Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Lots of tooling updates - too many to list, here's a few highlights:

   - Various subcommand updates to 'perf trace', 'perf report', 'perf
     record', 'perf annotate', 'perf script', 'perf test', etc.

   - CPU and NUMA topology and affinity handling improvements,

   - HW tracing and HW support updates:
      - Intel PT updates
      - ARM CoreSight updates
      - vendor HW event updates

   - BPF updates

   - Tons of infrastructure updates, both on the build system and the
     library support side

   - Documentation updates.

   - ... and lots of other changes, see the changelog for details.

  Kernel side updates:

   - Tighten up kprobes blacklist handling, reduce the number of places
     where developers can install a kprobe and hang/crash the system.

   - Fix/enhance vma address filter handling.

   - Various PMU driver updates, small fixes and additions.

   - refcount_t conversions

   - BPF updates

   - error code propagation enhancements

   - misc other changes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (238 commits)
  perf script python: Add Python3 support to syscall-counts-by-pid.py
  perf script python: Add Python3 support to syscall-counts.py
  perf script python: Add Python3 support to stat-cpi.py
  perf script python: Add Python3 support to stackcollapse.py
  perf script python: Add Python3 support to sctop.py
  perf script python: Add Python3 support to powerpc-hcalls.py
  perf script python: Add Python3 support to net_dropmonitor.py
  perf script python: Add Python3 support to mem-phys-addr.py
  perf script python: Add Python3 support to failed-syscalls-by-pid.py
  perf script python: Add Python3 support to netdev-times.py
  perf tools: Add perf_exe() helper to find perf binary
  perf script: Handle missing fields with -F +..
  perf data: Add perf_data__open_dir_data function
  perf data: Add perf_data__(create_dir|close_dir) functions
  perf data: Fail check_backup in case of error
  perf data: Make check_backup work over directories
  perf tools: Add rm_rf_perf_data function
  perf tools: Add pattern name checking to rm_rf
  perf tools: Add depth checking to rm_rf
  perf data: Add global path holder
  ...

115 files changed, 3719 insertions, 1402 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index af72be7f5b3b..8dd3102301ea 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,158 +1,164 @@
-libperf-y += annotate.o
-libperf-y += block-range.o
-libperf-y += build-id.o
-libperf-y += config.o
-libperf-y += ctype.o
-libperf-y += db-export.o
-libperf-y += env.o
-libperf-y += event.o
-libperf-y += evlist.o
-libperf-y += evsel.o
-libperf-y += evsel_fprintf.o
-libperf-y += find_bit.o
-libperf-y += get_current_dir_name.o
-libperf-y += kallsyms.o
-libperf-y += levenshtein.o
-libperf-y += llvm-utils.o
-libperf-y += mmap.o
-libperf-y += memswap.o
-libperf-y += parse-events.o
-libperf-y += perf_regs.o
-libperf-y += path.o
-libperf-y += print_binary.o
-libperf-y += rbtree.o
-libperf-y += libstring.o
-libperf-y += bitmap.o
-libperf-y += hweight.o
-libperf-y += smt.o
-libperf-y += strbuf.o
-libperf-y += string.o
-libperf-y += strlist.o
-libperf-y += strfilter.o
-libperf-y += top.o
-libperf-y += usage.o
-libperf-y += dso.o
-libperf-y += symbol.o
-libperf-y += symbol_fprintf.o
-libperf-y += color.o
-libperf-y += 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-$(CONFIG_TRACE) += syscalltbl.o
-libperf-y += ordered-events.o
-libperf-y += namespaces.o
-libperf-y += comm.o
-libperf-y += thread.o
-libperf-y += thread_map.o
-libperf-y += trace-event-parse.o
-libperf-y += parse-events-flex.o
-libperf-y += parse-events-bison.o
-libperf-y += pmu.o
-libperf-y += pmu-flex.o
-libperf-y += pmu-bison.o
-libperf-y += trace-event-read.o
-libperf-y += trace-event-info.o
-libperf-y += trace-event-scripting.o
-libperf-y += trace-event.o
-libperf-y += svghelper.o
-libperf-y += sort.o
-libperf-y += hist.o
-libperf-y += util.o
-libperf-y += xyarray.o
-libperf-y += cpumap.o
-libperf-y += cgroup.o
-libperf-y += target.o
-libperf-y += rblist.o
-libperf-y += intlist.o
-libperf-y += vdso.o
-libperf-y += counts.o
-libperf-y += stat.o
-libperf-y += stat-shadow.o
-libperf-y += stat-display.o
-libperf-y += record.o
-libperf-y += srcline.o
-libperf-y += srccode.o
-libperf-y += data.o
-libperf-y += tsc.o
-libperf-y += cloexec.o
-libperf-y += call-path.o
-libperf-y += rwsem.o
-libperf-y += thread-stack.o
-libperf-$(CONFIG_AUXTRACE) += auxtrace.o
-libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
-libperf-$(CONFIG_AUXTRACE) += intel-pt.o
-libperf-$(CONFIG_AUXTRACE) += intel-bts.o
-libperf-$(CONFIG_AUXTRACE) += arm-spe.o
-libperf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o
-libperf-$(CONFIG_AUXTRACE) += s390-cpumsf.o
+perf-y += annotate.o
+perf-y += block-range.o
+perf-y += build-id.o
+perf-y += config.o
+perf-y += ctype.o
+perf-y += db-export.o
+perf-y += env.o
+perf-y += event.o
+perf-y += evlist.o
+perf-y += evsel.o
+perf-y += evsel_fprintf.o
+perf-y += find_bit.o
+perf-y += get_current_dir_name.o
+perf-y += kallsyms.o
+perf-y += levenshtein.o
+perf-y += llvm-utils.o
+perf-y += mmap.o
+perf-y += memswap.o
+perf-y += parse-events.o
+perf-y += perf_regs.o
+perf-y += path.o
+perf-y += print_binary.o
+perf-y += rbtree.o
+perf-y += libstring.o
+perf-y += bitmap.o
+perf-y += hweight.o
+perf-y += smt.o
+perf-y += strbuf.o
+perf-y += string.o
+perf-y += strlist.o
+perf-y += strfilter.o
+perf-y += top.o
+perf-y += usage.o
+perf-y += dso.o
+perf-y += symbol.o
+perf-y += symbol_fprintf.o
+perf-y += color.o
+perf-y += color_config.o
+perf-y += metricgroup.o
+perf-y += header.o
+perf-y += callchain.o
+perf-y += values.o
+perf-y += debug.o
+perf-y += machine.o
+perf-y += map.o
+perf-y += pstack.o
+perf-y += session.o
+perf-y += sample-raw.o
+perf-y += s390-sample-raw.o
+perf-$(CONFIG_TRACE) += syscalltbl.o
+perf-y += ordered-events.o
+perf-y += namespaces.o
+perf-y += comm.o
+perf-y += thread.o
+perf-y += thread_map.o
+perf-y += trace-event-parse.o
+perf-y += parse-events-flex.o
+perf-y += parse-events-bison.o
+perf-y += pmu.o
+perf-y += pmu-flex.o
+perf-y += pmu-bison.o
+perf-y += trace-event-read.o
+perf-y += trace-event-info.o
+perf-y += trace-event-scripting.o
+perf-y += trace-event.o
+perf-y += svghelper.o
+perf-y += sort.o
+perf-y += hist.o
+perf-y += util.o
+perf-y += xyarray.o
+perf-y += cpumap.o
+perf-y += cputopo.o
+perf-y += cgroup.o
+perf-y += target.o
+perf-y += rblist.o
+perf-y += intlist.o
+perf-y += vdso.o
+perf-y += counts.o
+perf-y += stat.o
+perf-y += stat-shadow.o
+perf-y += stat-display.o
+perf-y += record.o
+perf-y += srcline.o
+perf-y += srccode.o
+perf-y += data.o
+perf-y += tsc.o
+perf-y += cloexec.o
+perf-y += call-path.o
+perf-y += rwsem.o
+perf-y += thread-stack.o
+perf-$(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
-
-libperf-$(CONFIG_LIBBPF) += bpf-loader.o
-libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
-libperf-$(CONFIG_LIBELF) += symbol-elf.o
-libperf-$(CONFIG_LIBELF) += probe-file.o
-libperf-$(CONFIG_LIBELF) += probe-event.o
+perf-y += parse-branch-options.o
+perf-y += dump-insn.o
+perf-y += parse-regs-options.o
+perf-y += term.o
+perf-y += help-unknown-cmd.o
+perf-y += mem-events.o
+perf-y += vsprintf.o
+perf-y += units.o
+perf-y += time-utils.o
+perf-y += expr-bison.o
+perf-y += branch.o
+perf-y += mem2node.o
+
+perf-$(CONFIG_LIBBPF) += bpf-loader.o
+perf-$(CONFIG_LIBBPF) += bpf_map.o
+perf-$(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-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))"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 70de8f6b3aee..11a8a447a3af 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -9,6 +9,7 @@
 
 #include <errno.h>
 #include <inttypes.h>
+#include <libgen.h>
 #include "util.h"
 #include "ui/ui.h"
 #include "sort.h"
@@ -16,6 +17,7 @@
 #include "color.h"
 #include "config.h"
 #include "cache.h"
+#include "map.h"
 #include "symbol.h"
 #include "units.h"
 #include "debug.h"
@@ -1889,6 +1891,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct annotation_options *options,
 		     struct arch **parch)
 {
+	struct annotation *notes = symbol__annotation(sym);
 	struct annotate_args args = {
 		.privsize	= privsize,
 		.evsel		= evsel,
@@ -1919,6 +1922,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 
 	args.ms.map = map;
 	args.ms.sym = sym;
+	notes->start = map__rip_2objdump(map, sym->start);
 
 	return symbol__disassemble(sym, &args);
 }
@@ -2794,8 +2798,6 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *ev
 
 	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);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index fb6463730ba4..95053cab41fe 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 perf_evsel;
+struct symbol;
 
 struct ins {
 	const char     *name;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index f69961c4a4f3..267e54df511b 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -27,6 +27,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/string.h>
+#include <linux/time64.h>
 
 #include <sys/param.h>
 #include <stdlib.h>
@@ -41,6 +42,7 @@
 #include "pmu.h"
 #include "evsel.h"
 #include "cpumap.h"
+#include "symbol.h"
 #include "thread_map.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
@@ -857,7 +859,7 @@ void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
 
 void auxtrace_synth_error(struct auxtrace_error_event *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;
 
@@ -869,7 +871,9 @@ void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
 	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 +
@@ -1159,12 +1163,27 @@ static const char *auxtrace_error_name(int type)
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 {
 	struct auxtrace_error_event *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);
+
+	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 %#"PRIx64" code %u: %s\n",
-		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+		       e->cpu, e->pid, e->tid, e->ip, e->code, msg);
 	return ret;
 }
 
@@ -1278,9 +1297,9 @@ static int __auxtrace_mmap__read(struct perf_mmap *map,
 	}
 
 	/* 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;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 8e50f96d4b23..c69bcd9a3091 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -40,6 +40,9 @@ struct record_opts;
 struct auxtrace_info_event;
 struct events_stats;
 
+/* 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,
@@ -516,7 +519,7 @@ void auxtrace_index__free(struct list_head *head);
 
 void auxtrace_synth_error(struct auxtrace_error_event *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,
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index f1451c987eec..1be432657501 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 a5ba719d69fb..ec0fb534bf56 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 000000000000..028c8ec1f62a
--- /dev/null
+++ b/tools/perf/util/bpf-event.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdlib.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <linux/btf.h>
+#include "bpf-event.h"
+#include "debug.h"
+#include "symbol.h"
+#include "machine.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;
+}
+
+int machine__process_bpf_event(struct machine *machine __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_bpf_event(event, stdout);
+	return 0;
+}
+
+/*
+ * 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_tool *tool,
+					       perf_event__handler_t process,
+					       struct machine *machine,
+					       int fd,
+					       union perf_event *event,
+					       struct record_opts *opts)
+{
+	struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
+	struct bpf_event *bpf_event = &event->bpf_event;
+	u32 sub_prog_cnt, i, func_info_rec_size = 0;
+	u8 (*prog_tags)[BPF_TAG_SIZE] = NULL;
+	struct bpf_prog_info info = { .type = 0, };
+	u32 info_len = sizeof(info);
+	void *func_infos = NULL;
+	u64 *prog_addrs = NULL;
+	struct btf *btf = NULL;
+	u32 *prog_lens = NULL;
+	bool has_btf = false;
+	char errbuf[512];
+	int err = 0;
+
+	/* Call bpf_obj_get_info_by_fd() to get sizes of arrays */
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+
+	if (err) {
+		pr_debug("%s: failed to get BPF program info: %s, aborting\n",
+			 __func__, str_error_r(errno, errbuf, sizeof(errbuf)));
+		return -1;
+	}
+	if (info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		pr_debug("%s: the kernel is too old, aborting\n", __func__);
+		return -2;
+	}
+
+	/* 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__);
+			return -1;
+		}
+		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);
+			return -1;
+		}
+		func_info_rec_size = info.func_info_rec_size;
+		func_infos = calloc(sub_prog_cnt, func_info_rec_size);
+		if (!func_infos) {
+			pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__);
+			return -1;
+		}
+		has_btf = true;
+	}
+
+	/*
+	 * We need address, length, and tag for each sub program.
+	 * Allocate memory and call bpf_obj_get_info_by_fd() again
+	 */
+	prog_addrs = calloc(sub_prog_cnt, sizeof(u64));
+	if (!prog_addrs) {
+		pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__);
+		goto out;
+	}
+	prog_lens = calloc(sub_prog_cnt, sizeof(u32));
+	if (!prog_lens) {
+		pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__);
+		goto out;
+	}
+	prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE);
+	if (!prog_tags) {
+		pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__);
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.nr_jited_ksyms = sub_prog_cnt;
+	info.nr_jited_func_lens = sub_prog_cnt;
+	info.nr_prog_tags = sub_prog_cnt;
+	info.jited_ksyms = ptr_to_u64(prog_addrs);
+	info.jited_func_lens = ptr_to_u64(prog_lens);
+	info.prog_tags = ptr_to_u64(prog_tags);
+	info_len = sizeof(info);
+	if (has_btf) {
+		info.nr_func_info = sub_prog_cnt;
+		info.func_info_rec_size = func_info_rec_size;
+		info.func_info = ptr_to_u64(func_infos);
+	}
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (err) {
+		pr_debug("%s: failed to get BPF program info, aborting\n", __func__);
+		goto out;
+	}
+
+	/* Synthesize PERF_RECORD_KSYMBOL */
+	for (i = 0; i < sub_prog_cnt; i++) {
+		const struct bpf_func_info *finfo;
+		const char *short_name = NULL;
+		const struct btf_type *t;
+		int name_len;
+
+		*ksymbol_event = (struct ksymbol_event){
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = offsetof(struct ksymbol_event, name),
+			},
+			.addr = prog_addrs[i],
+			.len = prog_lens[i],
+			.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+			.flags = 0,
+		};
+		name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN,
+				    "bpf_prog_");
+		name_len += snprintf_hex(ksymbol_event->name + name_len,
+					 KSYM_NAME_LEN - name_len,
+					 prog_tags[i], BPF_TAG_SIZE);
+		if (has_btf) {
+			finfo = func_infos + i * 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 (i == 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(ksymbol_event->name + name_len,
+					     KSYM_NAME_LEN - name_len,
+					     "_%s", short_name);
+
+		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);
+	}
+
+	/* Synthesize PERF_RECORD_BPF_EVENT */
+	if (opts->bpf_event) {
+		*bpf_event = (struct bpf_event){
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(struct bpf_event),
+			},
+			.type = PERF_BPF_EVENT_PROG_LOAD,
+			.flags = 0,
+			.id = info.id,
+		};
+		memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+		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);
+	}
+
+out:
+	free(prog_tags);
+	free(prog_lens);
+	free(prog_addrs);
+	free(func_infos);
+	free(btf);
+	return err ? -1 : 0;
+}
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      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_event) + 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(tool, 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;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
new file mode 100644
index 000000000000..7890067e1a37
--- /dev/null
+++ b/tools/perf/util/bpf-event.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_BPF_EVENT_H
+#define __PERF_BPF_EVENT_H
+
+#include <linux/compiler.h>
+#include "event.h"
+
+struct machine;
+union perf_event;
+struct perf_sample;
+struct perf_tool;
+struct record_opts;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int machine__process_bpf_event(struct machine *machine, union perf_event *event,
+			       struct perf_sample *sample);
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts);
+#else
+static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
+					     union perf_event *event __maybe_unused,
+					     struct perf_sample *sample __maybe_unused)
+{
+	return 0;
+}
+
+static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __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
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 31b7e5a1453b..251d9ea6252f 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include "perf.h"
 #include "debug.h"
+#include "evlist.h"
 #include "bpf-loader.h"
 #include "bpf-prologue.h"
 #include "probe-event.h"
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 62d245a90e1d..3f46856e3330 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,
@@ -44,6 +40,7 @@ enum bpf_loader_errno {
 };
 
 struct perf_evsel;
+struct perf_evlist;
 struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
@@ -87,6 +84,8 @@ struct perf_evsel *bpf__setup_output_event(struct perf_evlist *evlist, const cha
 int bpf__strerror_setup_output_event(struct perf_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,
diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c
new file mode 100644
index 000000000000..eb853ca67cf4
--- /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 000000000000..d6abd5e47af8
--- /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.h b/tools/perf/util/branch.h
index 1e3c7c5cdc63..64f96b79f1d7 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -1,8 +1,31 @@
 #ifndef _PERF_BRANCH_H
 #define _PERF_BRANCH_H 1
 
+#include <stdio.h>
 #include <stdint.h>
-#include "../perf.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_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 +36,6 @@ struct branch_type_stat {
 	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 04b1d53e4bf9..bff0d17920ed 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -15,6 +15,8 @@
 #include <sys/types.h>
 #include "build-id.h"
 #include "event.h"
+#include "namespaces.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include <linux/kernel.h>
@@ -363,7 +365,8 @@ int perf_session__write_buildid_table(struct perf_session *session,
 	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 +399,8 @@ int dsos__hit_all(struct perf_session *session)
 	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 +853,8 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 	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 +871,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
 	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 f0c565164a97..93668f38f1ed 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;
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
index 988fef1b11d7..613ecfd76527 100644
--- a/tools/perf/util/c++/Build
+++ b/tools/perf/util/c++/Build
@@ -1,2 +1,2 @@
-libperf-$(CONFIG_CLANGLLVM) += clang.o
-libperf-$(CONFIG_CLANGLLVM) += clang-test.o
+perf-$(CONFIG_CLANGLLVM) += clang.o
+perf-$(CONFIG_CLANGLLVM) += clang-test.o
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index dc2212e12184..abb608b09269 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -23,8 +23,10 @@
 #include "util.h"
 #include "sort.h"
 #include "machine.h"
+#include "map.h"
 #include "callchain.h"
 #include "branch.h"
+#include "symbol.h"
 
 #define CALLCHAIN_PARAM_DEFAULT			\
 	.mode		= CHAIN_GRAPH_ABS,	\
@@ -1577,3 +1579,18 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
 	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 99d38ac019b8..80e056a3d882 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -2,14 +2,14 @@
 #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 map;
+
 #define HELP_PAD "\t\t\t\t"
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
@@ -188,20 +188,7 @@ int callchain_append(struct callchain_root *root,
 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,
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 39e628b8938e..39b8c4ec4e2e 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include "cache.h"
-#include "config.h"
 #include <stdlib.h>
 #include <stdio.h>
 #include "color.h"
@@ -10,44 +9,6 @@
 
 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 22777b1812ee..01f7bed21c9b 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 000000000000..817dc56e7e95
--- /dev/null
+++ b/tools/perf/util/color_config.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include "cache.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 31279a7bd919..1066de92af12 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
+#include <linux/rbtree.h>
 #include "rwsem.h"
 
 struct comm_str {
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 3e5c438fe85e..f35d8fbfa2dd 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/config.c b/tools/perf/util/config.c
index 1ea8f898f1a1..fa092511c52b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -13,6 +13,7 @@
 #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 */
diff --git a/tools/perf/util/cpu-set-sched.h b/tools/perf/util/cpu-set-sched.h
new file mode 100644
index 000000000000..8cf4e40d322a
--- /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 383674f448fc..0b599229bc7e 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -681,7 +681,7 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
 
 #undef COMMA
 
-	pr_debug("cpumask list: %s\n", buf);
+	pr_debug2("cpumask list: %s\n", buf);
 	return ret;
 }
 
@@ -730,3 +730,13 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	buf[size - 1] = '\0';
 	return ptr - buf;
 }
+
+const struct cpu_map *cpu_map__online(void) /* thread unsafe */
+{
+	static const struct cpu_map *online = NULL;
+
+	if (!online)
+		online = 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 ed8999d1a640..f00ce624b9f7 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -29,6 +29,7 @@ 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);
+const struct 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);
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
new file mode 100644
index 000000000000..ece0710249d4
--- /dev/null
+++ b/tools/perf/util/cputopo.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/param.h>
+#include <inttypes.h>
+#include <api/fs/fs.h>
+
+#include "cputopo.h"
+#include "cpumap.h"
+#include "util.h"
+#include "env.h"
+
+
+#define CORE_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
+#define THRD_SIB_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_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_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:
+	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]);
+
+	for (i = 0 ; i < tp->thread_sib; i++)
+		zfree(&tp->thread_siblings[i]);
+
+	free(tp);
+}
+
+struct cpu_topology *cpu_topology__new(void)
+{
+	struct cpu_topology *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;
+	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_topology(tp, i);
+		if (ret < 0)
+			break;
+	}
+
+out_free:
+	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 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 = 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);
+	cpu_map__put(node_map);
+	return tp;
+}
+
+void numa_topology__delete(struct numa_topology *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->nr; i++)
+		free(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 000000000000..47a97e71acdf
--- /dev/null
+++ b/tools/perf/util/cputopo.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_CPUTOPO_H
+#define __PERF_CPUTOPO_H
+
+#include <linux/types.h>
+#include "env.h"
+
+struct cpu_topology {
+	u32	  core_sib;
+	u32	  thread_sib;
+	char	**core_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 bc22c39c727f..216cb17a3322 100644
--- a/tools/perf/util/cs-etm-decoder/Build
+++ b/tools/perf/util/cs-etm-decoder/Build
@@ -1 +1 @@
-libperf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
+perf-$(CONFIG_AUXTRACE) += cs-etm-decoder.o
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 8c155575c6c5..ba4c623cd8de 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -290,6 +290,12 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 		decoder->packet_buffer[i].instr_count = 0;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].last_instr_size = 0;
+		decoder->packet_buffer[i].last_instr_type = 0;
+		decoder->packet_buffer[i].last_instr_subtype = 0;
+		decoder->packet_buffer[i].last_instr_cond = 0;
+		decoder->packet_buffer[i].flags = 0;
+		decoder->packet_buffer[i].exception_number = UINT32_MAX;
+		decoder->packet_buffer[i].trace_chan_id = UINT8_MAX;
 		decoder->packet_buffer[i].cpu = INT_MIN;
 	}
 }
@@ -300,14 +306,12 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 			      enum cs_etm_sample_type sample_type)
 {
 	u32 et = 0;
-	struct int_node *inode = NULL;
+	int cpu;
 
 	if (decoder->packet_count >= 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;
@@ -317,12 +321,18 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 
 	decoder->packet_buffer[et].sample_type = sample_type;
 	decoder->packet_buffer[et].isa = CS_ETM_ISA_UNKNOWN;
-	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
+	decoder->packet_buffer[et].cpu = cpu;
 	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
 	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 	decoder->packet_buffer[et].instr_count = 0;
 	decoder->packet_buffer[et].last_instr_taken_branch = false;
 	decoder->packet_buffer[et].last_instr_size = 0;
+	decoder->packet_buffer[et].last_instr_type = 0;
+	decoder->packet_buffer[et].last_instr_subtype = 0;
+	decoder->packet_buffer[et].last_instr_cond = 0;
+	decoder->packet_buffer[et].flags = 0;
+	decoder->packet_buffer[et].exception_number = UINT32_MAX;
+	decoder->packet_buffer[et].trace_chan_id = trace_chan_id;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -366,6 +376,9 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 	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:
@@ -395,10 +408,20 @@ cs_etm_decoder__buffer_discontinuity(struct cs_etm_decoder *decoder,
 
 static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_exception(struct cs_etm_decoder *decoder,
+				 const ocsd_generic_trace_elem *elem,
 				 const uint8_t trace_chan_id)
-{
-	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
-					     CS_ETM_EXCEPTION);
+{	int ret = 0;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_EXCEPTION);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+	packet->exception_number = elem->exception_number;
+
+	return ret;
 }
 
 static ocsd_datapath_resp_t
@@ -432,7 +455,7 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
-		resp = cs_etm_decoder__buffer_exception(decoder,
+		resp = cs_etm_decoder__buffer_exception(decoder, elem,
 							trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION_RET:
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 a6407d41598f..3ab11dfa92ae 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -15,13 +15,6 @@
 
 struct cs_etm_decoder;
 
-struct cs_etm_buffer {
-	const unsigned char *buf;
-	size_t len;
-	u64 offset;
-	u64 ref_timestamp;
-};
-
 enum cs_etm_sample_type {
 	CS_ETM_EMPTY,
 	CS_ETM_RANGE,
@@ -43,8 +36,14 @@ struct cs_etm_packet {
 	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;
 };
 
@@ -99,9 +98,10 @@ enum {
 	CS_ETM_PROTO_PTM,
 };
 
-enum {
+enum cs_etm_decoder_operation {
 	CS_ETM_OPERATION_PRINT = 1,
 	CS_ETM_OPERATION_DECODE,
+	CS_ETM_OPERATION_MAX,
 };
 
 int cs_etm_decoder__process_data_block(struct cs_etm_decoder *decoder,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 27a374ddf661..110804936fc3 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -12,6 +12,7 @@
 #include <linux/log2.h>
 #include <linux/types.h>
 
+#include <opencsd/ocsd_if_types.h>
 #include <stdlib.h>
 
 #include "auxtrace.h"
@@ -24,6 +25,7 @@
 #include "machine.h"
 #include "map.h"
 #include "perf.h"
+#include "symbol.h"
 #include "thread.h"
 #include "thread_map.h"
 #include "thread-stack.h"
@@ -63,13 +65,10 @@ struct cs_etm_queue {
 	struct thread *thread;
 	struct cs_etm_decoder *decoder;
 	struct auxtrace_buffer *buffer;
-	const struct cs_etm_state *state;
 	union perf_event *event_buf;
 	unsigned int queue_nr;
 	pid_t pid, tid;
 	int cpu;
-	u64 time;
-	u64 timestamp;
 	u64 offset;
 	u64 period_instructions;
 	struct branch_stack *last_branch;
@@ -77,11 +76,13 @@ struct cs_etm_queue {
 	size_t last_branch_pos;
 	struct cs_etm_packet *prev_packet;
 	struct cs_etm_packet *packet;
+	const unsigned char *buf;
+	size_t buf_len, buf_used;
 };
 
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
 static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
-					   pid_t tid, u64 time_);
+					   pid_t tid);
 
 /* PTMs ETMIDR [11:8] set to b0011 */
 #define ETMIDR_PTM_VERSION 0x00000300
@@ -96,6 +97,34 @@ static u32 cs_etm__get_v7_protocol_version(u32 etmidr)
 	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;
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -109,10 +138,83 @@ static void cs_etm__packet_dump(const char *pkt_string)
 	fflush(stdout);
 }
 
+static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
+					  struct cs_etm_auxtrace *etm, int idx,
+					  u32 etmidr)
+{
+	u64 **metadata = etm->metadata;
+
+	t_params[idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
+	t_params[idx].etmv3.reg_ctrl = metadata[idx][CS_ETM_ETMCR];
+	t_params[idx].etmv3.reg_trc_id = metadata[idx][CS_ETM_ETMTRACEIDR];
+}
+
+static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params,
+					  struct cs_etm_auxtrace *etm, int idx)
+{
+	u64 **metadata = etm->metadata;
+
+	t_params[idx].protocol = CS_ETM_PROTO_ETMV4i;
+	t_params[idx].etmv4.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0];
+	t_params[idx].etmv4.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1];
+	t_params[idx].etmv4.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2];
+	t_params[idx].etmv4.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8];
+	t_params[idx].etmv4.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR];
+	t_params[idx].etmv4.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR];
+}
+
+static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
+				     struct cs_etm_auxtrace *etm)
+{
+	int i;
+	u32 etmidr;
+	u64 architecture;
+
+	for (i = 0; i < etm->num_cpu; i++) {
+		architecture = etm->metadata[i][CS_ETM_MAGIC];
+
+		switch (architecture) {
+		case __perf_cs_etmv3_magic:
+			etmidr = etm->metadata[i][CS_ETM_ETMIDR];
+			cs_etm__set_trace_param_etmv3(t_params, etm, i, etmidr);
+			break;
+		case __perf_cs_etmv4_magic:
+			cs_etm__set_trace_param_etmv4(t_params, etm, i);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int cs_etm__init_decoder_params(struct cs_etm_decoder_params *d_params,
+				       struct cs_etm_queue *etmq,
+				       enum cs_etm_decoder_operation mode)
+{
+	int ret = -EINVAL;
+
+	if (!(mode < CS_ETM_OPERATION_MAX))
+		goto out;
+
+	d_params->packet_printer = cs_etm__packet_dump;
+	d_params->operation = mode;
+	d_params->data = etmq;
+	d_params->formatted = true;
+	d_params->fsyncs = false;
+	d_params->hsyncs = false;
+	d_params->frame_aligned = true;
+
+	ret = 0;
+out:
+	return ret;
+}
+
 static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_buffer *buffer)
 {
-	int i, ret;
+	int ret;
 	const char *color = PERF_COLOR_BLUE;
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params *t_params;
@@ -126,48 +228,22 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 
 	/* Use metadata to fill in trace parameters for trace decoder */
 	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
-	for (i = 0; i < etm->num_cpu; i++) {
-		if (etm->metadata[i][CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
-			u32 etmidr = etm->metadata[i][CS_ETM_ETMIDR];
-
-			t_params[i].protocol =
-					cs_etm__get_v7_protocol_version(etmidr);
-			t_params[i].etmv3.reg_ctrl =
-					etm->metadata[i][CS_ETM_ETMCR];
-			t_params[i].etmv3.reg_trc_id =
-					etm->metadata[i][CS_ETM_ETMTRACEIDR];
-		} else if (etm->metadata[i][CS_ETM_MAGIC] ==
-						      __perf_cs_etmv4_magic) {
-			t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
-			t_params[i].etmv4.reg_idr0 =
-					etm->metadata[i][CS_ETMV4_TRCIDR0];
-			t_params[i].etmv4.reg_idr1 =
-					etm->metadata[i][CS_ETMV4_TRCIDR1];
-			t_params[i].etmv4.reg_idr2 =
-					etm->metadata[i][CS_ETMV4_TRCIDR2];
-			t_params[i].etmv4.reg_idr8 =
-					etm->metadata[i][CS_ETMV4_TRCIDR8];
-			t_params[i].etmv4.reg_configr =
-					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
-			t_params[i].etmv4.reg_traceidr =
-					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
-		}
-	}
+
+	if (!t_params)
+		return;
+
+	if (cs_etm__init_trace_params(t_params, etm))
+		goto out_free;
 
 	/* Set decoder parameters to simply print the trace packets */
-	d_params.packet_printer = cs_etm__packet_dump;
-	d_params.operation = CS_ETM_OPERATION_PRINT;
-	d_params.formatted = true;
-	d_params.fsyncs = false;
-	d_params.hsyncs = false;
-	d_params.frame_aligned = true;
+	if (cs_etm__init_decoder_params(&d_params, NULL,
+					CS_ETM_OPERATION_PRINT))
+		goto out_free;
 
 	decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
 
-	zfree(&t_params);
-
 	if (!decoder)
-		return;
+		goto out_free;
 	do {
 		size_t consumed;
 
@@ -182,6 +258,9 @@ static void cs_etm__dump_event(struct cs_etm_auxtrace *etm,
 	} while (buffer_used < buffer->size);
 
 	cs_etm_decoder__free(decoder);
+
+out_free:
+	zfree(&t_params);
 }
 
 static int cs_etm__flush_events(struct perf_session *session,
@@ -205,7 +284,7 @@ static int cs_etm__flush_events(struct perf_session *session,
 	if (ret < 0)
 		return ret;
 
-	return cs_etm__process_timeless_queues(etm, -1, MAX_TIMESTAMP - 1);
+	return cs_etm__process_timeless_queues(etm, -1);
 }
 
 static void cs_etm__free_queue(void *priv)
@@ -251,7 +330,7 @@ static void cs_etm__free(struct perf_session *session)
 	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 */
@@ -297,7 +376,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	struct	 addr_location al;
 
 	if (!etmq)
-		return -1;
+		return 0;
 
 	machine = etmq->etm->machine;
 	cpumode = cs_etm__cpu_mode(etmq, address);
@@ -305,7 +384,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	thread = etmq->thread;
 	if (!thread) {
 		if (cpumode != PERF_RECORD_MISC_KERNEL)
-			return -EINVAL;
+			return 0;
 		thread = etmq->etm->unknown_thread;
 	}
 
@@ -328,12 +407,10 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 	return len;
 }
 
-static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
-						unsigned int queue_nr)
+static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 {
-	int i;
 	struct cs_etm_decoder_params d_params;
-	struct cs_etm_trace_params  *t_params;
+	struct cs_etm_trace_params  *t_params = NULL;
 	struct cs_etm_queue *etmq;
 	size_t szp = sizeof(struct cs_etm_packet);
 
@@ -368,59 +445,22 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	if (!etmq->event_buf)
 		goto out_free;
 
-	etmq->etm = etm;
-	etmq->queue_nr = queue_nr;
-	etmq->pid = -1;
-	etmq->tid = -1;
-	etmq->cpu = -1;
-
 	/* Use metadata to fill in trace parameters for trace decoder */
 	t_params = zalloc(sizeof(*t_params) * etm->num_cpu);
 
 	if (!t_params)
 		goto out_free;
 
-	for (i = 0; i < etm->num_cpu; i++) {
-		if (etm->metadata[i][CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
-			u32 etmidr = etm->metadata[i][CS_ETM_ETMIDR];
-
-			t_params[i].protocol =
-					cs_etm__get_v7_protocol_version(etmidr);
-			t_params[i].etmv3.reg_ctrl =
-					etm->metadata[i][CS_ETM_ETMCR];
-			t_params[i].etmv3.reg_trc_id =
-					etm->metadata[i][CS_ETM_ETMTRACEIDR];
-		} else if (etm->metadata[i][CS_ETM_MAGIC] ==
-							__perf_cs_etmv4_magic) {
-			t_params[i].protocol = CS_ETM_PROTO_ETMV4i;
-			t_params[i].etmv4.reg_idr0 =
-					etm->metadata[i][CS_ETMV4_TRCIDR0];
-			t_params[i].etmv4.reg_idr1 =
-					etm->metadata[i][CS_ETMV4_TRCIDR1];
-			t_params[i].etmv4.reg_idr2 =
-					etm->metadata[i][CS_ETMV4_TRCIDR2];
-			t_params[i].etmv4.reg_idr8 =
-					etm->metadata[i][CS_ETMV4_TRCIDR8];
-			t_params[i].etmv4.reg_configr =
-					etm->metadata[i][CS_ETMV4_TRCCONFIGR];
-			t_params[i].etmv4.reg_traceidr =
-					etm->metadata[i][CS_ETMV4_TRCTRACEIDR];
-		}
-	}
+	if (cs_etm__init_trace_params(t_params, etm))
+		goto out_free;
 
-	/* Set decoder parameters to simply print the trace packets */
-	d_params.packet_printer = cs_etm__packet_dump;
-	d_params.operation = CS_ETM_OPERATION_DECODE;
-	d_params.formatted = true;
-	d_params.fsyncs = false;
-	d_params.hsyncs = false;
-	d_params.frame_aligned = true;
-	d_params.data = etmq;
+	/* Set decoder parameters to decode trace packets */
+	if (cs_etm__init_decoder_params(&d_params, etmq,
+					CS_ETM_OPERATION_DECODE))
+		goto out_free;
 
 	etmq->decoder = cs_etm_decoder__new(etm->num_cpu, &d_params, t_params);
 
-	zfree(&t_params);
-
 	if (!etmq->decoder)
 		goto out_free;
 
@@ -433,14 +473,13 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 					      cs_etm__mem_access))
 		goto out_free_decoder;
 
-	etmq->offset = 0;
-	etmq->period_instructions = 0;
-
+	zfree(&t_params);
 	return etmq;
 
 out_free_decoder:
 	cs_etm_decoder__free(etmq->decoder);
 out_free:
+	zfree(&t_params);
 	zfree(&etmq->event_buf);
 	zfree(&etmq->last_branch);
 	zfree(&etmq->last_branch_rb);
@@ -455,24 +494,30 @@ static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_queue *queue,
 			       unsigned int queue_nr)
 {
+	int ret = 0;
 	struct cs_etm_queue *etmq = queue->priv;
 
 	if (list_empty(&queue->head) || etmq)
-		return 0;
+		goto out;
 
-	etmq = cs_etm__alloc_queue(etm, queue_nr);
+	etmq = cs_etm__alloc_queue(etm);
 
-	if (!etmq)
-		return -ENOMEM;
+	if (!etmq) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	queue->priv = etmq;
-
-	if (queue->cpu != -1)
-		etmq->cpu = queue->cpu;
-
+	etmq->etm = etm;
+	etmq->queue_nr = queue_nr;
+	etmq->cpu = queue->cpu;
 	etmq->tid = queue->tid;
+	etmq->pid = -1;
+	etmq->offset = 0;
+	etmq->period_instructions = 0;
 
-	return 0;
+out:
+	return ret;
 }
 
 static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
@@ -480,6 +525,9 @@ static int cs_etm__setup_queues(struct cs_etm_auxtrace *etm)
 	unsigned int i;
 	int ret;
 
+	if (!etm->kernel_start)
+		etm->kernel_start = machine__kernel_start(etm->machine);
+
 	for (i = 0; i < etm->queues.nr_queues; i++) {
 		ret = cs_etm__setup_queue(etm, &etm->queues.queue_array[i], i);
 		if (ret)
@@ -637,7 +685,7 @@ static int cs_etm__inject_event(union perf_event *event,
 
 
 static int
-cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
+cs_etm__get_trace(struct cs_etm_queue *etmq)
 {
 	struct auxtrace_buffer *aux_buffer = etmq->buffer;
 	struct auxtrace_buffer *old_buffer = aux_buffer;
@@ -651,7 +699,7 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	if (!aux_buffer) {
 		if (old_buffer)
 			auxtrace_buffer__drop_data(old_buffer);
-		buff->len = 0;
+		etmq->buf_len = 0;
 		return 0;
 	}
 
@@ -671,13 +719,11 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	if (old_buffer)
 		auxtrace_buffer__drop_data(old_buffer);
 
-	buff->offset = aux_buffer->offset;
-	buff->len = aux_buffer->size;
-	buff->buf = aux_buffer->data;
-
-	buff->ref_timestamp = aux_buffer->reference;
+	etmq->buf_used = 0;
+	etmq->buf_len = aux_buffer->size;
+	etmq->buf = aux_buffer->data;
 
-	return buff->len;
+	return etmq->buf_len;
 }
 
 static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
@@ -719,7 +765,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.stream_id = etmq->etm->instructions_id;
 	sample.period = period;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.insn_len = 1;
 	sample.cpumode = event->sample.header.misc;
 
@@ -778,7 +824,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
-	sample.flags = 0;
+	sample.flags = etmq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
 	/*
@@ -1106,95 +1152,489 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq)
 
 	return 0;
 }
+/*
+ * cs_etm__get_data_block: Fetch a block from the auxtrace_buffer queue
+ *			   if need be.
+ * Returns:	< 0	if error
+ *		= 0	if no more auxtrace_buffer to read
+ *		> 0	if the current buffer isn't empty yet
+ */
+static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
+{
+	int ret;
+
+	if (!etmq->buf_len) {
+		ret = cs_etm__get_trace(etmq);
+		if (ret <= 0)
+			return ret;
+		/*
+		 * We cannot assume consecutive blocks in the data file
+		 * are contiguous, reset the decoder to force re-sync.
+		 */
+		ret = cs_etm_decoder__reset(etmq->decoder);
+		if (ret)
+			return ret;
+	}
+
+	return etmq->buf_len;
+}
+
+static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq,
+				 struct cs_etm_packet *packet,
+				 u64 end_addr)
+{
+	u16 instr16;
+	u32 instr32;
+	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, 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, 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, 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, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->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, prev_packet,
+					 prev_packet->end_addr))
+			return true;
+	}
+
+	return false;
+}
+
+static bool cs_etm__is_async_exception(struct cs_etm_queue *etmq, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->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, u64 magic)
+{
+	struct cs_etm_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->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, 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_packet *packet = etmq->packet;
+	struct cs_etm_packet *prev_packet = etmq->prev_packet;
+	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, 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, 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(etmq, 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, 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_decoder_queue(struct cs_etm_queue *etmq)
+{
+	int ret;
+
+		/* Process each packet in this chunk */
+		while (1) {
+			ret = cs_etm_decoder__get_packet(etmq->decoder,
+							 etmq->packet);
+			if (ret <= 0)
+				/*
+				 * Stop processing this chunk on
+				 * end of data or error
+				 */
+				break;
+
+			/*
+			 * Since packet addresses are swapped in packet
+			 * handling within below switch() statements,
+			 * thus setting sample flags must be called
+			 * prior to switch() statement to use address
+			 * information before packets swapping.
+			 */
+			ret = cs_etm__set_sample_flags(etmq);
+			if (ret < 0)
+				break;
+
+			switch (etmq->packet->sample_type) {
+			case CS_ETM_RANGE:
+				/*
+				 * If the packet contains an instruction
+				 * range, generate instruction sequence
+				 * events.
+				 */
+				cs_etm__sample(etmq);
+				break;
+			case CS_ETM_EXCEPTION:
+			case CS_ETM_EXCEPTION_RET:
+				/*
+				 * If the exception packet is coming,
+				 * make sure the previous instruction
+				 * range packet to be handled properly.
+				 */
+				cs_etm__exception(etmq);
+				break;
+			case CS_ETM_DISCONTINUITY:
+				/*
+				 * Discontinuity in trace, flush
+				 * previous branch stack
+				 */
+				cs_etm__flush(etmq);
+				break;
+			case CS_ETM_EMPTY:
+				/*
+				 * Should not receive empty packet,
+				 * report error.
+				 */
+				pr_err("CS ETM Trace: empty packet\n");
+				return -EINVAL;
+			default:
+				break;
+			}
+		}
+
+	return ret;
+}
 
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
-	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_buffer buffer;
-	size_t buffer_used, processed;
 	int err = 0;
 
-	if (!etm->kernel_start)
-		etm->kernel_start = machine__kernel_start(etm->machine);
-
 	/* Go through each buffer in the queue and decode them one by one */
 	while (1) {
-		buffer_used = 0;
-		memset(&buffer, 0, sizeof(buffer));
-		err = cs_etm__get_trace(&buffer, etmq);
+		err = cs_etm__get_data_block(etmq);
 		if (err <= 0)
 			return err;
-		/*
-		 * We cannot assume consecutive blocks in the data file are
-		 * contiguous, reset the decoder to force re-sync.
-		 */
-		err = cs_etm_decoder__reset(etmq->decoder);
-		if (err != 0)
-			return err;
 
 		/* Run trace decoder until buffer consumed or end of trace */
 		do {
-			processed = 0;
-			err = cs_etm_decoder__process_data_block(
-				etmq->decoder,
-				etmq->offset,
-				&buffer.buf[buffer_used],
-				buffer.len - buffer_used,
-				&processed);
+			err = cs_etm__decode_data_block(etmq);
 			if (err)
 				return err;
 
-			etmq->offset += processed;
-			buffer_used += processed;
-
-			/* Process each packet in this chunk */
-			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_EXCEPTION:
-				case CS_ETM_EXCEPTION_RET:
-					/*
-					 * If the exception packet is coming,
-					 * make sure the previous instruction
-					 * range packet to be handled properly.
-					 */
-					cs_etm__exception(etmq);
-					break;
-				case CS_ETM_DISCONTINUITY:
-					/*
-					 * Discontinuity in trace, flush
-					 * previous branch stack
-					 */
-					cs_etm__flush(etmq);
-					break;
-				case CS_ETM_EMPTY:
-					/*
-					 * Should not receive empty packet,
-					 * report error.
-					 */
-					pr_err("CS ETM Trace: empty packet\n");
-					return -EINVAL;
-				default:
-					break;
-				}
-			}
-		} while (buffer.len > buffer_used);
+			/*
+			 * Process each packet in this chunk, nothing to do if
+			 * an error occurs other than hoping the next one will
+			 * be better.
+			 */
+			err = cs_etm__process_decoder_queue(etmq);
+
+		} while (etmq->buf_len);
 
 		if (err == 0)
 			/* Flush any remaining branch stack entries */
@@ -1205,7 +1645,7 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 }
 
 static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
-					   pid_t tid, u64 time_)
+					   pid_t tid)
 {
 	unsigned int i;
 	struct auxtrace_queues *queues = &etm->queues;
@@ -1215,7 +1655,6 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm,
 		struct cs_etm_queue *etmq = queue->priv;
 
 		if (etmq && ((tid == -1) || (etmq->tid == tid))) {
-			etmq->time = time_;
 			cs_etm__set_pid_tid_cpu(etm, queue);
 			cs_etm__run_decoder(etmq);
 		}
@@ -1259,8 +1698,7 @@ static int cs_etm__process_event(struct perf_session *session,
 
 	if (event->header.type == PERF_RECORD_EXIT)
 		return cs_etm__process_timeless_queues(etm,
-						       event->fork.tid,
-						       sample->time);
+						       event->fork.tid);
 
 	return 0;
 }
@@ -1414,9 +1852,9 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 				    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) {
@@ -1482,8 +1920,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 			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];
 	}
 
 	/*
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 37f8d48179ca..0e97c196147a 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -53,7 +53,51 @@ enum {
 	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,
+};
+
+/* RB tree for quick conversion between traceID and metadata pointers */
 struct intlist *traceid_list;
 
 #define KiB(x) ((x) * 1024)
@@ -61,14 +105,15 @@ struct intlist *traceid_list;
 
 #define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64))
 
-static const u64 __perf_cs_etmv3_magic   = 0x3030303030303030ULL;
-static const u64 __perf_cs_etmv4_magic   = 0x4040404040404040ULL;
+#define __perf_cs_etmv3_magic 0x3030303030303030ULL
+#define __perf_cs_etmv4_magic 0x4040404040404040ULL
 #define CS_ETMV3_PRIV_SIZE (CS_ETM_PRIV_MAX * sizeof(u64))
 #define CS_ETMV4_PRIV_SIZE (CS_ETMV4_PRIV_MAX * sizeof(u64))
 
 #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);
 #else
 static inline int
 cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
@@ -76,6 +121,12 @@ cs_etm__process_auxtrace_info(union perf_event *event __maybe_unused,
 {
 	return -1;
 }
+
+static inline int cs_etm__get_cpu(u8 trace_chan_id __maybe_unused,
+				  int *cpu __maybe_unused)
+{
+	return -1;
+}
 #endif
 
 #endif
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2a36fab76994..26af43ad9ddd 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1578,7 +1578,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 {
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = { .path = input, .fd = -1 },
+		.path	   = input,
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = opts->force,
 	};
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 
 	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 d8cfc19ddb10..7bd5ddeb7a41 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,11 +7,117 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <string.h>
+#include <asm/bug.h>
+#include <sys/types.h>
+#include <dirent.h>
 
 #include "data.h"
 #include "util.h"
 #include "debug.h"
 
+static void close_dir(struct perf_data_file *files, int nr)
+{
+	while (--nr >= 1) {
+		close(files[nr].fd);
+		free(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;
+
+	files = zalloc(nr * sizeof(*files));
+	if (!files)
+		return -ENOMEM;
+
+	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;
+
+	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;
+}
+
 static bool check_pipe(struct perf_data *data)
 {
 	struct stat st;
@@ -19,11 +125,11 @@ static bool check_pipe(struct perf_data *data)
 	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;
 	}
 
@@ -37,13 +143,31 @@ static int check_backup(struct perf_data *data)
 {
 	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;
@@ -82,7 +206,7 @@ static int open_file_read(struct perf_data *data)
 		goto out_close;
 	}
 
-	data->size = st.st_size;
+	data->file.size = st.st_size;
 	return fd;
 
  out_close:
@@ -95,9 +219,6 @@ static int open_file_write(struct perf_data *data)
 	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 +236,22 @@ static int open_file(struct perf_data *data)
 	fd = perf_data__is_read(data) ?
 	     open_file_read(data) : open_file_write(data);
 
+	if (fd < 0) {
+		free(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);
 }
 
 int perf_data__open(struct perf_data *data)
@@ -124,14 +259,18 @@ int perf_data__open(struct perf_data *data)
 	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;
+
+	return open_file_dup(data);
 }
 
 void perf_data__close(struct perf_data *data)
 {
+	free(data->file.path);
 	close(data->file.fd);
 }
 
@@ -159,15 +298,15 @@ int perf_data__switch(struct perf_data *data,
 	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);
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 4828f7feea89..14b47be2bd69 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -10,16 +10,22 @@ enum perf_data_mode {
 };
 
 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			 force;
-	unsigned long		 size;
 	enum perf_data_mode	 mode;
+
+	struct {
+		struct perf_data_file	*files;
+		int			 nr;
+	} dir;
 };
 
 static inline bool perf_data__is_read(struct perf_data *data)
@@ -44,7 +50,7 @@ static inline int perf_data__fd(struct perf_data *data)
 
 static inline unsigned long perf_data__size(struct perf_data *data)
 {
-	return data->size;
+	return data->file.size;
 }
 
 int perf_data__open(struct perf_data *data);
@@ -63,4 +69,8 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 int perf_data__switch(struct perf_data *data,
 			   const char *postfix,
 			   size_t pos, bool at_exit);
+
+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);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 69fbb0a72d0c..de9b4769d06c 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -20,6 +20,7 @@
 #include "thread.h"
 #include "comm.h"
 #include "symbol.h"
+#include "map.h"
 #include "event.h"
 #include "util.h"
 #include "thread-stack.h"
diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c
deleted file mode 100644
index eec754243f4d..000000000000
--- 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 32bc9babc2e0..000000000000
--- 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 62c8cf622607..ba58ba603b69 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -8,8 +8,11 @@
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <libgen.h>
 #include "compress.h"
+#include "namespaces.h"
 #include "path.h"
+#include "map.h"
 #include "symbol.h"
 #include "srcline.h"
 #include "dso.h"
@@ -1195,10 +1198,10 @@ struct dso *dso__new(const char *name)
 		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;
@@ -1467,7 +1470,7 @@ size_t dso__fprintf(struct dso *dso, FILE *fp)
 	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 8c8a7abe809d..bb417c54c25a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -7,13 +7,14 @@
 #include <linux/rbtree.h>
 #include <sys/types.h>
 #include <stdbool.h>
+#include <stdio.h>
 #include "rwsem.h"
-#include <linux/types.h>
 #include <linux/bitops.h>
-#include "map.h"
-#include "namespaces.h"
 #include "build-id.h"
 
+struct machine;
+struct map;
+
 enum dso_binary_type {
 	DSO_BINARY_TYPE__KALLSYMS = 0,
 	DSO_BINARY_TYPE__GUEST_KALLSYMS,
@@ -140,10 +141,10 @@ struct dso {
 	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;
@@ -235,7 +236,7 @@ bool dso__loaded(const struct dso *dso);
 
 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);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 937a5a4f71cc..ba7be74fad6e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -21,9 +21,13 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "sane_ctype.h"
+#include "map.h"
+#include "symbol.h"
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
+#include "session.h"
+#include "bpf-event.h"
 
 #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
 
@@ -45,6 +49,8 @@ static const char *perf_event__names[] = {
 	[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",
@@ -1329,6 +1335,22 @@ int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
 	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_event(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event,
+				  struct perf_sample *sample __maybe_unused,
+				  struct machine *machine)
+{
+	return machine__process_bpf_event(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",
@@ -1461,6 +1483,21 @@ static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
 	return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
 }
 
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " ksymbol event with addr %" PRIx64 " len %u type %u flags 0x%x name %s\n",
+		       event->ksymbol_event.addr, event->ksymbol_event.len,
+		       event->ksymbol_event.ksym_type,
+		       event->ksymbol_event.flags, event->ksymbol_event.name);
+}
+
+size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " bpf event with type %u, flags %u, id %u\n",
+		       event->bpf_event.type, event->bpf_event.flags,
+		       event->bpf_event.id);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -1496,6 +1533,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	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(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index eb95f3384958..36ae7e92dab1 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -5,6 +5,7 @@
 #include <limits.h>
 #include <stdio.h>
 #include <linux/kernel.h>
+#include <linux/bpf.h>
 
 #include "../perf.h"
 #include "build-id.h"
@@ -84,6 +85,29 @@ struct throttle_event {
 	u64 stream_id;
 };
 
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+struct ksymbol_event {
+	struct perf_event_header header;
+	u64 addr;
+	u32 len;
+	u16 ksym_type;
+	u16 flags;
+	char name[KSYM_NAME_LEN];
+};
+
+struct bpf_event {
+	struct perf_event_header header;
+	u16 type;
+	u16 flags;
+	u32 id;
+
+	/* for bpf_prog types */
+	u8 tag[BPF_TAG_SIZE];  // prog tag
+};
+
 #define PERF_SAMPLE_MASK				\
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
@@ -137,26 +161,7 @@ struct ip_callchain {
 	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,
@@ -527,8 +532,9 @@ struct auxtrace_error_event {
 	u32 cpu;
 	u32 pid;
 	u32 tid;
-	u32 reserved__; /* For alignment */
+	u32 fmt;
 	u64 ip;
+	u64 time;
 	char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
@@ -651,6 +657,8 @@ union perf_event {
 	struct stat_round_event		stat_round;
 	struct time_conv_event		time_conv;
 	struct feature_event		feat;
+	struct ksymbol_event		ksymbol_event;
+	struct bpf_event		bpf_event;
 };
 
 void perf_event__print_totals(void);
@@ -748,6 +756,14 @@ int perf_event__process_exit(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+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_event(struct perf_tool *tool,
+				  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,
@@ -811,6 +827,8 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 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_event(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,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8c902276d4b4..08cedb643ea6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1022,7 +1022,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1032,7 +1032,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks };
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1064,7 +1064,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 868294491194..744906dd4887 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -49,6 +49,9 @@ struct perf_evlist {
 	struct perf_evsel *selected;
 	struct events_stats stats;
 	struct perf_env	*env;
+	void (*trace_event_sample_raw)(struct perf_evlist *evlist,
+				       union perf_event *event,
+				       struct perf_sample *sample);
 	u64		first_sample_time;
 	u64		last_sample_time;
 };
@@ -162,7 +165,7 @@ unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks);
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
@@ -314,5 +317,4 @@ void perf_evlist__force_leader(struct perf_evlist *evlist);
 
 struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
 						 struct perf_evsel *evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbc0466db368..dfe2958e6287 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -956,6 +956,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		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->attr.sample_type;
 	}
 
 	if (opts->no_samples)
@@ -1035,6 +1043,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	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->bpf_event &&
+		!perf_missing_features.bpf_event;
 
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
@@ -1652,6 +1663,8 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	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_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1811,6 +1824,10 @@ fallback_missing_features:
 				     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.ksymbol)
+		evsel->attr.ksymbol = 0;
+	if (perf_missing_features.bpf_event)
+		evsel->attr.bpf_event = 0;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1930,7 +1947,15 @@ try_fallback:
 	 * 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.bpf_event && evsel->attr.bpf_event) {
+		perf_missing_features.bpf_event = true;
+		pr_debug2("switching off bpf_event\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.ksymbol && evsel->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->attr.write_backward) {
 		perf_missing_features.write_backward = true;
 		pr_debug2("switching off write_backward\n");
 		goto out_close;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 82a289ce8b0c..cc578e02e08f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,7 +8,7 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 #include "xyarray.h"
-#include "symbol.h"
+#include "symbol_conf.h"
 #include "cpumap.h"
 #include "counts.h"
 
@@ -168,6 +168,8 @@ struct perf_missing_features {
 	bool lbr_flags;
 	bool write_backward;
 	bool group_read;
+	bool ksymbol;
+	bool bpf_event;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index dec6d218c31c..01b324c275b9 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -39,6 +39,7 @@
 #include "tool.h"
 #include "time-utils.h"
 #include "units.h"
+#include "cputopo.h"
 
 #include "sane_ctype.h"
 
@@ -526,17 +527,11 @@ static int write_event_desc(struct feat_fd *ff,
 static int write_cmdline(struct feat_fd *ff,
 			 struct perf_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 +552,15 @@ static int write_cmdline(struct feat_fd *ff,
 	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 cpu_topo *tp;
+	struct cpu_topology *tp;
 	u32 i;
 	int ret, j;
 
-	tp = build_cpu_topology();
+	tp = cpu_topology__new();
 	if (!tp)
 		return -1;
 
@@ -748,7 +598,7 @@ static int write_cpu_topology(struct feat_fd *ff,
 			return ret;
 	}
 done:
-	free_cpu_topo(tp);
+	cpu_topology__delete(tp);
 	return ret;
 }
 
@@ -783,112 +633,45 @@ static int write_total_mem(struct feat_fd *ff,
 	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)
 {
-	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;
-
-	if (getline(&buf, &len, fp) <= 0)
-		goto done;
+	tp = numa_topology__new();
+	if (!tp)
+		return -ENOMEM;
 
-	c = strchr(buf, '\n');
-	if (c)
-		*c = '\0';
+	ret = do_write(ff, &tp->nr, sizeof(u32));
+	if (ret < 0)
+		goto err;
 
-	node_map = cpu_map__new(buf);
-	if (!node_map)
-		goto done;
+	for (i = 0; i < tp->nr; i++) {
+		struct numa_topology_node *n = &tp->nodes[i];
 
-	nr = (u32)node_map->nr;
+		ret = do_write(ff, &n->node, sizeof(u32));
+		if (ret < 0)
+			goto err;
 
-	ret = do_write(ff, &nr, sizeof(nr));
-	if (ret < 0)
-		goto done;
+		ret = do_write(ff, &n->mem_total, sizeof(u64));
+		if (ret)
+			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;
+		ret = do_write(ff, &n->mem_free, sizeof(u64));
+		if (ret)
+			goto err;
 
-		ret = write_topo_node(ff, i);
+		ret = do_write_string(ff, n->cpus);
 		if (ret < 0)
-			break;
+			goto err;
 	}
-done:
-	free(buf);
-	fclose(fp);
-	cpu_map__put(node_map);
+
+	ret = 0;
+
+err:
+	numa_topology__delete(tp);
 	return ret;
 }
 
@@ -1042,11 +825,9 @@ static int write_cpuid(struct feat_fd *ff,
 	int ret;
 
 	ret = get_cpuid(buffer, sizeof(buffer));
-	if (!ret)
-		goto write_it;
+	if (ret)
+		return -1;
 
-	return -1;
-write_it:
 	return do_write_string(ff, buffer);
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8aad8330e392..669f961316f0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "callchain.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -11,6 +12,7 @@
 #include "evsel.h"
 #include "annotate.h"
 #include "srcline.h"
+#include "symbol.h"
 #include "thread.h"
 #include "ui/progress.h"
 #include <errno.h>
@@ -209,7 +211,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 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;
 
@@ -296,7 +298,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 	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 +313,8 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 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 +327,8 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 		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 +339,7 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 
 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 +355,7 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 
 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) {
@@ -435,8 +437,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 	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;
@@ -513,8 +515,9 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	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;
@@ -557,8 +560,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(entry, sample_self);
@@ -570,7 +575,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	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);
@@ -1279,16 +1284,17 @@ static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
 }
 
 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 +1314,10 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 
 		if (cmp < 0)
 			p = &parent->rb_left;
-		else
+		else {
 			p = &parent->rb_right;
+			leftmost = false;
+		}
 	}
 
 	new = hist_entry__new(he, true);
@@ -1343,12 +1351,12 @@ static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
 	}
 
 	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 +1403,14 @@ static int hists__hierarchy_insert_entry(struct hists *hists,
 }
 
 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 +1441,21 @@ static int hists__collapse_insert_entry(struct hists *hists,
 
 		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 +1478,7 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 
 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 +1490,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 
 	root = hists__get_rotate_entries_in(hists);
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 
 	while (next) {
 		if (session_done())
@@ -1487,7 +1498,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		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;
@@ -1558,7 +1569,7 @@ static void hierarchy_recalc_total_periods(struct hists *hists)
 	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 +1589,14 @@ static void hierarchy_recalc_total_periods(struct hists *hists)
 	}
 }
 
-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 +1604,14 @@ static void hierarchy_insert_output_entry(struct rb_root *root,
 
 		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 +1622,16 @@ static void hierarchy_insert_output_entry(struct rb_root *root,
 
 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 +1674,16 @@ static void hists__hierarchy_output_resort(struct hists *hists,
 	}
 }
 
-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 +1704,14 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
 		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 +1721,10 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 }
 
 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 +1754,14 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	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 +1775,8 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	}
 }
 
-void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+void perf_evsel__output_resort_cb(struct perf_evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg)
 {
 	bool use_callchain;
 
@@ -1768,18 +1787,23 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
 
 	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 perf_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 +1822,7 @@ struct rb_node *rb_hierarchy_last(struct rb_node *node)
 	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 +1833,7 @@ struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_di
 	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 +1871,7 @@ bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
 	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 +1989,7 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil
 	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 +1999,15 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil
 	}
 }
 
-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 +2015,24 @@ static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 
 		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 +2043,14 @@ static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 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 +2094,12 @@ static void hists__filter_hierarchy(struct hists *hists, int type, const void *a
 	 * 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 +2168,19 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered)
 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 +2193,10 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	he = hist_entry__new(pair, true);
@@ -2175,7 +2206,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 		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 +2215,16 @@ out:
 }
 
 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 +2241,16 @@ static struct hist_entry *add_dummy_hierarchy_entry(struct hists *hists,
 
 		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 +2267,9 @@ static struct hist_entry *hists__find_entry(struct hists *hists,
 	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 +2286,10 @@ static struct hist_entry *hists__find_entry(struct hists *hists,
 	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 +2314,13 @@ static struct hist_entry *hists__find_hierarchy_entry(struct rb_root *root,
 	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 +2336,7 @@ static void hists__match_hierarchy(struct rb_root *leader_root,
  */
 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 +2351,7 @@ void hists__match(struct hists *leader, struct hists *other)
 	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 +2362,13 @@ void hists__match(struct hists *leader, struct hists *other)
 
 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 +2411,7 @@ static int hists__link_hierarchy(struct hists *leader_hists,
  */
 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 +2427,7 @@ int hists__link(struct hists *leader, struct hists *other)
 	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)) {
@@ -2566,10 +2600,10 @@ int perf_hist_config(const char *var, const char *value)
 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 +2611,14 @@ int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 	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);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 664b5eda8d51..4af27fbab24f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -2,9 +2,9 @@
 #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"
@@ -13,6 +13,9 @@
 struct hist_entry;
 struct hist_entry_ops;
 struct addr_location;
+struct map_symbol;
+struct mem_info;
+struct branch_info;
 struct symbol;
 
 enum hist_filter {
@@ -70,10 +73,10 @@ struct thread;
 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;
@@ -160,8 +163,10 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   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_cb(struct perf_evsel *evsel, struct ui_progress *prog,
+				  hists__resort_cb_t cb, void *cb_arg);
 void perf_evsel__output_resort(struct perf_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,
@@ -230,7 +235,7 @@ static __pure inline bool hists__has_callchains(struct hists *hists)
 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;
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index ee6ca65f81f4..0c0180c67574 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -27,6 +27,8 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "session.h"
 #include "util.h"
 #include "thread.h"
@@ -142,7 +144,7 @@ static int intel_bts_lost(struct intel_bts *bts, struct perf_sample *sample)
 
 	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)
@@ -372,7 +374,7 @@ static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
 
 	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)
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 1b704fbea9de..23bf788f84b9 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
+perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
 
 inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
 inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 4503f3ca45ab..6e03db142091 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -26,6 +26,7 @@
 
 #include "../cache.h"
 #include "../util.h"
+#include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
 #include "intel-pt-pkt-decoder.h"
@@ -867,7 +868,7 @@ static int intel_pt_get_next_packet(struct intel_pt_decoder *decoder)
 
 		ret = intel_pt_get_packet(decoder->buf, decoder->len,
 					  &decoder->packet);
-		if (ret == INTEL_PT_NEED_MORE_BYTES &&
+		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)
@@ -1394,7 +1395,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 {
 	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;
@@ -2575,6 +2575,34 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 	}
 }
 
+#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.
@@ -2625,8 +2653,11 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 
 			/* 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 */
@@ -2689,7 +2720,7 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		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' */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 2e72373ec6df..3b497bab4324 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1411,7 +1411,7 @@ static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
 }
 
 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];
@@ -1420,7 +1420,7 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 	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)
@@ -1430,6 +1430,18 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 	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;
@@ -1676,10 +1688,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				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;
 			}
@@ -1804,7 +1813,7 @@ static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid,
 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)
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 85bab8735fa9..5c19ee001299 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -45,7 +45,7 @@ static inline unsigned int intlist__nr_entries(const struct intlist *ilist)
 /* 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 bf249552a9b0..eda28d3570bc 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>
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 7b1f06567521..1403dec189b4 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -3,12 +3,13 @@
 #define __PERF_KVM_STAT_H
 
 #include "../perf.h"
-#include "evsel.h"
-#include "evlist.h"
-#include "session.h"
 #include "tool.h"
 #include "stat.h"
 
+struct perf_evsel;
+struct perf_evlist;
+struct perf_session;
+
 struct event_key {
 	#define INVALID_KEY     (~0ULL)
 	u64 key;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 143f7057d581..61959aba7e27 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -10,6 +10,7 @@
 #include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "symbol.h"
 #include "sort.h"
 #include "strlist.h"
 #include "thread.h"
@@ -21,6 +22,7 @@
 #include "unwind.h"
 #include "linux/hash.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 
 #include "sane_ctype.h"
 #include <symbol/kallsyms.h>
@@ -41,7 +43,7 @@ static void machine__threads_init(struct machine *machine)
 
 	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);
@@ -179,7 +181,7 @@ void machine__delete_threads(struct machine *machine)
 	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);
 
@@ -222,7 +224,7 @@ void machine__delete(struct machine *machine)
 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 +236,10 @@ void machines__exit(struct machines *machines)
 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 +254,14 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 		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 +272,7 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec)
 
 	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 +281,7 @@ void machines__set_comm_exec(struct machines *machines, bool comm_exec)
 
 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 +344,7 @@ void machines__process_guests(struct machines *machines,
 {
 	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 +357,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 
 	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 +471,10 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 						  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 +492,10 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 
 		if (tid < th->tid)
 			p = &(*p)->rb_left;
-		else
+		else {
 			p = &(*p)->rb_right;
+			leftmost = false;
+		}
 	}
 
 	if (!create)
@@ -495,7 +504,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	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 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * 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;
@@ -681,6 +690,59 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	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_event.addr);
+	if (!map) {
+		map = dso__new_map(event->ksymbol_event.name);
+		if (!map)
+			return -ENOMEM;
+
+		map->start = event->ksymbol_event.addr;
+		map->pgoff = map->start;
+		map->end = map->start + event->ksymbol_event.len;
+		map_groups__insert(&machine->kmaps, map);
+	}
+
+	sym = symbol__new(event->ksymbol_event.addr, event->ksymbol_event.len,
+			  0, 0, event->ksymbol_event.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_event.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_event.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;
@@ -744,7 +806,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 	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 +826,7 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
 	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 +866,8 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 
 		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);
@@ -1107,7 +1170,7 @@ failure:
 
 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 +1178,7 @@ void machines__destroy_kernel_maps(struct machines *machines)
 		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);
 	}
 }
@@ -1680,7 +1743,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
 		down_write(&threads->lock);
-	rb_erase_init(&th->rb_node, &threads->entries);
+	rb_erase_cached(&th->rb_node, &threads->entries);
 	RB_CLEAR_NODE(&th->rb_node);
 	--threads->nr;
 	/*
@@ -1812,6 +1875,10 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 	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_event(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
@@ -2453,7 +2520,8 @@ int machine__for_each_thread(struct machine *machine,
 
 	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)
@@ -2480,7 +2548,7 @@ int machines__for_each_thread(struct machines *machines,
 	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);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a5d1da60f751..f70ab98a7bde 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,7 +4,7 @@
 
 #include <sys/types.h>
 #include <linux/rbtree.h>
-#include "map.h"
+#include "map_groups.h"
 #include "dso.h"
 #include "event.h"
 #include "rwsem.h"
@@ -29,11 +29,11 @@ struct vdso_info;
 #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 {
@@ -130,6 +130,9 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 				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);
 
@@ -137,7 +140,7 @@ typedef void (*machine__process_t)(struct machine *machine, void *data);
 
 struct machines {
 	struct machine host;
-	struct rb_root guests;
+	struct rb_root_cached guests;
 };
 
 void machines__init(struct machines *machines);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6751301a755c..fbeb0c6efaa6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -286,8 +286,8 @@ void map__put(struct map *map)
 
 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;
@@ -296,8 +296,8 @@ void map__fixup_start(struct map *map)
 
 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;
@@ -557,6 +557,12 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 	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;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 09282aa45c80..0e20749f2c55 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,12 +6,10 @@
 #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;
@@ -48,38 +46,7 @@ struct map {
 	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 rb_root	 names;
-	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);
@@ -174,18 +141,7 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
-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);
+struct srccode_state;
 
 int map__fprintf_srccode(struct map *map, u64 addr,
 			 FILE *fp, struct srccode_state *state);
@@ -198,61 +154,9 @@ void map__fixup_end(struct map *map);
 
 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);
 
diff --git a/tools/perf/util/map_groups.h b/tools/perf/util/map_groups.h
new file mode 100644
index 000000000000..4dcda33e0fdf
--- /dev/null
+++ b/tools/perf/util/map_groups.h
@@ -0,0 +1,91 @@
+/* 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;
+};
+
+#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);
+
+#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 000000000000..5a1aed9f6bb4
--- /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/metricgroup.c b/tools/perf/util/metricgroup.c
index a28f9b5cc4ff..b8d864ed4afe 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -270,7 +270,7 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
 }
 
 void metricgroup__print(bool metrics, bool metricgroups, char *filter,
-			bool raw)
+			bool raw, bool details)
 {
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
@@ -329,6 +329,12 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 					if (asprintf(&s, "%s\n%*s%s]",
 						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
+
+					if (details) {
+						if (asprintf(&s, "%s\n%*s%s]",
+							     s, 8, "[", pe->metric_expr) < 0)
+							return;
+					}
 				}
 
 				if (!s)
@@ -352,7 +358,7 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	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)
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 8a155dba0581..5c52097a5c63 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -27,6 +27,7 @@ int metricgroup__parse_groups(const struct option *opt,
 			const char *str,
 			struct rblist *metric_events);
 
-void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+void metricgroup__print(bool metrics, bool groups, char *filter,
+			bool raw, bool details);
 bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 8fc39311a30d..cdc7740fc181 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,6 +10,9 @@
 #include <sys/mman.h>
 #include <inttypes.h>
 #include <asm/bug.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
 #include "debug.h"
 #include "event.h"
 #include "mmap.h"
@@ -154,9 +157,72 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
 }
 
 #ifdef HAVE_AIO_SUPPORT
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_alloc(struct perf_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 perf_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 perf_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
+static int perf_mmap__aio_alloc(struct perf_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 perf_mmap *map, int idx)
+{
+	zfree(&(map->aio.data[idx]));
+}
+
+static int perf_mmap__aio_bind(struct perf_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 perf_mmap *map, struct mmap_params *mp)
 {
-	int delta_max, i, prio;
+	int delta_max, i, prio, ret;
 
 	map->aio.nr_cblocks = mp->nr_cblocks;
 	if (map->aio.nr_cblocks) {
@@ -177,11 +243,14 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
 		}
 		delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
 		for (i = 0; i < map->aio.nr_cblocks; ++i) {
-			map->aio.data[i] = malloc(perf_mmap__mmap_len(map));
-			if (!map->aio.data[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->cpu, mp->affinity);
+			if (ret == -1)
+				return -1;
 			/*
 			 * Use cblock.aio_fildes value different from -1
 			 * to denote started aio write operation on the
@@ -210,7 +279,7 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
 	int i;
 
 	for (i = 0; i < map->aio.nr_cblocks; ++i)
-		zfree(&map->aio.data[i]);
+		perf_mmap__aio_free(map, i);
 	if (map->aio.data)
 		zfree(&map->aio.data);
 	zfree(&map->aio.cblocks);
@@ -314,6 +383,32 @@ void perf_mmap__munmap(struct perf_mmap *map)
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
+static void build_node_mask(int node, cpu_set_t *mask)
+{
+	int c, cpu, nr_cpus;
+	const struct cpu_map *cpu_map = NULL;
+
+	cpu_map = cpu_map__online();
+	if (!cpu_map)
+		return;
+
+	nr_cpus = 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 perf_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->cpu), &map->affinity_mask);
+	else if (mp->affinity == PERF_AFFINITY_CPU)
+		CPU_SET(map->cpu, &map->affinity_mask);
+}
+
 int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
 	/*
@@ -343,6 +438,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
 	map->fd = fd;
 	map->cpu = cpu;
 
+	perf_mmap__setup_affinity_mask(map, mp);
+
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
 		return -1;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index aeb6942fdb00..e566c19b242b 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -38,6 +38,7 @@ struct perf_mmap {
 		int		 nr_cblocks;
 	} aio;
 #endif
+	cpu_set_t	affinity_mask;
 };
 
 /*
@@ -69,7 +70,7 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-	int			    prot, mask, nr_cblocks;
+	int			    prot, mask, nr_cblocks, affinity;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 920e1e6551dd..4dcc01b2532c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2540,7 +2540,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_sdt_events(NULL, NULL, name_only);
 
-	metricgroup__print(true, true, NULL, name_only);
+	metricgroup__print(true, true, NULL, name_only, details_flag);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index da8fe57691b8..44819bdb037d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -311,7 +311,7 @@ value_sym '/' event_config '/'
 	$$ = list;
 }
 |
-value_sym sep_slash_dc
+value_sym sep_slash_slash_dc
 {
 	struct list_head *list;
 	int type = $1 >> 16;
@@ -702,7 +702,7 @@ PE_VALUE PE_ARRAY_RANGE PE_VALUE
 
 sep_dc: ':' |
 
-sep_slash_dc: '/' | ':' |
+sep_slash_slash_dc: '/' '/' | ':' |
 
 %%
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 11a234740632..51d437f55d18 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -29,8 +29,6 @@ struct perf_pmu_format {
 	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;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 76fecec7b3f9..47253c3daf55 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 @@ enum {
 };
 
 #define PERF_PMU_FORMAT_BITS 64
+#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
 
 struct perf_event_attr;
 
@@ -29,7 +31,6 @@ struct perf_pmu {
 	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 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 18a59fba97ff..0030f9b9bf7e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -35,11 +35,14 @@
 
 #include "util.h"
 #include "event.h"
+#include "namespaces.h"
 #include "strlist.h"
 #include "strfilter.h"
 #include "debug.h"
 #include "cache.h"
 #include "color.h"
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
 #include "thread.h"
 #include <api/fs/fs.h>
@@ -3528,7 +3531,8 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
 	/* 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 15a98c3a2a2f..05c8d571a901 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 {
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 0b1195cad0e5..4062bc4412a9 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -20,6 +20,7 @@
 #include <sys/types.h>
 #include <sys/uio.h>
 #include <unistd.h>
+#include "namespaces.h"
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index a920f702a74d..376e86cb4c3c 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -140,12 +140,12 @@ struct __name##_sorted *__name = __name##_sorted__new
 
 /* 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 0efc3258c648..11e07fab20dc 100644
--- a/tools/perf/util/rblist.c
+++ b/tools/perf/util/rblist.c
@@ -13,8 +13,9 @@
 
 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 +25,10 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry)
 		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 +38,7 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry)
 		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 +46,7 @@ int rblist__add_node(struct rblist *rblist, const void *new_entry)
 
 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 +55,9 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist,
 					 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 +67,10 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist,
 		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 +79,8 @@ static struct rb_node *__rblist__findnew(struct rblist *rblist,
 		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 +101,7 @@ struct rb_node *rblist__findnew(struct rblist *rblist, const void *entry)
 void rblist__init(struct rblist *rblist)
 {
 	if (rblist != NULL) {
-		rblist->entries	 = RB_ROOT;
+		rblist->entries	 = RB_ROOT_CACHED;
 		rblist->nr_entries = 0;
 	}
 
@@ -103,7 +110,7 @@ void rblist__init(struct rblist *rblist)
 
 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 +131,8 @@ struct rb_node *rblist__entry(const struct rblist *rblist, unsigned int idx)
 {
 	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 76df15c27f5f..14b232a4d0b6 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/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
new file mode 100644
index 000000000000..d4356030b504
--- /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 68b2570304ec..c215704931dc 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -162,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "s390-cpumcf-kernel.h"
 #include "config.h"
 
 struct s390_cpumsf {
@@ -184,8 +185,58 @@ struct s390_cpumsf_queue {
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
 	FILE			*logfile;
+	FILE			*logfile_ctr;
 };
 
+/* 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 */
 static bool s390_cpumsf_basic_show(const char *color, size_t pos,
 				   struct hws_basic_entry *basic)
@@ -301,6 +352,11 @@ static bool s390_cpumsf_validate(int machine_type,
 			*dsdes = 85;
 			*bsdes = 32;
 			break;
+		case 2964:
+		case 2965:
+			*dsdes = 112;
+			*bsdes = 32;
+			break;
 		default:
 			/* Illegal trailer entry */
 			return false;
@@ -768,7 +824,7 @@ static int s390_cpumsf_process_queues(struct s390_cpumsf *sf, u64 timestamp)
 }
 
 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;
@@ -776,7 +832,7 @@ static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
 
 	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)
@@ -788,11 +844,12 @@ static int s390_cpumsf_synth_error(struct s390_cpumsf *sf, int code, int cpu,
 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)
@@ -801,6 +858,8 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
 					      struct s390_cpumsf,
 					      auxtrace);
 	u64 timestamp = sample->time;
+	struct perf_evsel *ev_bc000;
+
 	int err = 0;
 
 	if (dump_trace)
@@ -811,6 +870,16 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
 		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->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);
@@ -891,9 +960,15 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
 						queues->queue_array[i].priv;
 
-		if (sfq != NULL && sfq->logfile) {
-			fclose(sfq->logfile);
-			sfq->logfile = NULL;
+		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);
 	}
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
new file mode 100644
index 000000000000..6650f599ed9c
--- /dev/null
+++ b/tools/perf/util/s390-sample-raw.c
@@ -0,0 +1,222 @@
+// 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 "util.h"
+#include "auxtrace.h"
+#include "session.h"
+#include "evlist.h"
+#include "config.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 perf_evlist *evlist, union perf_event *event,
+				  struct perf_sample *sample)
+{
+	struct perf_evsel *ev_bc000;
+
+	if (event->header.type != PERF_RECORD_SAMPLE)
+		return;
+
+	ev_bc000 = perf_evlist__event2evsel(evlist, event);
+	if (ev_bc000 == NULL ||
+	    ev_bc000->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 000000000000..c21e1311fb0f
--- /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 perf_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 000000000000..95d445c87e93
--- /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 perf_evlist;
+union perf_event;
+struct perf_sample;
+
+void perf_evlist__s390_sample_raw(struct perf_evlist *evlist,
+				  union perf_event *event,
+				  struct perf_sample *sample);
+
+void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist);
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 82d28c67e0f3..7b342ce38d99 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,5 +1,5 @@
-libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
-libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
+perf-$(CONFIG_LIBPERL)   += trace-event-perl.o
+perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
 CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b93f36b887b5..5f06378a482b 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -37,6 +37,8 @@
 #include "../../perf.h"
 #include "../callchain.h"
 #include "../machine.h"
+#include "../map.h"
+#include "../symbol.h"
 #include "../thread.h"
 #include "../event.h"
 #include "../trace-event.h"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 87ef16a1b17e..0e17db41b49b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -44,6 +44,8 @@
 #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"
@@ -733,8 +735,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 		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->attr, sizeof(evsel->attr)));
 
 	pydict_set_item_string_decref(dict_sample, "pid",
 			_PyLong_FromLong(sample->pid));
@@ -1494,34 +1495,40 @@ static void _free_command_line(wchar_t **command_line, int num)
 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
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5456c84c7dd1..c764bbc91009 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -13,6 +13,8 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "memswap.h"
+#include "map.h"
+#include "symbol.h"
 #include "session.h"
 #include "tool.h"
 #include "sort.h"
@@ -23,6 +25,7 @@
 #include "auxtrace.h"
 #include "thread.h"
 #include "thread-stack.h"
+#include "sample-raw.h"
 #include "stat.h"
 #include "arch/common.h"
 
@@ -147,6 +150,8 @@ struct perf_session *perf_session__new(struct perf_data *data,
 				perf_session__set_id_hdr_size(session);
 				perf_session__set_comm_exec(session);
 			}
+
+			perf_evlist__init_trace_event_sample_raw(session->evlist);
 		}
 	} else  {
 		session->machines.host.env = &perf_env;
@@ -376,6 +381,10 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		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_event == NULL)
+		tool->bpf_event = perf_event__process_bpf_event;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -694,7 +703,10 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
 	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,
@@ -1065,6 +1077,8 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event,
 	       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);
@@ -1188,6 +1202,13 @@ static int deliver_sample_value(struct perf_evlist *evlist,
 		return 0;
 	}
 
+	/*
+	 * There's no reason to deliver sample
+	 * for zero period, bail out.
+	 */
+	if (!sample->period)
+		return 0;
+
 	return tool->sample(tool, event, sample, sid->evsel, machine);
 }
 
@@ -1305,6 +1326,10 @@ static int machines__deliver_event(struct machines *machines,
 	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_event(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
@@ -1820,38 +1845,35 @@ fetch_mmaped_event(struct perf_session *session,
 #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 {
+	int	fd;
+	u64	data_size;
+	u64	data_offset;
+};
+
+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;
-
-	if (data_size == 0)
-		goto out;
+	head = rd->data_offset - page_offset;
 
-	if (data_offset + data_size < file_size)
-		file_size = data_offset + data_size;
+	ui_progress__init_size(prog, data_size, "Processing events...");
 
-	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 +1887,12 @@ static int __perf_session__process_events(struct perf_session *session,
 		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);
@@ -1902,7 +1924,7 @@ more:
 		       file_offset + head, event->header.size,
 		       event->header.type);
 		err = -EINVAL;
-		goto out_err;
+		goto out;
 	}
 
 	if (skip)
@@ -1911,15 +1933,40 @@ more:
 	head += size;
 	file_pos += size;
 
-	ui_progress__update(&prog, size);
+	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 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,
+	};
+	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)
@@ -1944,20 +1991,13 @@ out_err:
 
 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)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 64d1f36dee99..5b5a167b43ce 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,5 +1,3 @@
-#!/usr/bin/python
-
 from os import getenv
 from subprocess import Popen, PIPE
 from re import sub
@@ -55,9 +53,14 @@ ext_sources = [f.strip() for f in open('util/python-ext-sources')
 # 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' ]
+
 perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
+		  libraries = extra_libraries,
 		  extra_compile_args = cflags,
 		  extra_objects = [libtraceevent, libapikfs],
                  )
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 6c1a83768eb0..d2299e912e59 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
+#include "map.h"
 #include "symbol.h"
 #include "thread.h"
 #include "evsel.h"
@@ -230,8 +231,14 @@ static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 	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);
@@ -428,8 +435,6 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 {
 
 	struct symbol *sym = he->ms.sym;
-	struct map *map = he->ms.map;
-	struct perf_evsel *evsel = hists_to_evsel(he->hists);
 	struct annotation *notes;
 	double ipc = 0.0, coverage = 0.0;
 	char tmp[64];
@@ -437,11 +442,6 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 	if (!sym)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 
-	if (!sym->annotate2 && symbol__annotate2(sym, map, evsel,
-		&annotation__default_options, NULL) < 0) {
-		return 0;
-	}
-
 	notes = symbol__annotation(sym);
 
 	if (notes->hit_cycles)
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 130fe37fe2df..2fbee0b1011c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -9,7 +9,8 @@
 #include <linux/list.h>
 #include "cache.h"
 #include <linux/rbtree.h>
-#include "symbol.h"
+#include "map_symbol.h"
+#include "symbol_conf.h"
 #include "string.h"
 #include "callchain.h"
 #include "values.h"
@@ -145,8 +146,8 @@ struct hist_entry {
 	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 */
 	};
diff --git a/tools/perf/util/srccode.h b/tools/perf/util/srccode.h
index e500a746d5f1..1b5ed769779c 100644
--- a/tools/perf/util/srccode.h
+++ b/tools/perf/util/srccode.h
@@ -1,6 +1,19 @@
 #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);
 
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index dc86597d0cc4..10ca1533937e 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -104,7 +104,7 @@ static struct symbol *new_inline_sym(struct dso *dso,
 	} 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);
@@ -594,11 +594,12 @@ struct srcline_node {
 	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) {
@@ -614,16 +615,18 @@ void srcline__tree_insert(struct rb_root *tree, u64 addr, char *srcline)
 		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,
@@ -640,15 +643,15 @@ char *srcline__tree_find(struct rb_root *tree, u64 addr)
 	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);
 	}
@@ -682,28 +685,32 @@ void inline_node__delete(struct inline_node *node)
 	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,
@@ -720,15 +727,15 @@ struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
 	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 5762212dc342..b11a0aaaa676 100644
--- a/tools/perf/util/srcline.h
+++ b/tools/perf/util/srcline.h
@@ -19,11 +19,11 @@ 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")
 
@@ -46,10 +46,11 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 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
index 665ee374fc01..6d043c78f3c2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -2,6 +2,7 @@
 #include <inttypes.h>
 #include <linux/time64.h>
 #include <math.h>
+#include "color.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "stat.h"
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 3c22c58b3e90..83d8094be4fe 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -168,7 +168,7 @@ static void reset_stat(struct runtime_stat *st)
 	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);
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index d58f1e08b170..7e82c71dcc42 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -57,7 +57,7 @@ static inline unsigned int strlist__nr_entries(const struct strlist *slist)
 /* 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/symbol-elf.c b/tools/perf/util/symbol-elf.c
index dca7dfae69ad..4ad106a5f2c0 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,8 @@
 #include <unistd.h>
 #include <inttypes.h>
 
+#include "map.h"
+#include "map_groups.h"
 #include "symbol.h"
 #include "demangle-java.h"
 #include "demangle-rust.h"
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 7119df77dc0b..17edbd4f6f85 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -3,6 +3,7 @@
 #include "util.h"
 
 #include <errno.h>
+#include <unistd.h>
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 48efad6d0f90..758bf5f74e6e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -17,6 +17,7 @@
 #include "util.h"
 #include "debug.h"
 #include "machine.h"
+#include "map.h"
 #include "symbol.h"
 #include "strlist.h"
 #include "intlist.h"
@@ -163,7 +164,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	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 +172,7 @@ void symbols__fixup_duplicate(struct rb_root *symbols)
 	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 +187,20 @@ again:
 			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)
@@ -282,25 +283,27 @@ void symbol__delete(struct symbol *sym)
 	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 +321,28 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
 		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 +358,9 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 	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 +368,9 @@ static struct symbol *symbols__first(struct rb_root *symbols)
 	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 +388,12 @@ static struct symbol *symbols__next(struct symbol *sym)
 	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 +402,21 @@ static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 		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 +439,7 @@ int symbol__match_symbol_name(const char *name, const char *str,
 		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 +449,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 	if (symbols == NULL)
 		return NULL;
 
-	n = symbols->rb_node;
+	n = symbols->rb_root.rb_node;
 
 	while (n) {
 		int cmp;
@@ -644,7 +652,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 {
 	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;
@@ -681,14 +689,14 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct
 	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;
@@ -696,8 +704,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct
 		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';
@@ -710,6 +718,8 @@ static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct
 		}
 
 		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);
@@ -734,8 +744,8 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso,
 	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;
 
@@ -849,7 +859,7 @@ static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso,
 		}
 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
@@ -857,7 +867,7 @@ add_symbol:
 
 		continue;
 discard_symbol:
-		rb_erase(&pos->rb_node, root);
+		rb_erase_cached(&pos->rb_node, root);
 		symbol__delete(pos);
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 14d9d438e7e2..9a8fe012910a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -5,16 +5,13 @@
 #include <linux/types.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 "map_symbol.h"
+#include "branch.h"
 #include "path.h"
+#include "symbol_conf.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -24,6 +21,10 @@
 
 #include "dso.h"
 
+struct map;
+struct map_groups;
+struct option;
+
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -68,7 +69,7 @@ struct symbol {
 };
 
 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)
  *
@@ -77,7 +78,7 @@ void symbols__delete(struct rb_root *symbols);
  * @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))
 
@@ -89,69 +90,6 @@ static inline size_t symbol__size(const struct symbol *sym)
 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,
-			*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;
-       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;
@@ -178,19 +116,6 @@ struct ref_reloc_sym {
 	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;
@@ -310,10 +235,11 @@ 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);
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
new file mode 100644
index 000000000000..fffea68c1203
--- /dev/null
+++ b/tools/perf/util/symbol_conf.h
@@ -0,0 +1,73 @@
+/* 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 {
+	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,
+			*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;
+       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;
+
+#endif // __PERF_SYMBOL_CONF
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index ed0205cc7942..02e89b02c2ce 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -3,6 +3,7 @@
 #include <inttypes.h>
 #include <stdio.h>
 
+#include "map.h"
 #include "symbol.h"
 
 size_t symbol__fprintf(struct symbol *sym, FILE *fp)
@@ -64,7 +65,7 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 	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/thread-stack.c b/tools/perf/util/thread-stack.c
index d52f27f373ce..a8b45168513c 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -20,6 +20,7 @@
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
+#include "env.h"
 #include "util.h"
 #include "debug.h"
 #include "symbol.h"
@@ -29,6 +30,19 @@
 
 #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
@@ -38,6 +52,7 @@
  * @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;
@@ -47,6 +62,7 @@ struct thread_stack_entry {
 	struct call_path *cp;
 	bool no_call;
 	bool trace_end;
+	bool non_call;
 };
 
 /**
@@ -62,6 +78,7 @@ struct thread_stack_entry {
  * @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;
@@ -74,6 +91,7 @@ struct thread_stack {
 	struct call_return_processor *crp;
 	struct comm *comm;
 	unsigned int arr_sz;
+	enum retpoline_state_t rstate;
 };
 
 /*
@@ -113,10 +131,16 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread,
 	if (err)
 		return err;
 
-	if (thread->mg && thread->mg->machine)
-		ts->kernel_start = machine__kernel_start(thread->mg->machine);
-	else
+	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;
@@ -268,6 +292,8 @@ static int thread_stack__call_return(struct thread *thread,
 		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);
 }
@@ -493,6 +519,9 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	struct thread_stack_entry *tse;
 	int err;
 
+	if (!cp)
+		return -ENOMEM;
+
 	if (ts->cnt == ts->sz) {
 		err = thread_stack__grow(ts);
 		if (err)
@@ -507,6 +536,7 @@ static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
 	tse->cp = cp;
 	tse->no_call = no_call;
 	tse->trace_end = trace_end;
+	tse->non_call = false;
 
 	return 0;
 }
@@ -528,14 +558,16 @@ static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
 							 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) {
@@ -576,8 +608,6 @@ static int thread_stack__bottom(struct thread_stack *ts,
 
 	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
 				ts->kernel_start);
-	if (!cp)
-		return -ENOMEM;
 
 	return thread_stack__push_cp(ts, ip, sample->time, ref, cp,
 				     true, false);
@@ -590,36 +620,36 @@ static int thread_stack__no_call_return(struct thread *thread,
 					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);
+							tm, ref, true);
 			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, false);
+			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);
+							tm, ref, true);
 			if (err)
 				return err;
 		}
@@ -628,21 +658,59 @@ static int thread_stack__no_call_return(struct thread *thread,
 	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;
+		}
+
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, root, tsym, addr, ks);
 
-	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
-				    true, false);
+			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,
@@ -680,8 +748,6 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 
 	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;
 
@@ -689,6 +755,70 @@ static int thread_stack__trace_end(struct thread_stack *ts,
 				     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,
 			  struct perf_sample *sample,
 			  struct addr_location *from_al,
@@ -696,6 +826,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 			  struct call_return_processor *crp)
 {
 	struct thread_stack *ts = thread__stack(thread, sample->cpu);
+	enum retpoline_state_t rstate;
 	int err = 0;
 
 	if (ts && !ts->crp) {
@@ -711,6 +842,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		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);
@@ -745,14 +880,27 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		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, 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)
 			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) {
@@ -765,6 +913,25 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 		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;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 1f626f4a1c40..b7c04e19ad41 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -35,10 +35,13 @@ struct call_path;
  *
  * 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,
 };
 
 /**
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index c83372329f89..4c179fef442d 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -12,6 +12,7 @@
 #include "debug.h"
 #include "namespaces.h"
 #include "comm.h"
+#include "symbol.h"
 #include "unwind.h"
 
 #include <api/fs/fs.h>
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 712dd48cc0ca..8276ffeec556 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -5,14 +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 "map.h"
+#include "srccode.h"
+#include "symbol_conf.h"
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
 
+struct addr_location;
+struct map;
+struct namespaces_event;
 struct thread_stack;
 struct unwind_libunwind_ops;
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 56e4ca54020a..250391672f9f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -53,7 +53,10 @@ struct perf_tool {
 			itrace_start,
 			context_switch,
 			throttle,
-			unthrottle;
+			unthrottle,
+			ksymbol,
+			bpf_event;
+
 	event_attr_op	attr;
 	event_attr_op	event_update;
 	event_op2	tracing_data;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5eff9bfc5758..407d0167b942 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -8,6 +8,8 @@
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
+#include "map.h"
+#include "symbol.h"
 #include "thread.h"
 #include <linux/types.h>
 #include "event.h"
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 79f521a552cf..f3c666a84e4d 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -34,6 +34,7 @@
 #include "session.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "map.h"
 #include "symbol.h"
 #include "util.h"
 #include "debug.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index b029a5e9ae49..9778b3133b77 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "unwind.h"
+#include "map.h"
 #include "thread.h"
 #include "session.h"
 #include "debug.h"
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 093352e93d50..d388f80d8703 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -2,6 +2,7 @@
 #include "../perf.h"
 #include "util.h"
 #include "debug.h"
+#include "namespaces.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
@@ -20,6 +21,7 @@
 #include <linux/time64.h>
 #include <unistd.h>
 #include "strlist.h"
+#include "string2.h"
 
 /*
  * XXX We need to find a better place for these things...
@@ -116,23 +118,67 @@ int mkdir_p(char *path, mode_t mode)
 	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;
 
+	/* 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 0;
+		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))
+			return -2;
+
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
 
@@ -144,7 +190,7 @@ int rm_rf(const char *path)
 		}
 
 		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 +202,22 @@ int rm_rf(const char *path)
 	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)
 {
@@ -506,3 +568,13 @@ out:
 
 	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 ece040b799f6..09c1b0f91f65 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -31,6 +31,7 @@ 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);
@@ -76,6 +77,8 @@ 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/vdso.c b/tools/perf/util/vdso.c
index 3702cba11d7d..5031b7b22bbd 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,6 +11,7 @@
 
 #include "vdso.h"
 #include "util.h"
+#include "map.h"
 #include "symbol.h"
 #include "machine.h"
 #include "thread.h"
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 902ce6384f57..512ad7c09b13 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -6,7 +6,6 @@
 #include <sys/mman.h>
 #include <zlib.h>
 #include <linux/compiler.h>
-#include <unistd.h>
 
 #include "util/compress.h"
 #include "util/util.h"