2104,7 @@
 	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 +2164,7 @@
 			       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 +2175,7 @@
 	}
 
 	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 +2221,7 @@
 }
 
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+__alloc_dynamic_entry(struct evsel *evsel, struct tep_format_field *field,
 		      int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2212,20 +2316,20 @@
  *   2. full event name (e.g. sched:sched_switch)
  *   3. partial event name (should not contain ':')
  */
-static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name)
+static struct evsel *find_evsel(struct evlist *evlist, char *event_name)
 {
-	struct perf_evsel *evsel = NULL;
-	struct perf_evsel *pos;
+	struct evsel *evsel = NULL;
+	struct evsel *pos;
 	bool full_name;
 
 	/* case 1 */
 	if (event_name[0] == '%') {
 		int nr = strtol(event_name+1, NULL, 0);
 
-		if (nr > evlist->nr_entries)
+		if (nr > evlist->core.nr_entries)
 			return NULL;
 
-		evsel = perf_evlist__first(evlist);
+		evsel = evlist__first(evlist);
 		while (--nr > 0)
 			evsel = perf_evsel__next(evsel);
 
@@ -2251,8 +2355,8 @@
 	return evsel;
 }
 
-static int __dynamic_dimension__add(struct perf_evsel *evsel,
-				    struct format_field *field,
+static int __dynamic_dimension__add(struct evsel *evsel,
+				    struct tep_format_field *field,
 				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
@@ -2267,10 +2371,10 @@
 	return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
+static int add_evsel_fields(struct 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) {
@@ -2283,14 +2387,14 @@
 	return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+static int add_all_dynamic_fields(struct evlist *evlist, bool raw_trace,
 				  int level)
 {
 	int ret;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
 		ret = add_evsel_fields(evsel, raw_trace, level);
@@ -2300,15 +2404,15 @@
 	return 0;
 }
 
-static int add_all_matching_fields(struct perf_evlist *evlist,
+static int add_all_matching_fields(struct evlist *evlist,
 				   char *field_name, bool raw_trace, int level)
 {
 	int ret = -ESRCH;
-	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct evsel *evsel;
+	struct tep_format_field *field;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
 		field = tep_find_any_field(evsel->tp_format, field_name);
@@ -2322,12 +2426,12 @@
 	return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+static int add_dynamic_entry(struct evlist *evlist, const char *tok,
 			     int level)
 {
 	char *str, *event_name, *field_name, *opt_name;
-	struct perf_evsel *evsel;
-	struct format_field *field;
+	struct evsel *evsel;
+	struct tep_format_field *field;
 	bool raw_trace = symbol_conf.raw_trace;
 	int ret = 0;
 
@@ -2369,7 +2473,7 @@
 		goto out;
 	}
 
-	if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+	if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) {
 		pr_debug("%s is not a tracepoint event\n", event_name);
 		ret = -EINVAL;
 		goto out;
@@ -2466,7 +2570,7 @@
 }
 
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
-			struct perf_evlist *evlist,
+			struct evlist *evlist,
 			int level)
 {
 	unsigned int i;
@@ -2562,7 +2666,7 @@
 }
 
 static int setup_sort_list(struct perf_hpp_list *list, char *str,
-			   struct perf_evlist *evlist)
+			   struct evlist *evlist)
 {
 	char *tmp, *tok;
 	int ret = 0;
@@ -2608,7 +2712,7 @@
 	return ret;
 }
 
-static const char *get_default_sort_order(struct perf_evlist *evlist)
+static const char *get_default_sort_order(struct evlist *evlist)
 {
 	const char *default_sort_orders[] = {
 		default_sort_order,
@@ -2619,7 +2723,7 @@
 		default_tracepoint_sort_order,
 	};
 	bool use_trace = true;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
@@ -2627,7 +2731,7 @@
 		goto out_no_evlist;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) {
 			use_trace = false;
 			break;
 		}
@@ -2642,7 +2746,7 @@
 	return default_sort_orders[sort__mode];
 }
 
-static int setup_sort_order(struct perf_evlist *evlist)
+static int setup_sort_order(struct evlist *evlist)
 {
 	char *new_sort_order;
 
@@ -2703,7 +2807,7 @@
 	return keys;
 }
 
-static int __setup_sorting(struct perf_evlist *evlist)
+static int __setup_sorting(struct evlist *evlist)
 {
 	char *str;
 	const char *sort_keys;
@@ -2956,7 +3060,7 @@
 	return ret;
 }
 
-int setup_sorting(struct perf_evlist *evlist)
+int setup_sorting(struct evlist *evlist)
 {
 	int err;
 
@@ -3007,3 +3111,54 @@
 	reset_dimensions();
 	perf_hpp__reset_output_field(&perf_hpp_list);
 }
+
+#define INDENT (3*8 + 1)
+
+static void add_key(struct strbuf *sb, const char *str, int *llen)
+{
+	if (*llen >= 75) {
+		strbuf_addstr(sb, "\n\t\t\t ");
+		*llen = INDENT;
+	}
+	strbuf_addf(sb, " %s", str);
+	*llen += strlen(str) + 1;
+}
+
+static void add_sort_string(struct strbuf *sb, struct sort_dimension *s, int n,
+			    int *llen)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		add_key(sb, s[i].name, llen);
+}
+
+static void add_hpp_sort_string(struct strbuf *sb, struct hpp_dimension *s, int n,
+				int *llen)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		add_key(sb, s[i].name, llen);
+}
+
+const char *sort_help(const char *prefix)
+{
+	struct strbuf sb;
+	char *s;
+	int len = strlen(prefix) + INDENT;
+
+	strbuf_init(&sb, 300);
+	strbuf_addstr(&sb, prefix);
+	add_hpp_sort_string(&sb, hpp_sort_dimensions,
+			    ARRAY_SIZE(hpp_sort_dimensions), &len);
+	add_sort_string(&sb, common_sort_dimensions,
+			    ARRAY_SIZE(common_sort_dimensions), &len);
+	add_sort_string(&sb, bstack_sort_dimensions,
+			    ARRAY_SIZE(bstack_sort_dimensions), &len);
+	add_sort_string(&sb, memory_sort_dimensions,
+			    ARRAY_SIZE(memory_sort_dimensions), &len);
+	s = strbuf_detach(&sb, NULL);
+	strbuf_release(&sb);
+	return s;
+}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index a97cf8e..7b93f34 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -1,28 +1,17 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __PERF_SORT_H
 #define __PERF_SORT_H
-#include "../builtin.h"
-
 #include <regex.h>
-
-#include "color.h"
+#include <stdbool.h>
 #include <linux/list.h>
-#include "cache.h"
 #include <linux/rbtree.h>
-#include "symbol.h"
-#include "string.h"
+#include "map_symbol.h"
+#include "symbol_conf.h"
 #include "callchain.h"
 #include "values.h"
-
-#include "../perf.h"
-#include "debug.h"
-#include "header.h"
-
-#include <subcmd/parse-options.h>
-#include "parse-events.h"
 #include "hist.h"
-#include "srcline.h"
 
+struct option;
 struct thread;
 
 extern regex_t parent_regex;
@@ -46,6 +35,12 @@
 extern enum sort_type sort__first_dimension;
 extern const char default_mem_sort_order[];
 
+struct res_sample {
+	u64 time;
+	int cpu;
+	int tid;
+};
+
 struct he_stat {
 	u64			period;
 	u64			period_sys;
@@ -72,6 +67,9 @@
 
 		/* HISTC_WEIGHTED_DIFF */
 		s64	wdiff;
+
+		/* PERF_HPP_DIFF__CYCLES */
+		s64	cycles;
 	};
 };
 
@@ -134,10 +132,14 @@
 	char			*srcfile;
 	struct symbol		*parent;
 	struct branch_info	*branch_info;
+	long			time;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
+	struct block_info	*block_info;
 	void			*raw_data;
 	u32			raw_size;
+	int			num_res;
+	struct res_sample	*res_samples;
 	void			*trace_output;
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
@@ -145,8 +147,8 @@
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
-			struct rb_root	hroot_in;
-			struct rb_root  hroot_out;
+			struct rb_root_cached	hroot_in;
+			struct rb_root_cached   hroot_out;
 		};				/* non-leaf entries */
 		struct rb_root	sorted_chain;	/* leaf entry has callchains */
 	};
@@ -190,18 +192,6 @@
 	return period * 100.0 / total_period;
 }
 
-static inline u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size() - 1));
-}
-
-static inline u64 cl_offset(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & (cacheline_size() - 1));
-}
-
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
@@ -229,6 +219,8 @@
 	SORT_SYM_SIZE,
 	SORT_DSO_SIZE,
 	SORT_CGROUP_ID,
+	SORT_SYM_IPC_NULL,
+	SORT_TIME,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -242,6 +234,7 @@
 	SORT_CYCLES,
 	SORT_SRCLINE_FROM,
 	SORT_SRCLINE_TO,
+	SORT_SYM_IPC,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,
@@ -272,17 +265,28 @@
 	u8	se_width_idx;
 };
 
+struct block_hist {
+	struct hists		block_hists;
+	struct perf_hpp_list	block_list;
+	struct perf_hpp_fmt	block_fmt;
+	int			block_idx;
+	bool			valid;
+	struct hist_entry	he;
+};
+
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-struct perf_evlist;
+struct evlist;
 struct tep_handle;
-int setup_sorting(struct perf_evlist *evlist);
+int setup_sorting(struct evlist *evlist);
 int setup_output_field(void);
 void reset_output_field(void);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
+const char *sort_help(const char *prefix);
+
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
 bool is_strict_order(const char *order);
@@ -290,7 +294,7 @@
 int hpp_dimension__add_output(unsigned col);
 void reset_dimensions(void);
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
-			struct perf_evlist *evlist,
+			struct evlist *evlist,
 			int level);
 int output_field_add(struct perf_hpp_list *list, char *tok);
 int64_t
diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c
new file mode 100644
index 0000000..d84ed8b
--- /dev/null
+++ b/tools/perf/util/srccode.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Manage printing of source lines
+ * Copyright (c) 2017, Intel Corporation.
+ * Author: Andi Kleen
+ */
+#include <linux/list.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <assert.h>
+#include <string.h>
+#include "srccode.h"
+#include "debug.h"
+#include <internal/lib.h> // page_size
+
+#define MAXSRCCACHE (32*1024*1024)
+#define MAXSRCFILES     64
+#define SRC_HTAB_SZ	64
+
+struct srcfile {
+	struct hlist_node hash_nd;
+	struct list_head nd;
+	char *fn;
+	char **lines;
+	char *map;
+	unsigned numlines;
+	size_t maplen;
+};
+
+static struct hlist_head srcfile_htab[SRC_HTAB_SZ];
+static LIST_HEAD(srcfile_list);
+static long map_total_sz;
+static int num_srcfiles;
+
+static unsigned shash(unsigned char *s)
+{
+	unsigned h = 0;
+	while (*s)
+		h = 65599 * h + *s++;
+	return h ^ (h >> 16);
+}
+
+static int countlines(char *map, int maplen)
+{
+	int numl;
+	char *end = map + maplen;
+	char *p = map;
+
+	if (maplen == 0)
+		return 0;
+	numl = 0;
+	while (p < end && (p = memchr(p, '\n', end - p)) != NULL) {
+		numl++;
+		p++;
+	}
+	if (p < end)
+		numl++;
+	return numl;
+}
+
+static void fill_lines(char **lines, int maxline, char *map, int maplen)
+{
+	int l;
+	char *end = map + maplen;
+	char *p = map;
+
+	if (maplen == 0 || maxline == 0)
+		return;
+	l = 0;
+	lines[l++] = map;
+	while (p < end && (p = memchr(p, '\n', end - p)) != NULL) {
+		if (l >= maxline)
+			return;
+		lines[l++] = ++p;
+	}
+	if (p < end)
+		lines[l] = p;
+}
+
+static void free_srcfile(struct srcfile *sf)
+{
+	list_del_init(&sf->nd);
+	hlist_del(&sf->hash_nd);
+	map_total_sz -= sf->maplen;
+	munmap(sf->map, sf->maplen);
+	zfree(&sf->lines);
+	zfree(&sf->fn);
+	free(sf);
+	num_srcfiles--;
+}
+
+static struct srcfile *find_srcfile(char *fn)
+{
+	struct stat st;
+	struct srcfile *h;
+	int fd;
+	unsigned long sz;
+	unsigned hval = shash((unsigned char *)fn) % SRC_HTAB_SZ;
+
+	hlist_for_each_entry (h, &srcfile_htab[hval], hash_nd) {
+		if (!strcmp(fn, h->fn)) {
+			/* Move to front */
+			list_del(&h->nd);
+			list_add(&h->nd, &srcfile_list);
+			return h;
+		}
+	}
+
+	/* Only prune if there is more than one entry */
+	while ((num_srcfiles > MAXSRCFILES || map_total_sz > MAXSRCCACHE) &&
+	       srcfile_list.next != &srcfile_list) {
+		assert(!list_empty(&srcfile_list));
+		h = list_entry(srcfile_list.prev, struct srcfile, nd);
+		free_srcfile(h);
+	}
+
+	fd = open(fn, O_RDONLY);
+	if (fd < 0 || fstat(fd, &st) < 0) {
+		pr_debug("cannot open source file %s\n", fn);
+		return NULL;
+	}
+
+	h = malloc(sizeof(struct srcfile));
+	if (!h)
+		return NULL;
+
+	h->fn = strdup(fn);
+	if (!h->fn)
+		goto out_h;
+
+	h->maplen = st.st_size;
+	sz = (h->maplen + page_size - 1) & ~(page_size - 1);
+	h->map = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
+	close(fd);
+	if (h->map == (char *)-1) {
+		pr_debug("cannot mmap source file %s\n", fn);
+		goto out_fn;
+	}
+	h->numlines = countlines(h->map, h->maplen);
+	h->lines = calloc(h->numlines, sizeof(char *));
+	if (!h->lines)
+		goto out_map;
+	fill_lines(h->lines, h->numlines, h->map, h->maplen);
+	list_add(&h->nd, &srcfile_list);
+	hlist_add_head(&h->hash_nd, &srcfile_htab[hval]);
+	map_total_sz += h->maplen;
+	num_srcfiles++;
+	return h;
+
+out_map:
+	munmap(h->map, sz);
+out_fn:
+	zfree(&h->fn);
+out_h:
+	free(h);
+	return NULL;
+}
+
+/* Result is not 0 terminated */
+char *find_sourceline(char *fn, unsigned line, int *lenp)
+{
+	char *l, *p;
+	struct srcfile *sf = find_srcfile(fn);
+	if (!sf)
+		return NULL;
+	line--;
+	if (line >= sf->numlines)
+		return NULL;
+	l = sf->lines[line];
+	if (!l)
+		return NULL;
+	p = memchr(l, '\n', sf->map + sf->maplen - l);
+	*lenp = p - l;
+	return l;
+}
diff --git a/tools/perf/util/srccode.h b/tools/perf/util/srccode.h
new file mode 100644
index 0000000..1b5ed76
--- /dev/null
+++ b/tools/perf/util/srccode.h
@@ -0,0 +1,20 @@
+#ifndef SRCCODE_H
+#define SRCCODE_H 1
+
+struct srccode_state {
+	char	 *srcfile;
+	unsigned line;
+};
+
+static inline void srccode_state_init(struct srccode_state *state)
+{
+	state->srcfile = NULL;
+	state->line    = 0;
+}
+
+void srccode_state_free(struct srccode_state *state);
+
+/* Result is not 0 terminated */
+char *find_sourceline(char *fn, unsigned line, int *lenp);
+
+#endif
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index e767c4a..6ccf6f6 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -5,11 +5,13 @@
 #include <string.h>
 
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 
 #include "util/dso.h"
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/callchain.h"
+#include "util/symbol_conf.h"
 #include "srcline.h"
 #include "string2.h"
 #include "symbol.h"
@@ -104,7 +106,7 @@
 	} else {
 		/* create a fake symbol for the inline frame */
 		inline_sym = symbol__new(base_sym ? base_sym->start : 0,
-					 base_sym ? base_sym->end : 0,
+					 base_sym ? (base_sym->end - base_sym->start) : 0,
 					 base_sym ? base_sym->binding : 0,
 					 base_sym ? base_sym->type : 0,
 					 funcname);
@@ -287,7 +289,8 @@
 	}
 
 	if (a2l == NULL) {
-		pr_warning("addr2line_init failed for %s\n", dso_name);
+		if (!symbol_conf.disable_add2line_warn)
+			pr_warning("addr2line_init failed for %s\n", dso_name);
 		return 0;
 	}
 
@@ -464,7 +467,7 @@
 		char *srcline;
 		struct symbol *inline_sym;
 
-		rtrim(funcname);
+		strim(funcname);
 
 		if (getline(&filename, &filelen, fp) == -1)
 			goto out;
@@ -548,6 +551,34 @@
 	return srcline;
 }
 
+/* Returns filename and fills in line number in line */
+char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line)
+{
+	char *file = NULL;
+	const char *dso_name;
+
+	if (!dso->has_srcline)
+		goto out;
+
+	dso_name = dso__name(dso);
+	if (dso_name == NULL)
+		goto out;
+
+	if (!addr2line(dso_name, addr, &file, line, dso, true, NULL, NULL))
+		goto out;
+
+	dso->a2l_fails = 0;
+	return file;
+
+out:
+	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
+		dso->has_srcline = 0;
+		dso__free_a2l(dso);
+	}
+
+	return NULL;
+}
+
 void free_srcline(char *srcline)
 {
 	if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
@@ -566,11 +597,12 @@
 	struct rb_node		rb_node;
 };
 
-void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
+void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline)
 {
-	struct rb_node **p = &tree->rb_node;
+	struct rb_node **p = &tree->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct srcline_node *i, *node;
+	bool leftmost = true;
 
 	node = zalloc(sizeof(struct srcline_node));
 	if (!node) {
@@ -586,16 +618,18 @@
 		i = rb_entry(parent, struct srcline_node, rb_node);
 		if (addr < i->addr)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&node->rb_node, parent, p);
-	rb_insert_color(&node->rb_node, tree);
+	rb_insert_color_cached(&node->rb_node, tree, leftmost);
 }
 
-char *srcline__tree_find(struct rb_root *tree, u64 addr)
+char *srcline__tree_find(struct rb_root_cached *tree, u64 addr)
 {
-	struct rb_node *n = tree->rb_node;
+	struct rb_node *n = tree->rb_root.rb_node;
 
 	while (n) {
 		struct srcline_node *i = rb_entry(n, struct srcline_node,
@@ -612,15 +646,15 @@
 	return NULL;
 }
 
-void srcline__tree_delete(struct rb_root *tree)
+void srcline__tree_delete(struct rb_root_cached *tree)
 {
 	struct srcline_node *pos;
-	struct rb_node *next = rb_first(tree);
+	struct rb_node *next = rb_first_cached(tree);
 
 	while (next) {
 		pos = rb_entry(next, struct srcline_node, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, tree);
+		rb_erase_cached(&pos->rb_node, tree);
 		free_srcline(pos->srcline);
 		zfree(&pos);
 	}
@@ -654,28 +688,32 @@
 	free(node);
 }
 
-void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+void inlines__tree_insert(struct rb_root_cached *tree,
+			  struct inline_node *inlines)
 {
-	struct rb_node **p = &tree->rb_node;
+	struct rb_node **p = &tree->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 addr = inlines->addr;
 	struct inline_node *i;
+	bool leftmost = true;
 
 	while (*p != NULL) {
 		parent = *p;
 		i = rb_entry(parent, struct inline_node, rb_node);
 		if (addr < i->addr)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&inlines->rb_node, parent, p);
-	rb_insert_color(&inlines->rb_node, tree);
+	rb_insert_color_cached(&inlines->rb_node, tree, leftmost);
 }
 
-struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr)
 {
-	struct rb_node *n = tree->rb_node;
+	struct rb_node *n = tree->rb_root.rb_node;
 
 	while (n) {
 		struct inline_node *i = rb_entry(n, struct inline_node,
@@ -692,15 +730,15 @@
 	return NULL;
 }
 
-void inlines__tree_delete(struct rb_root *tree)
+void inlines__tree_delete(struct rb_root_cached *tree)
 {
 	struct inline_node *pos;
-	struct rb_node *next = rb_first(tree);
+	struct rb_node *next = rb_first_cached(tree);
 
 	while (next) {
 		pos = rb_entry(next, struct inline_node, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, tree);
+		rb_erase_cached(&pos->rb_node, tree);
 		inline_node__delete(pos);
 	}
 }
diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h
index b2bb550..b11a0aa 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -16,13 +16,14 @@
 		  bool show_sym, bool show_addr, bool unwind_inlines,
 		  u64 ip);
 void free_srcline(char *srcline);
+char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line);
 
 /* insert the srcline into the DSO, which will take ownership */
-void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline);
+void srcline__tree_insert(struct rb_root_cached *tree, u64 addr, char *srcline);
 /* find previously inserted srcline */
-char *srcline__tree_find(struct rb_root *tree, u64 addr);
+char *srcline__tree_find(struct rb_root_cached *tree, u64 addr);
 /* delete all srclines within the tree */
-void srcline__tree_delete(struct rb_root *tree);
+void srcline__tree_delete(struct rb_root_cached *tree);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
@@ -45,10 +46,11 @@
 void inline_node__delete(struct inline_node *node);
 
 /* insert the inline node list into the DSO, which will take ownership */
-void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+void inlines__tree_insert(struct rb_root_cached *tree,
+			  struct inline_node *inlines);
 /* find previously inserted inline node list */
-struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+struct inline_node *inlines__tree_find(struct rb_root_cached *tree, u64 addr);
 /* delete all nodes within the tree of inline_node s */
-void inlines__tree_delete(struct rb_root *tree);
+void inlines__tree_delete(struct rb_root_cached *tree);
 
 #endif /* PERF_SRCLINE_H */
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
new file mode 100644
index 0000000..ed3b0ac
--- /dev/null
+++ b/tools/perf/util/stat-display.c
@@ -0,0 +1,1226 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/string.h>
+#include <linux/time64.h>
+#include <math.h>
+#include "color.h"
+#include "counts.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "stat.h"
+#include "top.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "string2.h"
+#include <linux/ctype.h>
+#include "cgroup.h"
+#include <api/fs/fs.h>
+
+#define CNTR_NOT_SUPPORTED	"<not supported>"
+#define CNTR_NOT_COUNTED	"<not counted>"
+
+static void print_running(struct perf_stat_config *config,
+			  u64 run, u64 ena)
+{
+	if (config->csv_output) {
+		fprintf(config->output, "%s%" PRIu64 "%s%.2f",
+					config->csv_sep,
+					run,
+					config->csv_sep,
+					ena ? 100.0 * run / ena : 100.0);
+	} else if (run != ena) {
+		fprintf(config->output, "  (%.2f%%)", 100.0 * run / ena);
+	}
+}
+
+static void print_noise_pct(struct perf_stat_config *config,
+			    double total, double avg)
+{
+	double pct = rel_stddev_stats(total, avg);
+
+	if (config->csv_output)
+		fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
+	else if (pct)
+		fprintf(config->output, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_stat_config *config,
+			struct evsel *evsel, double avg)
+{
+	struct perf_stat_evsel *ps;
+
+	if (config->run_count == 1)
+		return;
+
+	ps = evsel->stats;
+	print_noise_pct(config, stddev_stats(&ps->res_stats[0]), avg);
+}
+
+static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel)
+{
+	if (nr_cgroups) {
+		const char *cgrp_name = evsel->cgrp ? evsel->cgrp->name  : "";
+		fprintf(config->output, "%s%s", config->csv_sep, cgrp_name);
+	}
+}
+
+
+static void aggr_printout(struct perf_stat_config *config,
+			  struct evsel *evsel, int id, int nr)
+{
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+		fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			cpu_map__id_to_die(id),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_DIE:
+		fprintf(config->output, "S%d-D%*d%s%*d%s",
+			cpu_map__id_to_socket(id << 16),
+			config->csv_output ? 0 : -8,
+			cpu_map__id_to_die(id << 16),
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+		break;
+	case AGGR_SOCKET:
+		fprintf(config->output, "S%*d%s%*d%s",
+			config->csv_output ? 0 : -5,
+			id,
+			config->csv_sep,
+			config->csv_output ? 0 : 4,
+			nr,
+			config->csv_sep);
+			break;
+	case AGGR_NONE:
+		if (evsel->percore) {
+			fprintf(config->output, "S%d-D%d-C%*d%s",
+				cpu_map__id_to_socket(id),
+				cpu_map__id_to_die(id),
+				config->csv_output ? 0 : -5,
+				cpu_map__id_to_cpu(id), config->csv_sep);
+		} else {
+			fprintf(config->output, "CPU%*d%s ",
+				config->csv_output ? 0 : -5,
+				evsel__cpus(evsel)->map[id],
+				config->csv_sep);
+		}
+		break;
+	case AGGR_THREAD:
+		fprintf(config->output, "%*s-%*d%s",
+			config->csv_output ? 0 : 16,
+			perf_thread_map__comm(evsel->core.threads, id),
+			config->csv_output ? 0 : -8,
+			perf_thread_map__pid(evsel->core.threads, id),
+			config->csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+}
+
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(struct perf_stat_config *config __maybe_unused,
+			 void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+			    struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	if (config->aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(struct perf_stat_config *config,
+			     void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(config, os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(struct perf_stat_config *config, void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, config->csv_sep);
+	aggr_printout(config, os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(config->csv_sep, os->fh);
+}
+
+static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
+			     void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	ends = vals = skip_spaces(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, skip_spaces(unit));
+}
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(struct perf_stat_config *config,
+			      void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[1024], str[1024];
+	unsigned mlen = config->metric_only_len;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+
+	if (color)
+		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
+
+	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	fprintf(out, "%*s ", mlen, str);
+}
+
+static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
+				  void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	ends = vals = skip_spaces(buf);
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, config->csv_sep);
+}
+
+static void new_line_metric(struct perf_stat_config *config __maybe_unused,
+			    void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(struct perf_stat_config *config,
+				void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (config->csv_output)
+		fprintf(os->fh, "%s%s", unit, config->csv_sep);
+	else
+		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
+}
+
+static int first_shadow_cpu(struct perf_stat_config *config,
+			    struct evsel *evsel, int id)
+{
+	struct evlist *evlist = evsel->evlist;
+	int i;
+
+	if (!config->aggr_get_id)
+		return 0;
+
+	if (config->aggr_mode == AGGR_NONE)
+		return id;
+
+	if (config->aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = evsel__cpus(evsel)->map[i];
+
+		if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
+static void abs_printout(struct perf_stat_config *config,
+			 int id, int nr, struct evsel *evsel, double avg)
+{
+	FILE *output = config->output;
+	double sc =  evsel->scale;
+	const char *fmt;
+
+	if (config->csv_output) {
+		fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (config->big_num)
+			fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
+	}
+
+	aggr_printout(config, evsel, id, nr);
+
+	fprintf(output, fmt, avg, config->csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			evsel->unit, config->csv_sep);
+
+	fprintf(output, "%-*s", config->csv_output ? 0 : 25, perf_evsel__name(evsel));
+
+	print_cgroup(config, evsel);
+}
+
+static bool is_mixed_hw_group(struct evsel *counter)
+{
+	struct evlist *evlist = counter->evlist;
+	u32 pmu_type = counter->core.attr.type;
+	struct evsel *pos;
+
+	if (counter->core.nr_members < 2)
+		return false;
+
+	evlist__for_each_entry(evlist, pos) {
+		/* software events can be part of any hardware group */
+		if (pos->core.attr.type == PERF_TYPE_SOFTWARE)
+			continue;
+		if (pmu_type == PERF_TYPE_SOFTWARE) {
+			pmu_type = pos->core.attr.type;
+			continue;
+		}
+		if (pmu_type != pos->core.attr.type)
+			return true;
+	}
+
+	return false;
+}
+
+static void printout(struct perf_stat_config *config, int id, int nr,
+		     struct evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise,
+		     struct runtime_stat *st)
+{
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = config->output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	new_line_t nl;
+
+	if (config->metric_only) {
+		nl = new_line_metric;
+		if (config->csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (config->csv_output && !config->metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_DIE] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[config->aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (config->metric_only) {
+			pm(config, &os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(config, counter, id, nr);
+
+		fprintf(config->output, "%*s%s",
+			config->csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			config->csv_sep);
+
+		if (counter->supported) {
+			config->print_free_counters_hint = 1;
+			if (is_mixed_hw_group(counter))
+				config->print_mixed_hw_group_error = 1;
+		}
+
+		fprintf(config->output, "%-*s%s",
+			config->csv_output ? 0 : config->unit_width,
+			counter->unit, config->csv_sep);
+
+		fprintf(config->output, "%*s",
+			config->csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		print_cgroup(config, counter);
+
+		if (!config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+		if (config->csv_output)
+			pm(config, &os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (!config->metric_only)
+		abs_printout(config, id, nr, counter, uval);
+
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+	out.force_header = false;
+
+	if (config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+
+	perf_stat__print_shadow_stats(config, counter, uval,
+				first_shadow_cpu(config, counter, id),
+				&out, &config->metric_events, st);
+	if (!config->csv_output && !config->metric_only) {
+		print_noise(config, counter, noise);
+		print_running(config, run, ena);
+	}
+}
+
+static void aggr_update_shadow(struct perf_stat_config *config,
+			       struct evlist *evlist)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct evsel *counter;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		id = config->aggr_map->map[s];
+		evlist__for_each_entry(evlist, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			perf_stat__update_shadow_stats(counter, val,
+					first_shadow_cpu(config, counter, id),
+					&rt_stat);
+		}
+	}
+}
+
+static void uniquify_event_name(struct evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (counter->uniquified_name ||
+	    !counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+
+	counter->uniquified_name = true;
+}
+
+static void collect_all_aliases(struct perf_stat_config *config, struct evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	struct evlist *evlist = counter->evlist;
+	struct evsel *alias;
+
+	alias = list_prepare_entry(counter, &(evlist->core.entries), core.node);
+	list_for_each_entry_continue (alias, &evlist->core.entries, core.node) {
+		if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+		    alias->scale != counter->scale ||
+		    alias->cgrp != counter->cgrp ||
+		    strcmp(alias->unit, counter->unit) ||
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter) ||
+		    !strcmp(alias->pmu_name, counter->pmu_name))
+			break;
+		alias->merged_stat = true;
+		cb(config, alias, data, false);
+	}
+}
+
+static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
+			    void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
+				       bool first),
+			    void *data)
+{
+	if (counter->merged_stat)
+		return false;
+	cb(config, counter, data, true);
+	if (config->no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
+		collect_all_aliases(config, counter, cb, data);
+	return true;
+}
+
+struct aggr_data {
+	u64 ena, run, val;
+	int id;
+	int nr;
+	int cpu;
+};
+
+static void aggr_cb(struct perf_stat_config *config,
+		    struct evsel *counter, void *data, bool first)
+{
+	struct aggr_data *ad = data;
+	int cpu, s2;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct perf_counts_values *counts;
+
+		s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
+		if (s2 != ad->id)
+			continue;
+		if (first)
+			ad->nr++;
+		counts = perf_counts(counter->counts, cpu, 0);
+		/*
+		 * When any result is bad, make them all to give
+		 * consistent output in interval mode.
+		 */
+		if (counts->ena == 0 || counts->run == 0 ||
+		    counter->counts->scaled == -1) {
+			ad->ena = 0;
+			ad->run = 0;
+			break;
+		}
+		ad->val += counts->val;
+		ad->ena += counts->ena;
+		ad->run += counts->run;
+	}
+}
+
+static void print_counter_aggrdata(struct perf_stat_config *config,
+				   struct evsel *counter, int s,
+				   char *prefix, bool metric_only,
+				   bool *first)
+{
+	struct aggr_data ad;
+	FILE *output = config->output;
+	u64 ena, run, val;
+	int id, nr;
+	double uval;
+
+	ad.id = id = config->aggr_map->map[s];
+	ad.val = ad.ena = ad.run = 0;
+	ad.nr = 0;
+	if (!collect_data(config, counter, aggr_cb, &ad))
+		return;
+
+	nr = ad.nr;
+	ena = ad.ena;
+	run = ad.run;
+	val = ad.val;
+	if (*first && metric_only) {
+		*first = false;
+		aggr_printout(config, counter, id, nr);
+	}
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = val * counter->scale;
+	printout(config, id, nr, counter, uval, prefix,
+		 run, ena, 1.0, &rt_stat);
+	if (!metric_only)
+		fputc('\n', output);
+}
+
+static void print_aggr(struct perf_stat_config *config,
+		       struct evlist *evlist,
+		       char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	struct evsel *counter;
+	int s;
+	bool first;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	aggr_update_shadow(config, evlist);
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		first = true;
+		evlist__for_each_entry(evlist, counter) {
+			print_counter_aggrdata(config, counter, s,
+					       prefix, metric_only,
+					       &first);
+		}
+		if (metric_only)
+			fputc('\n', output);
+	}
+}
+
+static int cmp_val(const void *a, const void *b)
+{
+	return ((struct perf_aggr_thread_value *)b)->val -
+		((struct perf_aggr_thread_value *)a)->val;
+}
+
+static struct perf_aggr_thread_value *sort_aggr_thread(
+					struct evsel *counter,
+					int nthreads, int ncpus,
+					int *ret,
+					struct target *_target)
+{
+	int cpu, thread, i = 0;
+	double uval;
+	struct perf_aggr_thread_value *buf;
+
+	buf = calloc(nthreads, sizeof(struct perf_aggr_thread_value));
+	if (!buf)
+		return NULL;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		uval = val * counter->scale;
+
+		/*
+		 * Skip value 0 when enabling --per-thread globally,
+		 * otherwise too many 0 output.
+		 */
+		if (uval == 0.0 && target__has_per_thread(_target))
+			continue;
+
+		buf[i].counter = counter;
+		buf[i].id = thread;
+		buf[i].uval = uval;
+		buf[i].val = val;
+		buf[i].run = run;
+		buf[i].ena = ena;
+		i++;
+	}
+
+	qsort(buf, i, sizeof(struct perf_aggr_thread_value), cmp_val);
+
+	if (ret)
+		*ret = i;
+
+	return buf;
+}
+
+static void print_aggr_thread(struct perf_stat_config *config,
+			      struct target *_target,
+			      struct evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	int nthreads = perf_thread_map__nr(counter->core.threads);
+	int ncpus = perf_cpu_map__nr(counter->core.cpus);
+	int thread, sorted_threads, id;
+	struct perf_aggr_thread_value *buf;
+
+	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
+	if (!buf) {
+		perror("cannot sort aggr thread");
+		return;
+	}
+
+	for (thread = 0; thread < sorted_threads; thread++) {
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		id = buf[thread].id;
+		if (config->stats)
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &config->stats[id]);
+		else
+			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
+				 prefix, buf[thread].run, buf[thread].ena, 1.0,
+				 &rt_stat);
+		fputc('\n', output);
+	}
+
+	free(buf);
+}
+
+struct caggr_data {
+	double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_stat_config *config __maybe_unused,
+			    struct evsel *counter, void *data,
+			    bool first __maybe_unused)
+{
+	struct caggr_data *cd = data;
+	struct perf_stat_evsel *ps = counter->stats;
+
+	cd->avg += avg_stats(&ps->res_stats[0]);
+	cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+	cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
+/*
+ * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
+ */
+static void print_counter_aggr(struct perf_stat_config *config,
+			       struct evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	double uval;
+	struct caggr_data cd = { .avg = 0.0 };
+
+	if (!collect_data(config, counter, counter_aggr_cb, &cd))
+		return;
+
+	if (prefix && !metric_only)
+		fprintf(output, "%s", prefix);
+
+	uval = cd.avg * counter->scale;
+	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+		 cd.avg, &rt_stat);
+	if (!metric_only)
+		fprintf(output, "\n");
+}
+
+static void counter_cb(struct perf_stat_config *config __maybe_unused,
+		       struct evsel *counter, void *data,
+		       bool first __maybe_unused)
+{
+	struct aggr_data *ad = data;
+
+	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_stat_config *config,
+			  struct evsel *counter, char *prefix)
+{
+	FILE *output = config->output;
+	u64 ena, run, val;
+	double uval;
+	int cpu;
+
+	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+		struct aggr_data ad = { .cpu = cpu };
+
+		if (!collect_data(config, counter, counter_cb, &ad))
+			return;
+		val = ad.val;
+		ena = ad.ena;
+		run = ad.run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+			 &rt_stat);
+
+		fputc('\n', output);
+	}
+}
+
+static void print_no_aggr_metric(struct perf_stat_config *config,
+				 struct evlist *evlist,
+				 char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct evsel *counter;
+	u64 ena, run, val;
+	double uval;
+
+	nrcpus = evlist->core.cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
+
+		if (prefix)
+			fputs(prefix, config->output);
+		evlist__for_each_entry(evlist, counter) {
+			if (first) {
+				aggr_printout(config, counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
+				 &rt_stat);
+		}
+		fputc('\n', config->output);
+	}
+}
+
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 24,
+	[AGGR_DIE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
+
+static const char *aggr_header_csv[] = {
+	[AGGR_CORE] 	= 	"core,cpus,",
+	[AGGR_DIE] 	= 	"die,cpus",
+	[AGGR_SOCKET] 	= 	"socket,cpus",
+	[AGGR_NONE] 	= 	"cpu,",
+	[AGGR_THREAD] 	= 	"comm-pid,",
+	[AGGR_GLOBAL] 	=	""
+};
+
+static void print_metric_headers(struct perf_stat_config *config,
+				 struct evlist *evlist,
+				 const char *prefix, bool no_indent)
+{
+	struct perf_stat_output_ctx out;
+	struct evsel *counter;
+	struct outstate os = {
+		.fh = config->output
+	};
+
+	if (prefix)
+		fprintf(config->output, "%s", prefix);
+
+	if (!config->csv_output && !no_indent)
+		fprintf(config->output, "%*s",
+			aggr_header_lens[config->aggr_mode], "");
+	if (config->csv_output) {
+		if (config->interval)
+			fputs("time,", config->output);
+		fputs(aggr_header_csv[config->aggr_mode], config->output);
+	}
+
+	/* Print metrics headers only */
+	evlist__for_each_entry(evlist, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		out.force_header = true;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(config, counter, 0,
+					      0,
+					      &out,
+					      &config->metric_events,
+					      &rt_stat);
+	}
+	fputc('\n', config->output);
+}
+
+static void print_interval(struct perf_stat_config *config,
+			   struct evlist *evlist,
+			   char *prefix, struct timespec *ts)
+{
+	bool metric_only = config->metric_only;
+	unsigned int unit_width = config->unit_width;
+	FILE *output = config->output;
+	static int num_print_interval;
+
+	if (config->interval_clear)
+		puts(CONSOLE_CLEAR);
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+
+	if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
+		switch (config->aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_DIE:
+			fprintf(output, "#           time die          cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core            cpus");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU    ");
+			if (!metric_only)
+				fprintf(output, "                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid");
+			if (!metric_only)
+				fprintf(output, "                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time");
+			if (!metric_only)
+				fprintf(output, "             counts %*s events\n", unit_width, "unit");
+		case AGGR_UNSET:
+			break;
+		}
+	}
+
+	if ((num_print_interval == 0 || config->interval_clear) && metric_only)
+		print_metric_headers(config, evlist, " ", true);
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(struct perf_stat_config *config,
+			 struct target *_target,
+			 int argc, const char **argv)
+{
+	FILE *output = config->output;
+	int i;
+
+	fflush(stdout);
+
+	if (!config->csv_output) {
+		fprintf(output, "\n");
+		fprintf(output, " Performance counter stats for ");
+		if (_target->system_wide)
+			fprintf(output, "\'system wide");
+		else if (_target->cpu_list)
+			fprintf(output, "\'CPU(s) %s", _target->cpu_list);
+		else if (!target__has_task(_target)) {
+			fprintf(output, "\'%s", argv ? argv[0] : "pipe");
+			for (i = 1; argv && (i < argc); i++)
+				fprintf(output, " %s", argv[i]);
+		} else if (_target->pid)
+			fprintf(output, "process id \'%s", _target->pid);
+		else
+			fprintf(output, "thread id \'%s", _target->tid);
+
+		fprintf(output, "\'");
+		if (config->run_count > 1)
+			fprintf(output, " (%d runs)", config->run_count);
+		fprintf(output, ":\n\n");
+	}
+}
+
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(struct perf_stat_config *config,
+			FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < config->run_count; idx++) {
+		double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
+static double timeval2double(struct timeval *t)
+{
+	return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
+}
+
+static void print_footer(struct perf_stat_config *config)
+{
+	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+	FILE *output = config->output;
+	int n;
+
+	if (!config->null_run)
+		fprintf(output, "\n");
+
+	if (config->run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+
+		if (config->ru_display) {
+			double ru_utime = timeval2double(&config->ru_data.ru_utime);
+			double ru_stime = timeval2double(&config->ru_data.ru_stime);
+
+			fprintf(output, "\n\n");
+			fprintf(output, " %17.9f seconds user\n", ru_utime);
+			fprintf(output, " %17.9f seconds sys\n", ru_stime);
+		}
+	} else {
+		double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (config->walltime_run_table)
+			print_table(config, output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(config, sd, avg);
+	}
+	fprintf(output, "\n\n");
+
+	if (config->print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
+		fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+"	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+"	perf stat ...\n"
+"	echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+
+	if (config->print_mixed_hw_group_error)
+		fprintf(output,
+			"The events in group usually have to be from "
+			"the same PMU. Try reorganizing the group.\n");
+}
+
+static void print_percore(struct perf_stat_config *config,
+			  struct evsel *counter, char *prefix)
+{
+	bool metric_only = config->metric_only;
+	FILE *output = config->output;
+	int s;
+	bool first = true;
+
+	if (!(config->aggr_map || config->aggr_get_id))
+		return;
+
+	for (s = 0; s < config->aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
+		print_counter_aggrdata(config, counter, s,
+				       prefix, metric_only,
+				       &first);
+	}
+
+	if (metric_only)
+		fputc('\n', output);
+}
+
+void
+perf_evlist__print_counters(struct evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv)
+{
+	bool metric_only = config->metric_only;
+	int interval = config->interval;
+	struct evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(config, evlist, prefix = buf, ts);
+	else
+		print_header(config, _target, argc, argv);
+
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0 && !interval)
+			print_metric_headers(config, evlist, prefix, false);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (config->aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(config->output, "%s", prefix);
+	}
+
+	switch (config->aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_DIE:
+	case AGGR_SOCKET:
+		print_aggr(config, evlist, prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each_entry(evlist, counter) {
+			print_aggr_thread(config, _target, counter, prefix);
+		}
+		break;
+	case AGGR_GLOBAL:
+		evlist__for_each_entry(evlist, counter) {
+			print_counter_aggr(config, counter, prefix);
+		}
+		if (metric_only)
+			fputc('\n', config->output);
+		break;
+	case AGGR_NONE:
+		if (metric_only)
+			print_no_aggr_metric(config, evlist, prefix);
+		else {
+			evlist__for_each_entry(evlist, counter) {
+				if (counter->percore)
+					print_percore(config, counter, prefix);
+				else
+					print_counter(config, counter, prefix);
+			}
+		}
+		break;
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	if (!interval && !config->csv_output)
+		print_footer(config);
+
+	fflush(config->output);
+}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5..2c41d47 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,10 +8,12 @@
 #include "evlist.h"
 #include "expr.h"
 #include "metricgroup.h"
+#include <linux/zalloc.h>
 
 /*
  * AGGR_GLOBAL: Use CPU 0
  * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_DIE: Use first CPU of die
  * AGGR_CORE: Use first CPU of core
  * AGGR_NONE: Use matching CPU
  * AGGR_THREAD: Not supported?
@@ -23,12 +25,14 @@
 
 struct saved_value {
 	struct rb_node rb_node;
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	enum stat_type type;
 	int ctx;
 	int cpu;
 	struct runtime_stat *stat;
 	struct stats stats;
+	u64 metric_total;
+	int metric_other;
 };
 
 static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
@@ -92,7 +96,7 @@
 	free(v);
 }
 
-static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
+static struct saved_value *saved_value_lookup(struct evsel *evsel,
 					      int cpu,
 					      bool create,
 					      enum stat_type type,
@@ -144,19 +148,19 @@
 	runtime_stat__init(&rt_stat);
 }
 
-static int evsel_context(struct perf_evsel *evsel)
+static int evsel_context(struct evsel *evsel)
 {
 	int ctx = 0;
 
-	if (evsel->attr.exclude_kernel)
+	if (evsel->core.attr.exclude_kernel)
 		ctx |= CTX_BIT_KERNEL;
-	if (evsel->attr.exclude_user)
+	if (evsel->core.attr.exclude_user)
 		ctx |= CTX_BIT_USER;
-	if (evsel->attr.exclude_hv)
+	if (evsel->core.attr.exclude_hv)
 		ctx |= CTX_BIT_HV;
-	if (evsel->attr.exclude_host)
+	if (evsel->core.attr.exclude_host)
 		ctx |= CTX_BIT_HOST;
-	if (evsel->attr.exclude_idle)
+	if (evsel->core.attr.exclude_idle)
 		ctx |= CTX_BIT_IDLE;
 
 	return ctx;
@@ -168,7 +172,7 @@
 	struct rb_node *pos, *next;
 
 	rblist = &st->value_list;
-	next = rb_first(&rblist->entries);
+	next = rb_first_cached(&rblist->entries);
 	while (next) {
 		pos = next;
 		next = rb_next(pos);
@@ -205,16 +209,17 @@
  * more semantic information such as miss/hit ratios,
  * instruction rates, etc:
  */
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
+void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 				    int cpu, struct runtime_stat *st)
 {
 	int ctx = evsel_context(counter);
+	u64 count_ns = count;
+	struct saved_value *v;
 
 	count *= counter->scale;
 
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
-	    perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
-		update_runtime_stat(st, STAT_NSECS, 0, cpu, count);
+	if (perf_evsel__is_clock(counter))
+		update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
@@ -264,9 +269,15 @@
 		update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
 
 	if (counter->collect_stat) {
-		struct saved_value *v = saved_value_lookup(counter, cpu, true,
-							   STAT_NONE, 0, st);
+		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
 		update_stats(&v->stats, count);
+		if (counter->metric_leader)
+			v->metric_total += count;
+	} else if (counter->metric_leader) {
+		v = saved_value_lookup(counter->metric_leader,
+				       cpu, true, STAT_NONE, 0, st);
+		v->metric_total += count;
+		v->metric_other++;
 	}
 }
 
@@ -297,22 +308,22 @@
 	return color;
 }
 
-static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
+static struct evsel *perf_stat__find_event(struct evlist *evsel_list,
 						const char *name)
 {
-	struct perf_evsel *c2;
+	struct evsel *c2;
 
 	evlist__for_each_entry (evsel_list, c2) {
-		if (!strcasecmp(c2->name, name))
+		if (!strcasecmp(c2->name, name) && !c2->collect_stat)
 			return c2;
 	}
 	return NULL;
 }
 
 /* Mark MetricExpr target events and link events using them to them. */
-void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
+void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 {
-	struct perf_evsel *counter, *leader, **metric_events, *oc;
+	struct evsel *counter, *leader, **metric_events, *oc;
 	bool found;
 	const char **metric_names;
 	int i;
@@ -330,7 +341,7 @@
 						&metric_names, &num_metric_names) < 0)
 				continue;
 
-			metric_events = calloc(sizeof(struct perf_evsel *),
+			metric_events = calloc(sizeof(struct evsel *),
 					       num_metric_names + 1);
 			if (!metric_events)
 				return;
@@ -342,7 +353,8 @@
 			if (leader) {
 				/* Search in group */
 				for_each_group_member (oc, leader) {
-					if (!strcasecmp(oc->name, metric_names[i])) {
+					if (!strcasecmp(oc->name, metric_names[i]) &&
+						!oc->collect_stat) {
 						found = true;
 						break;
 					}
@@ -410,8 +422,9 @@
 	return v->stats.n;
 }
 
-static void print_stalled_cycles_frontend(int cpu,
-					  struct perf_evsel *evsel, double avg,
+static void print_stalled_cycles_frontend(struct perf_stat_config *config,
+					  int cpu,
+					  struct evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st)
 {
@@ -427,14 +440,15 @@
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
 	if (ratio)
-		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+		out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle",
 				  ratio);
 	else
-		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
+		out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(int cpu,
-					 struct perf_evsel *evsel, double avg,
+static void print_stalled_cycles_backend(struct perf_stat_config *config,
+					 int cpu,
+					 struct evsel *evsel, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st)
 {
@@ -449,11 +463,12 @@
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(int cpu,
-				struct perf_evsel *evsel,
+static void print_branch_misses(struct perf_stat_config *config,
+				int cpu,
+				struct evsel *evsel,
 				double avg,
 				struct perf_stat_output_ctx *out,
 				struct runtime_stat *st)
@@ -469,11 +484,12 @@
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(int cpu,
-				   struct perf_evsel *evsel,
+static void print_l1_dcache_misses(struct perf_stat_config *config,
+				   int cpu,
+				   struct evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
 				   struct runtime_stat *st)
@@ -490,11 +506,12 @@
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(int cpu,
-				   struct perf_evsel *evsel,
+static void print_l1_icache_misses(struct perf_stat_config *config,
+				   int cpu,
+				   struct evsel *evsel,
 				   double avg,
 				   struct perf_stat_output_ctx *out,
 				   struct runtime_stat *st)
@@ -510,11 +527,12 @@
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel,
+static void print_dtlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
+				    struct evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
 				    struct runtime_stat *st)
@@ -529,11 +547,12 @@
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel,
+static void print_itlb_cache_misses(struct perf_stat_config *config,
+				    int cpu,
+				    struct evsel *evsel,
 				    double avg,
 				    struct perf_stat_output_ctx *out,
 				    struct runtime_stat *st)
@@ -548,11 +567,12 @@
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(int cpu,
-				  struct perf_evsel *evsel,
+static void print_ll_cache_misses(struct perf_stat_config *config,
+				  int cpu,
+				  struct evsel *evsel,
 				  double avg,
 				  struct perf_stat_output_ctx *out,
 				  struct runtime_stat *st)
@@ -567,7 +587,7 @@
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
 /*
@@ -674,7 +694,8 @@
 	return sanitize_val(1.0 - sum);
 }
 
-static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config,
+			   int cpu, struct evsel *evsel,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -694,14 +715,16 @@
 
 	if (cost > 10)
 		color = PERF_COLOR_RED;
-	out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
-	out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+	out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+	out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num);
 }
 
-static void generic_metric(const char *metric_expr,
-			   struct perf_evsel **metric_events,
+static void generic_metric(struct perf_stat_config *config,
+			   const char *metric_expr,
+			   struct evsel **metric_events,
 			   char *name,
 			   const char *metric_name,
+			   const char *metric_unit,
 			   double avg,
 			   int cpu,
 			   struct perf_stat_output_ctx *out,
@@ -709,16 +732,18 @@
 {
 	print_metric_t print_metric = out->print_metric;
 	struct parse_ctx pctx;
-	double ratio;
+	double ratio, scale;
 	int i;
 	void *ctxp = out->ctx;
+	char *n, *pn;
 
 	expr__ctx_init(&pctx);
+	/* Must be first id entry */
 	expr__add_id(&pctx, name, avg);
 	for (i = 0; metric_events[i]; i++) {
 		struct saved_value *v;
 		struct stats *stats;
-		double scale;
+		u64 metric_total = 0;
 
 		if (!strcmp(metric_events[i]->name, "duration_time")) {
 			stats = &walltime_nsecs_stats;
@@ -730,27 +755,67 @@
 				break;
 			stats = &v->stats;
 			scale = 1.0;
+
+			if (v->metric_other)
+				metric_total = v->metric_total;
 		}
-		expr__add_id(&pctx, metric_events[i]->name, avg_stats(stats)*scale);
+
+		n = strdup(metric_events[i]->name);
+		if (!n)
+			return;
+		/*
+		 * This display code with --no-merge adds [cpu] postfixes.
+		 * These are not supported by the parser. Remove everything
+		 * after the space.
+		 */
+		pn = strchr(n, ' ');
+		if (pn)
+			*pn = 0;
+
+		if (metric_total)
+			expr__add_id(&pctx, n, metric_total);
+		else
+			expr__add_id(&pctx, n, avg_stats(stats)*scale);
 	}
+
 	if (!metric_events[i]) {
 		const char *p = metric_expr;
 
-		if (expr__parse(&ratio, &pctx, &p) == 0)
-			print_metric(ctxp, NULL, "%8.1f",
-				metric_name ?
-				metric_name :
-				out->force_header ?  name : "",
-				ratio);
-		else
-			print_metric(ctxp, NULL, NULL,
+		if (expr__parse(&ratio, &pctx, &p) == 0) {
+			char *unit;
+			char metric_bf[64];
+
+			if (metric_unit && metric_name) {
+				if (perf_pmu__convert_scale(metric_unit,
+					&unit, &scale) >= 0) {
+					ratio *= scale;
+				}
+
+				scnprintf(metric_bf, sizeof(metric_bf),
+					  "%s  %s", unit, metric_name);
+				print_metric(config, ctxp, NULL, "%8.1f",
+					     metric_bf, ratio);
+			} else {
+				print_metric(config, ctxp, NULL, "%8.1f",
+					metric_name ?
+					metric_name :
+					out->force_header ?  name : "",
+					ratio);
+			}
+		} else {
+			print_metric(config, ctxp, NULL, NULL,
 				     out->force_header ?
 				     (metric_name ? metric_name : name) : "", 0);
+		}
 	} else
-		print_metric(ctxp, NULL, NULL, "", 0);
+		print_metric(config, ctxp, NULL, NULL, "", 0);
+
+	for (i = 1; i < pctx.num_ids; i++)
+		zfree(&pctx.ids[i].name);
 }
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
@@ -769,10 +834,10 @@
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"insn per cycle", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
+			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
 		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
@@ -783,70 +848,71 @@
 						    ctx, cpu));
 
 		if (total && avg) {
-			out->new_line(ctxp);
+			out->new_line(config, ctxp);
 			ratio = total / avg;
-			print_metric(ctxp, NULL, "%7.2f ",
+			print_metric(config, ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(ctxp, NULL, NULL,
+			out->new_line(config, ctxp);
+			print_metric(config, ctxp, NULL, "%7.2f ",
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
 		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(cpu, evsel, avg, out, st);
+			print_branch_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all branches", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(cpu, evsel, avg, out, st);
+			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(cpu, evsel, avg, out, st);
+			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(cpu, evsel, avg, out, st);
+			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(cpu, evsel, avg, out, st);
+			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(cpu, evsel, avg, out, st);
+			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
@@ -854,32 +920,32 @@
 			ratio = avg * 100 / total;
 
 		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.3f %%",
+			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
 
 		if (total) {
 			ratio = avg / total;
-			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
+			print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			print_metric(ctxp, NULL, NULL, "Ghz", 0);
+			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
 
 		if (total)
-			print_metric(ctxp, NULL,
+			print_metric(config, ctxp, NULL,
 					"%7.2f%%", "transactional cycles",
 					100.0 * (avg / total));
 		else
-			print_metric(ctxp, NULL, NULL, "transactional cycles",
+			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
@@ -888,10 +954,10 @@
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
+			print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
 		else
-			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
 					 ctx, cpu);
@@ -900,10 +966,10 @@
 			ratio = total / avg;
 
 		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
-			print_metric(ctxp, NULL, "%8.0f",
+			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
-			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
@@ -912,33 +978,33 @@
 		if (avg)
 			ratio = total / avg;
 
-		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
+		print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+			print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized",
 				     avg / (ratio * evsel->scale));
 		else
-			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
 		double fe_bound = td_fe_bound(ctx, cpu, st);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
 		double retiring = td_retiring(ctx, cpu, st);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
-		print_metric(ctxp, color, "%8.1f%%", "retiring",
+		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
 		double bad_spec = td_bad_spec(ctx, cpu, st);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
-		print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
 		double be_bound = td_be_bound(ctx, cpu, st);
@@ -955,13 +1021,13 @@
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		if (td_total_slots(ctx, cpu, st) > 0)
-			print_metric(ctxp, color, "%8.1f%%", name,
+			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
-			print_metric(ctxp, NULL, NULL, name, 0);
+			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (evsel->metric_expr) {
-		generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
-				evsel->metric_name, avg, cpu, out, st);
+		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
+				evsel->metric_name, NULL, avg, cpu, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
 		char unit = 'M';
 		char unit_buf[10];
@@ -975,9 +1041,9 @@
 			unit = 'K';
 		}
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
-		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(cpu, evsel, out, st);
+		print_smi_cost(config, cpu, evsel, out, st);
 	} else {
 		num = 0;
 	}
@@ -987,12 +1053,12 @@
 
 		list_for_each_entry (mexp, &me->head, nd) {
 			if (num++ > 0)
-				out->new_line(ctxp);
-			generic_metric(mexp->metric_expr, mexp->metric_events,
+				out->new_line(config, ctxp);
+			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					evsel->name, mexp->metric_name,
-					avg, cpu, out, st);
+					mexp->metric_unit, avg, cpu, out, st);
 		}
 	}
 	if (num == 0)
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		print_metric(config, ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index a0061e0..ebdd130 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -2,10 +2,18 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <math.h>
+#include <string.h>
+#include "counts.h"
+#include "cpumap.h"
+#include "debug.h"
+#include "header.h"
 #include "stat.h"
+#include "session.h"
+#include "target.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
+#include <linux/zalloc.h>
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -67,7 +75,7 @@
 	return pct;
 }
 
-bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+bool __perf_evsel_stat__is(struct evsel *evsel,
 			   enum perf_stat_evsel_id id)
 {
 	struct perf_stat_evsel *ps = evsel->stats;
@@ -92,7 +100,7 @@
 };
 #undef ID
 
-static void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+static void perf_stat_evsel_id_init(struct evsel *evsel)
 {
 	struct perf_stat_evsel *ps = evsel->stats;
 	int i;
@@ -107,7 +115,7 @@
 	}
 }
 
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct evsel *evsel)
 {
 	int i;
 	struct perf_stat_evsel *ps = evsel->stats;
@@ -118,7 +126,7 @@
 	perf_stat_evsel_id_init(evsel);
 }
 
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct evsel *evsel)
 {
 	evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->stats == NULL)
@@ -127,16 +135,16 @@
 	return 0;
 }
 
-static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct evsel *evsel)
 {
 	struct perf_stat_evsel *ps = evsel->stats;
 
 	if (ps)
-		free(ps->group_data);
+		zfree(&ps->group_data);
 	zfree(&evsel->stats);
 }
 
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+static int perf_evsel__alloc_prev_raw_counts(struct evsel *evsel,
 					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
@@ -148,16 +156,25 @@
 	return counts ? 0 : -ENOMEM;
 }
 
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct evsel *evsel)
 {
 	perf_counts__delete(evsel->prev_raw_counts);
 	evsel->prev_raw_counts = NULL;
 }
 
-static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static void perf_evsel__reset_prev_raw_counts(struct evsel *evsel)
+{
+	if (evsel->prev_raw_counts) {
+		evsel->prev_raw_counts->aggr.val = 0;
+		evsel->prev_raw_counts->aggr.ena = 0;
+		evsel->prev_raw_counts->aggr.run = 0;
+       }
+}
+
+static int perf_evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
-	int nthreads = thread_map__nr(evsel->threads);
+	int nthreads = perf_thread_map__nr(evsel->core.threads);
 
 	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
 	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
@@ -167,9 +184,9 @@
 	return 0;
 }
 
-int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		if (perf_evsel__alloc_stats(evsel, alloc_raw))
@@ -183,9 +200,9 @@
 	return -1;
 }
 
-void perf_evlist__free_stats(struct perf_evlist *evlist)
+void perf_evlist__free_stats(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__free_stat_priv(evsel);
@@ -194,9 +211,9 @@
 	}
 }
 
-void perf_evlist__reset_stats(struct perf_evlist *evlist)
+void perf_evlist__reset_stats(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		perf_evsel__reset_stat_priv(evsel);
@@ -204,17 +221,25 @@
 	}
 }
 
-static void zero_per_pkg(struct perf_evsel *counter)
+void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
 {
-	if (counter->per_pkg_mask)
-		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		perf_evsel__reset_prev_raw_counts(evsel);
 }
 
-static int check_per_pkg(struct perf_evsel *counter,
+static void zero_per_pkg(struct evsel *counter)
+{
+	if (counter->per_pkg_mask)
+		memset(counter->per_pkg_mask, 0, cpu__max_cpu());
+}
+
+static int check_per_pkg(struct evsel *counter,
 			 struct perf_counts_values *vals, int cpu, bool *skip)
 {
 	unsigned long *mask = counter->per_pkg_mask;
-	struct cpu_map *cpus = perf_evsel__cpus(counter);
+	struct perf_cpu_map *cpus = evsel__cpus(counter);
 	int s;
 
 	*skip = false;
@@ -222,11 +247,11 @@
 	if (!counter->per_pkg)
 		return 0;
 
-	if (cpu_map__empty(cpus))
+	if (perf_cpu_map__empty(cpus))
 		return 0;
 
 	if (!mask) {
-		mask = zalloc(MAX_NR_CPUS);
+		mask = zalloc(cpu__max_cpu());
 		if (!mask)
 			return -ENOMEM;
 
@@ -253,7 +278,7 @@
 }
 
 static int
-process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel,
+process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 		       int cpu, int thread,
 		       struct perf_counts_values *count)
 {
@@ -272,14 +297,17 @@
 	switch (config->aggr_mode) {
 	case AGGR_THREAD:
 	case AGGR_CORE:
+	case AGGR_DIE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
 			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, config->scale, NULL);
-		if (config->aggr_mode == AGGR_NONE)
-			perf_stat__update_shadow_stats(evsel, count->val, cpu,
-						       &rt_stat);
+		if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
+			perf_stat__update_shadow_stats(evsel, count->val,
+						       cpu, &rt_stat);
+		}
+
 		if (config->aggr_mode == AGGR_THREAD) {
 			if (config->stats)
 				perf_stat__update_shadow_stats(evsel,
@@ -291,10 +319,8 @@
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
-		if (config->scale) {
-			aggr->ena += count->ena;
-			aggr->run += count->run;
-		}
+		aggr->ena += count->ena;
+		aggr->run += count->run;
 	case AGGR_UNSET:
 	default:
 		break;
@@ -304,13 +330,13 @@
 }
 
 static int process_counter_maps(struct perf_stat_config *config,
-				struct perf_evsel *counter)
+				struct evsel *counter)
 {
-	int nthreads = thread_map__nr(counter->threads);
+	int nthreads = perf_thread_map__nr(counter->core.threads);
 	int ncpus = perf_evsel__nr_cpus(counter);
 	int cpu, thread;
 
-	if (counter->system_wide)
+	if (counter->core.system_wide)
 		nthreads = 1;
 
 	for (thread = 0; thread < nthreads; thread++) {
@@ -325,7 +351,7 @@
 }
 
 int perf_stat_process_counter(struct perf_stat_config *config,
-			      struct perf_evsel *counter)
+			      struct evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat_evsel *ps = counter->stats;
@@ -374,13 +400,12 @@
 	return 0;
 }
 
-int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event,
-				   struct perf_session *session)
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event)
 {
 	struct perf_counts_values count;
-	struct stat_event *st = &event->stat;
-	struct perf_evsel *counter;
+	struct perf_record_stat *st = &event->stat;
+	struct evsel *counter;
 
 	count.val = st->val;
 	count.ena = st->ena;
@@ -399,12 +424,12 @@
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
 {
-	struct stat_event *st = (struct stat_event *) event;
+	struct perf_record_stat *st = (struct perf_record_stat *)event;
 	size_t ret;
 
-	ret  = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
+	ret  = fprintf(fp, "\n... id %" PRI_lu64 ", cpu %d, thread %d\n",
 		       st->id, st->cpu, st->thread);
-	ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
+	ret += fprintf(fp, "... value %" PRI_lu64 ", enabled %" PRI_lu64 ", running %" PRI_lu64 "\n",
 		       st->val, st->ena, st->run);
 
 	return ret;
@@ -412,10 +437,10 @@
 
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
 {
-	struct stat_round_event *rd = (struct stat_round_event *)event;
+	struct perf_record_stat_round *rd = (struct perf_record_stat_round *)event;
 	size_t ret;
 
-	ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
+	ret = fprintf(fp, "\n... time %" PRI_lu64 ", type %s\n", rd->time,
 		      rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
 
 	return ret;
@@ -435,3 +460,54 @@
 
 	return ret;
 }
+
+int create_perf_stat_counter(struct evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target)
+{
+	struct perf_event_attr *attr = &evsel->core.attr;
+	struct evsel *leader = evsel->leader;
+
+	attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+			    PERF_FORMAT_TOTAL_TIME_RUNNING;
+
+	/*
+	 * The event is part of non trivial group, let's enable
+	 * the group read (for leader) and ID retrieval for all
+	 * members.
+	 */
+	if (leader->core.nr_members > 1)
+		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
+
+	attr->inherit = !config->no_inherit;
+
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+
+	if (config->identifier)
+		attr->sample_type = PERF_SAMPLE_IDENTIFIER;
+
+	/*
+	 * Disabling all counters initially, they will be enabled
+	 * either manually by us or by kernel via enable_on_exec
+	 * set later.
+	 */
+	if (perf_evsel__is_group_leader(evsel)) {
+		attr->disabled = 1;
+
+		/*
+		 * In case of initial_delay we enable tracee
+		 * events manually.
+		 */
+		if (target__none(target) && !config->initial_delay)
+			attr->enable_on_exec = 1;
+	}
+
+	if (target__has_cpu(target) && !target__has_per_thread(target))
+		return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel));
+
+	return perf_evsel__open_per_thread(evsel, evsel->core.threads);
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 36efb98..edbeb2f 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -4,9 +4,14 @@
 
 #include <linux/types.h>
 #include <stdio.h>
-#include "xyarray.h"
+#include <sys/types.h>
+#include <sys/resource.h>
 #include "rblist.h"
 
+struct perf_cpu_map;
+struct perf_stat_config;
+struct timespec;
+
 struct stats {
 	double n, mean, M2;
 	u64 max, min;
@@ -38,6 +43,7 @@
 	AGGR_NONE,
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
+	AGGR_DIE,
 	AGGR_CORE,
 	AGGR_THREAD,
 	AGGR_UNSET,
@@ -84,15 +90,42 @@
 	struct rblist value_list;
 };
 
+typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+			     struct perf_cpu_map *m, int cpu);
+
 struct perf_stat_config {
-	enum aggr_mode	aggr_mode;
-	bool		scale;
-	FILE		*output;
-	unsigned int	interval;
-	unsigned int	timeout;
-	int		times;
-	struct runtime_stat *stats;
-	int		stats_num;
+	enum aggr_mode		 aggr_mode;
+	bool			 scale;
+	bool			 no_inherit;
+	bool			 identifier;
+	bool			 csv_output;
+	bool			 interval_clear;
+	bool			 metric_only;
+	bool			 null_run;
+	bool			 ru_display;
+	bool			 big_num;
+	bool			 no_merge;
+	bool			 walltime_run_table;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 initial_delay;
+	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
+	int			 times;
+	int			 run_count;
+	int			 print_free_counters_hint;
+	int			 print_mixed_hw_group_error;
+	struct runtime_stat	*stats;
+	int			 stats_num;
+	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
+	struct perf_cpu_map		*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct perf_cpu_map		*cpus_aggr_map;
+	u64			*walltime_run;
+	struct rblist		 metric_events;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -109,11 +142,11 @@
 	stats->max  = 0;
 }
 
-struct perf_evsel;
-struct perf_evlist;
+struct evsel;
+struct evlist;
 
 struct perf_aggr_thread_value {
-	struct perf_evsel *counter;
+	struct evsel *counter;
 	int id;
 	double uval;
 	u64 val;
@@ -121,7 +154,7 @@
 	u64 ena;
 };
 
-bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+bool __perf_evsel_stat__is(struct evsel *evsel,
 			   enum perf_stat_evsel_id id);
 
 #define perf_stat_evsel__is(evsel, id) \
@@ -130,16 +163,17 @@
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
-typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx, const char *color, const char *unit,
 			       const char *fmt, double val);
-typedef void (*new_line_t )(void *ctx);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
 
 void runtime_stat__init(struct runtime_stat *st);
 void runtime_stat__exit(struct runtime_stat *st);
 void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
+void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 				    int cpu, struct runtime_stat *st);
 struct perf_stat_output_ctx {
 	void *ctx;
@@ -148,27 +182,40 @@
 	bool force_header;
 };
 
-void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
 				   struct runtime_stat *st);
-void perf_stat__collect_metric_expr(struct perf_evlist *);
+void perf_stat__collect_metric_expr(struct evlist *);
 
-int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
-void perf_evlist__free_stats(struct perf_evlist *evlist);
-void perf_evlist__reset_stats(struct perf_evlist *evlist);
+int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
+void perf_evlist__free_stats(struct evlist *evlist);
+void perf_evlist__reset_stats(struct evlist *evlist);
+void perf_evlist__reset_prev_raw_counts(struct evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
-			      struct perf_evsel *counter);
+			      struct evsel *counter);
 struct perf_tool;
 union perf_event;
 struct perf_session;
-int perf_event__process_stat_event(struct perf_tool *tool,
-				   union perf_event *event,
-				   struct perf_session *session);
+struct target;
+
+int perf_event__process_stat_event(struct perf_session *session,
+				   union perf_event *event);
 
 size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+int create_perf_stat_counter(struct evsel *evsel,
+			     struct perf_stat_config *config,
+			     struct target *target);
+void
+perf_evlist__print_counters(struct evlist *evlist,
+			    struct perf_stat_config *config,
+			    struct target *_target,
+			    struct timespec *ts,
+			    int argc, const char **argv);
 #endif
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 9005fbe..a64a376 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,8 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "cache.h"
 #include "debug.h"
-#include "util.h"
+#include "strbuf.h"
 #include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
 
 /*
  * Used as the default ->buf value, so that people can always assume
@@ -109,7 +115,6 @@
 			return ret;
 		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
 			va_end(ap_saved);
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 7f3253d..78aa4c3 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -1,10 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
 #include "string2.h"
 #include "strfilter.h"
 
 #include <errno.h>
-#include "sane_ctype.h"
+#include <stdlib.h>
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 
 /* Operators */
 static const char *OP_and	= "&";	/* Logical AND */
@@ -37,8 +39,7 @@
 {
 	const char *p;
 
-	while (isspace(*s))	/* Skip spaces */
-		s++;
+	s = skip_spaces(s);
 
 	if (*s == '\0') {
 		p = s;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d8bfd0c..5260387 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -4,7 +4,16 @@
 #include <linux/string.h>
 #include <stdlib.h>
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+
+const char *graph_dotted_line =
+	"---------------------------------------------------------------------"
+	"---------------------------------------------------------------------"
+	"---------------------------------------------------------------------";
+const char *dots =
+	"....................................................................."
+	"....................................................................."
+	".....................................................................";
 
 #define K 1024LL
 /*
@@ -60,109 +69,6 @@
 	return -1;
 }
 
-/*
- * Helper function for splitting a string into an argv-like array.
- * originally copied from lib/argv_split.c
- */
-static const char *skip_sep(const char *cp)
-{
-	while (*cp && isspace(*cp))
-		cp++;
-
-	return cp;
-}
-
-static const char *skip_arg(const char *cp)
-{
-	while (*cp && !isspace(*cp))
-		cp++;
-
-	return cp;
-}
-
-static int count_argc(const char *str)
-{
-	int count = 0;
-
-	while (*str) {
-		str = skip_sep(str);
-		if (*str) {
-			count++;
-			str = skip_arg(str);
-		}
-	}
-
-	return count;
-}
-
-/**
- * argv_free - free an argv
- * @argv - the argument vector to be freed
- *
- * Frees an argv and the strings it points to.
- */
-void argv_free(char **argv)
-{
-	char **p;
-	for (p = argv; *p; p++) {
-		free(*p);
-		*p = NULL;
-	}
-
-	free(argv);
-}
-
-/**
- * argv_split - split a string at whitespace, returning an argv
- * @str: the string to be split
- * @argcp: returned argument count
- *
- * Returns an array of pointers to strings which are split out from
- * @str.  This is performed by strictly splitting on white-space; no
- * quote processing is performed.  Multiple whitespace characters are
- * considered to be a single argument separator.  The returned array
- * is always NULL-terminated.  Returns NULL on memory allocation
- * failure.
- */
-char **argv_split(const char *str, int *argcp)
-{
-	int argc = count_argc(str);
-	char **argv = calloc(argc + 1, sizeof(*argv));
-	char **argvp;
-
-	if (argv == NULL)
-		goto out;
-
-	if (argcp)
-		*argcp = argc;
-
-	argvp = argv;
-
-	while (*str) {
-		str = skip_sep(str);
-
-		if (*str) {
-			const char *p = str;
-			char *t;
-
-			str = skip_arg(str);
-
-			t = strndup(p, str-p);
-			if (t == NULL)
-				goto fail;
-			*argvp++ = t;
-		}
-	}
-	*argvp = NULL;
-
-out:
-	return argv;
-
-fail:
-	argv_free(argv);
-	return NULL;
-}
-
 /* Character class matching */
 static bool __match_charclass(const char *pat, char c, const char **npat)
 {
@@ -303,61 +209,6 @@
 	return 0;
 }
 
-/**
- * strxfrchar - Locate and replace character in @s
- * @s:    The string to be searched/changed.
- * @from: Source character to be replaced.
- * @to:   Destination character.
- *
- * Return pointer to the changed string.
- */
-char *strxfrchar(char *s, char from, char to)
-{
-	char *p = s;
-
-	while ((p = strchr(p, from)) != NULL)
-		*p++ = to;
-
-	return s;
-}
-
-/**
- * ltrim - Removes leading whitespace from @s.
- * @s: The string to be stripped.
- *
- * Return pointer to the first non-whitespace character in @s.
- */
-char *ltrim(char *s)
-{
-	while (isspace(*s))
-		s++;
-
-	return s;
-}
-
-/**
- * rtrim - Removes trailing whitespace from @s.
- * @s: The string to be stripped.
- *
- * Note that the first trailing whitespace is replaced with a %NUL-terminator
- * in the given string @s. Returns @s.
- */
-char *rtrim(char *s)
-{
-	size_t size = strlen(s);
-	char *end;
-
-	if (!size)
-		return s;
-
-	end = s + size - 1;
-	while (end >= s && isspace(*end))
-		end--;
-	*(end + 1) = '\0';
-
-	return s;
-}
-
 char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
 {
 	/*
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 4c68a09..708805f 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -2,13 +2,15 @@
 #ifndef PERF_STRING_H
 #define PERF_STRING_H
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <stddef.h>
 #include <string.h>
 
+extern const char *graph_dotted_line;
+extern const char *dots;
+
 s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strglobmatch_nocase(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
@@ -17,15 +19,6 @@
 	return strpbrk(str, "*?[") != NULL;
 }
 int strtailcmp(const char *s1, const char *s2);
-char *strxfrchar(char *s, char from, char to);
-
-char *ltrim(char *s);
-char *rtrim(char *s);
-
-static inline char *trim(char *s)
-{
-	return ltrim(rtrim(s));
-}
 
 char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
 
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 9de5434..8a868cb 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -1,16 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * (c) 2009 Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Licensed under the GPLv2.
  */
 
 #include "strlist.h"
-#include "util.h"
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/zalloc.h>
 
 static
 struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index d58f1e0..7e82c71 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -57,7 +57,7 @@
 /* For strlist iteration */
 static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&slist->rblist.entries);
+	struct rb_node *rn = rb_first_cached(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 1cbada2..96f941e 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * svghelper.c - helper functions for outputting svg
  *
@@ -5,11 +6,6 @@
  *
  * Authors:
  *     Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 
 #include <inttypes.h>
@@ -18,12 +14,14 @@
 #include <unistd.h>
 #include <string.h>
 #include <linux/bitmap.h>
+#include <linux/string.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
 
-#include "perf.h"
+#include "env.h"
 #include "svghelper.h"
-#include "util.h"
-#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
@@ -334,7 +332,7 @@
 	if (file) {
 		while (fgets(buf, 255, file)) {
 			if (strstr(buf, "model name")) {
-				strncpy(cpu_m, &buf[13], 255);
+				strlcpy(cpu_m, &buf[13], 255);
 				break;
 			}
 		}
@@ -698,7 +696,8 @@
 	int sib_thr_nr;
 };
 
-static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+static void scan_thread_topology(int *map, struct topology *t, int cpu,
+				 int *pos, int nr_cpus)
 {
 	int i;
 	int thr;
@@ -707,41 +706,37 @@
 		if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
 			continue;
 
-		for_each_set_bit(thr,
-				 cpumask_bits(&t->sib_thr[i]),
-				 MAX_NR_CPUS)
+		for_each_set_bit(thr, cpumask_bits(&t->sib_thr[i]), nr_cpus)
 			if (map[thr] == -1)
 				map[thr] = (*pos)++;
 	}
 }
 
-static void scan_core_topology(int *map, struct topology *t)
+static void scan_core_topology(int *map, struct topology *t, int nr_cpus)
 {
 	int pos = 0;
 	int i;
 	int cpu;
 
 	for (i = 0; i < t->sib_core_nr; i++)
-		for_each_set_bit(cpu,
-				 cpumask_bits(&t->sib_core[i]),
-				 MAX_NR_CPUS)
-			scan_thread_topology(map, t, cpu, &pos);
+		for_each_set_bit(cpu, cpumask_bits(&t->sib_core[i]), nr_cpus)
+			scan_thread_topology(map, t, cpu, &pos, nr_cpus);
 }
 
-static int str_to_bitmap(char *s, cpumask_t *b)
+static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 {
 	int i;
 	int ret = 0;
-	struct cpu_map *m;
+	struct perf_cpu_map *m;
 	int c;
 
-	m = cpu_map__new(s);
+	m = perf_cpu_map__new(s);
 	if (!m)
 		return -1;
 
 	for (i = 0; i < m->nr; i++) {
 		c = m->map[i];
-		if (c >= MAX_NR_CPUS) {
+		if (c >= nr_cpus) {
 			ret = -1;
 			break;
 		}
@@ -749,29 +744,34 @@
 		set_bit(c, cpumask_bits(b));
 	}
 
-	cpu_map__put(m);
+	perf_cpu_map__put(m);
 
 	return ret;
 }
 
-int svg_build_topology_map(char *sib_core, int sib_core_nr,
-			   char *sib_thr, int sib_thr_nr)
+int svg_build_topology_map(struct perf_env *env)
 {
-	int i;
+	int i, nr_cpus;
 	struct topology t;
+	char *sib_core, *sib_thr;
 
-	t.sib_core_nr = sib_core_nr;
-	t.sib_thr_nr = sib_thr_nr;
-	t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
-	t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+	nr_cpus = min(env->nr_cpus_online, MAX_NR_CPUS);
+
+	t.sib_core_nr = env->nr_sibling_cores;
+	t.sib_thr_nr = env->nr_sibling_threads;
+	t.sib_core = calloc(env->nr_sibling_cores, sizeof(cpumask_t));
+	t.sib_thr = calloc(env->nr_sibling_threads, sizeof(cpumask_t));
+
+	sib_core = env->sibling_cores;
+	sib_thr = env->sibling_threads;
 
 	if (!t.sib_core || !t.sib_thr) {
 		fprintf(stderr, "topology: no memory\n");
 		goto exit;
 	}
 
-	for (i = 0; i < sib_core_nr; i++) {
-		if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+	for (i = 0; i < env->nr_sibling_cores; i++) {
+		if (str_to_bitmap(sib_core, &t.sib_core[i], nr_cpus)) {
 			fprintf(stderr, "topology: can't parse siblings map\n");
 			goto exit;
 		}
@@ -779,8 +779,8 @@
 		sib_core += strlen(sib_core) + 1;
 	}
 
-	for (i = 0; i < sib_thr_nr; i++) {
-		if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+	for (i = 0; i < env->nr_sibling_threads; i++) {
+		if (str_to_bitmap(sib_thr, &t.sib_thr[i], nr_cpus)) {
 			fprintf(stderr, "topology: can't parse siblings map\n");
 			goto exit;
 		}
@@ -788,16 +788,16 @@
 		sib_thr += strlen(sib_thr) + 1;
 	}
 
-	topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+	topology_map = malloc(sizeof(int) * nr_cpus);
 	if (!topology_map) {
 		fprintf(stderr, "topology: no memory\n");
 		goto exit;
 	}
 
-	for (i = 0; i < MAX_NR_CPUS; i++)
+	for (i = 0; i < nr_cpus; i++)
 		topology_map[i] = -1;
 
-	scan_core_topology(topology_map, &t);
+	scan_core_topology(topology_map, &t, nr_cpus);
 
 	return 0;
 
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e55338d..81823e8 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -4,6 +4,8 @@
 
 #include <linux/types.h>
 
+struct perf_env;
+
 void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
 void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
@@ -28,7 +30,7 @@
 void svg_interrupt(u64 start, int row, const char *backtrace);
 void svg_text(int Yslot, u64 start, const char *text);
 void svg_close(void);
-int svg_build_topology_map(char *sib_core, int sib_core_nr, char *sib_thr, int sib_thr_nr);
+int svg_build_topology_map(struct perf_env *env);
 
 extern int svg_page_width;
 extern u64 svg_highlight;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6e70cc0..66f4be1 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -2,25 +2,54 @@
 #include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
+#include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <inttypes.h>
 
+#include "dso.h"
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
+#include "symsrc.h"
 #include "demangle-java.h"
 #include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
 #include "debug.h"
-#include "sane_ctype.h"
+#include "util/copyfile.h"
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <symbol/kallsyms.h>
+#include <internal/lib.h>
 
 #ifndef EM_AARCH64
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)	((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val)	ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
+#ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS     0              /* For readability... */
+#define DMGL_PARAMS      (1 << 0)       /* Include function args */
+#define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
+#endif
+
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
 
@@ -87,6 +116,11 @@
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+	return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +145,9 @@
 	return elf_sym__type(sym) == STT_NOTYPE &&
 		sym->st_name != 0 &&
 		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
+		sym->st_shndx != SHN_ABS &&
+		elf_sym__visibility(sym) != STV_HIDDEN &&
+		elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)
@@ -676,7 +712,6 @@
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		 enum dso_binary_type type)
 {
-	int err = -1;
 	GElf_Ehdr ehdr;
 	Elf *elf;
 	int fd;
@@ -770,7 +805,7 @@
 	elf_end(elf);
 out_close:
 	close(fd);
-	return err;
+	return -1;
 }
 
 /**
@@ -1453,7 +1488,7 @@
 	struct phdr_data *p, *tmp;
 
 	list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
-		list_del(&p->node);
+		list_del_init(&p->node);
 		free(p);
 	}
 }
@@ -1476,7 +1511,7 @@
 	struct sym_data *s, *tmp;
 
 	list_for_each_entry_safe(s, tmp, &kci->syms, node) {
-		list_del(&s->node);
+		list_del_init(&s->node);
 		free(s);
 	}
 }
@@ -1957,6 +1992,34 @@
 }
 
 #ifdef HAVE_GELF_GETNOTE_SUPPORT
+
+static void sdt_adjust_loc(struct sdt_note *tmp, GElf_Addr base_off)
+{
+	if (!base_off)
+		return;
+
+	if (tmp->bit32)
+		tmp->addr.a32[SDT_NOTE_IDX_LOC] =
+			tmp->addr.a32[SDT_NOTE_IDX_LOC] + base_off -
+			tmp->addr.a32[SDT_NOTE_IDX_BASE];
+	else
+		tmp->addr.a64[SDT_NOTE_IDX_LOC] =
+			tmp->addr.a64[SDT_NOTE_IDX_LOC] + base_off -
+			tmp->addr.a64[SDT_NOTE_IDX_BASE];
+}
+
+static void sdt_adjust_refctr(struct sdt_note *tmp, GElf_Addr base_addr,
+			      GElf_Addr base_off)
+{
+	if (!base_off)
+		return;
+
+	if (tmp->bit32 && tmp->addr.a32[SDT_NOTE_IDX_REFCTR])
+		tmp->addr.a32[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off);
+	else if (tmp->addr.a64[SDT_NOTE_IDX_REFCTR])
+		tmp->addr.a64[SDT_NOTE_IDX_REFCTR] -= (base_addr - base_off);
+}
+
 /**
  * populate_sdt_note : Parse raw data and identify SDT note
  * @elf: elf of the opened file
@@ -1974,7 +2037,6 @@
 	const char *provider, *name, *args;
 	struct sdt_note *tmp = NULL;
 	GElf_Ehdr ehdr;
-	GElf_Addr base_off = 0;
 	GElf_Shdr shdr;
 	int ret = -EINVAL;
 
@@ -2070,27 +2132,22 @@
 	 * base address in the description of the SDT note. If its different,
 	 * then accordingly, adjust the note location.
 	 */
-	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
-		base_off = shdr.sh_offset;
-		if (base_off) {
-			if (tmp->bit32)
-				tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
-					tmp->addr.a32[1];
-			else
-				tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
-					tmp->addr.a64[1];
-		}
-	}
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL))
+		sdt_adjust_loc(tmp, shdr.sh_offset);
+
+	/* Adjust reference counter offset */
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_PROBES_SCN, NULL))
+		sdt_adjust_refctr(tmp, shdr.sh_addr, shdr.sh_offset);
 
 	list_add_tail(&tmp->note_list, sdt_notes);
 	return 0;
 
 out_free_args:
-	free(tmp->args);
+	zfree(&tmp->args);
 out_free_name:
-	free(tmp->name);
+	zfree(&tmp->name);
 out_free_prov:
-	free(tmp->provider);
+	zfree(&tmp->provider);
 out_free_note:
 	free(tmp);
 out_err:
@@ -2205,9 +2262,9 @@
 	int nr_free = 0;
 
 	list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
-		list_del(&pos->note_list);
-		free(pos->name);
-		free(pos->provider);
+		list_del_init(&pos->note_list);
+		zfree(&pos->name);
+		zfree(&pos->provider);
 		free(pos);
 		nr_free++;
 	}
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 7119df7..d6e99af 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,14 +1,17 @@
-// SPDX-License-Identifier: GPL-2.0
+#include "dso.h"
 #include "symbol.h"
-#include "util.h"
+#include "symsrc.h"
 
 #include <errno.h>
+#include <unistd.h>
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
+#include <stdlib.h>
 #include <byteswap.h>
 #include <sys/stat.h>
-
+#include <linux/zalloc.h>
+#include <internal/lib.h>
 
 static bool check_need_swap(int file_endian)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index d188b75..a8f80e4 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -4,8 +4,11 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/mman.h>
+#include <linux/string.h>
+#include <linux/time64.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -14,16 +17,24 @@
 #include <inttypes.h>
 #include "annotate.h"
 #include "build-id.h"
-#include "util.h"
+#include "cap.h"
+#include "dso.h"
+#include "util.h" // lsdir()
 #include "debug.h"
+#include "event.h"
 #include "machine.h"
+#include "map.h"
 #include "symbol.h"
+#include "map_symbol.h"
+#include "mem-events.h"
+#include "symsrc.h"
 #include "strlist.h"
 #include "intlist.h"
 #include "namespaces.h"
 #include "header.h"
 #include "path.h"
-#include "sane_ctype.h"
+#include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 #include <elf.h>
 #include <limits.h>
@@ -38,15 +49,18 @@
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
+	.nanosecs		= false,
 	.use_modules		= true,
 	.try_vmlinux_path	= true,
 	.demangle		= true,
 	.demangle_kernel	= false,
 	.cumulate_callchain	= true,
+	.time_quantum		= 100 * NSEC_PER_MSEC, /* 100ms */
 	.show_hist_headers	= true,
 	.symfs			= "",
 	.event_group		= true,
 	.inline_name		= true,
+	.res_sample		= 0,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -86,6 +100,11 @@
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -163,7 +182,7 @@
 	return arch__choose_best_symbol(syma, symb);
 }
 
-void symbols__fixup_duplicate(struct rb_root *symbols)
+void symbols__fixup_duplicate(struct rb_root_cached *symbols)
 {
 	struct rb_node *nd;
 	struct symbol *curr, *next;
@@ -171,7 +190,7 @@
 	if (symbol_conf.allow_aliases)
 		return;
 
-	nd = rb_first(symbols);
+	nd = rb_first_cached(symbols);
 
 	while (nd) {
 		curr = rb_entry(nd, struct symbol, rb_node);
@@ -186,20 +205,20 @@
 			continue;
 
 		if (choose_best_symbol(curr, next) == SYMBOL_A) {
-			rb_erase(&next->rb_node, symbols);
+			rb_erase_cached(&next->rb_node, symbols);
 			symbol__delete(next);
 			goto again;
 		} else {
 			nd = rb_next(&curr->rb_node);
-			rb_erase(&curr->rb_node, symbols);
+			rb_erase_cached(&curr->rb_node, symbols);
 			symbol__delete(curr);
 		}
 	}
 }
 
-void symbols__fixup_end(struct rb_root *symbols)
+void symbols__fixup_end(struct rb_root_cached *symbols)
 {
-	struct rb_node *nd, *prevnd = rb_first(symbols);
+	struct rb_node *nd, *prevnd = rb_first_cached(symbols);
 	struct symbol *curr, *prev;
 
 	if (prevnd == NULL)
@@ -212,7 +231,7 @@
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
@@ -282,25 +301,27 @@
 	free(((void *)sym) - symbol_conf.priv_size);
 }
 
-void symbols__delete(struct rb_root *symbols)
+void symbols__delete(struct rb_root_cached *symbols)
 {
 	struct symbol *pos;
-	struct rb_node *next = rb_first(symbols);
+	struct rb_node *next = rb_first_cached(symbols);
 
 	while (next) {
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, symbols);
+		rb_erase_cached(&pos->rb_node, symbols);
 		symbol__delete(pos);
 	}
 }
 
-void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
+void __symbols__insert(struct rb_root_cached *symbols,
+		       struct symbol *sym, bool kernel)
 {
-	struct rb_node **p = &symbols->rb_node;
+	struct rb_node **p = &symbols->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = sym->start;
 	struct symbol *s;
+	bool leftmost = true;
 
 	if (kernel) {
 		const char *name = sym->name;
@@ -318,26 +339,28 @@
 		s = rb_entry(parent, struct symbol, rb_node);
 		if (ip < s->start)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&sym->rb_node, parent, p);
-	rb_insert_color(&sym->rb_node, symbols);
+	rb_insert_color_cached(&sym->rb_node, symbols, leftmost);
 }
 
-void symbols__insert(struct rb_root *symbols, struct symbol *sym)
+void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym)
 {
 	__symbols__insert(symbols, sym, false);
 }
 
-static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
+static struct symbol *symbols__find(struct rb_root_cached *symbols, u64 ip)
 {
 	struct rb_node *n;
 
 	if (symbols == NULL)
 		return NULL;
 
-	n = symbols->rb_node;
+	n = symbols->rb_root.rb_node;
 
 	while (n) {
 		struct symbol *s = rb_entry(n, struct symbol, rb_node);
@@ -353,9 +376,9 @@
 	return NULL;
 }
 
-static struct symbol *symbols__first(struct rb_root *symbols)
+static struct symbol *symbols__first(struct rb_root_cached *symbols)
 {
-	struct rb_node *n = rb_first(symbols);
+	struct rb_node *n = rb_first_cached(symbols);
 
 	if (n)
 		return rb_entry(n, struct symbol, rb_node);
@@ -363,9 +386,9 @@
 	return NULL;
 }
 
-static struct symbol *symbols__last(struct rb_root *symbols)
+static struct symbol *symbols__last(struct rb_root_cached *symbols)
 {
-	struct rb_node *n = rb_last(symbols);
+	struct rb_node *n = rb_last(&symbols->rb_root);
 
 	if (n)
 		return rb_entry(n, struct symbol, rb_node);
@@ -383,11 +406,12 @@
 	return NULL;
 }
 
-static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root_cached *symbols, struct symbol *sym)
 {
-	struct rb_node **p = &symbols->rb_node;
+	struct rb_node **p = &symbols->rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct symbol_name_rb_node *symn, *s;
+	bool leftmost = true;
 
 	symn = container_of(sym, struct symbol_name_rb_node, sym);
 
@@ -396,19 +420,21 @@
 		s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
 		if (strcmp(sym->name, s->sym.name) < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color(&symn->rb_node, symbols);
+	rb_insert_color_cached(&symn->rb_node, symbols, leftmost);
 }
 
-static void symbols__sort_by_name(struct rb_root *symbols,
-				  struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root_cached *symbols,
+				  struct rb_root_cached *source)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(source); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		symbols__insert_by_name(symbols, pos);
 	}
@@ -431,7 +457,7 @@
 		return arch__compare_symbol_names(name, str);
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+static struct symbol *symbols__find_by_name(struct rb_root_cached *symbols,
 					    const char *name,
 					    enum symbol_tag_include includes)
 {
@@ -441,7 +467,7 @@
 	if (symbols == NULL)
 		return NULL;
 
-	n = symbols->rb_node;
+	n = symbols->rb_root.rb_node;
 
 	while (n) {
 		int cmp;
@@ -614,6 +640,7 @@
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
 		"intel_idle",
@@ -643,7 +670,7 @@
 {
 	struct symbol *sym;
 	struct dso *dso = arg;
-	struct rb_root *root = &dso->symbols;
+	struct rb_root_cached *root = &dso->symbols;
 
 	if (!symbol_type__filter(type))
 		return 0;
@@ -680,14 +707,14 @@
 	struct map *curr_map;
 	struct symbol *pos;
 	int count = 0;
-	struct rb_root old_root = dso->symbols;
-	struct rb_root *root = &dso->symbols;
-	struct rb_node *next = rb_first(root);
+	struct rb_root_cached old_root = dso->symbols;
+	struct rb_root_cached *root = &dso->symbols;
+	struct rb_node *next = rb_first_cached(root);
 
 	if (!kmaps)
 		return -1;
 
-	*root = RB_ROOT;
+	*root = RB_ROOT_CACHED;
 
 	while (next) {
 		char *module;
@@ -695,8 +722,8 @@
 		pos = rb_entry(next, struct symbol, rb_node);
 		next = rb_next(&pos->rb_node);
 
-		rb_erase_init(&pos->rb_node, &old_root);
-
+		rb_erase_cached(&pos->rb_node, &old_root);
+		RB_CLEAR_NODE(&pos->rb_node);
 		module = strchr(pos->name, '\t');
 		if (module)
 			*module = '\0';
@@ -709,6 +736,8 @@
 		}
 
 		pos->start -= curr_map->start - curr_map->pgoff;
+		if (pos->end > curr_map->end)
+			pos->end = curr_map->end;
 		if (pos->end)
 			pos->end -= curr_map->start - curr_map->pgoff;
 		symbols__insert(&curr_map->dso->symbols, pos);
@@ -733,8 +762,8 @@
 	struct map *curr_map = initial_map;
 	struct symbol *pos;
 	int count = 0, moved = 0;
-	struct rb_root *root = &dso->symbols;
-	struct rb_node *next = rb_first(root);
+	struct rb_root_cached *root = &dso->symbols;
+	struct rb_node *next = rb_first_cached(root);
 	int kernel_range = 0;
 	bool x86_64;
 
@@ -848,7 +877,7 @@
 		}
 add_symbol:
 		if (curr_map != initial_map) {
-			rb_erase(&pos->rb_node, root);
+			rb_erase_cached(&pos->rb_node, root);
 			symbols__insert(&curr_map->dso->symbols, pos);
 			++moved;
 		} else
@@ -856,7 +885,7 @@
 
 		continue;
 discard_symbol:
-		rb_erase(&pos->rb_node, root);
+		rb_erase_cached(&pos->rb_node, root);
 		symbol__delete(pos);
 	}
 
@@ -1151,6 +1180,85 @@
 	return 0;
 }
 
+/*
+ * Merges map into map_groups by splitting the new map
+ * within the existing map regions.
+ */
+int map_groups__merge_in(struct map_groups *kmaps, struct map *new_map)
+{
+	struct map *old_map;
+	LIST_HEAD(merged);
+
+	for (old_map = map_groups__first(kmaps); old_map;
+	     old_map = map_groups__next(old_map)) {
+
+		/* no overload with this one */
+		if (new_map->end < old_map->start ||
+		    new_map->start >= old_map->end)
+			continue;
+
+		if (new_map->start < old_map->start) {
+			/*
+			 * |new......
+			 *       |old....
+			 */
+			if (new_map->end < old_map->end) {
+				/*
+				 * |new......|     -> |new..|
+				 *       |old....| ->       |old....|
+				 */
+				new_map->end = old_map->start;
+			} else {
+				/*
+				 * |new.............| -> |new..|       |new..|
+				 *       |old....|    ->       |old....|
+				 */
+				struct map *m = map__clone(new_map);
+
+				if (!m)
+					return -ENOMEM;
+
+				m->end = old_map->start;
+				list_add_tail(&m->node, &merged);
+				new_map->start = old_map->end;
+			}
+		} else {
+			/*
+			 *      |new......
+			 * |old....
+			 */
+			if (new_map->end < old_map->end) {
+				/*
+				 *      |new..|   -> x
+				 * |old.........| -> |old.........|
+				 */
+				map__put(new_map);
+				new_map = NULL;
+				break;
+			} else {
+				/*
+				 *      |new......| ->         |new...|
+				 * |old....|        -> |old....|
+				 */
+				new_map->start = old_map->end;
+			}
+		}
+	}
+
+	while (!list_empty(&merged)) {
+		old_map = list_entry(merged.next, struct map, node);
+		list_del_init(&old_map->node);
+		map_groups__insert(kmaps, old_map);
+		map__put(old_map);
+	}
+
+	if (new_map) {
+		map_groups__insert(kmaps, new_map);
+		map__put(new_map);
+	}
+	return 0;
+}
+
 static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
@@ -1207,7 +1315,12 @@
 	while (old_map) {
 		struct map *next = map_groups__next(old_map);
 
-		if (old_map != map)
+		/*
+		 * We need to preserve eBPF maps even if they are
+		 * covered by kcore, because we need to access
+		 * eBPF dso for source data.
+		 */
+		if (old_map != map && !__map__is_bpf_prog(old_map))
 			map_groups__remove(kmaps, old_map);
 		old_map = next;
 	}
@@ -1241,11 +1354,16 @@
 			map_groups__remove(kmaps, map);
 			map_groups__insert(kmaps, map);
 			map__put(map);
+			map__put(new_map);
 		} else {
-			map_groups__insert(kmaps, new_map);
+			/*
+			 * Merge kcore map into existing maps,
+			 * and ensure that current maps (eBPF)
+			 * stay intact.
+			 */
+			if (map_groups__merge_in(kmaps, new_map))
+				goto out_err;
 		}
-
-		map__put(new_map);
 	}
 
 	if (machine__is(machine, "x86_64")) {
@@ -1440,6 +1558,7 @@
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
 		return true;
 
+	case DSO_BINARY_TYPE__BPF_PROG_INFO:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 	default:
 		return false;
@@ -1537,17 +1656,6 @@
 	dso->adjust_symbols = 0;
 
 	if (perfmap) {
-		struct stat st;
-
-		if (lstat(map_path, &st) < 0)
-			goto out;
-
-		if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
-			pr_warning("File %s not owned by current user or root, "
-				   "ignoring it (use -f to override).\n", map_path);
-			goto out;
-		}
-
 		ret = dso__load_perf_map(map_path, dso);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
@@ -1680,11 +1788,22 @@
 {
 	struct maps *maps = &mg->maps;
 	struct map *map;
+	struct rb_node *node;
 
 	down_read(&maps->lock);
 
-	for (map = maps__first(maps); map; map = map__next(map)) {
-		if (map->dso && strcmp(map->dso->short_name, name) == 0)
+	for (node = maps->names.rb_node; node; ) {
+		int rc;
+
+		map = rb_entry(node, struct map, rb_node_name);
+
+		rc = strcmp(map->dso->short_name, name);
+		if (rc < 0)
+			node = node->rb_left;
+		else if (rc > 0)
+			node = node->rb_right;
+		else
+
 			goto out_unlock;
 	}
 
@@ -2084,13 +2203,19 @@
 		char line[8];
 
 		if (fgets(line, sizeof(line), fp) != NULL)
-			value = ((geteuid() != 0) || (getuid() != 0)) ?
-					(atoi(line) != 0) :
-					(atoi(line) == 2);
+			value = perf_cap__capable(CAP_SYSLOG) ?
+					(atoi(line) >= 2) :
+					(atoi(line) != 0);
 
 		fclose(fp);
 	}
 
+	/* Per kernel/kallsyms.c:
+	 * we also restrict when perf_event_paranoid > 1 w/o CAP_SYSLOG
+	 */
+	if (perf_event_paranoid() > 1 && !perf_cap__capable(CAP_SYSLOG))
+		value = true;
+
 	return value;
 }
 
@@ -2246,3 +2371,25 @@
 		refcount_set(&mi->refcnt, 1);
 	return mi;
 }
+
+struct block_info *block_info__get(struct block_info *bi)
+{
+	if (bi)
+		refcount_inc(&bi->refcnt);
+	return bi;
+}
+
+void block_info__put(struct block_info *bi)
+{
+	if (bi && refcount_dec_and_test(&bi->refcnt))
+		free(bi);
+}
+
+struct block_info *block_info__new(void)
+{
+	struct block_info *bi = zalloc(sizeof(*bi));
+
+	if (bi)
+		refcount_set(&bi->refcnt, 1);
+	return bi;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f25fae4..0b0c6b5 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -3,18 +3,14 @@
 #define __PERF_SYMBOL 1
 
 #include <linux/types.h>
+#include <linux/refcount.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include "map.h"
-#include "../perf.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdio.h>
-#include <byteswap.h>
-#include <libgen.h>
-#include "build-id.h"
-#include "event.h"
 #include "path.h"
+#include "symbol_conf.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -22,7 +18,10 @@
 #endif
 #include <elf.h>
 
-#include "dso.h"
+struct dso;
+struct map;
+struct map_groups;
+struct option;
 
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
@@ -39,15 +38,6 @@
 			     GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
-#ifndef DMGL_PARAMS
-#define DMGL_NO_OPTS     0              /* For readability... */
-#define DMGL_PARAMS      (1 << 0)       /* Include function args */
-#define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
-#endif
-
-#define DSO__NAME_KALLSYMS	"[kernel.kallsyms]"
-#define DSO__NAME_KCORE		"[kernel.kcore]"
-
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)
@@ -63,11 +53,12 @@
 	u8		ignore:1;
 	u8		inlined:1;
 	u8		arch_sym;
+	bool		annotate2;
 	char		name[0];
 };
 
 void symbol__delete(struct symbol *sym);
-void symbols__delete(struct rb_root *symbols);
+void symbols__delete(struct rb_root_cached *symbols);
 
 /* symbols__for_each_entry - iterate over symbols (rb_root)
  *
@@ -76,7 +67,7 @@
  * @nd: the 'struct rb_node *' to use as a temporary storage
  */
 #define symbols__for_each_entry(symbols, pos, nd)			\
-	for (nd = rb_first(symbols);					\
+	for (nd = rb_first_cached(symbols);					\
 	     nd && (pos = rb_entry(nd, struct symbol, rb_node));	\
 	     nd = rb_next(nd))
 
@@ -88,68 +79,6 @@
 struct strlist;
 struct intlist;
 
-struct symbol_conf {
-	unsigned short	priv_size;
-	bool		try_vmlinux_path,
-			init_annotation,
-			force,
-			ignore_vmlinux,
-			ignore_vmlinux_buildid,
-			show_kernel_path,
-			use_modules,
-			allow_aliases,
-			sort_by_name,
-			show_nr_samples,
-			show_total_period,
-			use_callchain,
-			cumulate_callchain,
-			show_branchflag_count,
-			exclude_other,
-			show_cpu_utilization,
-			initialized,
-			kptr_restrict,
-			event_group,
-			demangle,
-			demangle_kernel,
-			filter_relative,
-			show_hist_headers,
-			branch_callstack,
-			has_filter,
-			show_ref_callgraph,
-			hide_unresolved,
-			raw_trace,
-			report_hierarchy,
-			inline_name;
-	const char	*vmlinux_name,
-			*kallsyms_name,
-			*source_prefix,
-			*field_sep;
-	const char	*default_guest_vmlinux_name,
-			*default_guest_kallsyms,
-			*default_guest_modules;
-	const char	*guestmount;
-	const char	*dso_list_str,
-			*comm_list_str,
-			*pid_list_str,
-			*tid_list_str,
-			*sym_list_str,
-			*col_width_list_str,
-			*bt_stop_list_str;
-       struct strlist	*dso_list,
-			*comm_list,
-			*sym_list,
-			*dso_from_list,
-			*dso_to_list,
-			*sym_from_list,
-			*sym_to_list,
-			*bt_stop_list;
-	struct intlist	*pid_list,
-			*tid_list;
-	const char	*symfs;
-};
-
-extern struct symbol_conf symbol_conf;
-
 struct symbol_name_rb_node {
 	struct rb_node	rb_node;
 	struct symbol	sym;
@@ -176,31 +105,14 @@
 	u64		unrelocated_addr;
 };
 
-struct map_symbol {
-	struct map    *map;
-	struct symbol *sym;
-};
-
-struct addr_map_symbol {
-	struct map    *map;
-	struct symbol *sym;
-	u64	      addr;
-	u64	      al_addr;
-	u64	      phys_addr;
-};
-
-struct branch_info {
-	struct addr_map_symbol from;
-	struct addr_map_symbol to;
-	struct branch_flags flags;
-	char			*srcline_from;
-	char			*srcline_to;
-};
-
-struct mem_info {
-	struct addr_map_symbol	iaddr;
-	struct addr_map_symbol	daddr;
-	union perf_mem_data_src	data_src;
+struct block_info {
+	struct symbol		*sym;
+	u64			start;
+	u64			end;
+	u64			cycles;
+	u64			cycles_aggr;
+	int			num;
+	int			num_aggr;
 	refcount_t		refcnt;
 };
 
@@ -218,37 +130,6 @@
 	s32	      socket;
 };
 
-struct symsrc {
-	char *name;
-	int fd;
-	enum dso_binary_type type;
-
-#ifdef HAVE_LIBELF_SUPPORT
-	Elf *elf;
-	GElf_Ehdr ehdr;
-
-	Elf_Scn *opdsec;
-	size_t opdidx;
-	GElf_Shdr opdshdr;
-
-	Elf_Scn *symtab;
-	GElf_Shdr symshdr;
-
-	Elf_Scn *dynsym;
-	size_t dynsym_idx;
-	GElf_Shdr dynshdr;
-
-	bool adjust_symbols;
-	bool is_64_bit;
-#endif
-};
-
-void symsrc__destroy(struct symsrc *ss);
-int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
-		 enum dso_binary_type type);
-bool symsrc__has_symtab(struct symsrc *ss);
-bool symsrc__possibly_runtime(struct symsrc *ss);
-
 int dso__load(struct dso *dso, struct map *map);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated);
@@ -302,16 +183,19 @@
 int symbol__config_symfs(const struct option *opt __maybe_unused,
 			 const char *dir, int unset __maybe_unused);
 
+struct symsrc;
+
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule);
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
 
 char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
-void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
-void symbols__insert(struct rb_root *symbols, struct symbol *sym);
-void symbols__fixup_duplicate(struct rb_root *symbols);
-void symbols__fixup_end(struct rb_root *symbols);
+void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
+		       bool kernel);
+void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
+void symbols__fixup_duplicate(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols);
 void map_groups__fixup_end(struct map_groups *mg);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
@@ -349,6 +233,7 @@
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
@@ -379,12 +264,19 @@
 int cleanup_sdt_note_list(struct list_head *sdt_notes);
 int sdt_notes__get_count(struct list_head *start);
 
+#define SDT_PROBES_SCN ".probes"
 #define SDT_BASE_SCN ".stapsdt.base"
 #define SDT_NOTE_SCN  ".note.stapsdt"
 #define SDT_NOTE_TYPE 3
 #define SDT_NOTE_NAME "stapsdt"
 #define NR_ADDR 3
 
+enum {
+	SDT_NOTE_IDX_LOC = 0,
+	SDT_NOTE_IDX_BASE,
+	SDT_NOTE_IDX_REFCTR,
+};
+
 struct mem_info *mem_info__new(void);
 struct mem_info *mem_info__get(struct mem_info *mi);
 void   mem_info__put(struct mem_info *mi);
@@ -397,4 +289,16 @@
 
 #define mem_info__zput(mi) __mem_info__zput(&mi)
 
+struct block_info *block_info__new(void);
+struct block_info *block_info__get(struct block_info *bi);
+void   block_info__put(struct block_info *bi);
+
+static inline void __block_info__zput(struct block_info **bi)
+{
+	block_info__put(*bi);
+	*bi = NULL;
+}
+
+#define block_info__zput(bi) __block_info__zput(&bi)
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
new file mode 100644
index 0000000..e688078
--- /dev/null
+++ b/tools/perf/util/symbol_conf.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYMBOL_CONF
+#define __PERF_SYMBOL_CONF 1
+
+#include <stdbool.h>
+
+struct strlist;
+struct intlist;
+
+struct symbol_conf {
+	bool		nanosecs;
+	unsigned short	priv_size;
+	bool		try_vmlinux_path,
+			init_annotation,
+			force,
+			ignore_vmlinux,
+			ignore_vmlinux_buildid,
+			show_kernel_path,
+			use_modules,
+			allow_aliases,
+			sort_by_name,
+			show_nr_samples,
+			show_total_period,
+			use_callchain,
+			cumulate_callchain,
+			show_branchflag_count,
+			exclude_other,
+			show_cpu_utilization,
+			initialized,
+			kptr_restrict,
+			event_group,
+			demangle,
+			demangle_kernel,
+			filter_relative,
+			show_hist_headers,
+			branch_callstack,
+			has_filter,
+			show_ref_callgraph,
+			hide_unresolved,
+			raw_trace,
+			report_hierarchy,
+			report_block,
+			inline_name,
+			disable_add2line_warn;
+	const char	*vmlinux_name,
+			*kallsyms_name,
+			*source_prefix,
+			*field_sep,
+			*graph_function;
+	const char	*default_guest_vmlinux_name,
+			*default_guest_kallsyms,
+			*default_guest_modules;
+	const char	*guestmount;
+	const char	*dso_list_str,
+			*comm_list_str,
+			*pid_list_str,
+			*tid_list_str,
+			*sym_list_str,
+			*col_width_list_str,
+			*bt_stop_list_str;
+	unsigned long	time_quantum;
+       struct strlist	*dso_list,
+			*comm_list,
+			*sym_list,
+			*dso_from_list,
+			*dso_to_list,
+			*sym_from_list,
+			*sym_to_list,
+			*bt_stop_list;
+	struct intlist	*pid_list,
+			*tid_list;
+	const char	*symfs;
+	int		res_sample;
+	int		pad_output_len_dso;
+};
+
+extern struct symbol_conf symbol_conf;
+
+#endif // __PERF_SYMBOL_CONF
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index ed0205c..35c936c 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -3,6 +3,8 @@
 #include <inttypes.h>
 #include <stdio.h>
 
+#include "dso.h"
+#include "map.h"
 #include "symbol.h"
 
 size_t symbol__fprintf(struct symbol *sym, FILE *fp)
@@ -64,7 +66,7 @@
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) {
+	for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}
diff --git a/tools/perf/util/symsrc.h b/tools/perf/util/symsrc.h
new file mode 100644
index 0000000..2665b4b
--- /dev/null
+++ b/tools/perf/util/symsrc.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYMSRC_
+#define __PERF_SYMSRC_ 1
+
+#include <stdbool.h>
+#include <stddef.h>
+#include "dso.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+#include <libelf.h>
+#include <gelf.h>
+#endif
+#include <elf.h>
+
+struct symsrc {
+	char		     *name;
+	int		     fd;
+	enum dso_binary_type type;
+
+#ifdef HAVE_LIBELF_SUPPORT
+	Elf		     *elf;
+	GElf_Ehdr	     ehdr;
+
+	Elf_Scn		     *opdsec;
+	size_t		     opdidx;
+	GElf_Shdr	     opdshdr;
+
+	Elf_Scn		     *symtab;
+	GElf_Shdr	     symshdr;
+
+	Elf_Scn		     *dynsym;
+	size_t		     dynsym_idx;
+	GElf_Shdr	     dynshdr;
+
+	bool		     adjust_symbols;
+	bool		     is_64_bit;
+#endif
+};
+
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, enum dso_binary_type type);
+void symsrc__destroy(struct symsrc *ss);
+
+bool symsrc__has_symtab(struct symsrc *ss);
+bool symsrc__possibly_runtime(struct symsrc *ss);
+
+#endif /* __PERF_SYMSRC_ */
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
new file mode 100644
index 0000000..807cbca
--- /dev/null
+++ b/tools/perf/util/synthetic-events.c
@@ -0,0 +1,1884 @@
+// SPDX-License-Identifier: GPL-2.0-only 
+
+#include "util/debug.h"
+#include "util/dso.h"
+#include "util/event.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/map.h"
+#include "util/map_symbol.h"
+#include "util/branch.h"
+#include "util/memswap.h"
+#include "util/namespaces.h"
+#include "util/session.h"
+#include "util/stat.h"
+#include "util/symbol.h"
+#include "util/synthetic-events.h"
+#include "util/target.h"
+#include "util/time-utils.h"
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <linux/perf_event.h>
+#include <asm/bug.h>
+#include <perf/evsel.h>
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
+#include <internal/lib.h> // page_size
+#include <internal/threadmap.h>
+#include <perf/threadmap.h>
+#include <symbol/kallsyms.h>
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <string.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <api/fs/fs.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+#define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
+
+unsigned int proc_map_timeout = DEFAULT_PROC_MAP_PARSE_TIMEOUT;
+
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
+		.pid	   = -1,
+		.tid	   = -1,
+		.time	   = -1,
+		.stream_id = -1,
+		.cpu	   = -1,
+		.period	   = 1,
+		.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
+};
+
+/*
+ * Assumes that the first 4095 bytes of /proc/pid/stat contains
+ * the comm, tgid and ppid.
+ */
+static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
+				    pid_t *tgid, pid_t *ppid)
+{
+	char filename[PATH_MAX];
+	char bf[4096];
+	int fd;
+	size_t size = 0;
+	ssize_t n;
+	char *name, *tgids, *ppids;
+
+	*tgid = -1;
+	*ppid = -1;
+
+	snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0) {
+		pr_debug("couldn't open %s\n", filename);
+		return -1;
+	}
+
+	n = read(fd, bf, sizeof(bf) - 1);
+	close(fd);
+	if (n <= 0) {
+		pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
+			   pid);
+		return -1;
+	}
+	bf[n] = '\0';
+
+	name = strstr(bf, "Name:");
+	tgids = strstr(bf, "Tgid:");
+	ppids = strstr(bf, "PPid:");
+
+	if (name) {
+		char *nl;
+
+		name = skip_spaces(name + 5);  /* strlen("Name:") */
+		nl = strchr(name, '\n');
+		if (nl)
+			*nl = '\0';
+
+		size = strlen(name);
+		if (size >= len)
+			size = len - 1;
+		memcpy(comm, name, size);
+		comm[size] = '\0';
+	} else {
+		pr_debug("Name: string not found for pid %d\n", pid);
+	}
+
+	if (tgids) {
+		tgids += 5;  /* strlen("Tgid:") */
+		*tgid = atoi(tgids);
+	} else {
+		pr_debug("Tgid: string not found for pid %d\n", pid);
+	}
+
+	if (ppids) {
+		ppids += 5;  /* strlen("PPid:") */
+		*ppid = atoi(ppids);
+	} else {
+		pr_debug("PPid: string not found for pid %d\n", pid);
+	}
+
+	return 0;
+}
+
+static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
+				    struct machine *machine,
+				    pid_t *tgid, pid_t *ppid)
+{
+	size_t size;
+
+	*ppid = -1;
+
+	memset(&event->comm, 0, sizeof(event->comm));
+
+	if (machine__is_host(machine)) {
+		if (perf_event__get_comm_ids(pid, event->comm.comm,
+					     sizeof(event->comm.comm),
+					     tgid, ppid) != 0) {
+			return -1;
+		}
+	} else {
+		*tgid = machine->pid;
+	}
+
+	if (*tgid < 0)
+		return -1;
+
+	event->comm.pid = *tgid;
+	event->comm.header.type = PERF_RECORD_COMM;
+
+	size = strlen(event->comm.comm) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	memset(event->comm.comm + size, 0, machine->id_hdr_size);
+	event->comm.header.size = (sizeof(event->comm) -
+				(sizeof(event->comm.comm) - size) +
+				machine->id_hdr_size);
+	event->comm.tid = pid;
+
+	return 0;
+}
+
+pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+					 union perf_event *event, pid_t pid,
+					 perf_event__handler_t process,
+					 struct machine *machine)
+{
+	pid_t tgid, ppid;
+
+	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
+		return -1;
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return tgid;
+}
+
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+					 struct perf_ns_link_info *ns_link_info)
+{
+	struct stat64 st;
+	char proc_ns[128];
+
+	sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+	if (stat64(proc_ns, &st) == 0) {
+		ns_link_info->dev = st.st_dev;
+		ns_link_info->ino = st.st_ino;
+	}
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+				      union perf_event *event,
+				      pid_t pid, pid_t tgid,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	u32 idx;
+	struct perf_ns_link_info *ns_link_info;
+
+	if (!tool || !tool->namespace_events)
+		return 0;
+
+	memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+	       (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+	       machine->id_hdr_size));
+
+	event->namespaces.pid = tgid;
+	event->namespaces.tid = pid;
+
+	event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+	ns_link_info = event->namespaces.link_info;
+
+	for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+		perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+					     &ns_link_info[idx]);
+
+	event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+	event->namespaces.header.size = (sizeof(event->namespaces) +
+			(NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+			machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
+static int perf_event__synthesize_fork(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid, pid_t ppid,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
+
+	/*
+	 * for main thread set parent to ppid from status file. For other
+	 * threads set parent pid to main thread. ie., assume main thread
+	 * spawns all threads in a process
+	*/
+	if (tgid == pid) {
+		event->fork.ppid = ppid;
+		event->fork.ptid = ppid;
+	} else {
+		event->fork.ppid = tgid;
+		event->fork.ptid = tgid;
+	}
+	event->fork.pid  = tgid;
+	event->fork.tid  = pid;
+	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
+
+	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+		return -1;
+
+	return 0;
+}
+
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data)
+{
+	char filename[PATH_MAX];
+	FILE *fp;
+	unsigned long long t;
+	bool truncation = false;
+	unsigned long long timeout = proc_map_timeout * 1000000ULL;
+	int rc = 0;
+	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
+	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
+		 machine->root_dir, pid, pid);
+
+	fp = fopen(filename, "r");
+	if (fp == NULL) {
+		/*
+		 * We raced with a task exiting - just return:
+		 */
+		pr_debug("couldn't open %s\n", filename);
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
+
+	while (1) {
+		char bf[BUFSIZ];
+		char prot[5];
+		char execname[PATH_MAX];
+		char anonstr[] = "//anon";
+		unsigned int ino;
+		size_t size;
+		ssize_t n;
+
+		if (fgets(bf, sizeof(bf), fp) == NULL)
+			break;
+
+		if ((rdclock() - t) > timeout) {
+			pr_warning("Reading %s time out. "
+				   "You may want to increase "
+				   "the time limit by --proc-map-timeout\n",
+				   filename);
+			truncation = true;
+			goto out;
+		}
+
+		/* ensure null termination since stack will be reused. */
+		strcpy(execname, "");
+
+		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
+		n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
+		/*
+ 		 * Anon maps don't have the execname.
+ 		 */
+		if (n < 7)
+			continue;
+
+		event->mmap2.ino = (u64)ino;
+
+		/*
+		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_USER;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
+
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
+		if (prot[2] != 'x') {
+			if (!mmap_data || prot[0] != 'r')
+				continue;
+
+			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+		}
+
+out:
+		if (truncation)
+			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
+		if (!strcmp(execname, ""))
+			strcpy(execname, anonstr);
+
+		if (hugetlbfs_mnt_len &&
+		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
+			strcpy(execname, anonstr);
+			event->mmap2.flags |= MAP_HUGETLB;
+		}
+
+		size = strlen(execname) + 1;
+		memcpy(event->mmap2.filename, execname, size);
+		size = PERF_ALIGN(size, sizeof(u64));
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
+
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
+			rc = -1;
+			break;
+		}
+
+		if (truncation)
+			break;
+	}
+
+	fclose(fp);
+	return rc;
+}
+
+int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
+				   struct machine *machine)
+{
+	int rc = 0;
+	struct map *pos;
+	struct maps *maps = machine__kernel_maps(machine);
+	union perf_event *event = zalloc((sizeof(event->mmap) +
+					  machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	event->header.type = PERF_RECORD_MMAP;
+
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		size_t size;
+
+		if (!__map__is_kmodule(pos))
+			continue;
+
+		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+				        (sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+		event->mmap.header.size += machine->id_hdr_size;
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pid   = machine->pid;
+
+		memcpy(event->mmap.filename, pos->dso->long_name,
+		       pos->dso->long_name_len + 1);
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
+			rc = -1;
+			break;
+		}
+	}
+
+	free(event);
+	return rc;
+}
+
+static int __event__synthesize_thread(union perf_event *comm_event,
+				      union perf_event *mmap_event,
+				      union perf_event *fork_event,
+				      union perf_event *namespaces_event,
+				      pid_t pid, int full, perf_event__handler_t process,
+				      struct perf_tool *tool, struct machine *machine, bool mmap_data)
+{
+	char filename[PATH_MAX];
+	DIR *tasks;
+	struct dirent *dirent;
+	pid_t tgid, ppid;
+	int rc = 0;
+
+	/* special case: only send one comm event using passed in pid */
+	if (!full) {
+		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
+						   process, machine);
+
+		if (tgid == -1)
+			return -1;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+						      tgid, process, machine) < 0)
+			return -1;
+
+		/*
+		 * send mmap only for thread group leader
+		 * see thread__init_map_groups
+		 */
+		if (pid == tgid &&
+		    perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						       process, machine, mmap_data))
+			return -1;
+
+		return 0;
+	}
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
+
+	tasks = opendir(filename);
+	if (tasks == NULL) {
+		pr_debug("couldn't open %s\n", filename);
+		return 0;
+	}
+
+	while ((dirent = readdir(tasks)) != NULL) {
+		char *end;
+		pid_t _pid;
+
+		_pid = strtol(dirent->d_name, &end, 10);
+		if (*end)
+			continue;
+
+		rc = -1;
+		if (perf_event__prepare_comm(comm_event, _pid, machine,
+					     &tgid, &ppid) != 0)
+			break;
+
+		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
+						ppid, process, machine) < 0)
+			break;
+
+		if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+						      tgid, process, machine) < 0)
+			break;
+
+		/*
+		 * Send the prepared comm event
+		 */
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
+			break;
+
+		rc = 0;
+		if (_pid == pid) {
+			/* process the parent's maps too */
+			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						process, machine, mmap_data);
+			if (rc)
+				break;
+		}
+	}
+
+	closedir(tasks);
+	return rc;
+}
+
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+				      struct perf_thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      bool mmap_data)
+{
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
+	int err = -1, thread, j;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
+	err = 0;
+	for (thread = 0; thread < threads->nr; ++thread) {
+		if (__event__synthesize_thread(comm_event, mmap_event,
+					       fork_event, namespaces_event,
+					       perf_thread_map__pid(threads, thread), 0,
+					       process, tool, machine,
+					       mmap_data)) {
+			err = -1;
+			break;
+		}
+
+		/*
+		 * comm.pid is set to thread group id by
+		 * perf_event__synthesize_comm
+		 */
+		if ((int) comm_event->comm.pid != perf_thread_map__pid(threads, thread)) {
+			bool need_leader = true;
+
+			/* is thread group leader in thread_map? */
+			for (j = 0; j < threads->nr; ++j) {
+				if ((int) comm_event->comm.pid == perf_thread_map__pid(threads, j)) {
+					need_leader = false;
+					break;
+				}
+			}
+
+			/* if not, generate events for it */
+			if (need_leader &&
+			    __event__synthesize_thread(comm_event, mmap_event,
+						       fork_event, namespaces_event,
+						       comm_event->comm.pid, 0,
+						       process, tool, machine,
+						       mmap_data)) {
+				err = -1;
+				break;
+			}
+		}
+	}
+	free(namespaces_event);
+out_free_fork:
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
+}
+
+static int __perf_event__synthesize_threads(struct perf_tool *tool,
+					    perf_event__handler_t process,
+					    struct machine *machine,
+					    bool mmap_data,
+					    struct dirent **dirent,
+					    int start,
+					    int num)
+{
+	union perf_event *comm_event, *mmap_event, *fork_event;
+	union perf_event *namespaces_event;
+	int err = -1;
+	char *end;
+	pid_t pid;
+	int i;
+
+	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
+	if (comm_event == NULL)
+		goto out;
+
+	mmap_event = malloc(sizeof(mmap_event->mmap2) + machine->id_hdr_size);
+	if (mmap_event == NULL)
+		goto out_free_comm;
+
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
+	namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+				  (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+				  machine->id_hdr_size);
+	if (namespaces_event == NULL)
+		goto out_free_fork;
+
+	for (i = start; i < start + num; i++) {
+		if (!isdigit(dirent[i]->d_name[0]))
+			continue;
+
+		pid = (pid_t)strtol(dirent[i]->d_name, &end, 10);
+		/* only interested in proper numerical dirents */
+		if (*end)
+			continue;
+		/*
+		 * We may race with exiting thread, so don't stop just because
+		 * one thread couldn't be synthesized.
+		 */
+		__event__synthesize_thread(comm_event, mmap_event, fork_event,
+					   namespaces_event, pid, 1, process,
+					   tool, machine, mmap_data);
+	}
+	err = 0;
+
+	free(namespaces_event);
+out_free_fork:
+	free(fork_event);
+out_free_mmap:
+	free(mmap_event);
+out_free_comm:
+	free(comm_event);
+out:
+	return err;
+}
+
+struct synthesize_threads_arg {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	bool mmap_data;
+	struct dirent **dirent;
+	int num;
+	int start;
+};
+
+static void *synthesize_threads_worker(void *arg)
+{
+	struct synthesize_threads_arg *args = arg;
+
+	__perf_event__synthesize_threads(args->tool, args->process,
+					 args->machine, args->mmap_data,
+					 args->dirent,
+					 args->start, args->num);
+	return NULL;
+}
+
+int perf_event__synthesize_threads(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int nr_threads_synthesize)
+{
+	struct synthesize_threads_arg *args = NULL;
+	pthread_t *synthesize_threads = NULL;
+	char proc_path[PATH_MAX];
+	struct dirent **dirent;
+	int num_per_thread;
+	int m, n, i, j;
+	int thread_nr;
+	int base = 0;
+	int err = -1;
+
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+	n = scandir(proc_path, &dirent, 0, alphasort);
+	if (n < 0)
+		return err;
+
+	if (nr_threads_synthesize == UINT_MAX)
+		thread_nr = sysconf(_SC_NPROCESSORS_ONLN);
+	else
+		thread_nr = nr_threads_synthesize;
+
+	if (thread_nr <= 1) {
+		err = __perf_event__synthesize_threads(tool, process,
+						       machine, mmap_data,
+						       dirent, base, n);
+		goto free_dirent;
+	}
+	if (thread_nr > n)
+		thread_nr = n;
+
+	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	if (synthesize_threads == NULL)
+		goto free_dirent;
+
+	args = calloc(sizeof(*args), thread_nr);
+	if (args == NULL)
+		goto free_threads;
+
+	num_per_thread = n / thread_nr;
+	m = n % thread_nr;
+	for (i = 0; i < thread_nr; i++) {
+		args[i].tool = tool;
+		args[i].process = process;
+		args[i].machine = machine;
+		args[i].mmap_data = mmap_data;
+		args[i].dirent = dirent;
+	}
+	for (i = 0; i < m; i++) {
+		args[i].num = num_per_thread + 1;
+		args[i].start = i * args[i].num;
+	}
+	if (i != 0)
+		base = args[i-1].start + args[i-1].num;
+	for (j = i; j < thread_nr; j++) {
+		args[j].num = num_per_thread;
+		args[j].start = base + (j - i) * args[i].num;
+	}
+
+	for (i = 0; i < thread_nr; i++) {
+		if (pthread_create(&synthesize_threads[i], NULL,
+				   synthesize_threads_worker, &args[i]))
+			goto out_join;
+	}
+	err = 0;
+out_join:
+	for (i = 0; i < thread_nr; i++)
+		pthread_join(synthesize_threads[i], NULL);
+	free(args);
+free_threads:
+	free(synthesize_threads);
+free_dirent:
+	for (i = 0; i < n; i++)
+		zfree(&dirent[i]);
+	free(dirent);
+
+	return err;
+}
+
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+					      perf_event__handler_t process __maybe_unused,
+					      struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+						perf_event__handler_t process,
+						struct machine *machine)
+{
+	size_t size;
+	struct map *map = machine__kernel_map(machine);
+	struct kmap *kmap;
+	int err;
+	union perf_event *event;
+
+	if (map == NULL)
+		return -1;
+
+	kmap = map__kmap(map);
+	if (!kmap->ref_reloc_sym)
+		return -1;
+
+	/*
+	 * We should get this from /sys/kernel/sections/.text, but till that is
+	 * available use this, and after it is use this as a fallback for older
+	 * kernels.
+	 */
+	event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
+	if (event == NULL) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for kernel modules\n");
+		return -1;
+	}
+
+	if (machine__is_host(machine)) {
+		/*
+		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
+		 * see kernel/perf_event.c __perf_event_mmap
+		 */
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	} else {
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+	}
+
+	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
+			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
+	size = PERF_ALIGN(size, sizeof(u64));
+	event->mmap.header.type = PERF_RECORD_MMAP;
+	event->mmap.header.size = (sizeof(event->mmap) -
+			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
+	event->mmap.start = map->start;
+	event->mmap.len   = map->end - event->mmap.start;
+	event->mmap.pid   = machine->pid;
+
+	err = perf_tool__process_synth_event(tool, event, machine, process);
+	free(event);
+
+	return err;
+}
+
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int err;
+
+	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+	if (err < 0)
+		return err;
+
+	return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct perf_thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	union perf_event *event;
+	int i, err, size;
+
+	size  = sizeof(event->thread_map);
+	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_THREAD_MAP;
+	event->header.size = size;
+	event->thread_map.nr = threads->nr;
+
+	for (i = 0; i < threads->nr; i++) {
+		struct perf_record_thread_map_entry *entry = &event->thread_map.entries[i];
+		char *comm = perf_thread_map__comm(threads, i);
+
+		if (!comm)
+			comm = (char *) "";
+
+		entry->pid = perf_thread_map__pid(threads, i);
+		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+	}
+
+	err = process(tool, event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+			    struct perf_cpu_map *map)
+{
+	int i;
+
+	cpus->nr = map->nr;
+
+	for (i = 0; i < map->nr; i++)
+		cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct perf_record_record_cpu_map *mask,
+			    struct perf_cpu_map *map, int max)
+{
+	int i;
+
+	mask->nr = BITS_TO_LONGS(max);
+	mask->long_size = sizeof(long);
+
+	for (i = 0; i < map->nr; i++)
+		set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct perf_cpu_map *map)
+{
+	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct perf_cpu_map *map, int *max)
+{
+	int i;
+
+	*max = 0;
+
+	for (i = 0; i < map->nr; i++) {
+		/* bit possition of the cpu is + 1 */
+		int bit = map->map[i] + 1;
+
+		if (bit > *max)
+			*max = bit;
+	}
+
+	return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max)
+{
+	size_t size_cpus, size_mask;
+	bool is_dummy = perf_cpu_map__empty(map);
+
+	/*
+	 * Both array and mask data have variable size based
+	 * on the number of cpus and their actual values.
+	 * The size of the 'struct perf_record_cpu_map_data' is:
+	 *
+	 *   array = size of 'struct cpu_map_entries' +
+	 *           number of cpus * sizeof(u64)
+	 *
+	 *   mask  = size of 'struct perf_record_record_cpu_map' +
+	 *           maximum cpu bit converted to size of longs
+	 *
+	 * and finaly + the size of 'struct perf_record_cpu_map_data'.
+	 */
+	size_cpus = cpus_size(map);
+	size_mask = mask_size(map, max);
+
+	if (is_dummy || (size_cpus < size_mask)) {
+		*size += size_cpus;
+		*type  = PERF_CPU_MAP__CPUS;
+	} else {
+		*size += size_mask;
+		*type  = PERF_CPU_MAP__MASK;
+	}
+
+	*size += sizeof(struct perf_record_cpu_map_data);
+	*size = PERF_ALIGN(*size, sizeof(u64));
+	return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map,
+			      u16 type, int max)
+{
+	data->type = type;
+
+	switch (type) {
+	case PERF_CPU_MAP__CPUS:
+		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		break;
+	case PERF_CPU_MAP__MASK:
+		synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max);
+	default:
+		break;
+	};
+}
+
+static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map)
+{
+	size_t size = sizeof(struct perf_record_cpu_map);
+	struct perf_record_cpu_map *event;
+	int max;
+	u16 type;
+
+	event = cpu_map_data__alloc(map, &size, &type, &max);
+	if (!event)
+		return NULL;
+
+	event->header.type = PERF_RECORD_CPU_MAP;
+	event->header.size = size;
+	event->data.type   = type;
+
+	cpu_map_data__synthesize(&event->data, map, type, max);
+	return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct perf_cpu_map *map,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	struct perf_record_cpu_map *event;
+	int err;
+
+	event = cpu_map_event__new(map);
+	if (!event)
+		return -ENOMEM;
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	struct perf_record_stat_config *event;
+	int size, i = 0, err;
+
+	size  = sizeof(*event);
+	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_STAT_CONFIG;
+	event->header.size = size;
+	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)					\
+	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
+	event->data[i].val = __val;				\
+	i++;
+
+	ADD(AGGR_MODE,	config->aggr_mode)
+	ADD(INTERVAL,	config->interval)
+	ADD(SCALE,	config->scale)
+
+	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+		  "stat config terms unbalanced\n");
+#undef ADD
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	struct perf_record_stat event;
+
+	event.header.type = PERF_RECORD_STAT;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.id        = id;
+	event.cpu       = cpu;
+	event.thread    = thread;
+	event.val       = count->val;
+	event.ena       = count->ena;
+	event.run       = count->run;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 evtime, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	struct perf_record_stat_round event;
+
+	event.header.type = PERF_RECORD_STAT_ROUND;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.time = evtime;
+	event.type = type;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format)
+{
+	size_t sz, result = sizeof(struct perf_record_sample);
+
+	if (type & PERF_SAMPLE_IDENTIFIER)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_IP)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TIME)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ADDR)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_STREAM_ID)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_CPU)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_PERIOD)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_READ) {
+		result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+			result += sizeof(u64);
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+			result += sizeof(u64);
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		result += sizeof(u32);
+		result += sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		result += sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		result += sizeof(u64);
+		if (sz) {
+			result += sz;
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_DATA_SRC)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_TRANSACTION)
+		result += sizeof(u64);
+
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
+	if (type & PERF_SAMPLE_PHYS_ADDR)
+		result += sizeof(u64);
+
+	return result;
+}
+
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
+				  const struct perf_sample *sample)
+{
+	__u64 *array;
+	size_t sz;
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union u64_swap u;
+
+	array = event->sample.array;
+
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_IP) {
+		*array = sample->ip;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val32[0] = sample->pid;
+		u.val32[1] = sample->tid;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		*array = sample->time;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ADDR) {
+		*array = sample->addr;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		*array = sample->stream_id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u.val32[0] = sample->cpu;
+		u.val32[1] = 0;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_PERIOD) {
+		*array = sample->period;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_READ) {
+		if (read_format & PERF_FORMAT_GROUP)
+			*array = sample->read.group.nr;
+		else
+			*array = sample->read.one.value;
+		array++;
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+			*array = sample->read.time_enabled;
+			array++;
+		}
+
+		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+			*array = sample->read.time_running;
+			array++;
+		}
+
+		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+		if (read_format & PERF_FORMAT_GROUP) {
+			sz = sample->read.group.nr *
+			     sizeof(struct sample_read_value);
+			memcpy(array, sample->read.group.values, sz);
+			array = (void *)array + sz;
+		} else {
+			*array = sample->read.one.id;
+			array++;
+		}
+	}
+
+	if (type & PERF_SAMPLE_CALLCHAIN) {
+		sz = (sample->callchain->nr + 1) * sizeof(u64);
+		memcpy(array, sample->callchain, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_RAW) {
+		u.val32[0] = sample->raw_size;
+		*array = u.val64;
+		array = (void *)array + sizeof(u32);
+
+		memcpy(array, sample->raw_data, sample->raw_size);
+		array = (void *)array + sample->raw_size;
+	}
+
+	if (type & PERF_SAMPLE_BRANCH_STACK) {
+		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+		sz += sizeof(u64);
+		memcpy(array, sample->branch_stack, sz);
+		array = (void *)array + sz;
+	}
+
+	if (type & PERF_SAMPLE_REGS_USER) {
+		if (sample->user_regs.abi) {
+			*array++ = sample->user_regs.abi;
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
+			memcpy(array, sample->user_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_STACK_USER) {
+		sz = sample->user_stack.size;
+		*array++ = sz;
+		if (sz) {
+			memcpy(array, sample->user_stack.data, sz);
+			array = (void *)array + sz;
+			*array++ = sz;
+		}
+	}
+
+	if (type & PERF_SAMPLE_WEIGHT) {
+		*array = sample->weight;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		*array = sample->data_src;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		*array = sample->transaction;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			*array++ = sample->intr_regs.abi;
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
+			memcpy(array, sample->intr_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
+	if (type & PERF_SAMPLE_PHYS_ADDR) {
+		*array = sample->phys_addr;
+		array++;
+	}
+
+	return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
+				    struct evlist *evlist, struct machine *machine)
+{
+	union perf_event *ev;
+	struct evsel *evsel;
+	size_t nr = 0, i = 0, sz, max_nr, n;
+	int err;
+
+	pr_debug2("Synthesizing id index\n");
+
+	max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) /
+		 sizeof(struct id_index_entry);
+
+	evlist__for_each_entry(evlist, evsel)
+		nr += evsel->core.ids;
+
+	n = nr > max_nr ? max_nr : nr;
+	sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry);
+	ev = zalloc(sz);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = n;
+
+	evlist__for_each_entry(evlist, evsel) {
+		u32 j;
+
+		for (j = 0; j < evsel->core.ids; j++) {
+			struct id_index_entry *e;
+			struct perf_sample_id *sid;
+
+			if (i >= n) {
+				err = process(tool, ev, NULL, machine);
+				if (err)
+					goto out_err;
+				nr -= n;
+				i = 0;
+			}
+
+			e = &ev->id_index.entries[i++];
+
+			e->id = evsel->core.id[j];
+
+			sid = perf_evlist__id2sid(evlist, e->id);
+			if (!sid) {
+				free(ev);
+				return -ENOENT;
+			}
+
+			e->idx = sid->idx;
+			e->cpu = sid->cpu;
+			e->tid = sid->tid;
+		}
+	}
+
+	sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry);
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = nr;
+
+	err = process(tool, ev, NULL, machine);
+out_err:
+	free(ev);
+
+	return err;
+}
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct perf_thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int nr_threads_synthesize)
+{
+	if (target__has_task(target))
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+	else if (target__has_cpu(target))
+		return perf_event__synthesize_threads(tool, process,
+						      machine, data_mmap,
+						      nr_threads_synthesize);
+	/* command specified */
+	return 0;
+}
+
+int machine__synthesize_threads(struct machine *machine, struct target *target,
+				struct perf_thread_map *threads, bool data_mmap,
+				unsigned int nr_threads_synthesize)
+{
+	return __machine__synthesize_threads(machine, NULL, target, threads,
+					     perf_event__process, data_mmap,
+					     nr_threads_synthesize);
+}
+
+static struct perf_record_event_update *event_update_event__new(size_t size, u64 type, u64 id)
+{
+	struct perf_record_event_update *ev;
+
+	size += sizeof(*ev);
+	size  = PERF_ALIGN(size, sizeof(u64));
+
+	ev = zalloc(size);
+	if (ev) {
+		ev->header.type = PERF_RECORD_EVENT_UPDATE;
+		ev->header.size = (u16)size;
+		ev->type	= type;
+		ev->id		= id;
+	}
+	return ev;
+}
+
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	size_t size = strlen(evsel->unit);
+	struct perf_record_event_update *ev;
+	int err;
+
+	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->core.id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strlcpy(ev->data, evsel->unit, size + 1);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel,
+					      perf_event__handler_t process)
+{
+	struct perf_record_event_update *ev;
+	struct perf_record_event_update_scale *ev_data;
+	int err;
+
+	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->core.id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev_data = (struct perf_record_event_update_scale *)ev->data;
+	ev_data->scale = evsel->scale;
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	struct perf_record_event_update *ev;
+	size_t len = strlen(evsel->name);
+	int err;
+
+	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->core.id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strlcpy(ev->data, evsel->name, len + 1);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel,
+					     perf_event__handler_t process)
+{
+	size_t size = sizeof(struct perf_record_event_update);
+	struct perf_record_event_update *ev;
+	int max, err;
+	u16 type;
+
+	if (!evsel->core.own_cpus)
+		return 0;
+
+	ev = cpu_map_data__alloc(evsel->core.own_cpus, &size, &type, &max);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->header.type = PERF_RECORD_EVENT_UPDATE;
+	ev->header.size = (u16)size;
+	ev->type	= PERF_EVENT_UPDATE__CPUS;
+	ev->id		= evsel->core.id[0];
+
+	cpu_map_data__synthesize((struct perf_record_cpu_map_data *)ev->data,
+				 evsel->core.own_cpus, type, max);
+
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist,
+				 perf_event__handler_t process)
+{
+	struct evsel *evsel;
+	int err = 0;
+
+	evlist__for_each_entry(evlist, evsel) {
+		err = perf_event__synthesize_attr(tool, &evsel->core.attr, evsel->core.ids,
+						  evsel->core.id, process);
+		if (err) {
+			pr_debug("failed to create perf header attribute\n");
+			return err;
+		}
+	}
+
+	return err;
+}
+
+static bool has_unit(struct evsel *evsel)
+{
+	return evsel->unit && *evsel->unit;
+}
+
+static bool has_scale(struct evsel *evsel)
+{
+	return evsel->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list,
+				      perf_event__handler_t process, bool is_pipe)
+{
+	struct evsel *evsel;
+	int err;
+
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each_entry(evsel_list, evsel) {
+		if (!evsel->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(evsel)) {
+			err = perf_event__synthesize_event_update_unit(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(evsel)) {
+			err = perf_event__synthesize_event_update_scale(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel evsel.\n");
+				return err;
+			}
+		}
+
+		if (evsel->core.own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel cpus.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(tool, evsel, process);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr,
+				u32 ids, u64 *id, perf_event__handler_t process)
+{
+	union perf_event *ev;
+	size_t size;
+	int err;
+
+	size = sizeof(struct perf_event_attr);
+	size = PERF_ALIGN(size, sizeof(u64));
+	size += sizeof(struct perf_event_header);
+	size += ids * sizeof(u64);
+
+	ev = zalloc(size);
+
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev->attr.attr = *attr;
+	memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+	ev->attr.header.size = (u16)size;
+
+	if (ev->attr.header.size == size)
+		err = process(tool, ev, NULL, NULL);
+	else
+		err = -E2BIG;
+
+	free(ev);
+
+	return err;
+}
+
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist,
+					perf_event__handler_t process)
+{
+	union perf_event ev;
+	struct tracing_data *tdata;
+	ssize_t size = 0, aligned_size = 0, padding;
+	struct feat_fd ff;
+
+	/*
+	 * We are going to store the size of the data followed
+	 * by the data contents. Since the fd descriptor is a pipe,
+	 * we cannot seek back to store the size of the data once
+	 * we know it. Instead we:
+	 *
+	 * - write the tracing data to the temp file
+	 * - get/write the data size to pipe
+	 * - write the tracing data from the temp file
+	 *   to the pipe
+	 */
+	tdata = tracing_data_get(&evlist->core.entries, fd, true);
+	if (!tdata)
+		return -1;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+	size = tdata->size;
+	aligned_size = PERF_ALIGN(size, sizeof(u64));
+	padding = aligned_size - size;
+	ev.tracing_data.header.size = sizeof(ev.tracing_data);
+	ev.tracing_data.size = aligned_size;
+
+	process(tool, &ev, NULL, NULL);
+
+	/*
+	 * The put function will copy all the tracing data
+	 * stored in temp file to the pipe.
+	 */
+	tracing_data_put(tdata);
+
+	ff = (struct feat_fd){ .fd = fd };
+	if (write_padded(&ff, NULL, 0, padding))
+		return -1;
+
+	return aligned_size;
+}
+
+int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc,
+				    perf_event__handler_t process, struct machine *machine)
+{
+	union perf_event ev;
+	size_t len;
+
+	if (!pos->hit)
+		return 0;
+
+	memset(&ev, 0, sizeof(ev));
+
+	len = pos->long_name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+	memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+	ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+	ev.build_id.header.misc = misc;
+	ev.build_id.pid = machine->pid;
+	ev.build_id.header.size = sizeof(ev.build_id) + len;
+	memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+	return process(tool, &ev, NULL, machine);
+}
+
+int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool,
+				       struct evlist *evlist, perf_event__handler_t process, bool attrs)
+{
+	int err;
+
+	if (attrs) {
+		err = perf_event__synthesize_attrs(tool, evlist, process);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
+	err = perf_event__synthesize_extra_attr(tool, evlist, process, attrs);
+	err = perf_event__synthesize_thread_map2(tool, evlist->core.threads, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(tool, evlist->core.cpus, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(tool, config, process, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
+
+int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
+				       struct perf_tool *tool __maybe_unused,
+				       perf_event__handler_t process __maybe_unused,
+				       struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE];
+
+int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session,
+				    struct evlist *evlist, perf_event__handler_t process)
+{
+	struct perf_header *header = &session->header;
+	struct perf_record_header_feature *fe;
+	struct feat_fd ff;
+	size_t sz, sz_hdr;
+	int feat, ret;
+
+	sz_hdr = sizeof(fe->header);
+	sz = sizeof(union perf_event);
+	/* get a nice alignment */
+	sz = PERF_ALIGN(sz, page_size);
+
+	memset(&ff, 0, sizeof(ff));
+
+	ff.buf = malloc(sz);
+	if (!ff.buf)
+		return -ENOMEM;
+
+	ff.size = sz - sz_hdr;
+	ff.ph = &session->header;
+
+	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+		if (!feat_ops[feat].synthesize) {
+			pr_debug("No record header feature for header :%d\n", feat);
+			continue;
+		}
+
+		ff.offset = sizeof(*fe);
+
+		ret = feat_ops[feat].write(&ff, evlist);
+		if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
+			pr_debug("Error writing feature\n");
+			continue;
+		}
+		/* ff.buf may have changed due to realloc in do_write() */
+		fe = ff.buf;
+		memset(fe, 0, sizeof(*fe));
+
+		fe->feat_id = feat;
+		fe->header.type = PERF_RECORD_HEADER_FEATURE;
+		fe->header.size = ff.offset;
+
+		ret = process(tool, ff.buf, NULL, NULL);
+		if (ret) {
+			free(ff.buf);
+			return ret;
+		}
+	}
+
+	/* Send HEADER_LAST_FEATURE mark. */
+	fe = ff.buf;
+	fe->feat_id     = HEADER_LAST_FEATURE;
+	fe->header.type = PERF_RECORD_HEADER_FEATURE;
+	fe->header.size = sizeof(*fe);
+
+	ret = process(tool, ff.buf, NULL, NULL);
+
+	free(ff.buf);
+	return ret;
+}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
new file mode 100644
index 0000000..baead0c
--- /dev/null
+++ b/tools/perf/util/synthetic-events.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SYNTHETIC_EVENTS_H
+#define __PERF_SYNTHETIC_EVENTS_H
+
+#include <stdbool.h>
+#include <sys/types.h> // pid_t
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct auxtrace_record;
+struct dso;
+struct evlist;
+struct evsel;
+struct machine;
+struct perf_counts_values;
+struct perf_cpu_map;
+struct perf_event_attr;
+struct perf_event_mmap_page;
+struct perf_sample;
+struct perf_session;
+struct perf_stat_config;
+struct perf_thread_map;
+struct perf_tool;
+struct record_opts;
+struct target;
+
+union perf_event;
+
+typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event,
+				     struct perf_sample *sample, struct machine *machine);
+
+int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process);
+int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process);
+int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process);
+int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evsel_list, perf_event__handler_t process, bool is_pipe);
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process);
+int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine);
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);
+int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
+int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
+int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool mmap_data);
+int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int nr_threads_synthesize);
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct evlist *evlist, perf_event__handler_t process);
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
+pid_t perf_event__synthesize_comm(struct perf_tool *tool, union perf_event *event, pid_t pid, perf_event__handler_t process, struct machine *machine);
+
+int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process);
+
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format);
+
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct target *target, struct perf_thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int nr_threads_synthesize);
+int machine__synthesize_threads(struct machine *machine, struct target *target,
+				struct perf_thread_map *threads, bool data_mmap,
+				unsigned int nr_threads_synthesize);
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr, struct perf_tool *tool,
+					 struct perf_session *session, perf_event__handler_t process);
+
+#else // HAVE_AUXTRACE_SUPPORT
+
+#include <errno.h>
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+				     struct perf_tool *tool __maybe_unused,
+				     struct perf_session *session __maybe_unused,
+				     perf_event__handler_t process __maybe_unused)
+{
+	return -EINVAL;
+}
+#endif // HAVE_AUXTRACE_SUPPORT
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int perf_event__synthesize_bpf_events(struct perf_session *session, perf_event__handler_t process,
+				      struct machine *machine, struct record_opts *opts);
+#else // HAVE_LIBBPF_SUPPORT
+static inline int perf_event__synthesize_bpf_events(struct perf_session *session __maybe_unused,
+						    perf_event__handler_t process __maybe_unused,
+						    struct machine *machine __maybe_unused,
+						    struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+
+#endif // __PERF_SYNTHETIC_EVENTS_H
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 3393d7e..820fcee 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * System call table mapper
  *
  * (C) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include "syscalltbl.h"
@@ -18,9 +10,9 @@
 #include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE_SUPPORT
+#include <linux/zalloc.h>
 #include <string.h>
 #include "string2.h"
-#include "util.h"
 
 #if defined(__x86_64__)
 #include <asm/syscalls_64.c>
@@ -87,6 +79,7 @@
 
 	qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp);
 	tbl->syscalls.nr_entries = nr_entries;
+	tbl->syscalls.max_id	 = syscalltbl_native_max_id;
 	return 0;
 }
 
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
index c8e7e9c..9172613 100644
--- a/tools/perf/util/syscalltbl.h
+++ b/tools/perf/util/syscalltbl.h
@@ -6,6 +6,7 @@
 	union {
 		int audit_machine;
 		struct {
+			int max_id;
 			int nr_entries;
 			void *entries;
 		} syscalls;
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 21c4d9b..a3db13d 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -1,18 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Helper functions for handling target threads/cpus
  *
  * Copyright (C) 2012, LG Electronics, Namhyung Kim <namhyung.kim@lge.com>
- *
- * Released under the GPL v2.
  */
 
 #include "target.h"
-#include "util.h"
-#include "debug.h"
 
 #include <pwd.h>
+#include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
-
+#include <linux/kernel.h>
+#include <linux/string.h>
 
 enum target_errno target__validate(struct target *target)
 {
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index a5669d0..cd8a948 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -1,25 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * thread-stack.c: Synthesize a thread's stack using call / return events
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <errno.h>
+#include <stdlib.h>
+#include <string.h>
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
-#include "util.h"
+#include "env.h"
 #include "debug.h"
 #include "symbol.h"
 #include "comm.h"
@@ -28,22 +23,45 @@
 
 #define STACK_GROWTH 2048
 
+/*
+ * State of retpoline detection.
+ *
+ * RETPOLINE_NONE: no retpoline detection
+ * X86_RETPOLINE_POSSIBLE: x86 retpoline possible
+ * X86_RETPOLINE_DETECTED: x86 retpoline detected
+ */
+enum retpoline_state_t {
+	RETPOLINE_NONE,
+	X86_RETPOLINE_POSSIBLE,
+	X86_RETPOLINE_DETECTED,
+};
+
 /**
  * struct thread_stack_entry - thread stack entry.
  * @ret_addr: return address
  * @timestamp: timestamp (if known)
  * @ref: external reference (e.g. db_id of sample)
  * @branch_count: the branch count when the entry was created
+ * @insn_count: the instruction count when the entry was created
+ * @cyc_count the cycle count when the entry was created
+ * @db_id: id used for db-export
  * @cp: call path
  * @no_call: a 'call' was not seen
+ * @trace_end: a 'call' but trace ended
+ * @non_call: a branch but not a 'call' to the start of a different symbol
  */
 struct thread_stack_entry {
 	u64 ret_addr;
 	u64 timestamp;
 	u64 ref;
 	u64 branch_count;
+	u64 insn_count;
+	u64 cyc_count;
+	u64 db_id;
 	struct call_path *cp;
 	bool no_call;
+	bool trace_end;
+	bool non_call;
 };
 
 /**
@@ -54,10 +72,14 @@
  * @sz: current maximum stack size
  * @trace_nr: current trace number
  * @branch_count: running branch count
+ * @insn_count: running  instruction count
+ * @cyc_count running  cycle count
  * @kernel_start: kernel start address
  * @last_time: last timestamp
  * @crp: call/return processor
  * @comm: current comm
+ * @arr_sz: size of array if this is the first element of an array
+ * @rstate: used to detect retpolines
  */
 struct thread_stack {
 	struct thread_stack_entry *stack;
@@ -65,12 +87,26 @@
 	size_t sz;
 	u64 trace_nr;
 	u64 branch_count;
+	u64 insn_count;
+	u64 cyc_count;
 	u64 kernel_start;
 	u64 last_time;
 	struct call_return_processor *crp;
 	struct comm *comm;
+	unsigned int arr_sz;
+	enum retpoline_state_t rstate;
 };
 
+/*
+ * Assume pid == tid == 0 identifies the idle task as defined by
+ * perf_session__register_idle_thread(). The idle task is really 1 task per cpu,
+ * and therefore requires a stack for each cpu.
+ */
+static inline bool thread_stack__per_cpu(struct thread *thread)
+{
+	return !(thread->tid || thread->pid_);
+}
+
 static int thread_stack__grow(struct thread_stack *ts)
 {
 	struct thread_stack_entry *new_stack;
@@ -89,30 +125,95 @@
 	return 0;
 }
 
-static struct thread_stack *thread_stack__new(struct thread *thread,
+static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
+			      struct call_return_processor *crp)
+{
+	int err;
+
+	err = thread_stack__grow(ts);
+	if (err)
+		return err;
+
+	if (thread->mg && thread->mg->machine) {
+		struct machine *machine = thread->mg->machine;
+		const char *arch = perf_env__arch(machine->env);
+
+		ts->kernel_start = machine__kernel_start(machine);
+		if (!strcmp(arch, "x86"))
+			ts->rstate = X86_RETPOLINE_POSSIBLE;
+	} else {
+		ts->kernel_start = 1ULL << 63;
+	}
+	ts->crp = crp;
+
+	return 0;
+}
+
+static struct thread_stack *thread_stack__new(struct thread *thread, int cpu,
 					      struct call_return_processor *crp)
 {
-	struct thread_stack *ts;
+	struct thread_stack *ts = thread->ts, *new_ts;
+	unsigned int old_sz = ts ? ts->arr_sz : 0;
+	unsigned int new_sz = 1;
 
-	ts = zalloc(sizeof(struct thread_stack));
-	if (!ts)
-		return NULL;
+	if (thread_stack__per_cpu(thread) && cpu > 0)
+		new_sz = roundup_pow_of_two(cpu + 1);
 
-	if (thread_stack__grow(ts)) {
-		free(ts);
-		return NULL;
+	if (!ts || new_sz > old_sz) {
+		new_ts = calloc(new_sz, sizeof(*ts));
+		if (!new_ts)
+			return NULL;
+		if (ts)
+			memcpy(new_ts, ts, old_sz * sizeof(*ts));
+		new_ts->arr_sz = new_sz;
+		zfree(&thread->ts);
+		thread->ts = new_ts;
+		ts = new_ts;
 	}
 
-	if (thread->mg && thread->mg->machine)
-		ts->kernel_start = machine__kernel_start(thread->mg->machine);
-	else
-		ts->kernel_start = 1ULL << 63;
-	ts->crp = crp;
+	if (thread_stack__per_cpu(thread) && cpu > 0 &&
+	    (unsigned int)cpu < ts->arr_sz)
+		ts += cpu;
+
+	if (!ts->stack &&
+	    thread_stack__init(ts, thread, crp))
+		return NULL;
 
 	return ts;
 }
 
-static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+static struct thread_stack *thread__cpu_stack(struct thread *thread, int cpu)
+{
+	struct thread_stack *ts = thread->ts;
+
+	if (cpu < 0)
+		cpu = 0;
+
+	if (!ts || (unsigned int)cpu >= ts->arr_sz)
+		return NULL;
+
+	ts += cpu;
+
+	if (!ts->stack)
+		return NULL;
+
+	return ts;
+}
+
+static inline struct thread_stack *thread__stack(struct thread *thread,
+						    int cpu)
+{
+	if (!thread)
+		return NULL;
+
+	if (thread_stack__per_cpu(thread))
+		return thread__cpu_stack(thread, cpu);
+
+	return thread->ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr,
+			      bool trace_end)
 {
 	int err = 0;
 
@@ -124,6 +225,7 @@
 		}
 	}
 
+	ts->stack[ts->cnt].trace_end = trace_end;
 	ts->stack[ts->cnt++].ret_addr = ret_addr;
 
 	return err;
@@ -150,6 +252,18 @@
 	}
 }
 
+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)
@@ -169,20 +283,33 @@
 		.comm = ts->comm,
 		.db_id = 0,
 	};
+	u64 *parent_db_id;
 
 	tse = &ts->stack[idx];
 	cr.cp = tse->cp;
 	cr.call_time = tse->timestamp;
 	cr.return_time = timestamp;
 	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.insn_count = ts->insn_count - tse->insn_count;
+	cr.cyc_count = ts->cyc_count - tse->cyc_count;
+	cr.db_id = tse->db_id;
 	cr.call_ref = tse->ref;
 	cr.return_ref = ref;
 	if (tse->no_call)
 		cr.flags |= CALL_RETURN_NO_CALL;
 	if (no_return)
 		cr.flags |= CALL_RETURN_NO_RETURN;
+	if (tse->non_call)
+		cr.flags |= CALL_RETURN_NON_CALL;
 
-	return crp->process(&cr, crp->data);
+	/*
+	 * The parent db_id must be assigned before exporting the child. Note
+	 * it is not possible to export the parent first because its information
+	 * is not yet complete because its 'return' has not yet been processed.
+	 */
+	parent_db_id = idx ? &(tse - 1)->db_id : NULL;
+
+	return crp->process(&cr, parent_db_id, crp->data);
 }
 
 static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
@@ -210,25 +337,37 @@
 
 int thread_stack__flush(struct thread *thread)
 {
-	if (thread->ts)
-		return __thread_stack__flush(thread, thread->ts);
+	struct thread_stack *ts = thread->ts;
+	unsigned int pos;
+	int err = 0;
 
-	return 0;
+	if (ts) {
+		for (pos = 0; pos < ts->arr_sz; pos++) {
+			int ret = __thread_stack__flush(thread, ts + pos);
+
+			if (ret)
+				err = ret;
+		}
+	}
+
+	return err;
 }
 
-int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {
+	struct thread_stack *ts = thread__stack(thread, cpu);
+
 	if (!thread)
 		return -EINVAL;
 
-	if (!thread->ts) {
-		thread->ts = thread_stack__new(thread, NULL);
-		if (!thread->ts) {
+	if (!ts) {
+		ts = thread_stack__new(thread, cpu, NULL);
+		if (!ts) {
 			pr_warning("Out of memory: no thread stack\n");
 			return -ENOMEM;
 		}
-		thread->ts->trace_nr = trace_nr;
+		ts->trace_nr = trace_nr;
 	}
 
 	/*
@@ -236,14 +375,14 @@
 	 * the stack might be completely invalid.  Better to report nothing than
 	 * to report something misleading, so flush the stack.
 	 */
-	if (trace_nr != thread->ts->trace_nr) {
-		if (thread->ts->trace_nr)
-			__thread_stack__flush(thread, thread->ts);
-		thread->ts->trace_nr = trace_nr;
+	if (trace_nr != ts->trace_nr) {
+		if (ts->trace_nr)
+			__thread_stack__flush(thread, ts);
+		ts->trace_nr = trace_nr;
 	}
 
 	/* Stop here if thread_stack__process() is in use */
-	if (thread->ts->crp)
+	if (ts->crp)
 		return 0;
 
 	if (flags & PERF_IP_FLAG_CALL) {
@@ -254,33 +393,62 @@
 		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;
-		thread_stack__pop(thread->ts, to_ip);
+		return thread_stack__push(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(ts, to_ip);
+		thread_stack__pop_trace_end(ts);
+	} else if ((flags & PERF_IP_FLAG_RETURN) && from_ip) {
+		thread_stack__pop(ts, to_ip);
 	}
 
 	return 0;
 }
 
-void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr)
 {
-	if (!thread || !thread->ts)
+	struct thread_stack *ts = thread__stack(thread, cpu);
+
+	if (!ts)
 		return;
 
-	if (trace_nr != thread->ts->trace_nr) {
-		if (thread->ts->trace_nr)
-			__thread_stack__flush(thread, thread->ts);
-		thread->ts->trace_nr = trace_nr;
+	if (trace_nr != ts->trace_nr) {
+		if (ts->trace_nr)
+			__thread_stack__flush(thread, ts);
+		ts->trace_nr = trace_nr;
 	}
 }
 
+static void __thread_stack__free(struct thread *thread, struct thread_stack *ts)
+{
+	__thread_stack__flush(thread, ts);
+	zfree(&ts->stack);
+}
+
+static void thread_stack__reset(struct thread *thread, struct thread_stack *ts)
+{
+	unsigned int arr_sz = ts->arr_sz;
+
+	__thread_stack__free(thread, ts);
+	memset(ts, 0, sizeof(*ts));
+	ts->arr_sz = arr_sz;
+}
+
 void thread_stack__free(struct thread *thread)
 {
-	if (thread->ts) {
-		__thread_stack__flush(thread, thread->ts);
-		zfree(&thread->ts->stack);
+	struct thread_stack *ts = thread->ts;
+	unsigned int pos;
+
+	if (ts) {
+		for (pos = 0; pos < ts->arr_sz; pos++)
+			__thread_stack__free(thread, ts + pos);
 		zfree(&thread->ts);
 	}
 }
@@ -290,9 +458,11 @@
 	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
 }
 
-void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+void thread_stack__sample(struct thread *thread, int cpu,
+			  struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start)
 {
+	struct thread_stack *ts = thread__stack(thread, cpu);
 	u64 context = callchain_context(ip, kernel_start);
 	u64 last_context;
 	size_t i, j;
@@ -305,15 +475,15 @@
 	chain->ips[0] = context;
 	chain->ips[1] = ip;
 
-	if (!thread || !thread->ts) {
+	if (!ts) {
 		chain->nr = 2;
 		return;
 	}
 
 	last_context = context;
 
-	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
-		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+	for (i = 2, j = 1; i < sz && j <= ts->cnt; i++, j++) {
+		ip = ts->stack[ts->cnt - j].ret_addr;
 		context = callchain_context(ip, kernel_start);
 		if (context != last_context) {
 			if (i >= sz - 1)
@@ -328,7 +498,7 @@
 }
 
 struct call_return_processor *
-call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data)
 {
 	struct call_return_processor *crp;
@@ -358,11 +528,14 @@
 
 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;
 
+	if (!cp)
+		return -ENOMEM;
+
 	if (ts->cnt == ts->sz) {
 		err = thread_stack__grow(ts);
 		if (err)
@@ -374,8 +547,13 @@
 	tse->timestamp = timestamp;
 	tse->ref = ref;
 	tse->branch_count = ts->branch_count;
+	tse->insn_count = ts->insn_count;
+	tse->cyc_count = ts->cyc_count;
 	tse->cp = cp;
 	tse->no_call = no_call;
+	tse->trace_end = trace_end;
+	tse->non_call = false;
+	tse->db_id = 0;
 
 	return 0;
 }
@@ -397,14 +575,16 @@
 							 timestamp, ref, false);
 	}
 
-	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr &&
+	    !ts->stack[ts->cnt - 1].non_call) {
 		return thread_stack__call_return(thread, ts, --ts->cnt,
 						 timestamp, ref, false);
 	} else {
 		size_t i = ts->cnt - 1;
 
 		while (i--) {
-			if (ts->stack[i].ret_addr != ret_addr)
+			if (ts->stack[i].ret_addr != ret_addr ||
+			    ts->stack[i].non_call)
 				continue;
 			i += 1;
 			while (ts->cnt > i) {
@@ -423,7 +603,7 @@
 	return 1;
 }
 
-static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+static int thread_stack__bottom(struct thread_stack *ts,
 				struct perf_sample *sample,
 				struct addr_location *from_al,
 				struct addr_location *to_al, u64 ref)
@@ -445,11 +625,26 @@
 
 	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
-	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
-				     true);
+	return thread_stack__push_cp(ts, ip, sample->time, ref, cp,
+				     true, false);
+}
+
+static int thread_stack__pop_ks(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample, u64 ref)
+{
+	u64 tm = sample->time;
+	int err;
+
+	/* Return to userspace, so pop all kernel addresses */
+	while (thread_stack__in_kernel(ts)) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						tm, ref, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int thread_stack__no_call_return(struct thread *thread,
@@ -459,59 +654,91 @@
 					struct addr_location *to_al, u64 ref)
 {
 	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *root = &cpr->call_path;
+	struct symbol *fsym = from_al->sym;
+	struct symbol *tsym = to_al->sym;
 	struct call_path *cp, *parent;
 	u64 ks = ts->kernel_start;
+	u64 addr = sample->addr;
+	u64 tm = sample->time;
+	u64 ip = sample->ip;
 	int err;
 
-	if (sample->ip >= ks && sample->addr < ks) {
+	if (ip >= ks && addr < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							sample->time, ref,
-							true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 
 		/* If the stack is empty, push the userspace address */
 		if (!ts->cnt) {
-			cp = call_path__findnew(cpr, &cpr->call_path,
-						to_al->sym, sample->addr,
-						ts->kernel_start);
-			if (!cp)
-				return -ENOMEM;
-			return thread_stack__push_cp(ts, 0, sample->time, ref,
-						     cp, true);
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+			return thread_stack__push_cp(ts, 0, tm, ref, cp, true,
+						     false);
 		}
-	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+	} else if (thread_stack__in_kernel(ts) && ip < ks) {
 		/* Return to userspace, so pop all kernel addresses */
-		while (thread_stack__in_kernel(ts)) {
-			err = thread_stack__call_return(thread, ts, --ts->cnt,
-							sample->time, ref,
-							true);
-			if (err)
-				return err;
-		}
+		err = thread_stack__pop_ks(thread, ts, sample, ref);
+		if (err)
+			return err;
 	}
 
 	if (ts->cnt)
 		parent = ts->stack[ts->cnt - 1].cp;
 	else
-		parent = &cpr->call_path;
+		parent = root;
 
-	/* This 'return' had no 'call', so push and pop top of stack */
-	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
-				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
+	if (parent->sym == from_al->sym) {
+		/*
+		 * At the bottom of the stack, assume the missing 'call' was
+		 * before the trace started. So, pop the current symbol and push
+		 * the 'to' symbol.
+		 */
+		if (ts->cnt == 1) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							tm, ref, false);
+			if (err)
+				return err;
+		}
 
-	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true);
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
+
+			return thread_stack__push_cp(ts, addr, tm, ref, cp,
+						     true, false);
+		}
+
+		/*
+		 * Otherwise assume the 'return' is being used as a jump (e.g.
+		 * retpoline) and just push the 'to' symbol.
+		 */
+		cp = call_path__findnew(cpr, parent, tsym, addr, ks);
+
+		err = thread_stack__push_cp(ts, 0, tm, ref, cp, true, false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
+
+		return err;
+	}
+
+	/*
+	 * Assume 'parent' has not yet returned, so push 'to', and then push and
+	 * pop 'from'.
+	 */
+
+	cp = call_path__findnew(cpr, parent, tsym, addr, ks);
+
+	err = thread_stack__push_cp(ts, addr, tm, ref, cp, true, false);
 	if (err)
 		return err;
 
-	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
-				    to_al->sym);
+	cp = call_path__findnew(cpr, cp, fsym, ip, ks);
+
+	err = thread_stack__push_cp(ts, ip, tm, ref, cp, true, false);
+	if (err)
+		return err;
+
+	return thread_stack__call_return(thread, ts, --ts->cnt, tm, ref, false);
 }
 
 static int thread_stack__trace_begin(struct thread *thread,
@@ -526,7 +753,7 @@
 
 	/* 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)
@@ -549,13 +776,75 @@
 
 	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
 	ret_addr = sample->ip + sample->insn_len;
 
 	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
-				     false);
+				     false, true);
+}
+
+static bool is_x86_retpoline(const char *name)
+{
+	const char *p = strstr(name, "__x86_indirect_thunk_");
+
+	return p == name || !strcmp(name, "__indirect_thunk_start");
+}
+
+/*
+ * x86 retpoline functions pollute the call graph. This function removes them.
+ * This does not handle function return thunks, nor is there any improvement
+ * for the handling of inline thunks or extern thunks.
+ */
+static int thread_stack__x86_retpoline(struct thread_stack *ts,
+				       struct perf_sample *sample,
+				       struct addr_location *to_al)
+{
+	struct thread_stack_entry *tse = &ts->stack[ts->cnt - 1];
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct symbol *sym = tse->cp->sym;
+	struct symbol *tsym = to_al->sym;
+	struct call_path *cp;
+
+	if (sym && is_x86_retpoline(sym->name)) {
+		/*
+		 * This is a x86 retpoline fn. It pollutes the call graph by
+		 * showing up everywhere there is an indirect branch, but does
+		 * not itself mean anything. Here the top-of-stack is removed,
+		 * by decrementing the stack count, and then further down, the
+		 * resulting top-of-stack is replaced with the actual target.
+		 * The result is that the retpoline functions will no longer
+		 * appear in the call graph. Note this only affects the call
+		 * graph, since all the original branches are left unchanged.
+		 */
+		ts->cnt -= 1;
+		sym = ts->stack[ts->cnt - 2].cp->sym;
+		if (sym && sym == tsym && to_al->addr != tsym->start) {
+			/*
+			 * Target is back to the middle of the symbol we came
+			 * from so assume it is an indirect jmp and forget it
+			 * altogether.
+			 */
+			ts->cnt -= 1;
+			return 0;
+		}
+	} else if (sym && sym == tsym) {
+		/*
+		 * Target is back to the symbol we came from so assume it is an
+		 * indirect jmp and forget it altogether.
+		 */
+		ts->cnt -= 1;
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 2].cp, tsym,
+				sample->addr, ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	/* Replace the top-of-stack with the actual target */
+	ts->stack[ts->cnt - 1].cp = cp;
+
+	return 0;
 }
 
 int thread_stack__process(struct thread *thread, struct comm *comm,
@@ -564,27 +853,27 @@
 			  struct addr_location *to_al, u64 ref,
 			  struct call_return_processor *crp)
 {
-	struct thread_stack *ts = thread->ts;
+	struct thread_stack *ts = thread__stack(thread, sample->cpu);
+	enum retpoline_state_t rstate;
 	int err = 0;
 
-	if (ts) {
-		if (!ts->crp) {
-			/* Supersede thread_stack__event() */
-			thread_stack__free(thread);
-			thread->ts = thread_stack__new(thread, crp);
-			if (!thread->ts)
-				return -ENOMEM;
-			ts = thread->ts;
-			ts->comm = comm;
-		}
-	} else {
-		thread->ts = thread_stack__new(thread, crp);
-		if (!thread->ts)
+	if (ts && !ts->crp) {
+		/* Supersede thread_stack__event() */
+		thread_stack__reset(thread, ts);
+		ts = NULL;
+	}
+
+	if (!ts) {
+		ts = thread_stack__new(thread, sample->cpu, crp);
+		if (!ts)
 			return -ENOMEM;
-		ts = thread->ts;
 		ts->comm = comm;
 	}
 
+	rstate = ts->rstate;
+	if (rstate == X86_RETPOLINE_DETECTED)
+		ts->rstate = X86_RETPOLINE_POSSIBLE;
+
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
 		err = __thread_stack__flush(thread, ts);
@@ -595,16 +884,18 @@
 
 	/* If the stack is empty, put the current symbol on the stack */
 	if (!ts->cnt) {
-		err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
-					   ref);
+		err = thread_stack__bottom(ts, sample, from_al, to_al, ref);
 		if (err)
 			return err;
 	}
 
 	ts->branch_count += 1;
+	ts->insn_count += sample->insn_cnt;
+	ts->cyc_count += sample->cyc_cnt;
 	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;
@@ -619,14 +910,38 @@
 		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
 					to_al->sym, sample->addr,
 					ts->kernel_start);
-		if (!cp)
-			return -ENOMEM;
 		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
-					    cp, false);
+					    cp, false, trace_end);
+
+		/*
+		 * A call to the same symbol but not the start of the symbol,
+		 * may be the start of a x86 retpoline.
+		 */
+		if (!err && rstate == X86_RETPOLINE_POSSIBLE && to_al->sym &&
+		    from_al->sym == to_al->sym &&
+		    to_al->addr != to_al->sym->start)
+			ts->rstate = X86_RETPOLINE_DETECTED;
+
 	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
-		if (!sample->ip || !sample->addr)
+		if (!sample->addr) {
+			u32 return_from_kernel = PERF_IP_FLAG_SYSCALLRET |
+						 PERF_IP_FLAG_INTERRUPT;
+
+			if (!(sample->flags & return_from_kernel))
+				return 0;
+
+			/* Pop kernel stack */
+			return thread_stack__pop_ks(thread, ts, sample, ref);
+		}
+
+		if (!sample->ip)
 			return 0;
 
+		/* x86 retpoline 'return' doesn't match the stack */
+		if (rstate == X86_RETPOLINE_DETECTED && ts->cnt > 2 &&
+		    ts->stack[ts->cnt - 1].ret_addr != sample->addr)
+			return thread_stack__x86_retpoline(ts, sample, to_al);
+
 		err = thread_stack__pop_cp(thread, ts, sample->addr,
 					   sample->time, ref, from_al->sym);
 		if (err) {
@@ -639,14 +954,35 @@
 		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
 	} else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
 		err = thread_stack__trace_end(ts, sample, ref);
+	} else if (sample->flags & PERF_IP_FLAG_BRANCH &&
+		   from_al->sym != to_al->sym && to_al->sym &&
+		   to_al->addr == to_al->sym->start) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+
+		/*
+		 * The compiler might optimize a call/ret combination by making
+		 * it a jmp. Make that visible by recording on the stack a
+		 * branch to the start of a different symbol. Note, that means
+		 * when a ret pops the stack, all jmps must be popped off first.
+		 */
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		err = thread_stack__push_cp(ts, 0, sample->time, ref, cp, false,
+					    false);
+		if (!err)
+			ts->stack[ts->cnt - 1].non_call = true;
 	}
 
 	return err;
 }
 
-size_t thread_stack__depth(struct thread *thread)
+size_t thread_stack__depth(struct thread *thread, int cpu)
 {
-	if (!thread->ts)
+	struct thread_stack *ts = thread__stack(thread, cpu);
+
+	if (!ts)
 		return 0;
-	return thread->ts->cnt;
+	return ts->cnt;
 }
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index f97c00a..e1ec5a5 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * thread-stack.h: Synthesize a thread's stack using call / return events
  * Copyright (c) 2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
  */
 
 #ifndef __PERF_THREAD_STACK_H
@@ -35,10 +26,13 @@
  *
  * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
  * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ * CALL_RETURN_NON_CALL: a branch but not a 'call' to the start of a different
+ *                       symbol
  */
 enum {
 	CALL_RETURN_NO_CALL	= 1 << 0,
 	CALL_RETURN_NO_RETURN	= 1 << 1,
+	CALL_RETURN_NON_CALL	= 1 << 2,
 };
 
 /**
@@ -49,9 +43,12 @@
  * @call_time: timestamp of call (if known)
  * @return_time: timestamp of return (if known)
  * @branch_count: number of branches seen between call and return
+ * @insn_count: approx. number of instructions between call and return
+ * @cyc_count: approx. number of cycles between call and return
  * @call_ref: external reference to 'call' sample (e.g. db_id)
  * @return_ref:  external reference to 'return' sample (e.g. db_id)
  * @db_id: id used for db-export
+ * @parent_db_id: id of parent call used for db-export
  * @flags: Call/Return flags
  */
 struct call_return {
@@ -61,9 +58,12 @@
 	u64 call_time;
 	u64 return_time;
 	u64 branch_count;
+	u64 insn_count;
+	u64 cyc_count;
 	u64 call_ref;
 	u64 return_ref;
 	u64 db_id;
+	u64 parent_db_id;
 	u32 flags;
 };
 
@@ -76,21 +76,21 @@
  */
 struct call_return_processor {
 	struct call_path_root *cpr;
-	int (*process)(struct call_return *cr, void *data);
+	int (*process)(struct call_return *cr, u64 *parent_db_id, void *data);
 	void *data;
 };
 
-int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
-void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
-void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
-size_t thread_stack__depth(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread, int cpu);
 
 struct call_return_processor *
-call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
 			   void *data);
 void call_return_processor__free(struct call_return_processor *crp);
 int thread_stack__process(struct thread *thread, struct comm *comm,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d39..b64e9e0 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -1,18 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../perf.h"
 #include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
+#include "dso.h"
 #include "session.h"
 #include "thread.h"
 #include "thread-stack.h"
-#include "util.h"
 #include "debug.h"
 #include "namespaces.h"
 #include "comm.h"
+#include "map.h"
+#include "symbol.h"
 #include "unwind.h"
+#include "callchain.h"
 
 #include <api/fs/fs.h>
 
@@ -64,6 +67,7 @@
 		RB_CLEAR_NODE(&thread->rb_node);
 		/* Thread holds first ref to nsdata. */
 		thread->nsinfo = nsinfo__new(pid);
+		srccode_state_init(&thread->srccode_state);
 	}
 
 	return thread;
@@ -89,20 +93,20 @@
 	down_write(&thread->namespaces_lock);
 	list_for_each_entry_safe(namespaces, tmp_namespaces,
 				 &thread->namespaces_list, list) {
-		list_del(&namespaces->list);
+		list_del_init(&namespaces->list);
 		namespaces__free(namespaces);
 	}
 	up_write(&thread->namespaces_lock);
 
 	down_write(&thread->comm_lock);
 	list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
-		list_del(&comm->list);
+		list_del_init(&comm->list);
 		comm__free(comm);
 	}
 	up_write(&thread->comm_lock);
 
-	unwind__finish_access(thread);
 	nsinfo__zput(thread->nsinfo);
+	srccode_state_free(&thread->srccode_state);
 
 	exit_rwsem(&thread->namespaces_lock);
 	exit_rwsem(&thread->comm_lock);
@@ -120,15 +124,32 @@
 {
 	if (thread && refcount_dec_and_test(&thread->refcnt)) {
 		/*
-		 * Remove it from the dead_threads list, as last reference
-		 * is gone.
+		 * Remove it from the dead threads list, as last reference is
+		 * gone, if it is in a dead threads list.
+		 *
+		 * We may not be there anymore if say, the machine where it was
+		 * stored was already deleted, so we already removed it from
+		 * the dead threads and some other piece of code still keeps a
+		 * reference.
+		 *
+		 * This is what 'perf sched' does and finally drops it in
+		 * perf_sched__lat(), where it calls perf_sched__read_events(),
+		 * that processes the events by creating a session and deleting
+		 * it, which ends up destroying the list heads for the dead
+		 * threads, but before it does that it removes all threads from
+		 * it using list_del_init().
+		 *
+		 * So we need to check here if it is in a dead threads list and
+		 * if so, remove it before finally deleting the thread, to avoid
+		 * an use after free situation.
 		 */
-		list_del_init(&thread->node);
+		if (!list_empty(&thread->node))
+			list_del_init(&thread->node);
 		thread__delete(thread);
 	}
 }
 
-struct namespaces *thread__namespaces(const struct thread *thread)
+static struct namespaces *__thread__namespaces(const struct thread *thread)
 {
 	if (list_empty(&thread->namespaces_list))
 		return NULL;
@@ -136,10 +157,21 @@
 	return list_first_entry(&thread->namespaces_list, struct namespaces, list);
 }
 
-static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
-				    struct namespaces_event *event)
+struct namespaces *thread__namespaces(struct thread *thread)
 {
-	struct namespaces *new, *curr = thread__namespaces(thread);
+	struct namespaces *ns;
+
+	down_read(&thread->namespaces_lock);
+	ns = __thread__namespaces(thread);
+	up_read(&thread->namespaces_lock);
+
+	return ns;
+}
+
+static int __thread__set_namespaces(struct thread *thread, u64 timestamp,
+				    struct perf_record_namespaces *event)
+{
+	struct namespaces *new, *curr = __thread__namespaces(thread);
 
 	new = namespaces__new(event);
 	if (!new)
@@ -161,7 +193,7 @@
 }
 
 int thread__set_namespaces(struct thread *thread, u64 timestamp,
-			   struct namespaces_event *event)
+			   struct perf_record_namespaces *event)
 {
 	int ret;
 
@@ -181,14 +213,24 @@
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
@@ -209,7 +251,7 @@
 		list_add(&new->list, &thread->comm_list);
 
 		if (exec)
-			unwind__flush_access(thread);
+			unwind__flush_access(thread->mg);
 	}
 
 	thread->comm_set = true;
@@ -255,13 +297,13 @@
 	return comm__str(comm);
 }
 
-const char *thread__comm_str(const struct thread *thread)
+const char *thread__comm_str(struct thread *thread)
 {
 	const char *str;
 
-	down_read((struct rw_semaphore *)&thread->comm_lock);
+	down_read(&thread->comm_lock);
 	str = __thread__comm_str(thread);
-	up_read((struct rw_semaphore *)&thread->comm_lock);
+	up_read(&thread->comm_lock);
 
 	return str;
 }
@@ -289,7 +331,7 @@
 {
 	int ret;
 
-	ret = unwind__prepare_access(thread, map, NULL);
+	ret = unwind__prepare_access(thread->mg, map, NULL);
 	if (ret)
 		return ret;
 
@@ -309,7 +351,7 @@
 	down_read(&maps->lock);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
-		err = unwind__prepare_access(thread, map, &initialized);
+		err = unwind__prepare_access(thread->mg, map, &initialized);
 		if (err || initialized)
 			break;
 	}
@@ -323,14 +365,15 @@
 {
 	int err = 0;
 
-	if (symbol_conf.use_callchain)
+	if (dwarf_callchain_users)
 		err = __thread__prepare_access(thread);
 
 	return err;
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +384,11 @@
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +401,7 @@
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
@@ -393,3 +432,25 @@
 
 	return machine__find_thread(machine, thread->pid_, thread->pid_);
 }
+
+int thread__memcpy(struct thread *thread, struct machine *machine,
+		   void *buf, u64 ip, int len, bool *is64bit)
+{
+       u8 cpumode = PERF_RECORD_MISC_USER;
+       struct addr_location al;
+       long offset;
+
+       if (machine__kernel_ip(machine, ip))
+               cpumode = PERF_RECORD_MISC_KERNEL;
+
+       if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso ||
+	   al.map->dso->data.status == DSO_DATA_STATUS_ERROR ||
+	   map__load(al.map) < 0)
+               return -1;
+
+       offset = al.map->map_ip(al.map, ip);
+       if (is64bit)
+               *is64bit = al.map->dso->is_64_bit;
+
+       return dso__data_read_offset(al.map->dso, machine, offset, buf, len);
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa..51bdb9a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,13 +5,18 @@
 #include <linux/refcount.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <stdio.h>
 #include <unistd.h>
 #include <sys/types.h>
-#include "symbol.h"
+#include "srccode.h"
+#include "symbol_conf.h"
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
 
+struct addr_location;
+struct map;
+struct perf_record_namespaces;
 struct thread_stack;
 struct unwind_libunwind_ops;
 
@@ -38,10 +43,9 @@
 	void			*priv;
 	struct thread_stack	*ts;
 	struct nsinfo		*nsinfo;
-#ifdef HAVE_LIBUNWIND_SUPPORT
-	void				*addr_space;
-	struct unwind_libunwind_ops	*unwind_libunwind_ops;
-#endif
+	struct srccode_state	srccode_state;
+	bool			filter;
+	int			filter_entry_depth;
 };
 
 struct machine;
@@ -68,9 +72,9 @@
 	thread->dead = true;
 }
 
-struct namespaces *thread__namespaces(const struct thread *thread);
+struct namespaces *thread__namespaces(struct thread *thread);
 int thread__set_namespaces(struct thread *thread, u64 timestamp,
-			   struct namespaces_event *event);
+			   struct perf_record_namespaces *event);
 
 int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
 		       bool exec);
@@ -85,22 +89,29 @@
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
-const char *thread__comm_str(const struct thread *thread);
+const char *thread__comm_str(struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
 
 struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 			     struct addr_location *al);
+struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr,
+				struct addr_location *al);
 
 struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
 				   u64 addr, struct addr_location *al);
+struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
+				      u64 addr, struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al);
 
+int thread__memcpy(struct thread *thread, struct machine *machine,
+		   void *buf, u64 ip, int len, bool *is64bit);
+
 static inline void *thread__priv(struct thread *thread)
 {
 	return thread->priv;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5d467d8..c9bfe46 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -12,9 +12,10 @@
 #include "strlist.h"
 #include <string.h>
 #include <api/fs/fs.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
 #include "asm/bug.h"
 #include "thread_map.h"
-#include "util.h"
 #include "debug.h"
 #include "event.h"
 
@@ -27,34 +28,11 @@
 		return 1;
 }
 
-static void thread_map__reset(struct thread_map *map, int start, int nr)
+#define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr)
+
+struct perf_thread_map *thread_map__new_by_pid(pid_t pid)
 {
-	size_t size = (nr - start) * sizeof(map->map[0]);
-
-	memset(&map->map[start], 0, size);
-	map->err_thread = -1;
-}
-
-static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
-{
-	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
-	int start = map ? map->nr : 0;
-
-	map = realloc(map, size);
-	/*
-	 * We only realloc to add more items, let's reset new items.
-	 */
-	if (map)
-		thread_map__reset(map, start, nr);
-
-	return map;
-}
-
-#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
-
-struct thread_map *thread_map__new_by_pid(pid_t pid)
-{
-	struct thread_map *threads;
+	struct perf_thread_map *threads;
 	char name[256];
 	int items;
 	struct dirent **namelist = NULL;
@@ -68,7 +46,7 @@
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
+			perf_thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
 		refcount_set(&threads->refcnt, 1);
 	}
@@ -80,12 +58,12 @@
 	return threads;
 }
 
-struct thread_map *thread_map__new_by_tid(pid_t tid)
+struct perf_thread_map *thread_map__new_by_tid(pid_t tid)
 {
-	struct thread_map *threads = thread_map__alloc(1);
+	struct perf_thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		thread_map__set_pid(threads, 0, tid);
+		perf_thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
 		refcount_set(&threads->refcnt, 1);
 	}
@@ -93,13 +71,13 @@
 	return threads;
 }
 
-static struct thread_map *__thread_map__new_all_cpus(uid_t uid)
+static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
 	char path[NAME_MAX + 1 + 6];
 	struct dirent *dirent, **namelist = NULL;
-	struct thread_map *threads = thread_map__alloc(max_threads);
+	struct perf_thread_map *threads = thread_map__alloc(max_threads);
 
 	if (threads == NULL)
 		goto out;
@@ -139,9 +117,9 @@
 		}
 
 		if (grow) {
-			struct thread_map *tmp;
+			struct perf_thread_map *tmp;
 
-			tmp = thread_map__realloc(threads, max_threads);
+			tmp = perf_thread_map__realloc(threads, max_threads);
 			if (tmp == NULL)
 				goto out_free_namelist;
 
@@ -149,8 +127,8 @@
 		}
 
 		for (i = 0; i < items; i++) {
-			thread_map__set_pid(threads, threads->nr + i,
-					    atoi(namelist[i]->d_name));
+			perf_thread_map__set_pid(threads, threads->nr + i,
+						    atoi(namelist[i]->d_name));
 		}
 
 		for (i = 0; i < items; i++)
@@ -179,17 +157,17 @@
 	goto out_closedir;
 }
 
-struct thread_map *thread_map__new_all_cpus(void)
+struct perf_thread_map *thread_map__new_all_cpus(void)
 {
 	return __thread_map__new_all_cpus(UINT_MAX);
 }
 
-struct thread_map *thread_map__new_by_uid(uid_t uid)
+struct perf_thread_map *thread_map__new_by_uid(uid_t uid)
 {
 	return __thread_map__new_all_cpus(uid);
 }
 
-struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
+struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid)
 {
 	if (pid != -1)
 		return thread_map__new_by_pid(pid);
@@ -200,9 +178,9 @@
 	return thread_map__new_by_tid(tid);
 }
 
-static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
+static struct perf_thread_map *thread_map__new_by_pid_str(const char *pid_str)
 {
-	struct thread_map *threads = NULL, *nt;
+	struct perf_thread_map *threads = NULL, *nt;
 	char name[256];
 	int items, total_tasks = 0;
 	struct dirent **namelist = NULL;
@@ -232,14 +210,14 @@
 			goto out_free_threads;
 
 		total_tasks += items;
-		nt = thread_map__realloc(threads, total_tasks);
+		nt = perf_thread_map__realloc(threads, total_tasks);
 		if (nt == NULL)
 			goto out_free_namelist;
 
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
+			perf_thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -262,21 +240,9 @@
 	goto out;
 }
 
-struct thread_map *thread_map__new_dummy(void)
+struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str)
 {
-	struct thread_map *threads = thread_map__alloc(1);
-
-	if (threads != NULL) {
-		thread_map__set_pid(threads, 0, -1);
-		threads->nr = 1;
-		refcount_set(&threads->refcnt, 1);
-	}
-	return threads;
-}
-
-struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
-{
-	struct thread_map *threads = NULL, *nt;
+	struct perf_thread_map *threads = NULL, *nt;
 	int ntasks = 0;
 	pid_t tid, prev_tid = INT_MAX;
 	char *end_ptr;
@@ -286,7 +252,7 @@
 
 	/* perf-stat expects threads to be generated even if tid not given */
 	if (!tid_str)
-		return thread_map__new_dummy();
+		return perf_thread_map__new_dummy();
 
 	slist = strlist__new(tid_str, &slist_config);
 	if (!slist)
@@ -303,13 +269,13 @@
 			continue;
 
 		ntasks++;
-		nt = thread_map__realloc(threads, ntasks);
+		nt = perf_thread_map__realloc(threads, ntasks);
 
 		if (nt == NULL)
 			goto out_free_threads;
 
 		threads = nt;
-		thread_map__set_pid(threads, ntasks - 1, tid);
+		perf_thread_map__set_pid(threads, ntasks - 1, tid);
 		threads->nr = ntasks;
 	}
 out:
@@ -323,7 +289,7 @@
 	goto out;
 }
 
-struct thread_map *thread_map__new_str(const char *pid, const char *tid,
+struct perf_thread_map *thread_map__new_str(const char *pid, const char *tid,
 				       uid_t uid, bool all_threads)
 {
 	if (pid)
@@ -338,39 +304,13 @@
 	return thread_map__new_by_tid_str(tid);
 }
 
-static void thread_map__delete(struct thread_map *threads)
-{
-	if (threads) {
-		int i;
-
-		WARN_ONCE(refcount_read(&threads->refcnt) != 0,
-			  "thread map refcnt unbalanced\n");
-		for (i = 0; i < threads->nr; i++)
-			free(thread_map__comm(threads, i));
-		free(threads);
-	}
-}
-
-struct thread_map *thread_map__get(struct thread_map *map)
-{
-	if (map)
-		refcount_inc(&map->refcnt);
-	return map;
-}
-
-void thread_map__put(struct thread_map *map)
-{
-	if (map && refcount_dec_and_test(&map->refcnt))
-		thread_map__delete(map);
-}
-
-size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
+size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp)
 {
 	int i;
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
+		printed += fprintf(fp, "%s%d", i ? ", " : "", perf_thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }
@@ -392,16 +332,16 @@
 		 * mark the end of the string.
 		 */
 		(*comm)[size] = 0;
-		rtrim(*comm);
+		strim(*comm);
 	}
 
 	free(path);
 	return err;
 }
 
-static void comm_init(struct thread_map *map, int i)
+static void comm_init(struct perf_thread_map *map, int i)
 {
-	pid_t pid = thread_map__pid(map, i);
+	pid_t pid = perf_thread_map__pid(map, i);
 	char *comm = NULL;
 
 	/* dummy pid comm initialization */
@@ -420,7 +360,7 @@
 	map->map[i].comm = comm;
 }
 
-void thread_map__read_comms(struct thread_map *threads)
+void thread_map__read_comms(struct perf_thread_map *threads)
 {
 	int i;
 
@@ -428,24 +368,24 @@
 		comm_init(threads, i);
 }
 
-static void thread_map__copy_event(struct thread_map *threads,
-				   struct thread_map_event *event)
+static void thread_map__copy_event(struct perf_thread_map *threads,
+				   struct perf_record_thread_map *event)
 {
 	unsigned i;
 
 	threads->nr = (int) event->nr;
 
 	for (i = 0; i < event->nr; i++) {
-		thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
+		perf_thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
 		threads->map[i].comm = strndup(event->entries[i].comm, 16);
 	}
 
 	refcount_set(&threads->refcnt, 1);
 }
 
-struct thread_map *thread_map__new_event(struct thread_map_event *event)
+struct perf_thread_map *thread_map__new_event(struct perf_record_thread_map *event)
 {
-	struct thread_map *threads;
+	struct perf_thread_map *threads;
 
 	threads = thread_map__alloc(event->nr);
 	if (threads)
@@ -454,7 +394,7 @@
 	return threads;
 }
 
-bool thread_map__has(struct thread_map *threads, pid_t pid)
+bool thread_map__has(struct perf_thread_map *threads, pid_t pid)
 {
 	int i;
 
@@ -466,7 +406,7 @@
 	return false;
 }
 
-int thread_map__remove(struct thread_map *threads, int idx)
+int thread_map__remove(struct perf_thread_map *threads, int idx)
 {
 	int i;
 
@@ -479,7 +419,7 @@
 	/*
 	 * Free the 'idx' item and shift the rest up.
 	 */
-	free(threads->map[idx].comm);
+	zfree(&threads->map[idx].comm);
 
 	for (i = idx; i < threads->nr - 1; i++)
 		threads->map[i] = threads->map[i + 1];
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 2f689c9..3bb860a 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -5,61 +5,27 @@
 #include <sys/types.h>
 #include <stdio.h>
 #include <linux/refcount.h>
+#include <internal/threadmap.h>
+#include <perf/threadmap.h>
 
-struct thread_map_data {
-	pid_t    pid;
-	char	*comm;
-};
+struct perf_record_thread_map;
 
-struct thread_map {
-	refcount_t refcnt;
-	int nr;
-	int err_thread;
-	struct thread_map_data map[];
-};
+struct perf_thread_map *thread_map__new_dummy(void);
+struct perf_thread_map *thread_map__new_by_pid(pid_t pid);
+struct perf_thread_map *thread_map__new_by_tid(pid_t tid);
+struct perf_thread_map *thread_map__new_by_uid(uid_t uid);
+struct perf_thread_map *thread_map__new_all_cpus(void);
+struct perf_thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+struct perf_thread_map *thread_map__new_event(struct perf_record_thread_map *event);
 
-struct thread_map_event;
-
-struct thread_map *thread_map__new_dummy(void);
-struct thread_map *thread_map__new_by_pid(pid_t pid);
-struct thread_map *thread_map__new_by_tid(pid_t tid);
-struct thread_map *thread_map__new_by_uid(uid_t uid);
-struct thread_map *thread_map__new_all_cpus(void);
-struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
-struct thread_map *thread_map__new_event(struct thread_map_event *event);
-
-struct thread_map *thread_map__get(struct thread_map *map);
-void thread_map__put(struct thread_map *map);
-
-struct thread_map *thread_map__new_str(const char *pid,
+struct perf_thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid, bool all_threads);
 
-struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
+struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str);
 
-size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
+size_t thread_map__fprintf(struct perf_thread_map *threads, FILE *fp);
 
-static inline int thread_map__nr(struct thread_map *threads)
-{
-	return threads ? threads->nr : 1;
-}
-
-static inline pid_t thread_map__pid(struct thread_map *map, int thread)
-{
-	return map->map[thread].pid;
-}
-
-static inline void
-thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
-{
-	map->map[thread].pid = pid;
-}
-
-static inline char *thread_map__comm(struct thread_map *map, int thread)
-{
-	return map->map[thread].comm;
-}
-
-void thread_map__read_comms(struct thread_map *threads);
-bool thread_map__has(struct thread_map *threads, pid_t pid);
-int thread_map__remove(struct thread_map *threads, int idx);
+void thread_map__read_comms(struct perf_thread_map *threads);
+bool thread_map__has(struct perf_thread_map *threads, pid_t pid);
+int thread_map__remove(struct perf_thread_map *threads, int idx);
 #endif	/* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
index 6193b46..9796a2e 100644
--- a/tools/perf/util/time-utils.c
+++ b/tools/perf/util/time-utils.c
@@ -1,16 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdlib.h>
 #include <string.h>
+#include <linux/string.h>
 #include <sys/time.h>
 #include <linux/time64.h>
 #include <time.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <math.h>
+#include <linux/ctype.h>
 
-#include "perf.h"
 #include "debug.h"
 #include "time-utils.h"
+#include "session.h"
+#include "evlist.h"
 
 int parse_nsec_time(const char *str, u64 *ptime)
 {
@@ -114,6 +117,66 @@
 	return rc;
 }
 
+static int perf_time__parse_strs(struct perf_time_interval *ptime,
+				 const char *ostr, int size)
+{
+	const char *cp;
+	char *str, *arg, *p;
+	int i, num = 0, rc = 0;
+
+	/* Count the commas */
+	for (cp = ostr; *cp; cp++)
+		num += !!(*cp == ',');
+
+	if (!num)
+		return -EINVAL;
+
+	BUG_ON(num > size);
+
+	str = strdup(ostr);
+	if (!str)
+		return -ENOMEM;
+
+	/* Split the string and parse each piece, except the last */
+	for (i = 0, p = str; i < num - 1; i++) {
+		arg = p;
+		/* Find next comma, there must be one */
+		p = skip_spaces(strchr(p, ',') + 1);
+		/* Skip the value, must not contain space or comma */
+		while (*p && !isspace(*p)) {
+			if (*p++ == ',') {
+				rc = -EINVAL;
+				goto out;
+			}
+		}
+		/* Split and parse */
+		if (*p)
+			*p++ = 0;
+		rc = perf_time__parse_str(ptime + i, arg);
+		if (rc < 0)
+			goto out;
+	}
+
+	/* Parse the last piece */
+	rc = perf_time__parse_str(ptime + i, p);
+	if (rc < 0)
+		goto out;
+
+	/* Check there is no overlap */
+	for (i = 0; i < num - 1; i++) {
+		if (ptime[i].end >= ptime[i + 1].start) {
+			rc = -EINVAL;
+			goto out;
+		}
+	}
+
+	rc = num;
+out:
+	free(str);
+
+	return rc;
+}
+
 static int parse_percent(double *pcnt, char *str)
 {
 	char *c, *endptr;
@@ -133,12 +196,30 @@
 	return 0;
 }
 
+static int set_percent_time(struct perf_time_interval *ptime, double start_pcnt,
+			    double end_pcnt, u64 start, u64 end)
+{
+	u64 total = end - start;
+
+	if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
+	    end_pcnt < 0.0 || end_pcnt > 1.0) {
+		return -1;
+	}
+
+	ptime->start = start + round(start_pcnt * total);
+	ptime->end = start + round(end_pcnt * total);
+
+	if (ptime->end > ptime->start && ptime->end != end)
+		ptime->end -= 1;
+
+	return 0;
+}
+
 static int percent_slash_split(char *str, struct perf_time_interval *ptime,
 			       u64 start, u64 end)
 {
 	char *p, *end_str;
 	double pcnt, start_pcnt, end_pcnt;
-	u64 total = end - start;
 	int i;
 
 	/*
@@ -166,15 +247,7 @@
 	start_pcnt = pcnt * (i - 1);
 	end_pcnt = pcnt * i;
 
-	if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
-	    end_pcnt < 0.0 || end_pcnt > 1.0) {
-		return -1;
-	}
-
-	ptime->start = start + round(start_pcnt * total);
-	ptime->end = start + round(end_pcnt * total);
-
-	return 0;
+	return set_percent_time(ptime, start_pcnt, end_pcnt, start, end);
 }
 
 static int percent_dash_split(char *str, struct perf_time_interval *ptime,
@@ -182,7 +255,6 @@
 {
 	char *start_str = NULL, *end_str;
 	double start_pcnt, end_pcnt;
-	u64 total = end - start;
 	int ret;
 
 	/*
@@ -201,16 +273,7 @@
 
 	free(start_str);
 
-	if (start_pcnt < 0.0 || start_pcnt > 1.0 ||
-	    end_pcnt < 0.0 || end_pcnt > 1.0 ||
-	    start_pcnt > end_pcnt) {
-		return -1;
-	}
-
-	ptime->start = start + round(start_pcnt * total);
-	ptime->end = start + round(end_pcnt * total);
-
-	return 0;
+	return set_percent_time(ptime, start_pcnt, end_pcnt, start, end);
 }
 
 typedef int (*time_pecent_split)(char *, struct perf_time_interval *,
@@ -374,7 +437,7 @@
 	struct perf_time_interval *ptime;
 	int i;
 
-	if ((timestamp == 0) || (num == 0))
+	if ((!ptime_buf) || (timestamp == 0) || (num == 0))
 		return false;
 
 	if (num == 1)
@@ -387,13 +450,58 @@
 		ptime = &ptime_buf[i];
 
 		if (timestamp >= ptime->start &&
-		    ((timestamp < ptime->end && i < num - 1) ||
-		     (timestamp <= ptime->end && i == num - 1))) {
-			break;
+		    (timestamp <= ptime->end || !ptime->end)) {
+			return false;
 		}
 	}
 
-	return (i == num) ? true : false;
+	return true;
+}
+
+int perf_time__parse_for_ranges(const char *time_str,
+				struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num)
+{
+	bool has_percent = strchr(time_str, '%');
+	struct perf_time_interval *ptime_range;
+	int size, num, ret = -EINVAL;
+
+	ptime_range = perf_time__range_alloc(time_str, &size);
+	if (!ptime_range)
+		return -ENOMEM;
+
+	if (has_percent) {
+		if (session->evlist->first_sample_time == 0 &&
+		    session->evlist->last_sample_time == 0) {
+			pr_err("HINT: no first/last sample time found in perf data.\n"
+			       "Please use latest perf binary to execute 'perf record'\n"
+			       "(if '--buildid-all' is enabled, please set '--timestamp-boundary').\n");
+			goto error;
+		}
+
+		num = perf_time__percent_parse_str(
+				ptime_range, size,
+				time_str,
+				session->evlist->first_sample_time,
+				session->evlist->last_sample_time);
+	} else {
+		num = perf_time__parse_strs(ptime_range, time_str, size);
+	}
+
+	if (num < 0)
+		goto error_invalid;
+
+	*range_size = size;
+	*range_num = num;
+	*ranges = ptime_range;
+	return 0;
+
+error_invalid:
+	pr_err("Invalid time string\n");
+error:
+	free(ptime_range);
+	return ret;
 }
 
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
@@ -404,6 +512,14 @@
 	return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
 }
 
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz)
+{
+	u64 sec  = timestamp / NSEC_PER_SEC,
+	    nsec = timestamp % NSEC_PER_SEC;
+
+	return scnprintf(buf, sz, "%" PRIu64 ".%09" PRIu64, sec, nsec);
+}
+
 int fetch_current_timestamp(char *buf, size_t sz)
 {
 	struct timeval tv;
diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h
index 70b177d..4f42988 100644
--- a/tools/perf/util/time-utils.h
+++ b/tools/perf/util/time-utils.h
@@ -3,6 +3,7 @@
 #define _TIME_UTILS_H_
 
 #include <stddef.h>
+#include <time.h>
 #include <linux/types.h>
 
 struct perf_time_interval {
@@ -23,8 +24,23 @@
 bool perf_time__ranges_skip_sample(struct perf_time_interval *ptime_buf,
 				   int num, u64 timestamp);
 
+struct perf_session;
+
+int perf_time__parse_for_ranges(const char *str, struct perf_session *session,
+				struct perf_time_interval **ranges,
+				int *range_size, int *range_num);
+
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int timestamp__scnprintf_nsec(u64 timestamp, char *buf, size_t sz);
 
 int fetch_current_timestamp(char *buf, size_t sz);
 
+static inline unsigned long long rdclock(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
+}
+
 #endif
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 183c914..2abbf66 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -8,8 +8,8 @@
 
 struct perf_session;
 union perf_event;
-struct perf_evlist;
-struct perf_evsel;
+struct evlist;
+struct evsel;
 struct perf_sample;
 struct perf_tool;
 struct machine;
@@ -17,24 +17,22 @@
 
 typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
 			    struct perf_sample *sample,
-			    struct perf_evsel *evsel, struct machine *machine);
+			    struct evsel *evsel, struct machine *machine);
 
 typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
 			struct perf_sample *sample, struct machine *machine);
 
 typedef int (*event_attr_op)(struct perf_tool *tool,
 			     union perf_event *event,
-			     struct perf_evlist **pevlist);
+			     struct evlist **pevlist);
 
-typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
+typedef int (*event_op2)(struct perf_session *session, union perf_event *event);
+typedef s64 (*event_op3)(struct perf_session *session, union perf_event *event);
+typedef int (*event_op4)(struct perf_session *session, union perf_event *event, u64 data);
 
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
-typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
-			 struct perf_session *session);
-
 enum show_feature_header {
 	SHOW_FEAT_NO_HEADER = 0,
 	SHOW_FEAT_HEADER,
@@ -56,7 +54,10 @@
 			itrace_start,
 			context_switch,
 			throttle,
-			unthrottle;
+			unthrottle,
+			ksymbol,
+			bpf;
+
 	event_attr_op	attr;
 	event_attr_op	event_update;
 	event_op2	tracing_data;
@@ -72,6 +73,7 @@
 			stat,
 			stat_round,
 			feature;
+	event_op4	compressed;
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 8e517de..3dce2de 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -1,18 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  *
  * Refactored from builtin-top.c, see that files for further copyright notes.
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
-#include "cpumap.h"
 #include "event.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "parse-events.h"
 #include "symbol.h"
 #include "top.h"
+#include "../perf.h"
 #include <inttypes.h>
 
 #define SNPRINTF(buf, size, fmt, args...) \
@@ -46,8 +45,9 @@
 							samples_per_sec;
 		ret = SNPRINTF(bf, size,
 			       "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
-			       "  exact: %4.1f%% [", samples_per_sec,
-			       ksamples_percent, esamples_percent);
+			       "  exact: %4.1f%% lost: %" PRIu64 "/%" PRIu64 " drop: %" PRIu64 "/%" PRIu64 " [",
+			       samples_per_sec, ksamples_percent, esamples_percent,
+			       top->lost, top->lost_total, top->drop, top->drop_total);
 	} else {
 		float us_samples_per_sec = top->us_samples / top->delay_secs;
 		float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
@@ -70,10 +70,10 @@
 			       esamples_percent);
 	}
 
-	if (top->evlist->nr_entries == 1) {
-		struct perf_evsel *first = perf_evlist__first(top->evlist);
+	if (top->evlist->core.nr_entries == 1) {
+		struct evsel *first = evlist__first(top->evlist);
 		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
-				(uint64_t)first->attr.sample_period,
+				(uint64_t)first->core.attr.sample_period,
 				opts->freq ? "Hz" : "");
 	}
 
@@ -95,17 +95,18 @@
 
 	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
-				top->evlist->cpus->nr > 1 ? "s" : "",
+				top->evlist->core.cpus->nr > 1 ? "s" : "",
 				target->cpu_list);
 	else {
 		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
-					top->evlist->cpus->nr,
-					top->evlist->cpus->nr > 1 ? "s" : "");
+					top->evlist->core.cpus->nr,
+					top->evlist->core.cpus->nr > 1 ? "s" : "");
 	}
 
+	perf_top__reset_sample_counters(top);
 	return ret;
 }
 
@@ -113,5 +114,5 @@
 {
 	top->samples = top->us_samples = top->kernel_samples =
 	top->exact_samples = top->guest_kernel_samples =
-	top->guest_us_samples = 0;
+	top->guest_us_samples = top->lost = top->drop = 0;
 }
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 9add1f7..f117d4f 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -3,26 +3,30 @@
 #define __PERF_TOP_H 1
 
 #include "tool.h"
+#include "evswitch.h"
 #include "annotate.h"
+#include "ordered-events.h"
+#include "record.h"
 #include <linux/types.h>
 #include <stddef.h>
 #include <stdbool.h>
 #include <sys/ioctl.h>
 
-struct perf_evlist;
-struct perf_evsel;
+struct evlist;
+struct evsel;
 struct perf_session;
 
 struct perf_top {
 	struct perf_tool   tool;
-	struct perf_evlist *evlist;
+	struct evlist *evlist;
 	struct record_opts record_opts;
 	struct annotation_options annotation_opts;
+	struct evswitch	   evswitch;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.
 	 */
-	u64		   samples;
+	u64		   samples, lost, lost_total, drop, drop_total;
 	u64		   kernel_samples, us_samples;
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
@@ -33,13 +37,21 @@
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
 	struct hist_entry  *sym_filter_entry;
-	struct perf_evsel  *sym_evsel;
+	struct evsel 	   *sym_evsel;
 	struct perf_session *session;
 	struct winsize	   winsize;
 	int		   realtime_prio;
 	const char	   *sym_filter;
 	float		   min_percent;
 	unsigned int	   nr_threads_synthesize;
+
+	struct {
+		struct ordered_events	*in;
+		struct ordered_events	 data[2];
+		bool			 rotate;
+		pthread_mutex_t		 mutex;
+		pthread_cond_t		 cond;
+	} qe;
 };
 
 #define CONSOLE_CLEAR ""
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 8ad8e75..086e98f 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -1,24 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2008,2009, Steven Rostedt <srostedt@redhat.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#include "util.h"
 #include <dirent.h>
 #include <mntent.h>
 #include <stdio.h>
@@ -34,8 +17,9 @@
 #include <stdbool.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
+#include <internal/lib.h> // page_size
 
-#include "../perf.h"
 #include "trace-event.h"
 #include <api/fs/tracing_path.h>
 #include "evsel.h"
@@ -420,11 +404,11 @@
 get_tracepoints_path(struct list_head *pattrs)
 {
 	struct tracepoint_path path, *ppath = &path;
-	struct perf_evsel *pos;
+	struct evsel *pos;
 	int nr_tracepoints = 0;
 
-	list_for_each_entry(pos, pattrs, node) {
-		if (pos->attr.type != PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, core.node) {
+		if (pos->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 		++nr_tracepoints;
 
@@ -440,7 +424,7 @@
 		}
 
 try_id:
-		ppath->next = tracepoint_id_to_path(pos->attr.config);
+		ppath->next = tracepoint_id_to_path(pos->core.attr.config);
 		if (!ppath->next) {
 error:
 			pr_debug("No memory to alloc tracepoints list\n");
@@ -456,10 +440,10 @@
 
 bool have_tracepoints(struct list_head *pattrs)
 {
-	struct perf_evsel *pos;
+	struct evsel *pos;
 
-	list_for_each_entry(pos, pattrs, node)
-		if (pos->attr.type == PERF_TYPE_TRACEPOINT)
+	list_for_each_entry(pos, pattrs, core.node)
+		if (pos->core.attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 
 	return false;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index b15a9bf..9634f0a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1,46 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009, Steven Rostedt <srostedt@redhat.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
 
-#include "../perf.h"
 #include "debug.h"
 #include "trace-event.h"
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 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 *event;
+	struct tep_format_field *field;
 
 	if (!*size) {
-		if (!pevent->events)
+
+		event = tep_get_first_event(pevent);
+		if (!event)
 			return 0;
 
-		event = pevent->events[0];
 		field = tep_find_common_field(event, type);
 		if (!field)
 			return 0;
@@ -94,9 +78,9 @@
 }
 
 unsigned long long
-raw_field_value(struct event_format *event, const char *name, void *data)
+raw_field_value(struct tep_event *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 +92,12 @@
 	return val;
 }
 
-unsigned long long read_size(struct event_format *event, void *ptr, int size)
+unsigned long long read_size(struct tep_event *event, void *ptr, int size)
 {
-	return tep_read_number(event->pevent, ptr, size);
+	return tep_read_number(event->tep, ptr, size);
 }
 
-void event_format__fprintf(struct event_format *event,
+void event_format__fprintf(struct tep_event *event,
 			   int cpu, void *data, int size, FILE *fp)
 {
 	struct tep_record record;
@@ -125,12 +109,12 @@
 	record.data = data;
 
 	trace_seq_init(&s);
-	tep_event_info(&s, event, &record);
+	tep_print_event(event->tep, &s, &record, "%s", TEP_PRINT_INFO);
 	trace_seq_do_fprintf(&s, fp);
 	trace_seq_destroy(&s);
 }
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event *event,
 			 int cpu, void *data, int size)
 {
 	return event_format__fprintf(event, cpu, data, size, stdout);
@@ -189,33 +173,6 @@
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct event_format *trace_find_next_event(struct tep_handle *pevent,
-					   struct event_format *event)
-{
-	static int idx;
-
-	if (!pevent || !pevent->events)
-		return NULL;
-
-	if (!event) {
-		idx = 0;
-		return pevent->events[0];
-	}
-
-	if (idx < pevent->nr_events && event == pevent->events[idx]) {
-		idx++;
-		if (idx == pevent->nr_events)
-			return NULL;
-		return pevent->events[idx];
-	}
-
-	for (idx = 1; idx < pevent->nr_events; idx++) {
-		if (event == pevent->events[idx - 1])
-			return pevent->events[idx];
-	}
-	return NULL;
-}
-
 struct flag {
 	const char *name;
 	unsigned long long value;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 5eb1b24..8593d3c 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -1,22 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2009, Steven Rostedt <srostedt@redhat.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License (not later!)
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 #include <dirent.h>
 #include <stdio.h>
@@ -31,8 +15,6 @@
 #include <unistd.h>
 #include <errno.h>
 
-#include "../perf.h"
-#include "util.h"
 #include "trace-event.h"
 #include "debug.h"
 
@@ -102,7 +84,7 @@
 
 	if (do_read(&data, 4) < 0)
 		return 0;
-	return __data2host4(pevent, data);
+	return tep_read_number(pevent, &data, 4);
 }
 
 static unsigned long long read8(struct tep_handle *pevent)
@@ -111,7 +93,7 @@
 
 	if (do_read(&data, 8) < 0)
 		return 0;
-	return __data2host8(pevent, data);
+	return tep_read_number(pevent, &data, 8);
 }
 
 static char *read_string(void)
@@ -241,7 +223,7 @@
 		 * The commit field in the page is of type long,
 		 * use that instead, since it represents the kernel.
 		 */
-		tep_set_long_size(pevent, pevent->header_page_size_size);
+		tep_set_long_size(pevent, tep_get_header_page_size(pevent));
 	}
 	free(header_page);
 
@@ -297,10 +279,8 @@
 	}
 
 	ret = do_read(buf, size);
-	if (ret < 0) {
-		free(buf);
+	if (ret < 0)
 		goto out;
-	}
 
 	ret = parse_event_file(pevent, buf, size, sys);
 	if (ret < 0)
@@ -444,7 +424,7 @@
 
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, file_bigendian);
-	tep_set_host_bigendian(pevent, host_bigendian);
+	tep_set_local_bigendian(pevent, host_bigendian);
 
 	if (do_read(buf, 1) < 0)
 		goto out;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index b749f81..714581b 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -1,22 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * trace-event-scripting.  Scripting engine common and initialization code.
  *
  * Copyright (C) 2009-2010 Tom Zanussi <tzanussi@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
  */
 
 #include <stdio.h>
@@ -24,10 +10,9 @@
 #include <string.h>
 #include <errno.h>
 
-#include "../perf.h"
 #include "debug.h"
-#include "util.h"
 #include "trace-event.h"
+#include <linux/zalloc.h>
 
 struct scripting_context *scripting_context;
 
@@ -43,7 +28,7 @@
 
 static void process_event_unsupported(union perf_event *event __maybe_unused,
 				      struct perf_sample *sample __maybe_unused,
-				      struct perf_evsel *evsel __maybe_unused,
+				      struct evsel *evsel __maybe_unused,
 				      struct addr_location *al __maybe_unused)
 {
 }
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 58bb72f..b3ee651 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -14,7 +14,6 @@
 #include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
-#include "util.h"
 
 /*
  * global trace_event object used by trace_event__tp_format
@@ -40,7 +39,7 @@
 
 static int trace_event__init2(void)
 {
-	int be = tep_host_bigendian();
+	int be = tep_is_bigendian();
 	struct tep_handle *pevent;
 
 	if (trace_event__init(&tevent))
@@ -49,7 +48,7 @@
 	pevent = tevent.pevent;
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, be);
-	tep_set_host_bigendian(pevent, be);
+	tep_set_local_bigendian(pevent, be);
 	tevent_initialized = true;
 	return 0;
 }
@@ -72,12 +71,12 @@
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-static struct event_format*
+static struct tep_event*
 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 *event = NULL;
 	char path[PATH_MAX];
 	size_t size;
 	char *data;
@@ -102,7 +101,7 @@
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
-struct event_format*
+struct tep_event*
 trace_event__tp_format(const char *sys, const char *name)
 {
 	if (!tevent_initialized && trace_event__init2())
@@ -111,7 +110,7 @@
 	return tp_format(sys, name);
 }
 
-struct event_format *trace_event__tp_format_id(int id)
+struct tep_event *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 40204ec..72fdf2a 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -10,28 +10,28 @@
 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*
 trace_event__tp_format(const char *sys, const char *name);
 
-struct event_format *trace_event__tp_format_id(int id);
+struct tep_event *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 *event,
 			   int cpu, void *data, int size, FILE *fp);
 
-void event_format__print(struct event_format *event,
+void event_format__print(struct tep_event *event,
 			 int cpu, void *data, int size);
 
 int parse_ftrace_file(struct tep_handle *pevent, char *buf, unsigned long size);
@@ -39,7 +39,7 @@
 		     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 *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);
@@ -47,9 +47,7 @@
 
 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);
+unsigned long long read_size(struct tep_event *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);
@@ -78,10 +76,13 @@
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
-			       struct perf_evsel *evsel,
+			       struct evsel *evsel,
 			       struct addr_location *al);
+	void (*process_switch)(union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
 	void (*process_stat)(struct perf_stat_config *config,
-			     struct perf_evsel *evsel, u64 tstamp);
+			     struct evsel *evsel, u64 tstamp);
 	void (*process_stat_interval)(u64 tstamp);
 	int (*generate_script) (struct tep_handle *pevent, const char *outfile);
 };
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
index 88223bc..33e997f 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -2,7 +2,6 @@
 #ifndef __TRIGGER_H_
 #define __TRIGGER_H_ 1
 
-#include "util/debug.h"
 #include "asm/bug.h"
 
 /*
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index e0c3af3..3c5a632 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -4,13 +4,12 @@
 
 #include <linux/types.h>
 
-#include "event.h"
-
 struct perf_tsc_conversion {
 	u16 time_shift;
 	u32 time_mult;
 	u64 time_zero;
 };
+
 struct perf_event_mmap_page;
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
@@ -20,13 +19,4 @@
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
 
-struct perf_event_mmap_page;
-struct perf_tool;
-struct machine;
-
-int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
-				struct perf_tool *tool,
-				perf_event__handler_t process,
-				struct machine *machine);
-
-#endif
+#endif // __PERF_TSC_H
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5eff9bf..15f6e46 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -5,15 +5,18 @@
 #include <inttypes.h>
 #include <errno.h>
 #include "debug.h"
+#include "dso.h"
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "thread.h"
 #include <linux/types.h>
+#include <linux/zalloc.h>
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
-#include "util.h"
 
 static char *debuginfo_path;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 79f521a..1800887 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -25,6 +25,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
@@ -34,8 +35,8 @@
 #include "session.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "map.h"
 #include "symbol.h"
-#include "util.h"
 #include "debug.h"
 #include "asm/bug.h"
 #include "dso.h"
@@ -344,7 +345,7 @@
 							__func__,
 							dso->symsrc_filename,
 							debuglink);
-					free(dso->symsrc_filename);
+					zfree(&dso->symsrc_filename);
 				}
 				dso->symsrc_filename = debuglink;
 			} else {
@@ -614,32 +615,26 @@
 	.get_proc_name		= get_proc_name,
 };
 
-static int _unwind__prepare_access(struct thread *thread)
+static int _unwind__prepare_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return 0;
-	thread->addr_space = unw_create_addr_space(&accessors, 0);
-	if (!thread->addr_space) {
+	mg->addr_space = unw_create_addr_space(&accessors, 0);
+	if (!mg->addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
 		return -ENOMEM;
 	}
 
-	unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
+	unw_set_caching_policy(mg->addr_space, UNW_CACHE_GLOBAL);
 	return 0;
 }
 
-static void _unwind__flush_access(struct thread *thread)
+static void _unwind__flush_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-	unw_flush_cache(thread->addr_space, 0, 0);
+	unw_flush_cache(mg->addr_space, 0, 0);
 }
 
-static void _unwind__finish_access(struct thread *thread)
+static void _unwind__finish_access(struct map_groups *mg)
 {
-	if (!dwarf_callchain_users)
-		return;
-	unw_destroy_addr_space(thread->addr_space);
+	unw_destroy_addr_space(mg->addr_space);
 }
 
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
@@ -664,7 +659,7 @@
 	 */
 	if (max_stack - 1 > 0) {
 		WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
-		addr_space = ui->thread->addr_space;
+		addr_space = ui->thread->mg->addr_space;
 
 		if (addr_space == NULL)
 			return -1;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index b029a5e..a24fb57 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,21 +1,24 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "unwind.h"
+#include "dso.h"
+#include "map.h"
 #include "thread.h"
 #include "session.h"
 #include "debug.h"
 #include "env.h"
+#include "callchain.h"
 
 struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops;
 
-static void unwind__register_ops(struct thread *thread,
+static void unwind__register_ops(struct map_groups *mg,
 			  struct unwind_libunwind_ops *ops)
 {
-	thread->unwind_libunwind_ops = ops;
+	mg->unwind_libunwind_ops = ops;
 }
 
-int unwind__prepare_access(struct thread *thread, struct map *map,
+int unwind__prepare_access(struct map_groups *mg, struct map *map,
 			   bool *initialized)
 {
 	const char *arch;
@@ -23,7 +26,10 @@
 	struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops;
 	int err;
 
-	if (thread->addr_space) {
+	if (!dwarf_callchain_users)
+		return 0;
+
+	if (mg->addr_space) {
 		pr_debug("unwind: thread map already set, dso=%s\n",
 			 map->dso->name);
 		if (initialized)
@@ -32,14 +38,14 @@
 	}
 
 	/* env->arch is NULL for live-mode (i.e. perf top) */
-	if (!thread->mg->machine->env || !thread->mg->machine->env->arch)
+	if (!mg->machine->env || !mg->machine->env->arch)
 		goto out_register;
 
-	dso_type = dso__type(map->dso, thread->mg->machine);
+	dso_type = dso__type(map->dso, mg->machine);
 	if (dso_type == DSO__TYPE_UNKNOWN)
 		return 0;
 
-	arch = perf_env__arch(thread->mg->machine->env);
+	arch = perf_env__arch(mg->machine->env);
 
 	if (!strcmp(arch, "x86")) {
 		if (dso_type != DSO__TYPE_64BIT)
@@ -54,31 +60,31 @@
 		return 0;
 	}
 out_register:
-	unwind__register_ops(thread, ops);
+	unwind__register_ops(mg, ops);
 
-	err = thread->unwind_libunwind_ops->prepare_access(thread);
+	err = mg->unwind_libunwind_ops->prepare_access(mg);
 	if (initialized)
 		*initialized = err ? false : true;
 	return err;
 }
 
-void unwind__flush_access(struct thread *thread)
+void unwind__flush_access(struct map_groups *mg)
 {
-	if (thread->unwind_libunwind_ops)
-		thread->unwind_libunwind_ops->flush_access(thread);
+	if (mg->unwind_libunwind_ops)
+		mg->unwind_libunwind_ops->flush_access(mg);
 }
 
-void unwind__finish_access(struct thread *thread)
+void unwind__finish_access(struct map_groups *mg)
 {
-	if (thread->unwind_libunwind_ops)
-		thread->unwind_libunwind_ops->finish_access(thread);
+	if (mg->unwind_libunwind_ops)
+		mg->unwind_libunwind_ops->finish_access(mg);
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			 struct thread *thread,
 			 struct perf_sample *data, int max_stack)
 {
-	if (thread->unwind_libunwind_ops)
-		return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+	if (thread->mg->unwind_libunwind_ops)
+		return thread->mg->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
 	return 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 8a44a15..3a7d00c 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 
 struct map;
+struct map_groups;
 struct perf_sample;
 struct symbol;
 struct thread;
@@ -19,9 +20,9 @@
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 struct unwind_libunwind_ops {
-	int (*prepare_access)(struct thread *thread);
-	void (*flush_access)(struct thread *thread);
-	void (*finish_access)(struct thread *thread);
+	int (*prepare_access)(struct map_groups *mg);
+	void (*flush_access)(struct map_groups *mg);
+	void (*finish_access)(struct map_groups *mg);
 	int (*get_entries)(unwind_entry_cb_t cb, void *arg,
 			   struct thread *thread,
 			   struct perf_sample *data, int max_stack);
@@ -46,20 +47,20 @@
 #endif
 
 int LIBUNWIND__ARCH_REG_ID(int regnum);
-int unwind__prepare_access(struct thread *thread, struct map *map,
+int unwind__prepare_access(struct map_groups *mg, struct map *map,
 			   bool *initialized);
-void unwind__flush_access(struct thread *thread);
-void unwind__finish_access(struct thread *thread);
+void unwind__flush_access(struct map_groups *mg);
+void unwind__finish_access(struct map_groups *mg);
 #else
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused,
 					 struct map *map __maybe_unused,
 					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
 
-static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
-static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {}
+static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {}
 #endif
 #else
 static inline int
@@ -72,14 +73,14 @@
 	return 0;
 }
 
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+static inline int unwind__prepare_access(struct map_groups *mg __maybe_unused,
 					 struct map *map __maybe_unused,
 					 bool *initialized __maybe_unused)
 {
 	return 0;
 }
 
-static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
-static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
+static inline void unwind__flush_access(struct map_groups *mg __maybe_unused) {}
+static inline void unwind__finish_access(struct map_groups *mg __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 070d25c..196438e 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -8,7 +8,9 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "util.h"
-#include "debug.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
 
 static __noreturn void usage_builtin(const char *err)
 {
diff --git a/tools/perf/util/util-cxx.h b/tools/perf/util/util-cxx.h
deleted file mode 100644
index 80a99e4..0000000
--- a/tools/perf/util/util-cxx.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Support C++ source use utilities defined in util.h
- */
-
-#ifndef PERF_UTIL_UTIL_CXX_H
-#define PERF_UTIL_UTIL_CXX_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/*
- * Now 'new' is the only C++ keyword found in util.h:
- * in tools/include/linux/rbtree.h
- *
- * Other keywords, like class and delete, should be
- * redefined if necessary.
- */
-#define new _new
-#include "util.h"
-#undef new
-
-#ifdef __cplusplus
-}
-#endif
-#endif
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eac5b85..ae56c76 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../perf.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 #include <api/fs/fs.h>
-#include <sys/mman.h>
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <dirent.h>
@@ -15,11 +14,14 @@
 #include <string.h>
 #include <errno.h>
 #include <limits.h>
+#include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/time64.h>
 #include <unistd.h>
+#include "cap.h"
 #include "strlist.h"
+#include "string2.h"
 
 /*
  * XXX We need to find a better place for these things...
@@ -37,28 +39,6 @@
 	perf_singlethreaded = false;
 }
 
-unsigned int page_size;
-
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
-	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-		pr_debug("cannot determine cache line size");
-}
-#endif
-
-int cacheline_size(void)
-{
-	static int size;
-
-	if (!size)
-		cache_line_size(&size);
-
-	return size;
-}
-
 int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
@@ -116,23 +96,69 @@
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-int rm_rf(const char *path)
+static bool match_pat(char *file, const char **pat)
+{
+	int i = 0;
+
+	if (!pat)
+		return true;
+
+	while (pat[i]) {
+		if (strglobmatch(file, pat[i]))
+			return true;
+
+		i++;
+	}
+
+	return false;
+}
+
+/*
+ * The depth specify how deep the removal will go.
+ * 0       - will remove only files under the 'path' directory
+ * 1 .. x  - will dive in x-level deep under the 'path' directory
+ *
+ * If specified the pat is array of string patterns ended with NULL,
+ * which are checked upon every file/directory found. Only matching
+ * ones are removed.
+ *
+ * The function returns:
+ *    0 on success
+ *   -1 on removal failure with errno set
+ *   -2 on pattern failure
+ */
+static int rm_rf_depth_pat(const char *path, int depth, const char **pat)
 {
 	DIR *dir;
-	int ret = 0;
+	int ret;
 	struct dirent *d;
 	char namebuf[PATH_MAX];
+	struct stat statbuf;
 
-	dir = opendir(path);
-	if (dir == NULL)
+	/* Do not fail if there's no file. */
+	ret = lstat(path, &statbuf);
+	if (ret)
 		return 0;
 
+	/* Try to remove any file we get. */
+	if (!(statbuf.st_mode & S_IFDIR))
+		return unlink(path);
+
+	/* We have directory in path. */
+	dir = opendir(path);
+	if (dir == NULL)
+		return -1;
+
 	while ((d = readdir(dir)) != NULL && !ret) {
-		struct stat statbuf;
 
 		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
 			continue;
 
+		if (!match_pat(d->d_name, pat)) {
+			ret =  -2;
+			break;
+		}
+
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
 
@@ -144,7 +170,7 @@
 		}
 
 		if (S_ISDIR(statbuf.st_mode))
-			ret = rm_rf(namebuf);
+			ret = depth ? rm_rf_depth_pat(namebuf, depth - 1, pat) : 0;
 		else
 			ret = unlink(namebuf);
 	}
@@ -156,6 +182,22 @@
 	return rmdir(path);
 }
 
+int rm_rf_perf_data(const char *path)
+{
+	const char *pat[] = {
+		"header",
+		"data.*",
+		NULL,
+	};
+
+	return rm_rf_depth_pat(path, 0, pat);
+}
+
+int rm_rf(const char *path)
+{
+	return rm_rf_depth_pat(path, INT_MAX, NULL);
+}
+
 /* A filter which removes dot files */
 bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d)
 {
@@ -190,178 +232,6 @@
 	return list;
 }
 
-static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi)
-{
-	int err = -1;
-	char *line = NULL;
-	size_t n;
-	FILE *from_fp, *to_fp;
-	struct nscookie nsc;
-
-	nsinfo__mountns_enter(nsi, &nsc);
-	from_fp = fopen(from, "r");
-	nsinfo__mountns_exit(&nsc);
-	if (from_fp == NULL)
-		goto out;
-
-	to_fp = fopen(to, "w");
-	if (to_fp == NULL)
-		goto out_fclose_from;
-
-	while (getline(&line, &n, from_fp) > 0)
-		if (fputs(line, to_fp) == EOF)
-			goto out_fclose_to;
-	err = 0;
-out_fclose_to:
-	fclose(to_fp);
-	free(line);
-out_fclose_from:
-	fclose(from_fp);
-out:
-	return err;
-}
-
-static int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
-{
-	void *ptr;
-	loff_t pgoff;
-
-	pgoff = off_in & ~(page_size - 1);
-	off_in -= pgoff;
-
-	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
-	if (ptr == MAP_FAILED)
-		return -1;
-
-	while (size) {
-		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
-		if (ret < 0 && errno == EINTR)
-			continue;
-		if (ret <= 0)
-			break;
-
-		size -= ret;
-		off_in += ret;
-		off_out += ret;
-	}
-	munmap(ptr, off_in + size);
-
-	return size ? -1 : 0;
-}
-
-static int copyfile_mode_ns(const char *from, const char *to, mode_t mode,
-			    struct nsinfo *nsi)
-{
-	int fromfd, tofd;
-	struct stat st;
-	int err;
-	char *tmp = NULL, *ptr = NULL;
-	struct nscookie nsc;
-
-	nsinfo__mountns_enter(nsi, &nsc);
-	err = stat(from, &st);
-	nsinfo__mountns_exit(&nsc);
-	if (err)
-		goto out;
-	err = -1;
-
-	/* extra 'x' at the end is to reserve space for '.' */
-	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
-		tmp = NULL;
-		goto out;
-	}
-	ptr = strrchr(tmp, '/');
-	if (!ptr)
-		goto out;
-	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
-	*ptr = '.';
-
-	tofd = mkstemp(tmp);
-	if (tofd < 0)
-		goto out;
-
-	if (fchmod(tofd, mode))
-		goto out_close_to;
-
-	if (st.st_size == 0) { /* /proc? do it slowly... */
-		err = slow_copyfile(from, tmp, nsi);
-		goto out_close_to;
-	}
-
-	nsinfo__mountns_enter(nsi, &nsc);
-	fromfd = open(from, O_RDONLY);
-	nsinfo__mountns_exit(&nsc);
-	if (fromfd < 0)
-		goto out_close_to;
-
-	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
-
-	close(fromfd);
-out_close_to:
-	close(tofd);
-	if (!err)
-		err = link(tmp, to);
-	unlink(tmp);
-out:
-	free(tmp);
-	return err;
-}
-
-int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi)
-{
-	return copyfile_mode_ns(from, to, 0755, nsi);
-}
-
-int copyfile_mode(const char *from, const char *to, mode_t mode)
-{
-	return copyfile_mode_ns(from, to, mode, NULL);
-}
-
-int copyfile(const char *from, const char *to)
-{
-	return copyfile_mode(from, to, 0755);
-}
-
-static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
-{
-	void *buf_start = buf;
-	size_t left = n;
-
-	while (left) {
-		/* buf must be treated as const if !is_read. */
-		ssize_t ret = is_read ? read(fd, buf, left) :
-					write(fd, buf, left);
-
-		if (ret < 0 && errno == EINTR)
-			continue;
-		if (ret <= 0)
-			return ret;
-
-		left -= ret;
-		buf  += ret;
-	}
-
-	BUG_ON((size_t)(buf - buf_start) != n);
-	return n;
-}
-
-/*
- * Read exactly 'n' bytes or return an error.
- */
-ssize_t readn(int fd, void *buf, size_t n)
-{
-	return ion(true, fd, buf, n);
-}
-
-/*
- * Write exactly 'n' bytes or return an error.
- */
-ssize_t writen(int fd, const void *buf, size_t n)
-{
-	/* ion does not modify buf. */
-	return ion(false, fd, (void *)buf, n);
-}
-
 size_t hex_width(u64 v)
 {
 	size_t n = 1;
@@ -372,19 +242,6 @@
 	return n;
 }
 
-/*
- * While we find nice hex chars, build a long_val.
- * Return number of chars processed.
- */
-int hex2u64(const char *ptr, u64 *long_val)
-{
-	char *p;
-
-	*long_val = strtoull(ptr, &p, 16);
-
-	return p - ptr;
-}
-
 int perf_event_paranoid(void)
 {
 	int value;
@@ -394,6 +251,13 @@
 
 	return value;
 }
+
+bool perf_event_paranoid_check(int max_level)
+{
+	return perf_cap__capable(CAP_SYS_ADMIN) ||
+			perf_event_paranoid() <= max_level;
+}
+
 static int
 fetch_ubuntu_kernel_version(unsigned int *puint)
 {
@@ -506,3 +370,13 @@
 
 	return tip;
 }
+
+char *perf_exe(char *buf, int len)
+{
+	int n = readlink("/proc/self/exe", buf, len);
+	if (n > 0) {
+		buf[n] = 0;
+		return buf;
+	}
+	return strcpy(buf, "perf");
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dc58254..9969b8b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,10 +6,9 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
-#include <stdlib.h>
-#include <stdarg.h>
 #include <linux/compiler.h>
 #include <sys/types.h>
 
@@ -17,33 +16,16 @@
 void usage(const char *err) __noreturn;
 void die(const char *err, ...) __noreturn __printf(1, 2);
 
-static inline void *zalloc(size_t size)
-{
-	return calloc(1, size);
-}
-
-#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
-
 struct dirent;
-struct nsinfo;
 struct strlist;
 
 int mkdir_p(char *path, mode_t mode);
 int rm_rf(const char *path);
+int rm_rf_perf_data(const char *path);
 struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
-int copyfile(const char *from, const char *to);
-int copyfile_mode(const char *from, const char *to, mode_t mode);
-int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
-
-ssize_t readn(int fd, void *buf, size_t n);
-ssize_t writen(int fd, const void *buf, size_t n);
 
 size_t hex_width(u64 v);
-int hex2u64(const char *ptr, u64 *val);
-
-extern unsigned int page_size;
-int __pure cacheline_size(void);
 
 int sysctl__max_stack(void);
 
@@ -61,15 +43,13 @@
 int sched_getcpu(void);
 #endif
 
-#ifndef HAVE_SETNS_SUPPORT
-int setns(int fd, int nstype);
-#endif
-
 extern bool perf_singlethreaded;
 
 void perf_set_singlethreaded(void);
 void perf_set_multithreaded(void);
 
+char *perf_exe(char *buf, int len);
+
 #ifndef O_CLOEXEC
 #ifdef __sparc__
 #define O_CLOEXEC      0x400000
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 4b7a303..b9823f4 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -2,9 +2,10 @@
 #include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <errno.h>
+#include <linux/zalloc.h>
 
-#include "util.h"
 #include "values.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 741af20..ba4b439 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -10,18 +10,21 @@
 #include <linux/kernel.h>
 
 #include "vdso.h"
-#include "util.h"
+#include "dso.h"
+#include <internal/lib.h>
+#include "map.h"
 #include "symbol.h"
 #include "machine.h"
 #include "thread.h"
 #include "linux/string.h"
+#include <linux/zalloc.h>
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +79,7 @@
 	if (vdso_file->found)
 		return vdso_file->temp_file_name;
 
-	if (vdso_file->error || find_vdso_map(&start, &end))
+	if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
 		return NULL;
 
 	size = end - start;
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index dc95154..86889eb 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "xyarray.h"
-#include "util.h"
 #include <stdlib.h>
 #include <string.h>
+#include <linux/zalloc.h>
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 {
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
deleted file mode 100644
index 7ffe562..0000000
--- a/tools/perf/util/xyarray.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PERF_XYARRAY_H_
-#define _PERF_XYARRAY_H_ 1
-
-#include <sys/types.h>
-
-struct xyarray {
-	size_t row_size;
-	size_t entry_size;
-	size_t entries;
-	size_t max_x;
-	size_t max_y;
-	char contents[];
-};
-
-struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
-void xyarray__delete(struct xyarray *xy);
-void xyarray__reset(struct xyarray *xy);
-
-static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
-{
-	return &xy->contents[x * xy->row_size + y * xy->entry_size];
-}
-
-static inline int xyarray__max_y(struct xyarray *xy)
-{
-	return xy->max_y;
-}
-
-static inline int xyarray__max_x(struct xyarray *xy)
-{
-	return xy->max_x;
-}
-
-#endif /* _PERF_XYARRAY_H_ */
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 902ce63..78d2297 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -1,17 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <fcntl.h>
 #include <stdio.h>
+#include <string.h>
 #include <unistd.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <zlib.h>
 #include <linux/compiler.h>
-#include <unistd.h>
+#include <internal/lib.h>
 
 #include "util/compress.h"
-#include "util/util.h"
-#include "util/debug.h"
-
 
 #define CHUNK_SIZE  16384
 
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
new file mode 100644
index 0000000..d220239
--- /dev/null
+++ b/tools/perf/util/zstd.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include "util/compress.h"
+#include "util/debug.h"
+
+int zstd_init(struct zstd_data *data, int level)
+{
+	size_t ret;
+
+	data->dstream = ZSTD_createDStream();
+	if (data->dstream == NULL) {
+		pr_err("Couldn't create decompression stream.\n");
+		return -1;
+	}
+
+	ret = ZSTD_initDStream(data->dstream);
+	if (ZSTD_isError(ret)) {
+		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
+		return -1;
+	}
+
+	if (!level)
+		return 0;
+
+	data->cstream = ZSTD_createCStream();
+	if (data->cstream == NULL) {
+		pr_err("Couldn't create compression stream.\n");
+		return -1;
+	}
+
+	ret = ZSTD_initCStream(data->cstream, level);
+	if (ZSTD_isError(ret)) {
+		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
+		return -1;
+	}
+
+	return 0;
+}
+
+int zstd_fini(struct zstd_data *data)
+{
+	if (data->dstream) {
+		ZSTD_freeDStream(data->dstream);
+		data->dstream = NULL;
+	}
+
+	if (data->cstream) {
+		ZSTD_freeCStream(data->cstream);
+		data->cstream = NULL;
+	}
+
+	return 0;
+}
+
+size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+				       void *src, size_t src_size, size_t max_record_size,
+				       size_t process_header(void *record, size_t increment))
+{
+	size_t ret, size, compressed = 0;
+	ZSTD_inBuffer input = { src, src_size, 0 };
+	ZSTD_outBuffer output;
+	void *record;
+
+	while (input.pos < input.size) {
+		record = dst;
+		size = process_header(record, 0);
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+		output = (ZSTD_outBuffer){ dst, (dst_size > max_record_size) ?
+						max_record_size : dst_size, 0 };
+		ret = ZSTD_compressStream(data->cstream, &output, &input);
+		ZSTD_flushStream(data->cstream, &output);
+		if (ZSTD_isError(ret)) {
+			pr_err("failed to compress %ld bytes: %s\n",
+				(long)src_size, ZSTD_getErrorName(ret));
+			memcpy(dst, src, src_size);
+			return src_size;
+		}
+		size = output.pos;
+		size = process_header(record, size);
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+	}
+
+	return compressed;
+}
+
+size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size,
+			      void *dst, size_t dst_size)
+{
+	size_t ret;
+	ZSTD_inBuffer input = { src, src_size, 0 };
+	ZSTD_outBuffer output = { dst, dst_size, 0 };
+
+	while (input.pos < input.size) {
+		ret = ZSTD_decompressStream(data->dstream, &output, &input);
+		if (ZSTD_isError(ret)) {
+			pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n",
+			       src_size, output.size, dst_size, ZSTD_getErrorName(ret));
+			break;
+		}
+		output.dst  = dst + output.pos;
+		output.size = dst_size - output.pos;
+	}
+
+	return output.pos;
+}