Merge branch 'next' into for-linus

Prepare input updates for 6.11 merge window.

192 files changed, 10523 insertions, 8757 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 96f4ea1d45c5..e0a723e24503 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,6 @@
+include $(srctree)/tools/scripts/Makefile.include
+include $(srctree)/tools/scripts/utilities.mak
+
 perf-y += arm64-frame-pointer-unwind-support.o
 perf-y += addr_location.o
 perf-y += annotate.o
@@ -20,15 +23,16 @@ perf-y += evswitch.o
 perf-y += find_bit.o
 perf-y += get_current_dir_name.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 += print-events.o
 perf-y += tracepoint.o
 perf-y += perf_regs.o
+perf-y += perf-regs-arch/
 perf-y += path.o
 perf-y += print_binary.o
+perf-y += print_insn.o
 perf-y += rlimit.o
 perf-y += argv_split.o
 perf-y += rbtree.o
@@ -46,6 +50,7 @@ perf-y += dso.o
 perf-y += dsos.o
 perf-y += symbol.o
 perf-y += symbol_fprintf.o
+perf-y += map_symbol.o
 perf-y += color.o
 perf-y += color_config.o
 perf-y += metricgroup.o
@@ -67,6 +72,7 @@ perf-y += ordered-events.o
 perf-y += namespaces.o
 perf-y += comm.o
 perf-y += thread.o
+perf-y += threads.o
 perf-y += thread_map.o
 perf-y += parse-events-flex.o
 perf-y += parse-events-bison.o
@@ -147,7 +153,6 @@ perf-y += list_sort.o
 perf-y += mutex.o
 perf-y += sharded_mutex.o
 
-perf-$(CONFIG_LIBBPF) += bpf-loader.o
 perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
@@ -163,9 +168,9 @@ endif
 
 ifeq ($(CONFIG_LIBTRACEEVENT),y)
   perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o
+  perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork_top.o
 endif
 
-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
@@ -192,6 +197,8 @@ endif
 perf-$(CONFIG_DWARF) += probe-finder.o
 perf-$(CONFIG_DWARF) += dwarf-aux.o
 perf-$(CONFIG_DWARF) += dwarf-regs.o
+perf-$(CONFIG_DWARF) += debuginfo.o
+perf-$(CONFIG_DWARF) += annotate-data.o
 
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
@@ -229,12 +236,9 @@ perf-y += perf-hooks.o
 perf-$(CONFIG_LIBBPF) += bpf-event.o
 perf-$(CONFIG_LIBBPF) += bpf-utils.o
 
-perf-$(CONFIG_CXX) += c++/
-
 perf-$(CONFIG_LIBPFM4) += pfm.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_llvm-utils.o += -DLIBBPF_INCLUDE_DIR="BUILD_STR($(libbpf_include_dir_SQ))"
 
 # avoid compiler warnings in 32-bit mode
 CFLAGS_genelf_debug.o  += -Wno-packed
@@ -246,7 +250,7 @@ $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-flex.h: util/parse-
 
 $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/parse-events-bison.h: util/parse-events.y
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
+	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) $(BISON_FALLBACK_FLAGS) \
 		-o $(OUTPUT)util/parse-events-bison.c -p parse_events_
 
 $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-flex.h: util/expr.l $(OUTPUT)util/expr-bison.c
@@ -279,28 +283,58 @@ $(OUTPUT)util/bpf-filter-bison.c $(OUTPUT)util/bpf-filter-bison.h: util/bpf-filt
 	$(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \
 		-o $(OUTPUT)util/bpf-filter-bison.c -p perf_bpf_filter_
 
-FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e  's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26)
-ifeq ($(FLEX_GE_26),1)
-  flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations
-  CC_HASNT_MISLEADING_INDENTATION := $(shell echo "int main(void) { return 0 }" | $(CC) -Werror -Wno-misleading-indentation -o /dev/null -xc - 2>&1 | grep -q -- -Wno-misleading-indentation ; echo $$?)
-  ifeq ($(CC_HASNT_MISLEADING_INDENTATION), 1)
-    flex_flags += -Wno-misleading-indentation
+FLEX_VERSION := $(shell $(FLEX) --version | cut -d' ' -f2)
+
+FLEX_GE_260 := $(call version-ge3,$(FLEX_VERSION),2.6.0)
+ifeq ($(FLEX_GE_260),1)
+  flex_flags := -Wno-redundant-decls -Wno-switch-default -Wno-unused-function -Wno-misleading-indentation
+
+  # Some newer clang and gcc version complain about this
+  # util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable]
+  #  int yynerrs = 0;
+
+  flex_flags += -Wno-unused-but-set-variable
+
+  FLEX_LT_262 := $(call version-lt3,$(FLEX_VERSION),2.6.2)
+  ifeq ($(FLEX_LT_262),1)
+    flex_flags += -Wno-sign-compare
   endif
 else
   flex_flags := -w
 endif
-CFLAGS_parse-events-flex.o  += $(flex_flags)
-CFLAGS_pmu-flex.o           += $(flex_flags)
-CFLAGS_expr-flex.o          += $(flex_flags)
-CFLAGS_bpf-filter-flex.o    += $(flex_flags)
 
-bison_flags := -DYYENABLE_NLS=0
-BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35)
-ifeq ($(BISON_GE_35),1)
-  bison_flags += -Wno-unused-parameter -Wno-nested-externs -Wno-implicit-function-declaration -Wno-switch-enum -Wno-unused-but-set-variable -Wno-unknown-warning-option
+# Some newer clang and gcc version complain about this
+# util/parse-events-bison.c:1317:9: error: variable 'parse_events_nerrs' set but not used [-Werror,-Wunused-but-set-variable]
+#  int yynerrs = 0;
+
+bison_flags := -DYYENABLE_NLS=0 -Wno-unused-but-set-variable
+
+# Old clangs don't grok -Wno-unused-but-set-variable, remove it
+ifeq ($(CC_NO_CLANG), 0)
+  CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g')
+  ifeq ($(call version-lt3,$(CLANG_VERSION),13.0.0),1)
+    bison_flags := $(subst -Wno-unused-but-set-variable,,$(bison_flags))
+    flex_flags := $(subst -Wno-unused-but-set-variable,,$(flex_flags))
+  endif
+endif
+
+BISON_GE_382 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 382)
+ifeq ($(BISON_GE_382),1)
+  bison_flags += -Wno-switch-enum
 else
   bison_flags += -w
 endif
+
+BISON_LT_381 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \< 381)
+ifeq ($(BISON_LT_381),1)
+  bison_flags += -DYYNOMEM=YYABORT
+endif
+
+CFLAGS_parse-events-flex.o  += $(flex_flags) -Wno-unused-label
+CFLAGS_pmu-flex.o           += $(flex_flags)
+CFLAGS_expr-flex.o          += $(flex_flags)
+CFLAGS_bpf-filter-flex.o    += $(flex_flags)
+
 CFLAGS_parse-events-bison.o += $(bison_flags)
 CFLAGS_pmu-bison.o          += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
 CFLAGS_expr-bison.o         += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags)
@@ -316,10 +350,8 @@ CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_parse-events.o  += -Wno-redundant-decls
-CFLAGS_expr.o          += -Wno-redundant-decls
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
-CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/
+CFLAGS_arm-spe.o       += -I$(srctree)/tools/arch/arm64/include/ -I$(OUTPUT)arch/arm64/include/generated/
 
 $(OUTPUT)util/argv_split.o: ../lib/argv_split.c FORCE
 	$(call rule_mkdir)
diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c
index 6a6ddba76c75..9d0ce88e90e4 100644
--- a/tools/perf/util/amd-sample-raw.c
+++ b/tools/perf/util/amd-sample-raw.c
@@ -15,7 +15,6 @@
 #include "session.h"
 #include "evlist.h"
 #include "sample-raw.h"
-#include "pmu-events/pmu-events.h"
 #include "util/sample.h"
 
 static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type;
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
new file mode 100644
index 000000000000..30c4d19fcf11
--- /dev/null
+++ b/tools/perf/util/annotate-data.c
@@ -0,0 +1,486 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Convert sample address to data type using DWARF debug info.
+ *
+ * Written by Namhyung Kim <namhyung@kernel.org>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <inttypes.h>
+
+#include "annotate.h"
+#include "annotate-data.h"
+#include "debuginfo.h"
+#include "debug.h"
+#include "dso.h"
+#include "dwarf-regs.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "map.h"
+#include "map_symbol.h"
+#include "strbuf.h"
+#include "symbol.h"
+#include "symbol_conf.h"
+
+/*
+ * Compare type name and size to maintain them in a tree.
+ * I'm not sure if DWARF would have information of a single type in many
+ * different places (compilation units).  If not, it could compare the
+ * offset of the type entry in the .debug_info section.
+ */
+static int data_type_cmp(const void *_key, const struct rb_node *node)
+{
+	const struct annotated_data_type *key = _key;
+	struct annotated_data_type *type;
+
+	type = rb_entry(node, struct annotated_data_type, node);
+
+	if (key->self.size != type->self.size)
+		return key->self.size - type->self.size;
+	return strcmp(key->self.type_name, type->self.type_name);
+}
+
+static bool data_type_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+	struct annotated_data_type *a, *b;
+
+	a = rb_entry(node_a, struct annotated_data_type, node);
+	b = rb_entry(node_b, struct annotated_data_type, node);
+
+	if (a->self.size != b->self.size)
+		return a->self.size < b->self.size;
+	return strcmp(a->self.type_name, b->self.type_name) < 0;
+}
+
+/* Recursively add new members for struct/union */
+static int __add_member_cb(Dwarf_Die *die, void *arg)
+{
+	struct annotated_member *parent = arg;
+	struct annotated_member *member;
+	Dwarf_Die member_type, die_mem;
+	Dwarf_Word size, loc;
+	Dwarf_Attribute attr;
+	struct strbuf sb;
+	int tag;
+
+	if (dwarf_tag(die) != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	member = zalloc(sizeof(*member));
+	if (member == NULL)
+		return DIE_FIND_CB_END;
+
+	strbuf_init(&sb, 32);
+	die_get_typename(die, &sb);
+
+	die_get_real_type(die, &member_type);
+	if (dwarf_aggregate_size(&member_type, &size) < 0)
+		size = 0;
+
+	if (!dwarf_attr_integrate(die, DW_AT_data_member_location, &attr))
+		loc = 0;
+	else
+		dwarf_formudata(&attr, &loc);
+
+	member->type_name = strbuf_detach(&sb, NULL);
+	/* member->var_name can be NULL */
+	if (dwarf_diename(die))
+		member->var_name = strdup(dwarf_diename(die));
+	member->size = size;
+	member->offset = loc + parent->offset;
+	INIT_LIST_HEAD(&member->children);
+	list_add_tail(&member->node, &parent->children);
+
+	tag = dwarf_tag(&member_type);
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		die_find_child(&member_type, __add_member_cb, member, &die_mem);
+		break;
+	default:
+		break;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+static void add_member_types(struct annotated_data_type *parent, Dwarf_Die *type)
+{
+	Dwarf_Die die_mem;
+
+	die_find_child(type, __add_member_cb, &parent->self, &die_mem);
+}
+
+static void delete_members(struct annotated_member *member)
+{
+	struct annotated_member *child, *tmp;
+
+	list_for_each_entry_safe(child, tmp, &member->children, node) {
+		list_del(&child->node);
+		delete_members(child);
+		free(child->type_name);
+		free(child->var_name);
+		free(child);
+	}
+}
+
+static struct annotated_data_type *dso__findnew_data_type(struct dso *dso,
+							  Dwarf_Die *type_die)
+{
+	struct annotated_data_type *result = NULL;
+	struct annotated_data_type key;
+	struct rb_node *node;
+	struct strbuf sb;
+	char *type_name;
+	Dwarf_Word size;
+
+	strbuf_init(&sb, 32);
+	if (die_get_typename_from_type(type_die, &sb) < 0)
+		strbuf_add(&sb, "(unknown type)", 14);
+	type_name = strbuf_detach(&sb, NULL);
+	dwarf_aggregate_size(type_die, &size);
+
+	/* Check existing nodes in dso->data_types tree */
+	key.self.type_name = type_name;
+	key.self.size = size;
+	node = rb_find(&key, &dso->data_types, data_type_cmp);
+	if (node) {
+		result = rb_entry(node, struct annotated_data_type, node);
+		free(type_name);
+		return result;
+	}
+
+	/* If not, add a new one */
+	result = zalloc(sizeof(*result));
+	if (result == NULL) {
+		free(type_name);
+		return NULL;
+	}
+
+	result->self.type_name = type_name;
+	result->self.size = size;
+	INIT_LIST_HEAD(&result->self.children);
+
+	if (symbol_conf.annotate_data_member)
+		add_member_types(result, type_die);
+
+	rb_add(&result->node, &dso->data_types, data_type_less);
+	return result;
+}
+
+static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
+{
+	Dwarf_Off off, next_off;
+	size_t header_size;
+
+	if (dwarf_addrdie(di->dbg, pc, cu_die) != NULL)
+		return cu_die;
+
+	/*
+	 * There are some kernels don't have full aranges and contain only a few
+	 * aranges entries.  Fallback to iterate all CU entries in .debug_info
+	 * in case it's missing.
+	 */
+	off = 0;
+	while (dwarf_nextcu(di->dbg, off, &next_off, &header_size,
+			    NULL, NULL, NULL) == 0) {
+		if (dwarf_offdie(di->dbg, off + header_size, cu_die) &&
+		    dwarf_haspc(cu_die, pc))
+			return true;
+
+		off = next_off;
+	}
+	return false;
+}
+
+/* The type info will be saved in @type_die */
+static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
+			  bool is_pointer)
+{
+	Dwarf_Word size;
+
+	/* Get the type of the variable */
+	if (die_get_real_type(var_die, type_die) == NULL) {
+		pr_debug("variable has no type\n");
+		ann_data_stat.no_typeinfo++;
+		return -1;
+	}
+
+	/*
+	 * Usually it expects a pointer type for a memory access.
+	 * Convert to a real type it points to.  But global variables
+	 * and local variables are accessed directly without a pointer.
+	 */
+	if (is_pointer) {
+		if ((dwarf_tag(type_die) != DW_TAG_pointer_type &&
+		     dwarf_tag(type_die) != DW_TAG_array_type) ||
+		    die_get_real_type(type_die, type_die) == NULL) {
+			pr_debug("no pointer or no type\n");
+			ann_data_stat.no_typeinfo++;
+			return -1;
+		}
+	}
+
+	/* Get the size of the actual type */
+	if (dwarf_aggregate_size(type_die, &size) < 0) {
+		pr_debug("type size is unknown\n");
+		ann_data_stat.invalid_size++;
+		return -1;
+	}
+
+	/* Minimal sanity check */
+	if ((unsigned)offset >= size) {
+		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		ann_data_stat.bad_offset++;
+		return -1;
+	}
+
+	return 0;
+}
+
+/* The result will be saved in @type_die */
+static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
+			      const char *var_name, struct annotated_op_loc *loc,
+			      Dwarf_Die *type_die)
+{
+	Dwarf_Die cu_die, var_die;
+	Dwarf_Die *scopes = NULL;
+	int reg, offset;
+	int ret = -1;
+	int i, nr_scopes;
+	int fbreg = -1;
+	bool is_fbreg = false;
+	int fb_offset = 0;
+
+	/* Get a compile_unit for this address */
+	if (!find_cu_die(di, pc, &cu_die)) {
+		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+		ann_data_stat.no_cuinfo++;
+		return -1;
+	}
+
+	reg = loc->reg1;
+	offset = loc->offset;
+
+	if (reg == DWARF_REG_PC) {
+		if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
+			ret = check_variable(&var_die, type_die, offset,
+					     /*is_pointer=*/false);
+			loc->offset = offset;
+			goto out;
+		}
+
+		if (var_name && die_find_variable_at(&cu_die, var_name, pc,
+						     &var_die)) {
+			ret = check_variable(&var_die, type_die, 0,
+					     /*is_pointer=*/false);
+			/* loc->offset will be updated by the caller */
+			goto out;
+		}
+	}
+
+	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
+	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);
+
+	if (reg != DWARF_REG_PC && dwarf_hasattr(&scopes[0], DW_AT_frame_base)) {
+		Dwarf_Attribute attr;
+		Dwarf_Block block;
+
+		/* Check if the 'reg' is assigned as frame base register */
+		if (dwarf_attr(&scopes[0], DW_AT_frame_base, &attr) != NULL &&
+		    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
+			switch (*block.data) {
+			case DW_OP_reg0 ... DW_OP_reg31:
+				fbreg = *block.data - DW_OP_reg0;
+				break;
+			case DW_OP_call_frame_cfa:
+				if (die_get_cfa(di->dbg, pc, &fbreg,
+						&fb_offset) < 0)
+					fbreg = -1;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+retry:
+	is_fbreg = (reg == fbreg);
+	if (is_fbreg)
+		offset = loc->offset - fb_offset;
+
+	/* Search from the inner-most scope to the outer */
+	for (i = nr_scopes - 1; i >= 0; i--) {
+		if (reg == DWARF_REG_PC) {
+			if (!die_find_variable_by_addr(&scopes[i], pc, addr,
+						       &var_die, &offset))
+				continue;
+		} else {
+			/* Look up variables/parameters in this scope */
+			if (!die_find_variable_by_reg(&scopes[i], pc, reg,
+						      &offset, is_fbreg, &var_die))
+				continue;
+		}
+
+		/* Found a variable, see if it's correct */
+		ret = check_variable(&var_die, type_die, offset,
+				     reg != DWARF_REG_PC && !is_fbreg);
+		loc->offset = offset;
+		goto out;
+	}
+
+	if (loc->multi_regs && reg == loc->reg1 && loc->reg1 != loc->reg2) {
+		reg = loc->reg2;
+		goto retry;
+	}
+
+	if (ret < 0)
+		ann_data_stat.no_var++;
+
+out:
+	free(scopes);
+	return ret;
+}
+
+/**
+ * find_data_type - Return a data type at the location
+ * @ms: map and symbol at the location
+ * @ip: instruction address of the memory access
+ * @loc: instruction operand location
+ * @addr: data address of the memory access
+ * @var_name: global variable name
+ *
+ * This functions searches the debug information of the binary to get the data
+ * type it accesses.  The exact location is expressed by (@ip, reg, offset)
+ * for pointer variables or (@ip, @addr) for global variables.  Note that global
+ * variables might update the @loc->offset after finding the start of the variable.
+ * If it cannot find a global variable by address, it tried to fine a declaration
+ * of the variable using @var_name.  In that case, @loc->offset won't be updated.
+ *
+ * It return %NULL if not found.
+ */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   struct annotated_op_loc *loc, u64 addr,
+					   const char *var_name)
+{
+	struct annotated_data_type *result = NULL;
+	struct dso *dso = map__dso(ms->map);
+	struct debuginfo *di;
+	Dwarf_Die type_die;
+	u64 pc;
+
+	di = debuginfo__new(dso->long_name);
+	if (di == NULL) {
+		pr_debug("cannot get the debug info\n");
+		return NULL;
+	}
+
+	/*
+	 * IP is a relative instruction address from the start of the map, as
+	 * it can be randomized/relocated, it needs to translate to PC which is
+	 * a file address for DWARF processing.
+	 */
+	pc = map__rip_2objdump(ms->map, ip);
+	if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
+		goto out;
+
+	result = dso__findnew_data_type(dso, &type_die);
+
+out:
+	debuginfo__delete(di);
+	return result;
+}
+
+static int alloc_data_type_histograms(struct annotated_data_type *adt, int nr_entries)
+{
+	int i;
+	size_t sz = sizeof(struct type_hist);
+
+	sz += sizeof(struct type_hist_entry) * adt->self.size;
+
+	/* Allocate a table of pointers for each event */
+	adt->nr_histograms = nr_entries;
+	adt->histograms = calloc(nr_entries, sizeof(*adt->histograms));
+	if (adt->histograms == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Each histogram is allocated for the whole size of the type.
+	 * TODO: Probably we can move the histogram to members.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		adt->histograms[i] = zalloc(sz);
+		if (adt->histograms[i] == NULL)
+			goto err;
+	}
+	return 0;
+
+err:
+	while (--i >= 0)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+	return -ENOMEM;
+}
+
+static void delete_data_type_histograms(struct annotated_data_type *adt)
+{
+	for (int i = 0; i < adt->nr_histograms; i++)
+		free(adt->histograms[i]);
+	free(adt->histograms);
+}
+
+void annotated_data_type__tree_delete(struct rb_root *root)
+{
+	struct annotated_data_type *pos;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node = rb_first(root);
+
+		rb_erase(node, root);
+		pos = rb_entry(node, struct annotated_data_type, node);
+		delete_members(&pos->self);
+		delete_data_type_histograms(pos);
+		free(pos->self.type_name);
+		free(pos);
+	}
+}
+
+/**
+ * annotated_data_type__update_samples - Update histogram
+ * @adt: Data type to update
+ * @evsel: Event to update
+ * @offset: Offset in the type
+ * @nr_samples: Number of samples at this offset
+ * @period: Event count at this offset
+ *
+ * This function updates type histogram at @ofs for @evsel.  Samples are
+ * aggregated before calling this function so it can be called with more
+ * than one samples at a certain offset.
+ */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period)
+{
+	struct type_hist *h;
+
+	if (adt == NULL)
+		return 0;
+
+	if (adt->histograms == NULL) {
+		int nr = evsel->evlist->core.nr_entries;
+
+		if (alloc_data_type_histograms(adt, nr) < 0)
+			return -1;
+	}
+
+	if (offset < 0 || offset >= adt->self.size)
+		return -1;
+
+	h = adt->histograms[evsel->core.idx];
+
+	h->nr_samples += nr_samples;
+	h->addr[offset].nr_samples += nr_samples;
+	h->period += period;
+	h->addr[offset].period += period;
+	return 0;
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
new file mode 100644
index 000000000000..1b0db8e8c40e
--- /dev/null
+++ b/tools/perf/util/annotate-data.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PERF_ANNOTATE_DATA_H
+#define _PERF_ANNOTATE_DATA_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+struct annotated_op_loc;
+struct evsel;
+struct map_symbol;
+
+/**
+ * struct annotated_member - Type of member field
+ * @node: List entry in the parent list
+ * @children: List head for child nodes
+ * @type_name: Name of the member type
+ * @var_name: Name of the member variable
+ * @offset: Offset from the outer data type
+ * @size: Size of the member field
+ *
+ * This represents a member type in a data type.
+ */
+struct annotated_member {
+	struct list_head node;
+	struct list_head children;
+	char *type_name;
+	char *var_name;
+	int offset;
+	int size;
+};
+
+/**
+ * struct type_hist_entry - Histogram entry per offset
+ * @nr_samples: Number of samples
+ * @period: Count of event
+ */
+struct type_hist_entry {
+	int nr_samples;
+	u64 period;
+};
+
+/**
+ * struct type_hist - Type histogram for each event
+ * @nr_samples: Total number of samples in this data type
+ * @period: Total count of the event in this data type
+ * @offset: Array of histogram entry
+ */
+struct type_hist {
+	u64			nr_samples;
+	u64			period;
+	struct type_hist_entry	addr[];
+};
+
+/**
+ * struct annotated_data_type - Data type to profile
+ * @node: RB-tree node for dso->type_tree
+ * @self: Actual type information
+ * @nr_histogram: Number of histogram entries
+ * @histograms: An array of pointers to histograms
+ *
+ * This represents a data type accessed by samples in the profile data.
+ */
+struct annotated_data_type {
+	struct rb_node node;
+	struct annotated_member self;
+	int nr_histograms;
+	struct type_hist **histograms;
+};
+
+extern struct annotated_data_type unknown_type;
+extern struct annotated_data_type stackop_type;
+
+/**
+ * struct annotated_data_stat - Debug statistics
+ * @total: Total number of entry
+ * @no_sym: No symbol or map found
+ * @no_insn: Failed to get disasm line
+ * @no_insn_ops: The instruction has no operands
+ * @no_mem_ops: The instruction has no memory operands
+ * @no_reg: Failed to extract a register from the operand
+ * @no_dbginfo: The binary has no debug information
+ * @no_cuinfo: Failed to find a compile_unit
+ * @no_var: Failed to find a matching variable
+ * @no_typeinfo: Failed to get a type info for the variable
+ * @invalid_size: Failed to get a size info of the type
+ * @bad_offset: The access offset is out of the type
+ */
+struct annotated_data_stat {
+	int total;
+	int no_sym;
+	int no_insn;
+	int no_insn_ops;
+	int no_mem_ops;
+	int no_reg;
+	int no_dbginfo;
+	int no_cuinfo;
+	int no_var;
+	int no_typeinfo;
+	int invalid_size;
+	int bad_offset;
+};
+extern struct annotated_data_stat ann_data_stat;
+
+#ifdef HAVE_DWARF_SUPPORT
+
+/* Returns data type at the location (ip, reg, offset) */
+struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
+					   struct annotated_op_loc *loc, u64 addr,
+					   const char *var_name);
+
+/* Update type access histogram at the given offset */
+int annotated_data_type__update_samples(struct annotated_data_type *adt,
+					struct evsel *evsel, int offset,
+					int nr_samples, u64 period);
+
+/* Release all data type information in the tree */
+void annotated_data_type__tree_delete(struct rb_root *root);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline struct annotated_data_type *
+find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
+	       struct annotated_op_loc *loc __maybe_unused,
+	       u64 addr __maybe_unused, const char *var_name __maybe_unused)
+{
+	return NULL;
+}
+
+static inline int
+annotated_data_type__update_samples(struct annotated_data_type *adt __maybe_unused,
+				    struct evsel *evsel __maybe_unused,
+				    int offset __maybe_unused,
+				    int nr_samples __maybe_unused,
+				    u64 period __maybe_unused)
+{
+	return -1;
+}
+
+static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ba988a13dacb..50ca92255ff6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,16 +25,20 @@
 #include "units.h"
 #include "debug.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "bpf-event.h"
 #include "bpf-utils.h"
 #include "block-range.h"
 #include "string2.h"
+#include "dwarf-regs.h"
 #include "util/event.h"
 #include "util/sharded_mutex.h"
 #include "arch/common.h"
 #include "namespaces.h"
+#include "thread.h"
+#include "hashmap.h"
 #include <regex.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
@@ -57,6 +61,9 @@
 
 #include <linux/ctype.h>
 
+/* global annotation options */
+struct annotation_options annotate_opts;
+
 static regex_t	 file_lineno;
 
 static struct ins_ops *ins__find(struct arch *arch, const char *name);
@@ -85,6 +92,8 @@ struct arch {
 	struct		{
 		char comment_char;
 		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
 	} objdump;
 };
 
@@ -96,6 +105,18 @@ static struct ins_ops nop_ops;
 static struct ins_ops lock_ops;
 static struct ins_ops ret_ops;
 
+/* Data type collection debug statistics */
+struct annotated_data_stat ann_data_stat;
+LIST_HEAD(ann_insn_stat);
+
+/* Pseudo data types */
+struct annotated_data_type stackop_type = {
+	.self = {
+		.type_name = (char *)"(stack operation)",
+		.children = LIST_HEAD_INIT(stackop_type.self.children),
+	},
+};
+
 static int arch__grow_instructions(struct arch *arch)
 {
 	struct ins *new_instructions;
@@ -188,6 +209,8 @@ static struct arch architectures[] = {
 		.insn_suffix = "bwlq",
 		.objdump =  {
 			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
 		},
 	},
 	{
@@ -340,10 +363,10 @@ bool ins__is_call(const struct ins *ins)
  */
 static inline const char *validate_comma(const char *c, struct ins_operands *ops)
 {
-	if (ops->raw_comment && c > ops->raw_comment)
+	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
 		return NULL;
 
-	if (ops->raw_func_start && c > ops->raw_func_start)
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
 		return NULL;
 
 	return c;
@@ -359,8 +382,8 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 	const char *c = strchr(ops->raw, ',');
 	u64 start, end;
 
-	ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->raw_func_start = strchr(ops->raw, '<');
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
 
 	c = validate_comma(c, ops);
 
@@ -462,7 +485,16 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			 ops->target.offset);
 }
 
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+	/*
+	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+	 * raw string, don't free them.
+	 */
+}
+
 static struct ins_ops jump_ops = {
+	.free	   = jump__delete,
 	.parse	   = jump__parse,
 	.scnprintf = jump__scnprintf,
 };
@@ -557,6 +589,34 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
 static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
@@ -584,6 +644,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->source.raw == NULL)
 		return -1;
 
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
 	target = skip_spaces(++s);
 	comment = strchr(s, arch->objdump.comment_char);
 
@@ -604,6 +666,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
 	if (comment == NULL)
 		return 0;
 
@@ -795,6 +859,22 @@ static struct arch *arch__find(const char *name)
 	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
 }
 
+bool arch__is(struct arch *arch, const char *name)
+{
+	return !strcmp(arch->name, name);
+}
+
+/* symbol histogram: key = offset << 16 | evsel->core.idx */
+static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
+{
+	return (key >> 16) + (key & 0xffff);
+}
+
+static bool sym_hist_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
 static struct annotated_source *annotated_source__new(void)
 {
 	struct annotated_source *src = zalloc(sizeof(*src));
@@ -809,54 +889,28 @@ static __maybe_unused void annotated_source__delete(struct annotated_source *src
 {
 	if (src == NULL)
 		return;
+
+	hashmap__free(src->samples);
 	zfree(&src->histograms);
-	zfree(&src->cycles_hist);
 	free(src);
 }
 
 static int annotated_source__alloc_histograms(struct annotated_source *src,
-					      size_t size, int nr_hists)
+					      int nr_hists)
 {
-	size_t sizeof_sym_hist;
-
-	/*
-	 * Add buffer of one element for zero length symbol.
-	 * When sample is taken from first instruction of
-	 * zero length symbol, perf still resolves it and
-	 * shows symbol name in perf report and allows to
-	 * annotate it.
-	 */
-	if (size == 0)
-		size = 1;
+	src->nr_histograms   = nr_hists;
+	src->histograms	     = calloc(nr_hists, sizeof(*src->histograms));
 
-	/* Check for overflow when calculating sizeof_sym_hist */
-	if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry))
+	if (src->histograms == NULL)
 		return -1;
 
-	sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry));
+	src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL);
+	if (src->samples == NULL)
+		zfree(&src->histograms);
 
-	/* Check for overflow in zalloc argument */
-	if (sizeof_sym_hist > SIZE_MAX / nr_hists)
-		return -1;
-
-	src->sizeof_sym_hist = sizeof_sym_hist;
-	src->nr_histograms   = nr_hists;
-	src->histograms	     = calloc(nr_hists, sizeof_sym_hist) ;
 	return src->histograms ? 0 : -1;
 }
 
-/* The cycles histogram is lazily allocated. */
-static int symbol__alloc_hist_cycles(struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	const size_t size = symbol__size(sym);
-
-	notes->src->cycles_hist = calloc(size, sizeof(struct cyc_hist));
-	if (notes->src->cycles_hist == NULL)
-		return -1;
-	return 0;
-}
-
 void symbol__annotate_zero_histograms(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -864,10 +918,12 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	annotation__lock(notes);
 	if (notes->src != NULL) {
 		memset(notes->src->histograms, 0,
-		       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
-		if (notes->src->cycles_hist)
-			memset(notes->src->cycles_hist, 0,
-				symbol__size(sym) * sizeof(struct cyc_hist));
+		       notes->src->nr_histograms * sizeof(*notes->src->histograms));
+		hashmap__clear(notes->src->samples);
+	}
+	if (notes->branch && notes->branch->cycles_hist) {
+		memset(notes->branch->cycles_hist, 0,
+		       symbol__size(sym) * sizeof(struct cyc_hist));
 	}
 	annotation__unlock(notes);
 }
@@ -927,8 +983,10 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 				      struct perf_sample *sample)
 {
 	struct symbol *sym = ms->sym;
-	unsigned offset;
+	long hash_key;
+	u64 offset;
 	struct sym_hist *h;
+	struct sym_hist_entry *entry;
 
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map__unmap_ip(ms->map, addr));
 
@@ -946,35 +1004,56 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms,
 			 __func__, __LINE__, sym->name, sym->start, addr, sym->end, sym->type == STT_FUNC);
 		return -ENOMEM;
 	}
+
+	hash_key = offset << 16 | evidx;
+	if (!hashmap__find(src->samples, hash_key, &entry)) {
+		entry = zalloc(sizeof(*entry));
+		if (entry == NULL)
+			return -ENOMEM;
+
+		if (hashmap__add(src->samples, hash_key, entry) < 0)
+			return -ENOMEM;
+	}
+
 	h->nr_samples++;
-	h->addr[offset].nr_samples++;
 	h->period += sample->period;
-	h->addr[offset].period += sample->period;
+	entry->nr_samples++;
+	entry->period += sample->period;
 
 	pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
 		  ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n",
 		  sym->start, sym->name, addr, addr - sym->start, evidx,
-		  h->addr[offset].nr_samples, h->addr[offset].period);
+		  entry->nr_samples, entry->period);
 	return 0;
 }
 
+struct annotated_branch *annotation__get_branch(struct annotation *notes)
+{
+	if (notes == NULL)
+		return NULL;
+
+	if (notes->branch == NULL)
+		notes->branch = zalloc(sizeof(*notes->branch));
+
+	return notes->branch;
+}
+
 static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
+	struct annotated_branch *branch;
 
-	if (notes->src == NULL) {
-		notes->src = annotated_source__new();
-		if (notes->src == NULL)
-			return NULL;
-		goto alloc_cycles_hist;
-	}
+	branch = annotation__get_branch(notes);
+	if (branch == NULL)
+		return NULL;
+
+	if (branch->cycles_hist == NULL) {
+		const size_t size = symbol__size(sym);
 
-	if (!notes->src->cycles_hist) {
-alloc_cycles_hist:
-		symbol__alloc_hist_cycles(sym);
+		branch->cycles_hist = calloc(size, sizeof(struct cyc_hist));
 	}
 
-	return notes->src->cycles_hist;
+	return branch->cycles_hist;
 }
 
 struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
@@ -990,8 +1069,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
 
 	if (notes->src->histograms == NULL) {
 alloc_histograms:
-		annotated_source__alloc_histograms(notes->src, symbol__size(sym),
-						   nr_hists);
+		annotated_source__alloc_histograms(notes->src, nr_hists);
 	}
 
 	return notes->src;
@@ -1077,12 +1155,20 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64
 	u64 offset;
 
 	for (offset = start; offset <= end; offset++) {
-		if (notes->offsets[offset])
+		if (notes->src->offsets[offset])
 			n_insn++;
 	}
 	return n_insn;
 }
 
+static void annotated_branch__delete(struct annotated_branch *branch)
+{
+	if (branch) {
+		zfree(&branch->cycles_hist);
+		free(branch);
+	}
+}
+
 static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
 {
 	unsigned n_insn;
@@ -1091,6 +1177,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 
 	n_insn = annotation__count_insn(notes, start, end);
 	if (n_insn && ch->num && ch->cycles) {
+		struct annotated_branch *branch;
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
 		/* Hide data when there are too many overlaps. */
@@ -1098,54 +1185,76 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 			return;
 
 		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = notes->offsets[offset];
+			struct annotation_line *al = notes->src->offsets[offset];
 
-			if (al && al->ipc == 0.0) {
-				al->ipc = ipc;
+			if (al && al->cycles && al->cycles->ipc == 0.0) {
+				al->cycles->ipc = ipc;
 				cover_insn++;
 			}
 		}
 
-		if (cover_insn) {
-			notes->hit_cycles += ch->cycles;
-			notes->hit_insn += n_insn * ch->num;
-			notes->cover_insn += cover_insn;
+		branch = annotation__get_branch(notes);
+		if (cover_insn && branch) {
+			branch->hit_cycles += ch->cycles;
+			branch->hit_insn += n_insn * ch->num;
+			branch->cover_insn += cover_insn;
 		}
 	}
 }
 
-void annotation__compute_ipc(struct annotation *notes, size_t size)
+static int annotation__compute_ipc(struct annotation *notes, size_t size)
 {
+	int err = 0;
 	s64 offset;
 
-	if (!notes->src || !notes->src->cycles_hist)
-		return;
+	if (!notes->branch || !notes->branch->cycles_hist)
+		return 0;
 
-	notes->total_insn = annotation__count_insn(notes, 0, size - 1);
-	notes->hit_cycles = 0;
-	notes->hit_insn = 0;
-	notes->cover_insn = 0;
+	notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1);
+	notes->branch->hit_cycles = 0;
+	notes->branch->hit_insn = 0;
+	notes->branch->cover_insn = 0;
 
 	annotation__lock(notes);
 	for (offset = size - 1; offset >= 0; --offset) {
 		struct cyc_hist *ch;
 
-		ch = &notes->src->cycles_hist[offset];
+		ch = &notes->branch->cycles_hist[offset];
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
+			al = notes->src->offsets[offset];
+			if (al && al->cycles == NULL) {
+				al->cycles = zalloc(sizeof(*al->cycles));
+				if (al->cycles == NULL) {
+					err = ENOMEM;
+					break;
+				}
+			}
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
-			al = notes->offsets[offset];
 			if (al && ch->num_aggr) {
-				al->cycles = ch->cycles_aggr / ch->num_aggr;
-				al->cycles_max = ch->cycles_max;
-				al->cycles_min = ch->cycles_min;
+				al->cycles->avg = ch->cycles_aggr / ch->num_aggr;
+				al->cycles->max = ch->cycles_max;
+				al->cycles->min = ch->cycles_min;
+			}
+		}
+	}
+
+	if (err) {
+		while (++offset < (s64)size) {
+			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
+
+			if (ch && ch->cycles) {
+				struct annotation_line *al = notes->src->offsets[offset];
+				if (al)
+					zfree(&al->cycles);
 			}
-			notes->have_cycles = true;
 		}
 	}
+
 	annotation__unlock(notes);
+	return 0;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
@@ -1225,6 +1334,7 @@ static void annotation_line__exit(struct annotation_line *al)
 {
 	zfree_srcline(&al->path);
 	zfree(&al->line);
+	zfree(&al->cycles);
 }
 
 static size_t disasm_line_size(int nr)
@@ -1299,6 +1409,7 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r
 void annotation__exit(struct annotation *notes)
 {
 	annotated_source__delete(notes->src);
+	annotated_branch__delete(notes->branch);
 }
 
 static struct sharded_mutex *sharded_mutex;
@@ -1817,7 +1928,6 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 				   struct annotate_args *args)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	struct annotation_options *opts = args->options;
 	struct bpf_prog_linfo *prog_linfo = NULL;
 	struct bpf_prog_info_node *info_node;
 	int len = sym->end - sym->start;
@@ -1846,8 +1956,11 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	perf_exe(tpath, sizeof(tpath));
 
 	bfdf = bfd_openr(tpath, NULL);
-	assert(bfdf);
-	assert(bfd_check_format(bfdf, bfd_object));
+	if (bfdf == NULL)
+		abort();
+
+	if (!bfd_check_format(bfdf, bfd_object))
+		abort();
 
 	s = open_memstream(&buf, &buf_size);
 	if (!s) {
@@ -1895,7 +2008,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 #else
 	disassemble = disassembler(bfdf);
 #endif
-	assert(disassemble);
+	if (disassemble == NULL)
+		abort();
 
 	fflush(s);
 	do {
@@ -1923,7 +2037,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		prev_buf_size = buf_size;
 		fflush(s);
 
-		if (!opts->hide_src_code && srcline) {
+		if (!annotate_opts.hide_src_code && srcline) {
 			args->offset = -1;
 			args->line = strdup(srcline);
 			args->line_nr = 0;
@@ -2046,7 +2160,7 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len)
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
-	struct annotation_options *opts = args->options;
+	struct annotation_options *opts = &annotate_opts;
 	struct map *map = args->ms.map;
 	struct dso *dso = map__dso(map);
 	char *command;
@@ -2109,12 +2223,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s %s %c%s%c %s%s -C \"$1\"",
+		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
+		 opts->show_linenr ? "-l" : "",
 		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
 		 opts->annotate_src ? "-S" : "",
 		 opts->prefix ? "--prefix " : "",
@@ -2227,17 +2342,25 @@ out_remove_tmp:
 	return err;
 }
 
-static void calc_percent(struct sym_hist *sym_hist,
-			 struct hists *hists,
+static void calc_percent(struct annotation *notes,
+			 struct evsel *evsel,
 			 struct annotation_data *data,
 			 s64 offset, s64 end)
 {
+	struct hists *hists = evsel__hists(evsel);
+	int evidx = evsel->core.idx;
+	struct sym_hist *sym_hist = annotation__histogram(notes, evidx);
 	unsigned int hits = 0;
 	u64 period = 0;
 
 	while (offset < end) {
-		hits   += sym_hist->addr[offset].nr_samples;
-		period += sym_hist->addr[offset].period;
+		struct sym_hist_entry *entry;
+
+		entry = annotated_source__hist_entry(notes->src, evidx, offset);
+		if (entry) {
+			hits   += entry->nr_samples;
+			period += entry->period;
+		}
 		++offset;
 	}
 
@@ -2274,16 +2397,13 @@ static void annotation__calc_percent(struct annotation *notes,
 		end  = next ? next->offset : len;
 
 		for_each_group_evsel(evsel, leader) {
-			struct hists *hists = evsel__hists(evsel);
 			struct annotation_data *data;
-			struct sym_hist *sym_hist;
 
 			BUG_ON(i >= al->data_nr);
 
-			sym_hist = annotation__histogram(notes, evsel->core.idx);
 			data = &al->data[i++];
 
-			calc_percent(sym_hist, hists, data, al->offset, end);
+			calc_percent(notes, evsel, data, al->offset, end);
 		}
 	}
 }
@@ -2295,15 +2415,8 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel)
 	annotation__calc_percent(notes, evsel, symbol__size(sym));
 }
 
-int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
-		     struct annotation_options *options, struct arch **parch)
+static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
 {
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
-	struct annotate_args args = {
-		.evsel		= evsel,
-		.options	= options,
-	};
 	struct perf_env *env = evsel__env(evsel);
 	const char *arch_name = perf_env__arch(env);
 	struct arch *arch;
@@ -2312,25 +2425,48 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (!arch_name)
 		return errno;
 
-	args.arch = arch = arch__find(arch_name);
+	*parch = arch = arch__find(arch_name);
 	if (arch == NULL) {
 		pr_err("%s: unsupported arch %s\n", __func__, arch_name);
 		return ENOTSUP;
 	}
 
-	if (parch)
-		*parch = arch;
-
 	if (arch->init) {
 		err = arch->init(arch, env ? env->cpuid : NULL);
 		if (err) {
-			pr_err("%s: failed to initialize %s arch priv area\n", __func__, arch->name);
+			pr_err("%s: failed to initialize %s arch priv area\n",
+			       __func__, arch->name);
 			return err;
 		}
 	}
+	return 0;
+}
+
+int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
+		     struct arch **parch)
+{
+	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotate_args args = {
+		.evsel		= evsel,
+		.options	= &annotate_opts,
+	};
+	struct arch *arch = NULL;
+	int err;
+
+	err = evsel__get_arch(evsel, &arch);
+	if (err < 0)
+		return err;
 
+	if (parch)
+		*parch = arch;
+
+	if (!list_empty(&notes->src->source))
+		return 0;
+
+	args.arch = arch;
 	args.ms = *ms;
-	if (notes->options && notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2338,12 +2474,12 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	return symbol__disassemble(sym, &args);
 }
 
-static void insert_source_line(struct rb_root *root, struct annotation_line *al,
-			       struct annotation_options *opts)
+static void insert_source_line(struct rb_root *root, struct annotation_line *al)
 {
 	struct annotation_line *iter;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
+	unsigned int percent_type = annotate_opts.percent_type;
 	int i, ret;
 
 	while (*p != NULL) {
@@ -2354,7 +2490,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 		if (ret == 0) {
 			for (i = 0; i < al->data_nr; i++) {
 				iter->data[i].percent_sum += annotation_data__percent(&al->data[i],
-										      opts->percent_type);
+										      percent_type);
 			}
 			return;
 		}
@@ -2367,7 +2503,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al,
 
 	for (i = 0; i < al->data_nr; i++) {
 		al->data[i].percent_sum = annotation_data__percent(&al->data[i],
-								   opts->percent_type);
+								   percent_type);
 	}
 
 	rb_link_node(&al->rb_node, parent, p);
@@ -2465,14 +2601,19 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 static void symbol__annotate_hits(struct symbol *sym, struct evsel *evsel)
 {
+	int evidx = evsel->core.idx;
 	struct annotation *notes = symbol__annotation(sym);
-	struct sym_hist *h = annotation__histogram(notes, evsel->core.idx);
+	struct sym_hist *h = annotation__histogram(notes, evidx);
 	u64 len = symbol__size(sym), offset;
 
-	for (offset = 0; offset < len; ++offset)
-		if (h->addr[offset].nr_samples != 0)
+	for (offset = 0; offset < len; ++offset) {
+		struct sym_hist_entry *entry;
+
+		entry = annotated_source__hist_entry(notes->src, evidx, offset);
+		if (entry && entry->nr_samples != 0)
 			printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
-			       sym->start + offset, h->addr[offset].nr_samples);
+			       sym->start + offset, entry->nr_samples);
+	}
 	printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
 }
 
@@ -2489,8 +2630,7 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start)
 	return 0;
 }
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *opts)
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
@@ -2501,6 +2641,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evsel->core.idx);
 	struct annotation_line *pos, *queue = NULL;
+	struct annotation_options *opts = &annotate_opts;
 	u64 start = map__rip_2objdump(map, sym->start);
 	int printed = 2, queue_len = 0, addr_fmt_width;
 	int more = 0;
@@ -2629,8 +2770,7 @@ static void FILE__write_graph(void *fp, int graph)
 	fputs(s, fp);
 }
 
-static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
-				     struct annotation_options *opts)
+static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotation_write_ops wops = {
@@ -2645,9 +2785,9 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	struct annotation_line *al;
 
 	list_for_each_entry(al, &notes->src->source, node) {
-		if (annotation_line__filter(al, notes))
+		if (annotation_line__filter(al))
 			continue;
-		annotation_line__write(al, notes, &wops, opts);
+		annotation_line__write(al, notes, &wops);
 		fputc('\n', fp);
 		wops.first_line = false;
 	}
@@ -2655,8 +2795,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp,
 	return 0;
 }
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts)
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel)
 {
 	const char *ev_name = evsel__name(evsel);
 	char buf[1024];
@@ -2678,7 +2817,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
 
 	fprintf(fp, "%s() %s\nEvent: %s\n\n",
 		ms->sym->name, map__dso(ms->map)->long_name, ev_name);
-	symbol__annotate_fprintf2(ms->sym, fp, opts);
+	symbol__annotate_fprintf2(ms->sym, fp);
 
 	fclose(fp);
 	err = 0;
@@ -2692,7 +2831,7 @@ void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
 
-	memset(h, 0, notes->src->sizeof_sym_hist);
+	memset(h, 0, sizeof(*notes->src->histograms) * notes->src->nr_histograms);
 }
 
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
@@ -2703,8 +2842,14 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
 
 	h->nr_samples = 0;
 	for (offset = 0; offset < len; ++offset) {
-		h->addr[offset].nr_samples = h->addr[offset].nr_samples * 7 / 8;
-		h->nr_samples += h->addr[offset].nr_samples;
+		struct sym_hist_entry *entry;
+
+		entry = annotated_source__hist_entry(notes->src, evidx, offset);
+		if (entry == NULL)
+			continue;
+
+		entry->nr_samples = entry->nr_samples * 7 / 8;
+		h->nr_samples += entry->nr_samples;
 	}
 }
 
@@ -2765,7 +2910,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		return;
 
 	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = notes->offsets[offset];
+		struct annotation_line *al = notes->src->offsets[offset];
 		struct disasm_line *dl;
 
 		dl = disasm_line(al);
@@ -2773,7 +2918,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 		if (!disasm_line__is_valid_local_jump(dl, sym))
 			continue;
 
-		al = notes->offsets[dl->ops.target.offset];
+		al = notes->src->offsets[dl->ops.target.offset];
 
 		/*
 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
@@ -2790,19 +2935,20 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 void annotation__set_offsets(struct annotation *notes, s64 size)
 {
 	struct annotation_line *al;
+	struct annotated_source *src = notes->src;
 
-	notes->max_line_len = 0;
-	notes->nr_entries = 0;
-	notes->nr_asm_entries = 0;
+	src->max_line_len = 0;
+	src->nr_entries = 0;
+	src->nr_asm_entries = 0;
 
-	list_for_each_entry(al, &notes->src->source, node) {
+	list_for_each_entry(al, &src->source, node) {
 		size_t line_len = strlen(al->line);
 
-		if (notes->max_line_len < line_len)
-			notes->max_line_len = line_len;
-		al->idx = notes->nr_entries++;
+		if (src->max_line_len < line_len)
+			src->max_line_len = line_len;
+		al->idx = src->nr_entries++;
 		if (al->offset != -1) {
-			al->idx_asm = notes->nr_asm_entries++;
+			al->idx_asm = src->nr_asm_entries++;
 			/*
 			 * FIXME: short term bandaid to cope with assembly
 			 * routines that comes with labels in the same column
@@ -2811,7 +2957,7 @@ void annotation__set_offsets(struct annotation *notes, s64 size)
 			 * E.g. copy_user_generic_unrolled
  			 */
 			if (al->offset < size)
-				notes->offsets[al->offset] = al;
+				notes->src->offsets[al->offset] = al;
 		} else
 			al->idx_asm = -1;
 	}
@@ -2854,24 +3000,24 @@ void annotation__init_column_widths(struct annotation *notes, struct symbol *sym
 
 void annotation__update_column_widths(struct annotation *notes)
 {
-	if (notes->options->use_offset)
+	if (annotate_opts.use_offset)
 		notes->widths.target = notes->widths.min_addr;
-	else if (notes->options->full_addr)
+	else if (annotate_opts.full_addr)
 		notes->widths.target = BITS_PER_LONG / 4;
 	else
 		notes->widths.target = notes->widths.max_addr;
 
 	notes->widths.addr = notes->widths.target;
 
-	if (notes->options->show_nr_jumps)
+	if (annotate_opts.show_nr_jumps)
 		notes->widths.addr += notes->widths.jumps + 1;
 }
 
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
 {
-	notes->options->full_addr = !notes->options->full_addr;
+	annotate_opts.full_addr = !annotate_opts.full_addr;
 
-	if (notes->options->full_addr)
+	if (annotate_opts.full_addr)
 		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
 		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
@@ -2880,8 +3026,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 }
 
 static void annotation__calc_lines(struct annotation *notes, struct map *map,
-				   struct rb_root *root,
-				   struct annotation_options *opts)
+				   struct rb_root *root)
 {
 	struct annotation_line *al;
 	struct rb_root tmp_root = RB_ROOT;
@@ -2894,7 +3039,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i],
-							   opts->percent_type);
+							   annotate_opts.percent_type);
 
 			if (percent > percent_max)
 				percent_max = percent;
@@ -2905,22 +3050,20 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
 				       false, true, notes->start + al->offset);
-		insert_source_line(&tmp_root, al, opts);
+		insert_source_line(&tmp_root, al);
 	}
 
 	resort_source_line(root, &tmp_root);
 }
 
-static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root,
-			       struct annotation_options *opts)
+static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root, opts);
+	annotation__calc_lines(notes, ms->map, root);
 }
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
-			  struct annotation_options *opts)
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
@@ -2929,7 +3072,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 	char buf[1024];
 	int err;
 
-	err = symbol__annotate2(ms, evsel, opts, NULL);
+	err = symbol__annotate2(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -2939,31 +3082,31 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel,
 		return -1;
 	}
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
 	hists__scnprintf_title(hists, buf, sizeof(buf));
 	fprintf(stdout, "%s, [percent: %s]\n%s() %s\n",
-		buf, percent_type_str(opts->percent_type), sym->name, dso->long_name);
-	symbol__annotate_fprintf2(sym, stdout, opts);
+		buf, percent_type_str(annotate_opts.percent_type), sym->name,
+		dso->long_name);
+	symbol__annotate_fprintf2(sym, stdout);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
 	return 0;
 }
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct annotation_options *opts)
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel)
 {
 	struct dso *dso = map__dso(ms->map);
 	struct symbol *sym = ms->sym;
 	struct rb_root source_line = RB_ROOT;
 	int err;
 
-	err = symbol__annotate(ms, evsel, opts, NULL);
+	err = symbol__annotate(ms, evsel, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 
@@ -2975,13 +3118,13 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	symbol__calc_percent(sym, evsel);
 
-	if (opts->print_lines) {
-		srcline_full_filename = opts->full_path;
-		symbol__calc_lines(ms, &source_line, opts);
+	if (annotate_opts.print_lines) {
+		srcline_full_filename = annotate_opts.full_path;
+		symbol__calc_lines(ms, &source_line);
 		print_summary(&source_line, dso->long_name);
 	}
 
-	symbol__annotate_printf(ms, evsel, opts);
+	symbol__annotate_printf(ms, evsel);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
 
@@ -3042,19 +3185,20 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name);
+	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
 {
 	double ipc = 0.0, coverage = 0.0;
+	struct annotated_branch *branch = annotation__get_branch(notes);
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)",
@@ -3079,8 +3223,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	int printed;
 
 	if (first_line && (al->offset == -1 || percent_max == 0.0)) {
-		if (notes->have_cycles) {
-			if (al->ipc == 0.0 && al->cycles == 0)
+		if (notes->branch && al->cycles) {
+			if (al->cycles->ipc == 0.0 && al->cycles->avg == 0)
 				show_title = true;
 		} else
 			show_title = true;
@@ -3116,18 +3260,18 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		}
 	}
 
-	if (notes->have_cycles) {
-		if (al->ipc)
-			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc);
+	if (notes->branch) {
+		if (al->cycles && al->cycles->ipc)
+			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc);
 		else if (!show_title)
 			obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " ");
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (!notes->options->show_minmax_cycle) {
-			if (al->cycles)
+		if (!annotate_opts.show_minmax_cycle) {
+			if (al->cycles && al->cycles->avg)
 				obj__printf(obj, "%*" PRIu64 " ",
-					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
+					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg);
 			else if (!show_title)
 				obj__printf(obj, "%*s",
 					    ANNOTATION__CYCLES_WIDTH, " ");
@@ -3141,8 +3285,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 
 				scnprintf(str, sizeof(str),
 					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
-					al->cycles, al->cycles_min,
-					al->cycles_max);
+					al->cycles->avg, al->cycles->min,
+					al->cycles->max);
 
 				obj__printf(obj, "%*s ",
 					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
@@ -3168,7 +3312,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (!*al->line)
 		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
 	else if (al->offset == -1) {
-		if (al->line_nr && notes->options->show_linenr)
+		if (al->line_nr && annotate_opts.show_linenr)
 			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
 		else
 			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
@@ -3178,15 +3322,15 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		u64 addr = al->offset;
 		int color = -1;
 
-		if (!notes->options->use_offset)
+		if (!annotate_opts.use_offset)
 			addr += notes->start;
 
-		if (!notes->options->use_offset) {
+		if (!annotate_opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
 			if (al->jump_sources &&
-			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
-				if (notes->options->show_nr_jumps) {
+			    annotate_opts.offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
+				if (annotate_opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
 							    notes->widths.jumps,
@@ -3200,9 +3344,9 @@ print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
 			} else if (ins__is_call(&disasm_line(al)->ins) &&
-				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				   annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
 				goto print_addr;
-			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+			} else if (annotate_opts.offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
 				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
@@ -3224,43 +3368,44 @@ print_addr:
 }
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *wops,
-			    struct annotation_options *opts)
+			    struct annotation_write_ops *wops)
 {
 	__annotation_line__write(al, notes, wops->first_line, wops->current_entry,
 				 wops->change_color, wops->width, wops->obj,
-				 opts->percent_type,
+				 annotate_opts.percent_type,
 				 wops->set_color, wops->set_percent_color,
 				 wops->set_jumps_percent_color, wops->printf,
 				 wops->write_graph);
 }
 
 int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
-		      struct annotation_options *options, struct arch **parch)
+		      struct arch **parch)
 {
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	size_t size = symbol__size(sym);
 	int nr_pcnt = 1, err;
 
-	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (notes->offsets == NULL)
+	notes->src->offsets = zalloc(size * sizeof(struct annotation_line *));
+	if (notes->src->offsets == NULL)
 		return ENOMEM;
 
 	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
-	err = symbol__annotate(ms, evsel, options, parch);
+	err = symbol__annotate(ms, evsel, parch);
 	if (err)
 		goto out_free_offsets;
 
-	notes->options = options;
-
 	symbol__calc_percent(sym, evsel);
 
 	annotation__set_offsets(notes, size);
 	annotation__mark_jump_targets(notes, sym);
-	annotation__compute_ipc(notes, size);
+
+	err = annotation__compute_ipc(notes, size);
+	if (err)
+		goto out_free_offsets;
+
 	annotation__init_column_widths(notes, sym);
 	notes->nr_events = nr_pcnt;
 
@@ -3270,7 +3415,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return 0;
 
 out_free_offsets:
-	zfree(&notes->offsets);
+	zfree(&notes->src->offsets);
 	return err;
 }
 
@@ -3333,8 +3478,10 @@ static int annotation__config(const char *var, const char *value, void *data)
 	return 0;
 }
 
-void annotation_options__init(struct annotation_options *opt)
+void annotation_options__init(void)
 {
+	struct annotation_options *opt = &annotate_opts;
+
 	memset(opt, 0, sizeof(*opt));
 
 	/* Default values. */
@@ -3345,16 +3492,15 @@ void annotation_options__init(struct annotation_options *opt)
 	opt->percent_type = PERCENT_PERIOD_LOCAL;
 }
 
-
-void annotation_options__exit(struct annotation_options *opt)
+void annotation_options__exit(void)
 {
-	zfree(&opt->disassembler_style);
-	zfree(&opt->objdump_path);
+	zfree(&annotate_opts.disassembler_style);
+	zfree(&annotate_opts.objdump_path);
 }
 
-void annotation_config__init(struct annotation_options *opt)
+void annotation_config__init(void)
 {
-	perf_config(annotation__config, opt);
+	perf_config(annotation__config, &annotate_opts);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
@@ -3378,10 +3524,9 @@ static unsigned int parse_percent_type(char *str1, char *str2)
 	return type;
 }
 
-int annotate_parse_percent_type(const struct option *opt, const char *_str,
+int annotate_parse_percent_type(const struct option *opt __maybe_unused, const char *_str,
 				int unset __maybe_unused)
 {
-	struct annotation_options *opts = opt->value;
 	unsigned int type;
 	char *str1, *str2;
 	int err = -1;
@@ -3400,7 +3545,7 @@ int annotate_parse_percent_type(const struct option *opt, const char *_str,
 	if (type == (unsigned int) -1)
 		type = parse_percent_type(str2, str1);
 	if (type != (unsigned int) -1) {
-		opts->percent_type = type;
+		annotate_opts.percent_type = type;
 		err = 0;
 	}
 
@@ -3409,11 +3554,389 @@ out:
 	return err;
 }
 
-int annotate_check_args(struct annotation_options *args)
+int annotate_check_args(void)
 {
+	struct annotation_options *args = &annotate_opts;
+
 	if (args->prefix_strip && !args->prefix) {
 		pr_err("--prefix-strip requires --prefix\n");
 		return -1;
 	}
 	return 0;
 }
+
+/*
+ * Get register number and access offset from the given instruction.
+ * It assumes AT&T x86 asm format like OFFSET(REG).  Maybe it needs
+ * to revisit the format when it handles different architecture.
+ * Fills @reg and @offset when return 0.
+ */
+static int extract_reg_offset(struct arch *arch, const char *str,
+			      struct annotated_op_loc *op_loc)
+{
+	char *p;
+	char *regname;
+
+	if (arch->objdump.register_char == 0)
+		return -1;
+
+	/*
+	 * It should start from offset, but it's possible to skip 0
+	 * in the asm.  So 0(%rax) should be same as (%rax).
+	 *
+	 * However, it also start with a segment select register like
+	 * %gs:0x18(%rbx).  In that case it should skip the part.
+	 */
+	if (*str == arch->objdump.register_char) {
+		while (*str && !isdigit(*str) &&
+		       *str != arch->objdump.memory_ref_char)
+			str++;
+	}
+
+	op_loc->offset = strtol(str, &p, 0);
+
+	p = strchr(p, arch->objdump.register_char);
+	if (p == NULL)
+		return -1;
+
+	regname = strdup(p);
+	if (regname == NULL)
+		return -1;
+
+	op_loc->reg1 = get_dwarf_regnum(regname, 0);
+	free(regname);
+
+	/* Get the second register */
+	if (op_loc->multi_regs) {
+		p = strchr(p + 1, arch->objdump.register_char);
+		if (p == NULL)
+			return -1;
+
+		regname = strdup(p);
+		if (regname == NULL)
+			return -1;
+
+		op_loc->reg2 = get_dwarf_regnum(regname, 0);
+		free(regname);
+	}
+	return 0;
+}
+
+/**
+ * annotate_get_insn_location - Get location of instruction
+ * @arch: the architecture info
+ * @dl: the target instruction
+ * @loc: a buffer to save the data
+ *
+ * Get detailed location info (register and offset) in the instruction.
+ * It needs both source and target operand and whether it accesses a
+ * memory location.  The offset field is meaningful only when the
+ * corresponding mem flag is set.  The reg2 field is meaningful only
+ * when multi_regs flag is set.
+ *
+ * Some examples on x86:
+ *
+ *   mov  (%rax), %rcx   # src_reg1 = rax, src_mem = 1, src_offset = 0
+ *                       # dst_reg1 = rcx, dst_mem = 0
+ *
+ *   mov  0x18, %r8      # src_reg1 = -1, src_mem = 0
+ *                       # dst_reg1 = r8, dst_mem = 0
+ *
+ *   mov  %rsi, 8(%rbx,%rcx,4)  # src_reg1 = rsi, src_mem = 0, dst_multi_regs = 0
+ *                              # dst_reg1 = rbx, dst_reg2 = rcx, dst_mem = 1
+ *                              # dst_multi_regs = 1, dst_offset = 8
+ */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc)
+{
+	struct ins_operands *ops;
+	struct annotated_op_loc *op_loc;
+	int i;
+
+	if (!strcmp(dl->ins.name, "lock"))
+		ops = dl->ops.locked.ops;
+	else
+		ops = &dl->ops;
+
+	if (ops == NULL)
+		return -1;
+
+	memset(loc, 0, sizeof(*loc));
+
+	for_each_insn_op_loc(loc, i, op_loc) {
+		const char *insn_str = ops->source.raw;
+		bool multi_regs = ops->source.multi_regs;
+
+		if (i == INSN_OP_TARGET) {
+			insn_str = ops->target.raw;
+			multi_regs = ops->target.multi_regs;
+		}
+
+		/* Invalidate the register by default */
+		op_loc->reg1 = -1;
+		op_loc->reg2 = -1;
+
+		if (insn_str == NULL)
+			continue;
+
+		if (strchr(insn_str, arch->objdump.memory_ref_char)) {
+			op_loc->mem_ref = true;
+			op_loc->multi_regs = multi_regs;
+			extract_reg_offset(arch, insn_str, op_loc);
+		} else {
+			char *s = strdup(insn_str);
+
+			if (s) {
+				op_loc->reg1 = get_dwarf_regnum(s, 0);
+				free(s);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
+{
+	struct disasm_line *dl, *tmp_dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(ms->sym);
+	if (!list_empty(&notes->src->source))
+		return;
+
+	if (symbol__annotate(ms, evsel, NULL) < 0)
+		return;
+
+	/* remove non-insn disasm lines for simplicity */
+	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+}
+
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+{
+	struct disasm_line *dl;
+	struct annotation *notes;
+
+	notes = symbol__annotation(sym);
+
+	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (sym->start + dl->al.offset == ip) {
+			/*
+			 * llvm-objdump places "lock" in a separate line and
+			 * in that case, we want to get the next line.
+			 */
+			if (!strcmp(dl->ins.name, "lock") && *dl->ops.raw == '\0') {
+				ip++;
+				continue;
+			}
+			return dl;
+		}
+	}
+	return NULL;
+}
+
+static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
+						      const char *name)
+{
+	struct annotated_item_stat *istat;
+
+	list_for_each_entry(istat, head, list) {
+		if (!strcmp(istat->name, name))
+			return istat;
+	}
+
+	istat = zalloc(sizeof(*istat));
+	if (istat == NULL)
+		return NULL;
+
+	istat->name = strdup(name);
+	if (istat->name == NULL) {
+		free(istat);
+		return NULL;
+	}
+
+	list_add_tail(&istat->list, head);
+	return istat;
+}
+
+static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
+{
+	if (arch__is(arch, "x86")) {
+		if (!strncmp(dl->ins.name, "push", 4) ||
+		    !strncmp(dl->ins.name, "pop", 3) ||
+		    !strncmp(dl->ins.name, "ret", 3))
+			return true;
+	}
+
+	return false;
+}
+
+u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
+			struct disasm_line *dl)
+{
+	struct annotation *notes;
+	struct disasm_line *next;
+	u64 addr;
+
+	notes = symbol__annotation(ms->sym);
+	/*
+	 * PC-relative addressing starts from the next instruction address
+	 * But the IP is for the current instruction.  Since disasm_line
+	 * doesn't have the instruction size, calculate it using the next
+	 * disasm_line.  If it's the last one, we can use symbol's end
+	 * address directly.
+	 */
+	if (&dl->al.node == notes->src->source.prev)
+		addr = ms->sym->end + offset;
+	else {
+		next = list_next_entry(dl, al.node);
+		addr = ip + (next->al.offset - dl->al.offset) + offset;
+	}
+	return map__rip_2objdump(ms->map, addr);
+}
+
+/**
+ * hist_entry__get_data_type - find data type for given hist entry
+ * @he: hist entry
+ *
+ * This function first annotates the instruction at @he->ip and extracts
+ * register and offset info from it.  Then it searches the DWARF debug
+ * info to get a variable and type information using the address, register,
+ * and offset.
+ */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
+{
+	struct map_symbol *ms = &he->ms;
+	struct evsel *evsel = hists_to_evsel(he->hists);
+	struct arch *arch;
+	struct disasm_line *dl;
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *op_loc;
+	struct annotated_data_type *mem_type;
+	struct annotated_item_stat *istat;
+	u64 ip = he->ip, addr = 0;
+	const char *var_name = NULL;
+	int var_offset;
+	int i;
+
+	ann_data_stat.total++;
+
+	if (ms->map == NULL || ms->sym == NULL) {
+		ann_data_stat.no_sym++;
+		return NULL;
+	}
+
+	if (!symbol_conf.init_annotation) {
+		ann_data_stat.no_sym++;
+		return NULL;
+	}
+
+	if (evsel__get_arch(evsel, &arch) < 0) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+	/* Make sure it runs objdump to get disasm of the function */
+	symbol__ensure_annotate(ms, evsel);
+
+	/*
+	 * Get a disasm to extract the location from the insn.
+	 * This is too slow...
+	 */
+	dl = find_disasm_line(ms->sym, ip);
+	if (dl == NULL) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+retry:
+	istat = annotate_data_stat(&ann_insn_stat, dl->ins.name);
+	if (istat == NULL) {
+		ann_data_stat.no_insn++;
+		return NULL;
+	}
+
+	if (annotate_get_insn_location(arch, dl, &loc) < 0) {
+		ann_data_stat.no_insn_ops++;
+		istat->bad++;
+		return NULL;
+	}
+
+	if (is_stack_operation(arch, dl)) {
+		istat->good++;
+		he->mem_type_off = 0;
+		return &stackop_type;
+	}
+
+	for_each_insn_op_loc(&loc, i, op_loc) {
+		if (!op_loc->mem_ref)
+			continue;
+
+		/* Recalculate IP because of LOCK prefix or insn fusion */
+		ip = ms->sym->start + dl->al.offset;
+
+		var_offset = op_loc->offset;
+
+		/* PC-relative addressing */
+		if (op_loc->reg1 == DWARF_REG_PC) {
+			struct addr_location al;
+			struct symbol *var;
+			u64 map_addr;
+
+			addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl);
+			/* Kernel symbols might be relocated */
+			map_addr = addr + map__reloc(ms->map);
+
+			addr_location__init(&al);
+			var = thread__find_symbol_fb(he->thread, he->cpumode,
+						     map_addr, &al);
+			if (var) {
+				var_name = var->name;
+				/* Calculate type offset from the start of variable */
+				var_offset = map_addr - map__unmap_ip(al.map, var->start);
+			}
+			addr_location__exit(&al);
+		}
+
+		mem_type = find_data_type(ms, ip, op_loc, addr, var_name);
+		if (mem_type)
+			istat->good++;
+		else
+			istat->bad++;
+
+		if (mem_type && var_name)
+			op_loc->offset = var_offset;
+
+		if (symbol_conf.annotate_data_sample) {
+			annotated_data_type__update_samples(mem_type, evsel,
+							    op_loc->offset,
+							    he->stat.nr_events,
+							    he->stat.period);
+		}
+		he->mem_type_off = op_loc->offset;
+		return mem_type;
+	}
+
+	/*
+	 * Some instructions can be fused and the actual memory access came
+	 * from the previous instruction.
+	 */
+	if (dl->al.offset > 0) {
+		struct disasm_line *prev_dl;
+
+		prev_dl = list_prev_entry(dl, al.node);
+		if (ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
+			dl = prev_dl;
+			goto retry;
+		}
+	}
+
+	ann_data_stat.no_mem_ops++;
+	istat->bad++;
+	return NULL;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 962780559176..13cc659e508c 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -12,6 +12,7 @@
 #include "symbol_conf.h"
 #include "mutex.h"
 #include "spark.h"
+#include "hashmap.h"
 
 struct hist_browser_timer;
 struct hist_entry;
@@ -23,6 +24,7 @@ struct option;
 struct perf_sample;
 struct evsel;
 struct symbol;
+struct annotated_data_type;
 
 struct ins {
 	const char     *name;
@@ -31,8 +33,6 @@ struct ins {
 
 struct ins_operands {
 	char	*raw;
-	char	*raw_comment;
-	char	*raw_func_start;
 	struct {
 		char	*raw;
 		char	*name;
@@ -41,22 +41,30 @@ struct ins_operands {
 		s64	offset;
 		bool	offset_avail;
 		bool	outside;
+		bool	multi_regs;
 	} target;
 	union {
 		struct {
 			char	*raw;
 			char	*name;
 			u64	addr;
+			bool	multi_regs;
 		} source;
 		struct {
 			struct ins	    ins;
 			struct ins_operands *ops;
 		} locked;
+		struct {
+			char	*raw_comment;
+			char	*raw_func_start;
+		} jump;
 	};
 };
 
 struct arch;
 
+bool arch__is(struct arch *arch, const char *name);
+
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
 	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
@@ -101,6 +109,8 @@ struct annotation_options {
 	unsigned int percent_type;
 };
 
+extern struct annotation_options annotate_opts;
+
 enum {
 	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
 	ANNOTATION__OFFSET_CALL,
@@ -130,6 +140,13 @@ struct annotation_data {
 	struct sym_hist_entry	 he;
 };
 
+struct cycles_info {
+	float			 ipc;
+	u64			 avg;
+	u64			 max;
+	u64			 min;
+};
+
 struct annotation_line {
 	struct list_head	 node;
 	struct rb_node		 rb_node;
@@ -137,12 +154,9 @@ struct annotation_line {
 	char			*line;
 	int			 line_nr;
 	char			*fileloc;
-	int			 jump_sources;
-	float			 ipc;
-	u64			 cycles;
-	u64			 cycles_max;
-	u64			 cycles_min;
 	char			*path;
+	struct cycles_info	*cycles;
+	int			 jump_sources;
 	u32			 idx;
 	int			 idx_asm;
 	int			 data_nr;
@@ -214,8 +228,7 @@ struct annotation_write_ops {
 };
 
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
-			    struct annotation_write_ops *ops,
-			    struct annotation_options *opts);
+			    struct annotation_write_ops *ops);
 
 int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   char *bf, size_t size,
@@ -226,12 +239,42 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct evsel *evsel);
 
+/**
+ * struct sym_hist - symbol histogram information for an event
+ *
+ * @nr_samples: Total number of samples.
+ * @period: Sum of sample periods.
+ */
 struct sym_hist {
 	u64		      nr_samples;
 	u64		      period;
-	struct sym_hist_entry addr[];
 };
 
+/**
+ * struct cyc_hist - (CPU) cycle histogram for a basic block
+ *
+ * @start: Start address of current block (if known).
+ * @cycles: Sum of cycles for the longest basic block.
+ * @cycles_aggr: Total cycles for this address.
+ * @cycles_max: Max cycles for this address.
+ * @cycles_min: Min cycles for this address.
+ * @cycles_spark: History of cycles for the longest basic block.
+ * @num: Number of samples for the longest basic block.
+ * @num_aggr: Total number of samples for this address.
+ * @have_start: Whether the current branch info has a start address.
+ * @reset: Number of resets due to a different start address.
+ *
+ * If sample has branch_stack and cycles info, it can construct basic blocks
+ * between two adjacent branches.  It'd have start and end addresses but
+ * sometimes the start address may not be available.  So the cycles are
+ * accounted at the end address.  If multiple basic blocks end at the same
+ * address, it will take the longest one.
+ *
+ * The @start, @cycles, @cycles_spark and @num fields are used for the longest
+ * block only.  Other fields are used for all cases.
+ *
+ * See __symbol__account_cycles().
+ */
 struct cyc_hist {
 	u64	start;
 	u64	cycles;
@@ -246,45 +289,71 @@ struct cyc_hist {
 	u16	reset;
 };
 
-/** struct annotated_source - symbols with hits have this attached as in sannotation
+/**
+ * struct annotated_source - symbols with hits have this attached as in annotation
  *
- * @histograms: Array of addr hit histograms per event being monitored
- * nr_histograms: This may not be the same as evsel->evlist->core.nr_entries if
+ * @source: List head for annotated_line (embeded in disasm_line).
+ * @histograms: Array of symbol histograms per event to maintain the total number
+ * 		of samples and period.
+ * @nr_histograms: This may not be the same as evsel->evlist->core.nr_entries if
  * 		  we have more than a group in a evlist, where we will want
  * 		  to see each group separately, that is why symbol__annotate2()
  * 		  sets src->nr_histograms to evsel->nr_members.
- * @lines: If 'print_lines' is specified, per source code line percentages
- * @source: source parsed from a disassembler like objdump -dS
- * @cyc_hist: Average cycles per basic block
+ * @offsets: Array of annotation_line to be accessed by offset.
+ * @samples: Hash map of sym_hist_entry.  Keyed by event index and offset in symbol.
+ * @nr_entries: Number of annotated_line in the source list.
+ * @nr_asm_entries: Number of annotated_line with actual asm instruction in the
+ * 		    source list.
+ * @max_line_len: Maximum length of objdump output in an annotated_line.
  *
- * lines is allocated, percentages calculated and all sorted by percentage
+ * disasm_lines are allocated, percentages calculated and all sorted by percentage
  * when the annotation is about to be presented, so the percentages are for
  * one of the entries in the histogram array, i.e. for the event/counter being
  * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
  * returns.
  */
 struct annotated_source {
-	struct list_head   source;
-	int    		   nr_histograms;
-	size_t		   sizeof_sym_hist;
-	struct cyc_hist	   *cycles_hist;
-	struct sym_hist	   *histograms;
+	struct list_head	source;
+	struct sym_hist		*histograms;
+	struct annotation_line	**offsets;
+	struct hashmap	   	*samples;
+	int    			nr_histograms;
+	int			nr_entries;
+	int			nr_asm_entries;
+	u16			max_line_len;
 };
 
-struct LOCKABLE annotation {
-	u64			max_coverage;
-	u64			start;
+/**
+ * struct annotated_branch - basic block and IPC information for a symbol.
+ *
+ * @hit_cycles: Total executed cycles.
+ * @hit_insn: Total number of instructions executed.
+ * @total_insn: Number of instructions in the function.
+ * @cover_insn: Number of distinct, actually executed instructions.
+ * @cycles_hist: Array of cyc_hist for each instruction.
+ * @max_coverage: Maximum number of covered basic block (used for block-range).
+ *
+ * This struct is used by two different codes when the sample has branch stack
+ * and cycles information.  annotation__compute_ipc() calculates average IPC
+ * using @hit_insn / @hit_cycles.  The actual coverage can be calculated using
+ * @cover_insn / @total_insn.  The @cycles_hist can give IPC for each (longest)
+ * basic block ends at the given address.
+ * process_basic_block() calculates coverage of instructions (or basic blocks)
+ * in the function.
+ */
+struct annotated_branch {
 	u64			hit_cycles;
 	u64			hit_insn;
 	unsigned int		total_insn;
 	unsigned int		cover_insn;
-	struct annotation_options *options;
-	struct annotation_line	**offsets;
+	struct cyc_hist		*cycles_hist;
+	u64			max_coverage;
+};
+
+struct LOCKABLE annotation {
+	u64			start;
 	int			nr_events;
 	int			max_jump_sources;
-	int			nr_entries;
-	int			nr_asm_entries;
-	u16			max_line_len;
 	struct {
 		u8		addr;
 		u8		jumps;
@@ -293,8 +362,8 @@ struct LOCKABLE annotation {
 		u8		max_addr;
 		u8		max_ins_name;
 	} widths;
-	bool			have_cycles;
 	struct annotated_source *src;
+	struct annotated_branch *branch;
 };
 
 static inline void annotation__init(struct annotation *notes __maybe_unused)
@@ -308,10 +377,10 @@ bool annotation__trylock(struct annotation *notes) EXCLUSIVE_TRYLOCK_FUNCTION(tr
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
-	if (notes->have_cycles && notes->options->show_minmax_cycle)
+	if (notes->branch && annotate_opts.show_minmax_cycle)
 		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
 
-	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
+	return notes->branch ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
 static inline int annotation__pcnt_width(struct annotation *notes)
@@ -319,13 +388,12 @@ static inline int annotation__pcnt_width(struct annotation *notes)
 	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
 }
 
-static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
+static inline bool annotation_line__filter(struct annotation_line *al)
 {
-	return notes->options->hide_src_code && al->offset == -1;
+	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
 void annotation__set_offsets(struct annotation *notes, s64 size);
-void annotation__compute_ipc(struct annotation *notes, size_t size);
 void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym);
 void annotation__update_column_widths(struct annotation *notes);
 void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
@@ -333,7 +401,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 
 static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx)
 {
-	return ((void *)src->histograms) + (src->sizeof_sym_hist * idx);
+	return &src->histograms[idx];
 }
 
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
@@ -341,6 +409,17 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
 	return annotated_source__histogram(notes->src, idx);
 }
 
+static inline struct sym_hist_entry *
+annotated_source__hist_entry(struct annotated_source *src, int idx, u64 offset)
+{
+	struct sym_hist_entry *entry;
+	long key = offset << 16 | idx;
+
+	if (!hashmap__find(src->samples, key, &entry))
+		return NULL;
+	return entry;
+}
+
 static inline struct annotation *symbol__annotation(struct symbol *sym)
 {
 	return (void *)sym - symbol_conf.priv_size;
@@ -349,6 +428,8 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
 				 struct evsel *evsel);
 
+struct annotated_branch *annotation__get_branch(struct annotation *notes);
+
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
 				    unsigned cycles);
@@ -361,11 +442,9 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct map_symbol *ms,
 		     struct evsel *evsel,
-		     struct annotation_options *options,
 		     struct arch **parch);
 int symbol__annotate2(struct map_symbol *ms,
 		      struct evsel *evsel,
-		      struct annotation_options *options,
 		      struct arch **parch);
 
 enum symbol_disassemble_errno {
@@ -392,43 +471,94 @@ enum symbol_disassemble_errno {
 
 int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen);
 
-int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel,
-			    struct annotation_options *options);
+int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
-int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel,
-				struct annotation_options *opts);
+int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel);
 
 bool ui__has_annotation(void);
 
-int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel);
 
-int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts);
+int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel);
 
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			 struct hist_browser_timer *hbt,
-			 struct annotation_options *opts);
+			 struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 				struct evsel *evsel  __maybe_unused,
-				struct hist_browser_timer *hbt __maybe_unused,
-				struct annotation_options *opts __maybe_unused)
+				struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
 #endif
 
-void annotation_options__init(struct annotation_options *opt);
-void annotation_options__exit(struct annotation_options *opt);
+void annotation_options__init(void);
+void annotation_options__exit(void);
 
-void annotation_config__init(struct annotation_options *opt);
+void annotation_config__init(void);
 
 int annotate_parse_percent_type(const struct option *opt, const char *_str,
 				int unset);
 
-int annotate_check_args(struct annotation_options *args);
+int annotate_check_args(void);
+
+/**
+ * struct annotated_op_loc - Location info of instruction operand
+ * @reg1: First register in the operand
+ * @reg2: Second register in the operand
+ * @offset: Memory access offset in the operand
+ * @mem_ref: Whether the operand accesses memory
+ * @multi_regs: Whether the second register is used
+ */
+struct annotated_op_loc {
+	int reg1;
+	int reg2;
+	int offset;
+	bool mem_ref;
+	bool multi_regs;
+};
+
+enum annotated_insn_ops {
+	INSN_OP_SOURCE = 0,
+	INSN_OP_TARGET = 1,
+
+	INSN_OP_MAX,
+};
+
+/**
+ * struct annotated_insn_loc - Location info of instruction
+ * @ops: Array of location info for source and target operands
+ */
+struct annotated_insn_loc {
+	struct annotated_op_loc ops[INSN_OP_MAX];
+};
+
+#define for_each_insn_op_loc(insn_loc, i, op_loc)			\
+	for (i = INSN_OP_SOURCE, op_loc = &(insn_loc)->ops[i];		\
+	     i < INSN_OP_MAX;						\
+	     i++, op_loc++)
+
+/* Get detailed location info in the instruction */
+int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
+			       struct annotated_insn_loc *loc);
+
+/* Returns a data type from the sample instruction (if any) */
+struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he);
+
+struct annotated_item_stat {
+	struct list_head list;
+	char *name;
+	int good;
+	int bad;
+};
+extern struct list_head ann_insn_stat;
+
+/* Calculate PC-relative address */
+u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
+			struct disasm_line *dl);
 
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h
index 98d3235781c3..4f4900c18f3e 100644
--- a/tools/perf/util/arm-spe.h
+++ b/tools/perf/util/arm-spe.h
@@ -27,5 +27,7 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 int arm_spe_process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
 
-struct perf_event_attr *arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu);
+void arm_spe_pmu_default_config(const struct perf_pmu *arm_spe_pmu,
+				struct perf_event_attr *attr);
+
 #endif
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index a0368202a746..3684e6009b63 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct evlist *evlist,
 				   struct evsel *evsel, int idx)
 {
-	bool per_cpu = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	mp->mmap_needed = evsel->needs_auxtrace_mmap;
 
@@ -648,7 +648,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 
 static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps) {
 		struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
@@ -1638,6 +1638,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		case 'Z':
 			synth_opts->timeless_decoding = true;
 			break;
+		case 'T':
+			synth_opts->use_timestamp = true;
+			break;
 		case ' ':
 		case ',':
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 29eb82dff574..55702215a82d 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -99,6 +99,7 @@ enum itrace_period_type {
  * @remote_access: whether to synthesize remote access events
  * @mem: whether to synthesize memory events
  * @timeless_decoding: prefer "timeless" decoding i.e. ignore timestamps
+ * @use_timestamp: use the timestamp trace as kernel time
  * @vm_time_correlation: perform VM Time Correlation
  * @vm_tm_corr_dry_run: VM Time Correlation dry-run
  * @vm_tm_corr_args:  VM Time Correlation implementation-specific arguments
@@ -146,6 +147,7 @@ struct itrace_synth_opts {
 	bool			remote_access;
 	bool			mem;
 	bool			timeless_decoding;
+	bool			use_timestamp;
 	bool			vm_time_correlation;
 	bool			vm_tm_corr_dry_run;
 	char			*vm_tm_corr_args;
@@ -678,6 +680,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session,
 "				q:			quicker (less detailed) decoding\n" \
 "				A:			approximate IPC\n" \
 "				Z:			prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \
+"				T:			use the timestamp trace as kernel time\n" \
 "				PERIOD[ns|us|ms|i|t]:   specify period to sample stream\n" \
 "				concatenate multiple options. Default is iybxwpe or cewp\n"
 
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 591fc1edd385..dec910989701 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -129,9 +129,9 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 	al.sym = he->ms.sym;
 
 	notes = symbol__annotation(he->ms.sym);
-	if (!notes || !notes->src || !notes->src->cycles_hist)
+	if (!notes || !notes->branch || !notes->branch->cycles_hist)
 		return 0;
-	ch = notes->src->cycles_hist;
+	ch = notes->branch->cycles_hist;
 	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
 		if (ch[i].num_aggr) {
 			struct block_info *bi;
@@ -464,8 +464,7 @@ void block_info__free_report(struct block_report *reps, int nr_reps)
 }
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts)
+			       struct evsel *evsel, struct perf_env *env)
 {
 	int ret;
 
@@ -477,8 +476,7 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
 		return 0;
 	case 1:
 		symbol_conf.report_individual_block = true;
-		ret = block_hists_tui_browse(bh, evsel, min_percent,
-					     env, annotation_opts);
+		ret = block_hists_tui_browse(bh, evsel, min_percent, env);
 		return ret;
 	default:
 		return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index 42e9dcc4cf0a..96f53e89795e 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -78,8 +78,7 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 void block_info__free_report(struct block_report *reps, int nr_reps);
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
-			       struct evsel *evsel, struct perf_env *env,
-			       struct annotation_options *annotation_opts);
+			       struct evsel *evsel, struct perf_env *env);
 
 float block_info__total_cycles_percent(struct hist_entry *he);
 
diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c
index 680e92774d0c..15c42196c24c 100644
--- a/tools/perf/util/block-range.c
+++ b/tools/perf/util/block-range.c
@@ -311,6 +311,7 @@ done:
 double block_range__coverage(struct block_range *br)
 {
 	struct symbol *sym;
+	struct annotated_branch *branch;
 
 	if (!br) {
 		if (block_ranges.blocks)
@@ -323,5 +324,9 @@ double block_range__coverage(struct block_range *br)
 	if (!sym)
 		return -1;
 
-	return (double)br->coverage / symbol__annotation(sym)->max_coverage;
+	branch = symbol__annotation(sym)->branch;
+	if (!branch)
+		return -1;
+
+	return (double)br->coverage / branch->max_coverage;
 }
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 38fcf3ba5749..83709146a48a 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -63,6 +63,7 @@ static int machine__process_bpf_event_load(struct machine *machine,
 			dso->bpf_prog.id = id;
 			dso->bpf_prog.sub_id = i;
 			dso->bpf_prog.env = env;
+			map__put(map);
 		}
 	}
 	return 0;
@@ -386,6 +387,9 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	int err;
 	int fd;
 
+	if (opts->no_bpf_event)
+		return 0;
+
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
@@ -542,9 +546,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp)
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp)
 {
 	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
 	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
@@ -560,7 +564,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	if (info->btf_id) {
 		struct btf_node *node;
 
-		node = perf_env__find_btf(env, info->btf_id);
+		node = __perf_env__find_btf(env, info->btf_id);
 		if (node)
 			btf = btf__new((__u8 *)(node->data),
 				       node->data_size);
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index 1bcbd4fb6c66..e2f0420905f5 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -33,9 +33,9 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp);
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp);
 #else
 static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 				       union perf_event *event __maybe_unused,
@@ -50,9 +50,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
-						  struct perf_env *env __maybe_unused,
-						  FILE *fp __maybe_unused)
+static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						    struct perf_env *env __maybe_unused,
+						    FILE *fp __maybe_unused)
 {
 
 }
diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index 0b30688d78a7..b51544996046 100644
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -9,8 +9,8 @@
 #include "util/evsel.h"
 
 #include "util/bpf-filter.h"
-#include "util/bpf-filter-flex.h"
-#include "util/bpf-filter-bison.h"
+#include <util/bpf-filter-flex.h>
+#include <util/bpf-filter-bison.h>
 
 #include "bpf_skel/sample-filter.h"
 #include "bpf_skel/sample_filter.skel.h"
@@ -62,6 +62,16 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr *
 	if (evsel->core.attr.sample_type & expr->sample_flags)
 		return 0;
 
+	if (expr->op == PBF_OP_GROUP_BEGIN) {
+		struct perf_bpf_filter_expr *group;
+
+		list_for_each_entry(group, &expr->groups, list) {
+			if (check_sample_flags(evsel, group) < 0)
+				return -1;
+		}
+		return 0;
+	}
+
 	info = get_sample_info(expr->sample_flags);
 	if (info == NULL) {
 		pr_err("Error: %s event does not have sample flags %lx\n",
diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y
index 07d6c7926c13..0e4d6de3c2ad 100644
--- a/tools/perf/util/bpf-filter.y
+++ b/tools/perf/util/bpf-filter.y
@@ -3,12 +3,18 @@
 
 %{
 
+#ifndef NDEBUG
+#define YYDEBUG 1
+#endif
+
 #include <stdio.h>
 #include <string.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include "bpf-filter.h"
 
+int perf_bpf_filter_lex(void);
+
 static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
 				  char const *msg)
 {
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
deleted file mode 100644
index 44cde27d6389..000000000000
--- a/tools/perf/util/bpf-loader.c
+++ /dev/null
@@ -1,2110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-loader.c
- *
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- */
-
-#include <linux/bpf.h>
-#include <bpf/libbpf.h>
-#include <bpf/bpf.h>
-#include <linux/filter.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/zalloc.h>
-#include <errno.h>
-#include <stdlib.h>
-#include "debug.h"
-#include "evlist.h"
-#include "bpf-loader.h"
-#include "bpf-prologue.h"
-#include "probe-event.h"
-#include "probe-finder.h" // for MAX_PROBES
-#include "parse-events.h"
-#include "strfilter.h"
-#include "util.h"
-#include "llvm-utils.h"
-#include "c++/clang-c.h"
-#include "util/hashmap.h"
-#include "asm/bug.h"
-
-#include <internal/xyarray.h>
-
-/* temporarily disable libbpf deprecation warnings */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
-static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)),
-			      const char *fmt, va_list args)
-{
-	return veprintf(1, verbose, pr_fmt(fmt), args);
-}
-
-struct bpf_prog_priv {
-	bool is_tp;
-	char *sys_name;
-	char *evt_name;
-	struct perf_probe_event pev;
-	bool need_prologue;
-	struct bpf_insn *insns_buf;
-	int nr_types;
-	int *type_mapping;
-	int *prologue_fds;
-};
-
-struct bpf_perf_object {
-	struct list_head list;
-	struct bpf_object *obj;
-};
-
-struct bpf_preproc_result {
-	struct bpf_insn *new_insn_ptr;
-	int new_insn_cnt;
-};
-
-static LIST_HEAD(bpf_objects_list);
-static struct hashmap *bpf_program_hash;
-static struct hashmap *bpf_map_hash;
-
-static struct bpf_perf_object *
-bpf_perf_object__next(struct bpf_perf_object *prev)
-{
-	if (!prev) {
-		if (list_empty(&bpf_objects_list))
-			return NULL;
-
-		return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list);
-	}
-	if (list_is_last(&prev->list, &bpf_objects_list))
-		return NULL;
-
-	return list_next_entry(prev, list);
-}
-
-#define bpf_perf_object__for_each(perf_obj, tmp)	\
-	for ((perf_obj) = bpf_perf_object__next(NULL),	\
-	     (tmp) = bpf_perf_object__next(perf_obj);	\
-	     (perf_obj) != NULL;			\
-	     (perf_obj) = (tmp), (tmp) = bpf_perf_object__next(tmp))
-
-static bool libbpf_initialized;
-static int libbpf_sec_handler;
-
-static int bpf_perf_object__add(struct bpf_object *obj)
-{
-	struct bpf_perf_object *perf_obj = zalloc(sizeof(*perf_obj));
-
-	if (perf_obj) {
-		INIT_LIST_HEAD(&perf_obj->list);
-		perf_obj->obj = obj;
-		list_add_tail(&perf_obj->list, &bpf_objects_list);
-	}
-	return perf_obj ? 0 : -ENOMEM;
-}
-
-static void *program_priv(const struct bpf_program *prog)
-{
-	void *priv;
-
-	if (IS_ERR_OR_NULL(bpf_program_hash))
-		return NULL;
-	if (!hashmap__find(bpf_program_hash, prog, &priv))
-		return NULL;
-	return priv;
-}
-
-static struct bpf_insn prologue_init_insn[] = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-};
-
-static int libbpf_prog_prepare_load_fn(struct bpf_program *prog,
-				       struct bpf_prog_load_opts *opts __maybe_unused,
-				       long cookie __maybe_unused)
-{
-	size_t init_size_cnt = ARRAY_SIZE(prologue_init_insn);
-	size_t orig_insn_cnt, insn_cnt, init_size, orig_size;
-	struct bpf_prog_priv *priv = program_priv(prog);
-	const struct bpf_insn *orig_insn;
-	struct bpf_insn *insn;
-
-	if (IS_ERR_OR_NULL(priv)) {
-		pr_debug("bpf: failed to get private field\n");
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (!priv->need_prologue)
-		return 0;
-
-	/* prepend initialization code to program instructions */
-	orig_insn = bpf_program__insns(prog);
-	orig_insn_cnt = bpf_program__insn_cnt(prog);
-	init_size = init_size_cnt * sizeof(*insn);
-	orig_size = orig_insn_cnt * sizeof(*insn);
-
-	insn_cnt = orig_insn_cnt + init_size_cnt;
-	insn = malloc(insn_cnt * sizeof(*insn));
-	if (!insn)
-		return -ENOMEM;
-
-	memcpy(insn, prologue_init_insn, init_size);
-	memcpy((char *) insn + init_size, orig_insn, orig_size);
-	bpf_program__set_insns(prog, insn, insn_cnt);
-	return 0;
-}
-
-static int libbpf_init(void)
-{
-	LIBBPF_OPTS(libbpf_prog_handler_opts, handler_opts,
-		.prog_prepare_load_fn = libbpf_prog_prepare_load_fn,
-	);
-
-	if (libbpf_initialized)
-		return 0;
-
-	libbpf_set_print(libbpf_perf_print);
-	libbpf_sec_handler = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_KPROBE,
-							  0, &handler_opts);
-	if (libbpf_sec_handler < 0) {
-		pr_debug("bpf: failed to register libbpf section handler: %d\n",
-			 libbpf_sec_handler);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	libbpf_initialized = true;
-	return 0;
-}
-
-struct bpf_object *
-bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name);
-	struct bpf_object *obj;
-	int err;
-
-	err = libbpf_init();
-	if (err)
-		return ERR_PTR(err);
-
-	obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
-	if (IS_ERR_OR_NULL(obj)) {
-		pr_debug("bpf: failed to load buffer\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	if (bpf_perf_object__add(obj)) {
-		bpf_object__close(obj);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return obj;
-}
-
-static void bpf_perf_object__close(struct bpf_perf_object *perf_obj)
-{
-	list_del(&perf_obj->list);
-	bpf_object__close(perf_obj->obj);
-	free(perf_obj);
-}
-
-struct bpf_object *bpf__prepare_load(const char *filename, bool source)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename);
-	struct bpf_object *obj;
-	int err;
-
-	err = libbpf_init();
-	if (err)
-		return ERR_PTR(err);
-
-	if (source) {
-		void *obj_buf;
-		size_t obj_buf_sz;
-
-		perf_clang__init();
-		err = perf_clang__compile_bpf(filename, &obj_buf, &obj_buf_sz);
-		perf_clang__cleanup();
-		if (err) {
-			pr_debug("bpf: builtin compilation failed: %d, try external compiler\n", err);
-			err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
-			if (err)
-				return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
-		} else
-			pr_debug("bpf: successful builtin compilation\n");
-		obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
-
-		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
-			llvm__dump_obj(filename, obj_buf, obj_buf_sz);
-
-		free(obj_buf);
-	} else {
-		obj = bpf_object__open(filename);
-	}
-
-	if (IS_ERR_OR_NULL(obj)) {
-		pr_debug("bpf: failed to load %s\n", filename);
-		return obj;
-	}
-
-	if (bpf_perf_object__add(obj)) {
-		bpf_object__close(obj);
-		return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
-	}
-
-	return obj;
-}
-
-static void close_prologue_programs(struct bpf_prog_priv *priv)
-{
-	struct perf_probe_event *pev;
-	int i, fd;
-
-	if (!priv->need_prologue)
-		return;
-	pev = &priv->pev;
-	for (i = 0; i < pev->ntevs; i++) {
-		fd = priv->prologue_fds[i];
-		if (fd != -1)
-			close(fd);
-	}
-}
-
-static void
-clear_prog_priv(const struct bpf_program *prog __maybe_unused,
-		void *_priv)
-{
-	struct bpf_prog_priv *priv = _priv;
-
-	close_prologue_programs(priv);
-	cleanup_perf_probe_events(&priv->pev, 1);
-	zfree(&priv->insns_buf);
-	zfree(&priv->prologue_fds);
-	zfree(&priv->type_mapping);
-	zfree(&priv->sys_name);
-	zfree(&priv->evt_name);
-	free(priv);
-}
-
-static void bpf_program_hash_free(void)
-{
-	struct hashmap_entry *cur;
-	size_t bkt;
-
-	if (IS_ERR_OR_NULL(bpf_program_hash))
-		return;
-
-	hashmap__for_each_entry(bpf_program_hash, cur, bkt)
-		clear_prog_priv(cur->pkey, cur->pvalue);
-
-	hashmap__free(bpf_program_hash);
-	bpf_program_hash = NULL;
-}
-
-static void bpf_map_hash_free(void);
-
-void bpf__clear(void)
-{
-	struct bpf_perf_object *perf_obj, *tmp;
-
-	bpf_perf_object__for_each(perf_obj, tmp) {
-		bpf__unprobe(perf_obj->obj);
-		bpf_perf_object__close(perf_obj);
-	}
-
-	bpf_program_hash_free();
-	bpf_map_hash_free();
-}
-
-static size_t ptr_hash(const long __key, void *ctx __maybe_unused)
-{
-	return __key;
-}
-
-static bool ptr_equal(long key1, long key2, void *ctx __maybe_unused)
-{
-	return key1 == key2;
-}
-
-static int program_set_priv(struct bpf_program *prog, void *priv)
-{
-	void *old_priv;
-
-	/*
-	 * Should not happen, we warn about it in the
-	 * caller function - config_bpf_program
-	 */
-	if (IS_ERR(bpf_program_hash))
-		return PTR_ERR(bpf_program_hash);
-
-	if (!bpf_program_hash) {
-		bpf_program_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
-		if (IS_ERR(bpf_program_hash))
-			return PTR_ERR(bpf_program_hash);
-	}
-
-	old_priv = program_priv(prog);
-	if (old_priv) {
-		clear_prog_priv(prog, old_priv);
-		return hashmap__set(bpf_program_hash, prog, priv, NULL, NULL);
-	}
-	return hashmap__add(bpf_program_hash, prog, priv);
-}
-
-static int
-prog_config__exec(const char *value, struct perf_probe_event *pev)
-{
-	pev->uprobes = true;
-	pev->target = strdup(value);
-	if (!pev->target)
-		return -ENOMEM;
-	return 0;
-}
-
-static int
-prog_config__module(const char *value, struct perf_probe_event *pev)
-{
-	pev->uprobes = false;
-	pev->target = strdup(value);
-	if (!pev->target)
-		return -ENOMEM;
-	return 0;
-}
-
-static int
-prog_config__bool(const char *value, bool *pbool, bool invert)
-{
-	int err;
-	bool bool_value;
-
-	if (!pbool)
-		return -EINVAL;
-
-	err = strtobool(value, &bool_value);
-	if (err)
-		return err;
-
-	*pbool = invert ? !bool_value : bool_value;
-	return 0;
-}
-
-static int
-prog_config__inlines(const char *value,
-		     struct perf_probe_event *pev __maybe_unused)
-{
-	return prog_config__bool(value, &probe_conf.no_inlines, true);
-}
-
-static int
-prog_config__force(const char *value,
-		   struct perf_probe_event *pev __maybe_unused)
-{
-	return prog_config__bool(value, &probe_conf.force_add, false);
-}
-
-static struct {
-	const char *key;
-	const char *usage;
-	const char *desc;
-	int (*func)(const char *, struct perf_probe_event *);
-} bpf_prog_config_terms[] = {
-	{
-		.key	= "exec",
-		.usage	= "exec=<full path of file>",
-		.desc	= "Set uprobe target",
-		.func	= prog_config__exec,
-	},
-	{
-		.key	= "module",
-		.usage	= "module=<module name>    ",
-		.desc	= "Set kprobe module",
-		.func	= prog_config__module,
-	},
-	{
-		.key	= "inlines",
-		.usage	= "inlines=[yes|no]        ",
-		.desc	= "Probe at inline symbol",
-		.func	= prog_config__inlines,
-	},
-	{
-		.key	= "force",
-		.usage	= "force=[yes|no]          ",
-		.desc	= "Forcibly add events with existing name",
-		.func	= prog_config__force,
-	},
-};
-
-static int
-do_prog_config(const char *key, const char *value,
-	       struct perf_probe_event *pev)
-{
-	unsigned int i;
-
-	pr_debug("config bpf program: %s=%s\n", key, value);
-	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
-		if (strcmp(key, bpf_prog_config_terms[i].key) == 0)
-			return bpf_prog_config_terms[i].func(value, pev);
-
-	pr_debug("BPF: ERROR: invalid program config option: %s=%s\n",
-		 key, value);
-
-	pr_debug("\nHint: Valid options are:\n");
-	for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++)
-		pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage,
-			 bpf_prog_config_terms[i].desc);
-	pr_debug("\n");
-
-	return -BPF_LOADER_ERRNO__PROGCONF_TERM;
-}
-
-static const char *
-parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev)
-{
-	char *text = strdup(config_str);
-	char *sep, *line;
-	const char *main_str = NULL;
-	int err = 0;
-
-	if (!text) {
-		pr_debug("Not enough memory: dup config_str failed\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	line = text;
-	while ((sep = strchr(line, ';'))) {
-		char *equ;
-
-		*sep = '\0';
-		equ = strchr(line, '=');
-		if (!equ) {
-			pr_warning("WARNING: invalid config in BPF object: %s\n",
-				   line);
-			pr_warning("\tShould be 'key=value'.\n");
-			goto nextline;
-		}
-		*equ = '\0';
-
-		err = do_prog_config(line, equ + 1, pev);
-		if (err)
-			break;
-nextline:
-		line = sep + 1;
-	}
-
-	if (!err)
-		main_str = config_str + (line - text);
-	free(text);
-
-	return err ? ERR_PTR(err) : main_str;
-}
-
-static int
-parse_prog_config(const char *config_str, const char **p_main_str,
-		  bool *is_tp, struct perf_probe_event *pev)
-{
-	int err;
-	const char *main_str = parse_prog_config_kvpair(config_str, pev);
-
-	if (IS_ERR(main_str))
-		return PTR_ERR(main_str);
-
-	*p_main_str = main_str;
-	if (!strchr(main_str, '=')) {
-		/* Is a tracepoint event? */
-		const char *s = strchr(main_str, ':');
-
-		if (!s) {
-			pr_debug("bpf: '%s' is not a valid tracepoint\n",
-				 config_str);
-			return -BPF_LOADER_ERRNO__CONFIG;
-		}
-
-		*is_tp = true;
-		return 0;
-	}
-
-	*is_tp = false;
-	err = parse_perf_probe_command(main_str, pev);
-	if (err < 0) {
-		pr_debug("bpf: '%s' is not a valid config string\n",
-			 config_str);
-		/* parse failed, don't need clear pev. */
-		return -BPF_LOADER_ERRNO__CONFIG;
-	}
-	return 0;
-}
-
-static int
-config_bpf_program(struct bpf_program *prog)
-{
-	struct perf_probe_event *pev = NULL;
-	struct bpf_prog_priv *priv = NULL;
-	const char *config_str, *main_str;
-	bool is_tp = false;
-	int err;
-
-	/* Initialize per-program probing setting */
-	probe_conf.no_inlines = false;
-	probe_conf.force_add = false;
-
-	priv = calloc(sizeof(*priv), 1);
-	if (!priv) {
-		pr_debug("bpf: failed to alloc priv\n");
-		return -ENOMEM;
-	}
-	pev = &priv->pev;
-
-	config_str = bpf_program__section_name(prog);
-	pr_debug("bpf: config program '%s'\n", config_str);
-	err = parse_prog_config(config_str, &main_str, &is_tp, pev);
-	if (err)
-		goto errout;
-
-	if (is_tp) {
-		char *s = strchr(main_str, ':');
-
-		priv->is_tp = true;
-		priv->sys_name = strndup(main_str, s - main_str);
-		priv->evt_name = strdup(s + 1);
-		goto set_priv;
-	}
-
-	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
-		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
-			 config_str, PERF_BPF_PROBE_GROUP);
-		err = -BPF_LOADER_ERRNO__GROUP;
-		goto errout;
-	} else if (!pev->group)
-		pev->group = strdup(PERF_BPF_PROBE_GROUP);
-
-	if (!pev->group) {
-		pr_debug("bpf: strdup failed\n");
-		err = -ENOMEM;
-		goto errout;
-	}
-
-	if (!pev->event) {
-		pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
-			 config_str);
-		err = -BPF_LOADER_ERRNO__EVENTNAME;
-		goto errout;
-	}
-	pr_debug("bpf: config '%s' is ok\n", config_str);
-
-set_priv:
-	err = program_set_priv(prog, priv);
-	if (err) {
-		pr_debug("Failed to set priv for program '%s'\n", config_str);
-		goto errout;
-	}
-
-	return 0;
-
-errout:
-	if (pev)
-		clear_perf_probe_event(pev);
-	free(priv);
-	return err;
-}
-
-static int bpf__prepare_probe(void)
-{
-	static int err = 0;
-	static bool initialized = false;
-
-	/*
-	 * Make err static, so if init failed the first, bpf__prepare_probe()
-	 * fails each time without calling init_probe_symbol_maps multiple
-	 * times.
-	 */
-	if (initialized)
-		return err;
-
-	initialized = true;
-	err = init_probe_symbol_maps(false);
-	if (err < 0)
-		pr_debug("Failed to init_probe_symbol_maps\n");
-	probe_conf.max_probes = MAX_PROBES;
-	return err;
-}
-
-static int
-preproc_gen_prologue(struct bpf_program *prog, int n,
-		     const struct bpf_insn *orig_insns, int orig_insns_cnt,
-		     struct bpf_preproc_result *res)
-{
-	struct bpf_prog_priv *priv = program_priv(prog);
-	struct probe_trace_event *tev;
-	struct perf_probe_event *pev;
-	struct bpf_insn *buf;
-	size_t prologue_cnt = 0;
-	int i, err;
-
-	if (IS_ERR_OR_NULL(priv) || priv->is_tp)
-		goto errout;
-
-	pev = &priv->pev;
-
-	if (n < 0 || n >= priv->nr_types)
-		goto errout;
-
-	/* Find a tev belongs to that type */
-	for (i = 0; i < pev->ntevs; i++) {
-		if (priv->type_mapping[i] == n)
-			break;
-	}
-
-	if (i >= pev->ntevs) {
-		pr_debug("Internal error: prologue type %d not found\n", n);
-		return -BPF_LOADER_ERRNO__PROLOGUE;
-	}
-
-	tev = &pev->tevs[i];
-
-	buf = priv->insns_buf;
-	err = bpf__gen_prologue(tev->args, tev->nargs,
-				buf, &prologue_cnt,
-				BPF_MAXINSNS - orig_insns_cnt);
-	if (err) {
-		const char *title;
-
-		title = bpf_program__section_name(prog);
-		pr_debug("Failed to generate prologue for program %s\n",
-			 title);
-		return err;
-	}
-
-	memcpy(&buf[prologue_cnt], orig_insns,
-	       sizeof(struct bpf_insn) * orig_insns_cnt);
-
-	res->new_insn_ptr = buf;
-	res->new_insn_cnt = prologue_cnt + orig_insns_cnt;
-	return 0;
-
-errout:
-	pr_debug("Internal error in preproc_gen_prologue\n");
-	return -BPF_LOADER_ERRNO__PROLOGUE;
-}
-
-/*
- * compare_tev_args is reflexive, transitive and antisymmetric.
- * I can proof it but this margin is too narrow to contain.
- */
-static int compare_tev_args(const void *ptev1, const void *ptev2)
-{
-	int i, ret;
-	const struct probe_trace_event *tev1 =
-		*(const struct probe_trace_event **)ptev1;
-	const struct probe_trace_event *tev2 =
-		*(const struct probe_trace_event **)ptev2;
-
-	ret = tev2->nargs - tev1->nargs;
-	if (ret)
-		return ret;
-
-	for (i = 0; i < tev1->nargs; i++) {
-		struct probe_trace_arg *arg1, *arg2;
-		struct probe_trace_arg_ref *ref1, *ref2;
-
-		arg1 = &tev1->args[i];
-		arg2 = &tev2->args[i];
-
-		ret = strcmp(arg1->value, arg2->value);
-		if (ret)
-			return ret;
-
-		ref1 = arg1->ref;
-		ref2 = arg2->ref;
-
-		while (ref1 && ref2) {
-			ret = ref2->offset - ref1->offset;
-			if (ret)
-				return ret;
-
-			ref1 = ref1->next;
-			ref2 = ref2->next;
-		}
-
-		if (ref1 || ref2)
-			return ref2 ? 1 : -1;
-	}
-
-	return 0;
-}
-
-/*
- * Assign a type number to each tevs in a pev.
- * mapping is an array with same slots as tevs in that pev.
- * nr_types will be set to number of types.
- */
-static int map_prologue(struct perf_probe_event *pev, int *mapping,
-			int *nr_types)
-{
-	int i, type = 0;
-	struct probe_trace_event **ptevs;
-
-	size_t array_sz = sizeof(*ptevs) * pev->ntevs;
-
-	ptevs = malloc(array_sz);
-	if (!ptevs) {
-		pr_debug("Not enough memory: alloc ptevs failed\n");
-		return -ENOMEM;
-	}
-
-	pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs);
-	for (i = 0; i < pev->ntevs; i++)
-		ptevs[i] = &pev->tevs[i];
-
-	qsort(ptevs, pev->ntevs, sizeof(*ptevs),
-	      compare_tev_args);
-
-	for (i = 0; i < pev->ntevs; i++) {
-		int n;
-
-		n = ptevs[i] - pev->tevs;
-		if (i == 0) {
-			mapping[n] = type;
-			pr_debug("mapping[%d]=%d\n", n, type);
-			continue;
-		}
-
-		if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0)
-			mapping[n] = type;
-		else
-			mapping[n] = ++type;
-
-		pr_debug("mapping[%d]=%d\n", n, mapping[n]);
-	}
-	free(ptevs);
-	*nr_types = type + 1;
-
-	return 0;
-}
-
-static int hook_load_preprocessor(struct bpf_program *prog)
-{
-	struct bpf_prog_priv *priv = program_priv(prog);
-	struct perf_probe_event *pev;
-	bool need_prologue = false;
-	int i;
-
-	if (IS_ERR_OR_NULL(priv)) {
-		pr_debug("Internal error when hook preprocessor\n");
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (priv->is_tp) {
-		priv->need_prologue = false;
-		return 0;
-	}
-
-	pev = &priv->pev;
-	for (i = 0; i < pev->ntevs; i++) {
-		struct probe_trace_event *tev = &pev->tevs[i];
-
-		if (tev->nargs > 0) {
-			need_prologue = true;
-			break;
-		}
-	}
-
-	/*
-	 * Since all tevs don't have argument, we don't need generate
-	 * prologue.
-	 */
-	if (!need_prologue) {
-		priv->need_prologue = false;
-		return 0;
-	}
-
-	priv->need_prologue = true;
-	priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS);
-	if (!priv->insns_buf) {
-		pr_debug("Not enough memory: alloc insns_buf failed\n");
-		return -ENOMEM;
-	}
-
-	priv->prologue_fds = malloc(sizeof(int) * pev->ntevs);
-	if (!priv->prologue_fds) {
-		pr_debug("Not enough memory: alloc prologue fds failed\n");
-		return -ENOMEM;
-	}
-	memset(priv->prologue_fds, -1, sizeof(int) * pev->ntevs);
-
-	priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
-	if (!priv->type_mapping) {
-		pr_debug("Not enough memory: alloc type_mapping failed\n");
-		return -ENOMEM;
-	}
-	memset(priv->type_mapping, -1,
-	       sizeof(int) * pev->ntevs);
-
-	return map_prologue(pev, priv->type_mapping, &priv->nr_types);
-}
-
-int bpf__probe(struct bpf_object *obj)
-{
-	int err = 0;
-	struct bpf_program *prog;
-	struct bpf_prog_priv *priv;
-	struct perf_probe_event *pev;
-
-	err = bpf__prepare_probe();
-	if (err) {
-		pr_debug("bpf__prepare_probe failed\n");
-		return err;
-	}
-
-	bpf_object__for_each_program(prog, obj) {
-		err = config_bpf_program(prog);
-		if (err)
-			goto out;
-
-		priv = program_priv(prog);
-		if (IS_ERR_OR_NULL(priv)) {
-			if (!priv)
-				err = -BPF_LOADER_ERRNO__INTERNAL;
-			else
-				err = PTR_ERR(priv);
-			goto out;
-		}
-
-		if (priv->is_tp) {
-			bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-			continue;
-		}
-
-		bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
-		pev = &priv->pev;
-
-		err = convert_perf_probe_events(pev, 1);
-		if (err < 0) {
-			pr_debug("bpf_probe: failed to convert perf probe events\n");
-			goto out;
-		}
-
-		err = apply_perf_probe_events(pev, 1);
-		if (err < 0) {
-			pr_debug("bpf_probe: failed to apply perf probe events\n");
-			goto out;
-		}
-
-		/*
-		 * After probing, let's consider prologue, which
-		 * adds program fetcher to BPF programs.
-		 *
-		 * hook_load_preprocessor() hooks pre-processor
-		 * to bpf_program, let it generate prologue
-		 * dynamically during loading.
-		 */
-		err = hook_load_preprocessor(prog);
-		if (err)
-			goto out;
-	}
-out:
-	return err < 0 ? err : 0;
-}
-
-#define EVENTS_WRITE_BUFSIZE  4096
-int bpf__unprobe(struct bpf_object *obj)
-{
-	int err, ret = 0;
-	struct bpf_program *prog;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		int i;
-
-		if (IS_ERR_OR_NULL(priv) || priv->is_tp)
-			continue;
-
-		for (i = 0; i < priv->pev.ntevs; i++) {
-			struct probe_trace_event *tev = &priv->pev.tevs[i];
-			char name_buf[EVENTS_WRITE_BUFSIZE];
-			struct strfilter *delfilter;
-
-			snprintf(name_buf, EVENTS_WRITE_BUFSIZE,
-				 "%s:%s", tev->group, tev->event);
-			name_buf[EVENTS_WRITE_BUFSIZE - 1] = '\0';
-
-			delfilter = strfilter__new(name_buf, NULL);
-			if (!delfilter) {
-				pr_debug("Failed to create filter for unprobing\n");
-				ret = -ENOMEM;
-				continue;
-			}
-
-			err = del_perf_probe_events(delfilter);
-			strfilter__delete(delfilter);
-			if (err) {
-				pr_debug("Failed to delete %s\n", name_buf);
-				ret = err;
-				continue;
-			}
-		}
-	}
-	return ret;
-}
-
-static int bpf_object__load_prologue(struct bpf_object *obj)
-{
-	int init_cnt = ARRAY_SIZE(prologue_init_insn);
-	const struct bpf_insn *orig_insns;
-	struct bpf_preproc_result res;
-	struct perf_probe_event *pev;
-	struct bpf_program *prog;
-	int orig_insns_cnt;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		int err, i, fd;
-
-		if (IS_ERR_OR_NULL(priv)) {
-			pr_debug("bpf: failed to get private field\n");
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-
-		if (!priv->need_prologue)
-			continue;
-
-		/*
-		 * For each program that needs prologue we do following:
-		 *
-		 * - take its current instructions and use them
-		 *   to generate the new code with prologue
-		 * - load new instructions with bpf_prog_load
-		 *   and keep the fd in prologue_fds
-		 * - new fd will be used in bpf__foreach_event
-		 *   to connect this program with perf evsel
-		 */
-		orig_insns = bpf_program__insns(prog);
-		orig_insns_cnt = bpf_program__insn_cnt(prog);
-
-		pev = &priv->pev;
-		for (i = 0; i < pev->ntevs; i++) {
-			/*
-			 * Skipping artificall prologue_init_insn instructions
-			 * (init_cnt), so the prologue can be generated instead
-			 * of them.
-			 */
-			err = preproc_gen_prologue(prog, i,
-						   orig_insns + init_cnt,
-						   orig_insns_cnt - init_cnt,
-						   &res);
-			if (err)
-				return err;
-
-			fd = bpf_prog_load(bpf_program__get_type(prog),
-					   bpf_program__name(prog), "GPL",
-					   res.new_insn_ptr,
-					   res.new_insn_cnt, NULL);
-			if (fd < 0) {
-				char bf[128];
-
-				libbpf_strerror(-errno, bf, sizeof(bf));
-				pr_debug("bpf: load objects with prologue failed: err=%d: (%s)\n",
-					 -errno, bf);
-				return -errno;
-			}
-			priv->prologue_fds[i] = fd;
-		}
-		/*
-		 * We no longer need the original program,
-		 * we can unload it.
-		 */
-		bpf_program__unload(prog);
-	}
-	return 0;
-}
-
-int bpf__load(struct bpf_object *obj)
-{
-	int err;
-
-	err = bpf_object__load(obj);
-	if (err) {
-		char bf[128];
-		libbpf_strerror(err, bf, sizeof(bf));
-		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
-		return err;
-	}
-	return bpf_object__load_prologue(obj);
-}
-
-int bpf__foreach_event(struct bpf_object *obj,
-		       bpf_prog_iter_callback_t func,
-		       void *arg)
-{
-	struct bpf_program *prog;
-	int err;
-
-	bpf_object__for_each_program(prog, obj) {
-		struct bpf_prog_priv *priv = program_priv(prog);
-		struct probe_trace_event *tev;
-		struct perf_probe_event *pev;
-		int i, fd;
-
-		if (IS_ERR_OR_NULL(priv)) {
-			pr_debug("bpf: failed to get private field\n");
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-
-		if (priv->is_tp) {
-			fd = bpf_program__fd(prog);
-			err = (*func)(priv->sys_name, priv->evt_name, fd, obj, arg);
-			if (err) {
-				pr_debug("bpf: tracepoint call back failed, stop iterate\n");
-				return err;
-			}
-			continue;
-		}
-
-		pev = &priv->pev;
-		for (i = 0; i < pev->ntevs; i++) {
-			tev = &pev->tevs[i];
-
-			if (priv->need_prologue)
-				fd = priv->prologue_fds[i];
-			else
-				fd = bpf_program__fd(prog);
-
-			if (fd < 0) {
-				pr_debug("bpf: failed to get file descriptor\n");
-				return fd;
-			}
-
-			err = (*func)(tev->group, tev->event, fd, obj, arg);
-			if (err) {
-				pr_debug("bpf: call back failed, stop iterate\n");
-				return err;
-			}
-		}
-	}
-	return 0;
-}
-
-enum bpf_map_op_type {
-	BPF_MAP_OP_SET_VALUE,
-	BPF_MAP_OP_SET_EVSEL,
-};
-
-enum bpf_map_key_type {
-	BPF_MAP_KEY_ALL,
-	BPF_MAP_KEY_RANGES,
-};
-
-struct bpf_map_op {
-	struct list_head list;
-	enum bpf_map_op_type op_type;
-	enum bpf_map_key_type key_type;
-	union {
-		struct parse_events_array array;
-	} k;
-	union {
-		u64 value;
-		struct evsel *evsel;
-	} v;
-};
-
-struct bpf_map_priv {
-	struct list_head ops_list;
-};
-
-static void
-bpf_map_op__delete(struct bpf_map_op *op)
-{
-	if (!list_empty(&op->list))
-		list_del_init(&op->list);
-	if (op->key_type == BPF_MAP_KEY_RANGES)
-		parse_events__clear_array(&op->k.array);
-	free(op);
-}
-
-static void
-bpf_map_priv__purge(struct bpf_map_priv *priv)
-{
-	struct bpf_map_op *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
-		list_del_init(&pos->list);
-		bpf_map_op__delete(pos);
-	}
-}
-
-static void
-bpf_map_priv__clear(const struct bpf_map *map __maybe_unused,
-		    void *_priv)
-{
-	struct bpf_map_priv *priv = _priv;
-
-	bpf_map_priv__purge(priv);
-	free(priv);
-}
-
-static void *map_priv(const struct bpf_map *map)
-{
-	void *priv;
-
-	if (IS_ERR_OR_NULL(bpf_map_hash))
-		return NULL;
-	if (!hashmap__find(bpf_map_hash, map, &priv))
-		return NULL;
-	return priv;
-}
-
-static void bpf_map_hash_free(void)
-{
-	struct hashmap_entry *cur;
-	size_t bkt;
-
-	if (IS_ERR_OR_NULL(bpf_map_hash))
-		return;
-
-	hashmap__for_each_entry(bpf_map_hash, cur, bkt)
-		bpf_map_priv__clear(cur->pkey, cur->pvalue);
-
-	hashmap__free(bpf_map_hash);
-	bpf_map_hash = NULL;
-}
-
-static int map_set_priv(struct bpf_map *map, void *priv)
-{
-	void *old_priv;
-
-	if (WARN_ON_ONCE(IS_ERR(bpf_map_hash)))
-		return PTR_ERR(bpf_program_hash);
-
-	if (!bpf_map_hash) {
-		bpf_map_hash = hashmap__new(ptr_hash, ptr_equal, NULL);
-		if (IS_ERR(bpf_map_hash))
-			return PTR_ERR(bpf_map_hash);
-	}
-
-	old_priv = map_priv(map);
-	if (old_priv) {
-		bpf_map_priv__clear(map, old_priv);
-		return hashmap__set(bpf_map_hash, map, priv, NULL, NULL);
-	}
-	return hashmap__add(bpf_map_hash, map, priv);
-}
-
-static int
-bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
-{
-	op->key_type = BPF_MAP_KEY_ALL;
-	if (!term)
-		return 0;
-
-	if (term->array.nr_ranges) {
-		size_t memsz = term->array.nr_ranges *
-				sizeof(op->k.array.ranges[0]);
-
-		op->k.array.ranges = memdup(term->array.ranges, memsz);
-		if (!op->k.array.ranges) {
-			pr_debug("Not enough memory to alloc indices for map\n");
-			return -ENOMEM;
-		}
-		op->key_type = BPF_MAP_KEY_RANGES;
-		op->k.array.nr_ranges = term->array.nr_ranges;
-	}
-	return 0;
-}
-
-static struct bpf_map_op *
-bpf_map_op__new(struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	int err;
-
-	op = zalloc(sizeof(*op));
-	if (!op) {
-		pr_debug("Failed to alloc bpf_map_op\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	INIT_LIST_HEAD(&op->list);
-
-	err = bpf_map_op_setkey(op, term);
-	if (err) {
-		free(op);
-		return ERR_PTR(err);
-	}
-	return op;
-}
-
-static struct bpf_map_op *
-bpf_map_op__clone(struct bpf_map_op *op)
-{
-	struct bpf_map_op *newop;
-
-	newop = memdup(op, sizeof(*op));
-	if (!newop) {
-		pr_debug("Failed to alloc bpf_map_op\n");
-		return NULL;
-	}
-
-	INIT_LIST_HEAD(&newop->list);
-	if (op->key_type == BPF_MAP_KEY_RANGES) {
-		size_t memsz = op->k.array.nr_ranges *
-			       sizeof(op->k.array.ranges[0]);
-
-		newop->k.array.ranges = memdup(op->k.array.ranges, memsz);
-		if (!newop->k.array.ranges) {
-			pr_debug("Failed to alloc indices for map\n");
-			free(newop);
-			return NULL;
-		}
-	}
-
-	return newop;
-}
-
-static struct bpf_map_priv *
-bpf_map_priv__clone(struct bpf_map_priv *priv)
-{
-	struct bpf_map_priv *newpriv;
-	struct bpf_map_op *pos, *newop;
-
-	newpriv = zalloc(sizeof(*newpriv));
-	if (!newpriv) {
-		pr_debug("Not enough memory to alloc map private\n");
-		return NULL;
-	}
-	INIT_LIST_HEAD(&newpriv->ops_list);
-
-	list_for_each_entry(pos, &priv->ops_list, list) {
-		newop = bpf_map_op__clone(pos);
-		if (!newop) {
-			bpf_map_priv__purge(newpriv);
-			return NULL;
-		}
-		list_add_tail(&newop->list, &newpriv->ops_list);
-	}
-
-	return newpriv;
-}
-
-static int
-bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
-{
-	const char *map_name = bpf_map__name(map);
-	struct bpf_map_priv *priv = map_priv(map);
-
-	if (IS_ERR(priv)) {
-		pr_debug("Failed to get private from map %s\n", map_name);
-		return PTR_ERR(priv);
-	}
-
-	if (!priv) {
-		priv = zalloc(sizeof(*priv));
-		if (!priv) {
-			pr_debug("Not enough memory to alloc map private\n");
-			return -ENOMEM;
-		}
-		INIT_LIST_HEAD(&priv->ops_list);
-
-		if (map_set_priv(map, priv)) {
-			free(priv);
-			return -BPF_LOADER_ERRNO__INTERNAL;
-		}
-	}
-
-	list_add_tail(&op->list, &priv->ops_list);
-	return 0;
-}
-
-static struct bpf_map_op *
-bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	int err;
-
-	op = bpf_map_op__new(term);
-	if (IS_ERR(op))
-		return op;
-
-	err = bpf_map__add_op(map, op);
-	if (err) {
-		bpf_map_op__delete(op);
-		return ERR_PTR(err);
-	}
-	return op;
-}
-
-static int
-__bpf_map__config_value(struct bpf_map *map,
-			struct parse_events_term *term)
-{
-	struct bpf_map_op *op;
-	const char *map_name = bpf_map__name(map);
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) {
-		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
-			 map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-	}
-	if (bpf_map__key_size(map) < sizeof(unsigned int)) {
-		pr_debug("Map %s has incorrect key size\n", map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
-	}
-	switch (bpf_map__value_size(map)) {
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		break;
-	default:
-		pr_debug("Map %s has incorrect value size\n", map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
-	}
-
-	op = bpf_map__add_newop(map, term);
-	if (IS_ERR(op))
-		return PTR_ERR(op);
-	op->op_type = BPF_MAP_OP_SET_VALUE;
-	op->v.value = term->val.num;
-	return 0;
-}
-
-static int
-bpf_map__config_value(struct bpf_map *map,
-		      struct parse_events_term *term,
-		      struct evlist *evlist __maybe_unused)
-{
-	if (!term->err_val) {
-		pr_debug("Config value not set\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
-	}
-
-	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
-		pr_debug("ERROR: wrong value type for 'value'\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
-	}
-
-	return __bpf_map__config_value(map, term);
-}
-
-static int
-__bpf_map__config_event(struct bpf_map *map,
-			struct parse_events_term *term,
-			struct evlist *evlist)
-{
-	struct bpf_map_op *op;
-	const char *map_name = bpf_map__name(map);
-	struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str);
-
-	if (!evsel) {
-		pr_debug("Event (for '%s') '%s' doesn't exist\n",
-			 map_name, term->val.str);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return PTR_ERR(map);
-	}
-
-	/*
-	 * No need to check key_size and value_size:
-	 * kernel has already checked them.
-	 */
-	if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
-		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
-			 map_name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-	}
-
-	op = bpf_map__add_newop(map, term);
-	if (IS_ERR(op))
-		return PTR_ERR(op);
-	op->op_type = BPF_MAP_OP_SET_EVSEL;
-	op->v.evsel = evsel;
-	return 0;
-}
-
-static int
-bpf_map__config_event(struct bpf_map *map,
-		      struct parse_events_term *term,
-		      struct evlist *evlist)
-{
-	if (!term->err_val) {
-		pr_debug("Config value not set\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
-	}
-
-	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
-		pr_debug("ERROR: wrong value type for 'event'\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
-	}
-
-	return __bpf_map__config_event(map, term, evlist);
-}
-
-struct bpf_obj_config__map_func {
-	const char *config_opt;
-	int (*config_func)(struct bpf_map *, struct parse_events_term *,
-			   struct evlist *);
-};
-
-struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
-	{"value", bpf_map__config_value},
-	{"event", bpf_map__config_event},
-};
-
-static int
-config_map_indices_range_check(struct parse_events_term *term,
-			       struct bpf_map *map,
-			       const char *map_name)
-{
-	struct parse_events_array *array = &term->array;
-	unsigned int i;
-
-	if (!array->nr_ranges)
-		return 0;
-	if (!array->ranges) {
-		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
-			 map_name, (int)array->nr_ranges);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", map_name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	for (i = 0; i < array->nr_ranges; i++) {
-		unsigned int start = array->ranges[i].start;
-		size_t length = array->ranges[i].length;
-		unsigned int idx = start + length - 1;
-
-		if (idx >= bpf_map__max_entries(map)) {
-			pr_debug("ERROR: index %d too large\n", idx);
-			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
-		}
-	}
-	return 0;
-}
-
-static int
-bpf__obj_config_map(struct bpf_object *obj,
-		    struct parse_events_term *term,
-		    struct evlist *evlist,
-		    int *key_scan_pos)
-{
-	/* key is "map:<mapname>.<config opt>" */
-	char *map_name = strdup(term->config + sizeof("map:") - 1);
-	struct bpf_map *map;
-	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
-	char *map_opt;
-	size_t i;
-
-	if (!map_name)
-		return -ENOMEM;
-
-	map_opt = strchr(map_name, '.');
-	if (!map_opt) {
-		pr_debug("ERROR: Invalid map config: %s\n", map_name);
-		goto out;
-	}
-
-	*map_opt++ = '\0';
-	if (*map_opt == '\0') {
-		pr_debug("ERROR: Invalid map option: %s\n", term->config);
-		goto out;
-	}
-
-	map = bpf_object__find_map_by_name(obj, map_name);
-	if (!map) {
-		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
-		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
-		goto out;
-	}
-
-	*key_scan_pos += strlen(map_opt);
-	err = config_map_indices_range_check(term, map, map_name);
-	if (err)
-		goto out;
-	*key_scan_pos -= strlen(map_opt);
-
-	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
-		struct bpf_obj_config__map_func *func =
-				&bpf_obj_config__map_funcs[i];
-
-		if (strcmp(map_opt, func->config_opt) == 0) {
-			err = func->config_func(map, term, evlist);
-			goto out;
-		}
-	}
-
-	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
-	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
-out:
-	if (!err)
-		*key_scan_pos += strlen(map_opt);
-
-	free(map_name);
-	return err;
-}
-
-int bpf__config_obj(struct bpf_object *obj,
-		    struct parse_events_term *term,
-		    struct evlist *evlist,
-		    int *error_pos)
-{
-	int key_scan_pos = 0;
-	int err;
-
-	if (!obj || !term || !term->config)
-		return -EINVAL;
-
-	if (strstarts(term->config, "map:")) {
-		key_scan_pos = sizeof("map:") - 1;
-		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
-		goto out;
-	}
-	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
-out:
-	if (error_pos)
-		*error_pos = key_scan_pos;
-	return err;
-
-}
-
-typedef int (*map_config_func_t)(const char *name, int map_fd,
-				 const struct bpf_map *map,
-				 struct bpf_map_op *op,
-				 void *pkey, void *arg);
-
-static int
-foreach_key_array_all(map_config_func_t func,
-		      void *arg, const char *name,
-		      int map_fd, const struct bpf_map *map,
-		      struct bpf_map_op *op)
-{
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < bpf_map__max_entries(map); i++) {
-		err = func(name, map_fd, map, op, &i, arg);
-		if (err) {
-			pr_debug("ERROR: failed to insert value to %s[%u]\n",
-				 name, i);
-			return err;
-		}
-	}
-	return 0;
-}
-
-static int
-foreach_key_array_ranges(map_config_func_t func, void *arg,
-			 const char *name, int map_fd,
-			 const struct bpf_map *map,
-			 struct bpf_map_op *op)
-{
-	unsigned int i, j;
-	int err;
-
-	for (i = 0; i < op->k.array.nr_ranges; i++) {
-		unsigned int start = op->k.array.ranges[i].start;
-		size_t length = op->k.array.ranges[i].length;
-
-		for (j = 0; j < length; j++) {
-			unsigned int idx = start + j;
-
-			err = func(name, map_fd, map, op, &idx, arg);
-			if (err) {
-				pr_debug("ERROR: failed to insert value to %s[%u]\n",
-					 name, idx);
-				return err;
-			}
-		}
-	}
-	return 0;
-}
-
-static int
-bpf_map_config_foreach_key(struct bpf_map *map,
-			   map_config_func_t func,
-			   void *arg)
-{
-	int err, map_fd, type;
-	struct bpf_map_op *op;
-	const char *name = bpf_map__name(map);
-	struct bpf_map_priv *priv = map_priv(map);
-
-	if (IS_ERR(priv)) {
-		pr_debug("ERROR: failed to get private from map %s\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	if (!priv || list_empty(&priv->ops_list)) {
-		pr_debug("INFO: nothing to config for map %s\n", name);
-		return 0;
-	}
-
-	if (!map) {
-		pr_debug("Map '%s' is invalid\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	map_fd = bpf_map__fd(map);
-	if (map_fd < 0) {
-		pr_debug("ERROR: failed to get fd from map %s\n", name);
-		return map_fd;
-	}
-
-	type = bpf_map__type(map);
-	list_for_each_entry(op, &priv->ops_list, list) {
-		switch (type) {
-		case BPF_MAP_TYPE_ARRAY:
-		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
-			switch (op->key_type) {
-			case BPF_MAP_KEY_ALL:
-				err = foreach_key_array_all(func, arg, name,
-							    map_fd, map, op);
-				break;
-			case BPF_MAP_KEY_RANGES:
-				err = foreach_key_array_ranges(func, arg, name,
-							       map_fd, map, op);
-				break;
-			default:
-				pr_debug("ERROR: keytype for map '%s' invalid\n",
-					 name);
-				return -BPF_LOADER_ERRNO__INTERNAL;
-			}
-			if (err)
-				return err;
-			break;
-		default:
-			pr_debug("ERROR: type of '%s' incorrect\n", name);
-			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
-		}
-	}
-
-	return 0;
-}
-
-static int
-apply_config_value_for_key(int map_fd, void *pkey,
-			   size_t val_size, u64 val)
-{
-	int err = 0;
-
-	switch (val_size) {
-	case 1: {
-		u8 _val = (u8)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 2: {
-		u16 _val = (u16)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 4: {
-		u32 _val = (u32)(val);
-		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
-		break;
-	}
-	case 8: {
-		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
-		break;
-	}
-	default:
-		pr_debug("ERROR: invalid value size\n");
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
-	}
-	if (err && errno)
-		err = -errno;
-	return err;
-}
-
-static int
-apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
-			   struct evsel *evsel)
-{
-	struct xyarray *xy = evsel->core.fd;
-	struct perf_event_attr *attr;
-	unsigned int key, events;
-	bool check_pass = false;
-	int *evt_fd;
-	int err;
-
-	if (!xy) {
-		pr_debug("ERROR: evsel not ready for map %s\n", name);
-		return -BPF_LOADER_ERRNO__INTERNAL;
-	}
-
-	if (xy->row_size / xy->entry_size != 1) {
-		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
-			 name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
-	}
-
-	attr = &evsel->core.attr;
-	if (attr->inherit) {
-		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
-	}
-
-	if (evsel__is_bpf_output(evsel))
-		check_pass = true;
-	if (attr->type == PERF_TYPE_RAW)
-		check_pass = true;
-	if (attr->type == PERF_TYPE_HARDWARE)
-		check_pass = true;
-	if (!check_pass) {
-		pr_debug("ERROR: Event type is wrong for map %s\n", name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
-	}
-
-	events = xy->entries / (xy->row_size / xy->entry_size);
-	key = *((unsigned int *)pkey);
-	if (key >= events) {
-		pr_debug("ERROR: there is no event %d for map %s\n",
-			 key, name);
-		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
-	}
-	evt_fd = xyarray__entry(xy, key, 0);
-	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
-	if (err && errno)
-		err = -errno;
-	return err;
-}
-
-static int
-apply_obj_config_map_for_key(const char *name, int map_fd,
-			     const struct bpf_map *map,
-			     struct bpf_map_op *op,
-			     void *pkey, void *arg __maybe_unused)
-{
-	int err;
-
-	switch (op->op_type) {
-	case BPF_MAP_OP_SET_VALUE:
-		err = apply_config_value_for_key(map_fd, pkey,
-						 bpf_map__value_size(map),
-						 op->v.value);
-		break;
-	case BPF_MAP_OP_SET_EVSEL:
-		err = apply_config_evsel_for_key(name, map_fd, pkey,
-						 op->v.evsel);
-		break;
-	default:
-		pr_debug("ERROR: unknown value type for '%s'\n", name);
-		err = -BPF_LOADER_ERRNO__INTERNAL;
-	}
-	return err;
-}
-
-static int
-apply_obj_config_map(struct bpf_map *map)
-{
-	return bpf_map_config_foreach_key(map,
-					  apply_obj_config_map_for_key,
-					  NULL);
-}
-
-static int
-apply_obj_config_object(struct bpf_object *obj)
-{
-	struct bpf_map *map;
-	int err;
-
-	bpf_object__for_each_map(map, obj) {
-		err = apply_obj_config_map(map);
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
-int bpf__apply_obj_config(void)
-{
-	struct bpf_perf_object *perf_obj, *tmp;
-	int err;
-
-	bpf_perf_object__for_each(perf_obj, tmp) {
-		err = apply_obj_config_object(perf_obj->obj);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-#define bpf__perf_for_each_map(map, pobj, tmp)			\
-	bpf_perf_object__for_each(pobj, tmp)			\
-		bpf_object__for_each_map(map, pobj->obj)
-
-#define bpf__perf_for_each_map_named(map, pobj, pobjtmp, name)	\
-	bpf__perf_for_each_map(map, pobj, pobjtmp)		\
-		if (bpf_map__name(map) && (strcmp(name, bpf_map__name(map)) == 0))
-
-struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name)
-{
-	struct bpf_map_priv *tmpl_priv = NULL;
-	struct bpf_perf_object *perf_obj, *tmp;
-	struct evsel *evsel = NULL;
-	struct bpf_map *map;
-	int err;
-	bool need_init = false;
-
-	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
-		struct bpf_map_priv *priv = map_priv(map);
-
-		if (IS_ERR(priv))
-			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
-
-		/*
-		 * No need to check map type: type should have been
-		 * verified by kernel.
-		 */
-		if (!need_init && !priv)
-			need_init = !priv;
-		if (!tmpl_priv && priv)
-			tmpl_priv = priv;
-	}
-
-	if (!need_init)
-		return NULL;
-
-	if (!tmpl_priv) {
-		char *event_definition = NULL;
-
-		if (asprintf(&event_definition, "bpf-output/no-inherit=1,name=%s/", name) < 0)
-			return ERR_PTR(-ENOMEM);
-
-		err = parse_event(evlist, event_definition);
-		free(event_definition);
-
-		if (err) {
-			pr_debug("ERROR: failed to create the \"%s\" bpf-output event\n", name);
-			return ERR_PTR(-err);
-		}
-
-		evsel = evlist__last(evlist);
-	}
-
-	bpf__perf_for_each_map_named(map, perf_obj, tmp, name) {
-		struct bpf_map_priv *priv = map_priv(map);
-
-		if (IS_ERR(priv))
-			return ERR_PTR(-BPF_LOADER_ERRNO__INTERNAL);
-		if (priv)
-			continue;
-
-		if (tmpl_priv) {
-			priv = bpf_map_priv__clone(tmpl_priv);
-			if (!priv)
-				return ERR_PTR(-ENOMEM);
-
-			err = map_set_priv(map, priv);
-			if (err) {
-				bpf_map_priv__clear(map, priv);
-				return ERR_PTR(err);
-			}
-		} else if (evsel) {
-			struct bpf_map_op *op;
-
-			op = bpf_map__add_newop(map, NULL);
-			if (IS_ERR(op))
-				return ERR_CAST(op);
-			op->op_type = BPF_MAP_OP_SET_EVSEL;
-			op->v.evsel = evsel;
-		}
-	}
-
-	return evsel;
-}
-
-int bpf__setup_stdout(struct evlist *evlist)
-{
-	struct evsel *evsel = bpf__setup_output_event(evlist, "__bpf_stdout__");
-	return PTR_ERR_OR_ZERO(evsel);
-}
-
-#define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
-#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
-#define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
-
-static const char *bpf_loader_strerror_table[NR_ERRNO] = {
-	[ERRCODE_OFFSET(CONFIG)]	= "Invalid config string",
-	[ERRCODE_OFFSET(GROUP)]		= "Invalid group name",
-	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
-	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
-	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
-	[ERRCODE_OFFSET(PROGCONF_TERM)]	= "Invalid program config term in config string",
-	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
-	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
-	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
-	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
-	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
-	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
-	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
-	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
-	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
-	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
-	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
-	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
-	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
-	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
-	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
-};
-
-static int
-bpf_loader_strerror(int err, char *buf, size_t size)
-{
-	char sbuf[STRERR_BUFSIZE];
-	const char *msg;
-
-	if (!buf || !size)
-		return -1;
-
-	err = err > 0 ? err : -err;
-
-	if (err >= __LIBBPF_ERRNO__START)
-		return libbpf_strerror(err, buf, size);
-
-	if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
-		msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
-		snprintf(buf, size, "%s", msg);
-		buf[size - 1] = '\0';
-		return 0;
-	}
-
-	if (err >= __BPF_LOADER_ERRNO__END)
-		snprintf(buf, size, "Unknown bpf loader error %d", err);
-	else
-		snprintf(buf, size, "%s",
-			 str_error_r(err, sbuf, sizeof(sbuf)));
-
-	buf[size - 1] = '\0';
-	return -1;
-}
-
-#define bpf__strerror_head(err, buf, size) \
-	char sbuf[STRERR_BUFSIZE], *emsg;\
-	if (!size)\
-		return 0;\
-	if (err < 0)\
-		err = -err;\
-	bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
-	emsg = sbuf;\
-	switch (err) {\
-	default:\
-		scnprintf(buf, size, "%s", emsg);\
-		break;
-
-#define bpf__strerror_entry(val, fmt...)\
-	case val: {\
-		scnprintf(buf, size, fmt);\
-		break;\
-	}
-
-#define bpf__strerror_end(buf, size)\
-	}\
-	buf[size - 1] = '\0';
-
-int bpf__strerror_prepare_load(const char *filename, bool source,
-			       int err, char *buf, size_t size)
-{
-	size_t n;
-	int ret;
-
-	n = snprintf(buf, size, "Failed to load %s%s: ",
-			 filename, source ? " from source" : "");
-	if (n >= size) {
-		buf[size - 1] = '\0';
-		return 0;
-	}
-	buf += n;
-	size -= n;
-
-	ret = bpf_loader_strerror(err, buf, size);
-	buf[size - 1] = '\0';
-	return ret;
-}
-
-int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
-			int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	case BPF_LOADER_ERRNO__PROGCONF_TERM: {
-		scnprintf(buf, size, "%s (add -v to see detail)", emsg);
-		break;
-	}
-	bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'");
-	bpf__strerror_entry(EACCES, "You need to be root");
-	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
-	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_load(struct bpf_object *obj,
-		       int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	case LIBBPF_ERRNO__KVER: {
-		unsigned int obj_kver = bpf_object__kversion(obj);
-		unsigned int real_kver;
-
-		if (fetch_kernel_version(&real_kver, NULL, 0)) {
-			scnprintf(buf, size, "Unable to fetch kernel version");
-			break;
-		}
-
-		if (obj_kver != real_kver) {
-			scnprintf(buf, size,
-				  "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
-				  KVER_PARAM(obj_kver),
-				  KVER_PARAM(real_kver));
-			break;
-		}
-
-		scnprintf(buf, size, "Failed to load program for unknown reason");
-		break;
-	}
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
-			     struct parse_events_term *term __maybe_unused,
-			     struct evlist *evlist __maybe_unused,
-			     int *error_pos __maybe_unused, int err,
-			     char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
-			    "Can't use this config term with this map type");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
-			    "Cannot set event to BPF map in multi-thread tracing");
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
-			    "%s (Hint: use -i to turn off inherit)", emsg);
-	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
-			    "Can only put raw, hardware and BPF output event into a BPF map");
-	bpf__strerror_end(buf, size);
-	return 0;
-}
-
-int bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
-				     int err, char *buf, size_t size)
-{
-	bpf__strerror_head(err, buf, size);
-	bpf__strerror_end(buf, size);
-	return 0;
-}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
deleted file mode 100644
index 5d1c725cea29..000000000000
--- a/tools/perf/util/bpf-loader.h
+++ /dev/null
@@ -1,216 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-#ifndef __BPF_LOADER_H
-#define __BPF_LOADER_H
-
-#include <linux/compiler.h>
-#include <linux/err.h>
-
-#ifdef HAVE_LIBBPF_SUPPORT
-#include <bpf/libbpf.h>
-
-enum bpf_loader_errno {
-	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
-	/* Invalid config string */
-	BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START,
-	BPF_LOADER_ERRNO__GROUP,	/* Invalid group name */
-	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
-	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
-	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
-	BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */
-	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
-	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
-	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
-	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
-	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
-	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
-	__BPF_LOADER_ERRNO__END,
-};
-#endif // HAVE_LIBBPF_SUPPORT
-
-struct evsel;
-struct evlist;
-struct bpf_object;
-struct parse_events_term;
-#define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
-
-typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event,
-					int fd, struct bpf_object *obj, void *arg);
-
-#ifdef HAVE_LIBBPF_SUPPORT
-struct bpf_object *bpf__prepare_load(const char *filename, bool source);
-int bpf__strerror_prepare_load(const char *filename, bool source,
-			       int err, char *buf, size_t size);
-
-struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz,
-					    const char *name);
-
-void bpf__clear(void);
-
-int bpf__probe(struct bpf_object *obj);
-int bpf__unprobe(struct bpf_object *obj);
-int bpf__strerror_probe(struct bpf_object *obj, int err,
-			char *buf, size_t size);
-
-int bpf__load(struct bpf_object *obj);
-int bpf__strerror_load(struct bpf_object *obj, int err,
-		       char *buf, size_t size);
-int bpf__foreach_event(struct bpf_object *obj,
-		       bpf_prog_iter_callback_t func, void *arg);
-
-int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
-		    struct evlist *evlist, int *error_pos);
-int bpf__strerror_config_obj(struct bpf_object *obj,
-			     struct parse_events_term *term,
-			     struct evlist *evlist,
-			     int *error_pos, int err, char *buf,
-			     size_t size);
-int bpf__apply_obj_config(void);
-int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
-
-int bpf__setup_stdout(struct evlist *evlist);
-struct evsel *bpf__setup_output_event(struct evlist *evlist, const char *name);
-int bpf__strerror_setup_output_event(struct evlist *evlist, int err, char *buf, size_t size);
-#else
-#include <errno.h>
-#include <string.h>
-#include "debug.h"
-
-static inline struct bpf_object *
-bpf__prepare_load(const char *filename __maybe_unused,
-		  bool source __maybe_unused)
-{
-	pr_debug("ERROR: eBPF object loading is disabled during compiling.\n");
-	return ERR_PTR(-ENOTSUP);
-}
-
-static inline struct bpf_object *
-bpf__prepare_load_buffer(void *obj_buf __maybe_unused,
-					   size_t obj_buf_sz __maybe_unused)
-{
-	return ERR_PTR(-ENOTSUP);
-}
-
-static inline void bpf__clear(void) { }
-
-static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;}
-static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0;}
-static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; }
-
-static inline int
-bpf__foreach_event(struct bpf_object *obj __maybe_unused,
-		   bpf_prog_iter_callback_t func __maybe_unused,
-		   void *arg __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-bpf__config_obj(struct bpf_object *obj __maybe_unused,
-		struct parse_events_term *term __maybe_unused,
-		struct evlist *evlist __maybe_unused,
-		int *error_pos __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-bpf__apply_obj_config(void)
-{
-	return 0;
-}
-
-static inline int
-bpf__setup_stdout(struct evlist *evlist __maybe_unused)
-{
-	return 0;
-}
-
-static inline struct evsel *
-bpf__setup_output_event(struct evlist *evlist __maybe_unused, const char *name __maybe_unused)
-{
-	return NULL;
-}
-
-static inline int
-__bpf_strerror(char *buf, size_t size)
-{
-	if (!size)
-		return 0;
-	strncpy(buf,
-		"ERROR: eBPF object loading is disabled during compiling.\n",
-		size);
-	buf[size - 1] = '\0';
-	return 0;
-}
-
-static inline
-int bpf__strerror_prepare_load(const char *filename __maybe_unused,
-			       bool source __maybe_unused,
-			       int err __maybe_unused,
-			       char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
-		    int err __maybe_unused,
-		    char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
-				     int err __maybe_unused,
-				     char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
-			 struct parse_events_term *term __maybe_unused,
-			 struct evlist *evlist __maybe_unused,
-			 int *error_pos __maybe_unused,
-			 int err __maybe_unused,
-			 char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_apply_obj_config(int err __maybe_unused,
-			       char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-static inline int
-bpf__strerror_setup_output_event(struct evlist *evlist __maybe_unused,
-				 int err __maybe_unused, char *buf, size_t size)
-{
-	return __bpf_strerror(buf, size);
-}
-
-#endif
-
-static inline int bpf__strerror_setup_stdout(struct evlist *evlist, int err, char *buf, size_t size)
-{
-	return bpf__strerror_setup_output_event(evlist, err, buf, size);
-}
-#endif
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
deleted file mode 100644
index 9887ae09242d..000000000000
--- a/tools/perf/util/bpf-prologue.c
+++ /dev/null
@@ -1,508 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * bpf-prologue.c
- *
- * Copyright (C) 2015 He Kuang <hekuang@huawei.com>
- * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015 Huawei Inc.
- */
-
-#include <bpf/libbpf.h>
-#include "debug.h"
-#include "bpf-loader.h"
-#include "bpf-prologue.h"
-#include "probe-finder.h"
-#include <errno.h>
-#include <stdlib.h>
-#include <dwarf-regs.h>
-#include <linux/filter.h>
-
-#define BPF_REG_SIZE		8
-
-#define JMP_TO_ERROR_CODE	-1
-#define JMP_TO_SUCCESS_CODE	-2
-#define JMP_TO_USER_CODE	-3
-
-struct bpf_insn_pos {
-	struct bpf_insn *begin;
-	struct bpf_insn *end;
-	struct bpf_insn *pos;
-};
-
-static inline int
-pos_get_cnt(struct bpf_insn_pos *pos)
-{
-	return pos->pos - pos->begin;
-}
-
-static int
-append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos)
-{
-	if (!pos->pos)
-		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-
-	if (pos->pos + 1 >= pos->end) {
-		pr_err("bpf prologue: prologue too long\n");
-		pos->pos = NULL;
-		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-	}
-
-	*(pos->pos)++ = new_insn;
-	return 0;
-}
-
-static int
-check_pos(struct bpf_insn_pos *pos)
-{
-	if (!pos->pos || pos->pos >= pos->end)
-		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-	return 0;
-}
-
-/*
- * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
- * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM
- * instruction (BPF_{B,H,W,DW}).
- */
-static int
-argtype_to_ldx_size(const char *type)
-{
-	int arg_size = type ? atoi(&type[1]) : 64;
-
-	switch (arg_size) {
-	case 8:
-		return BPF_B;
-	case 16:
-		return BPF_H;
-	case 32:
-		return BPF_W;
-	case 64:
-	default:
-		return BPF_DW;
-	}
-}
-
-static const char *
-insn_sz_to_str(int insn_sz)
-{
-	switch (insn_sz) {
-	case BPF_B:
-		return "BPF_B";
-	case BPF_H:
-		return "BPF_H";
-	case BPF_W:
-		return "BPF_W";
-	case BPF_DW:
-		return "BPF_DW";
-	default:
-		return "UNKNOWN";
-	}
-}
-
-/* Give it a shorter name */
-#define ins(i, p) append_insn((i), (p))
-
-/*
- * Give a register name (in 'reg'), generate instruction to
- * load register into an eBPF register rd:
- *   'ldd target_reg, offset(ctx_reg)', where:
- * ctx_reg is pre initialized to pointer of 'struct pt_regs'.
- */
-static int
-gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg,
-		     const char *reg, int target_reg)
-{
-	int offset = regs_query_register_offset(reg);
-
-	if (offset < 0) {
-		pr_err("bpf: prologue: failed to get register %s\n",
-		       reg);
-		return offset;
-	}
-	ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos);
-
-	return check_pos(pos);
-}
-
-/*
- * Generate a BPF_FUNC_probe_read function call.
- *
- * src_base_addr_reg is a register holding base address,
- * dst_addr_reg is a register holding dest address (on stack),
- * result is:
- *
- *  *[dst_addr_reg] = *([src_base_addr_reg] + offset)
- *
- * Arguments of BPF_FUNC_probe_read:
- *     ARG1: ptr to stack (dest)
- *     ARG2: size (8)
- *     ARG3: unsafe ptr (src)
- */
-static int
-gen_read_mem(struct bpf_insn_pos *pos,
-	     int src_base_addr_reg,
-	     int dst_addr_reg,
-	     long offset,
-	     int probeid)
-{
-	/* mov arg3, src_base_addr_reg */
-	if (src_base_addr_reg != BPF_REG_ARG3)
-		ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos);
-	/* add arg3, #offset */
-	if (offset)
-		ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos);
-
-	/* mov arg2, #reg_size */
-	ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos);
-
-	/* mov arg1, dst_addr_reg */
-	if (dst_addr_reg != BPF_REG_ARG1)
-		ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
-
-	/* Call probe_read  */
-	ins(BPF_EMIT_CALL(probeid), pos);
-	/*
-	 * Error processing: if read fail, goto error code,
-	 * will be relocated. Target should be the start of
-	 * error processing code.
-	 */
-	ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE),
-	    pos);
-
-	return check_pos(pos);
-}
-
-/*
- * Each arg should be bare register. Fetch and save them into argument
- * registers (r3 - r5).
- *
- * BPF_REG_1 should have been initialized with pointer to
- * 'struct pt_regs'.
- */
-static int
-gen_prologue_fastpath(struct bpf_insn_pos *pos,
-		      struct probe_trace_arg *args, int nargs)
-{
-	int i, err = 0;
-
-	for (i = 0; i < nargs; i++) {
-		err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value,
-					   BPF_PROLOGUE_START_ARG_REG + i);
-		if (err)
-			goto errout;
-	}
-
-	return check_pos(pos);
-errout:
-	return err;
-}
-
-/*
- * Slow path:
- *   At least one argument has the form of 'offset($rx)'.
- *
- * Following code first stores them into stack, then loads all of then
- * to r2 - r5.
- * Before final loading, the final result should be:
- *
- * low address
- * BPF_REG_FP - 24  ARG3
- * BPF_REG_FP - 16  ARG2
- * BPF_REG_FP - 8   ARG1
- * BPF_REG_FP
- * high address
- *
- * For each argument (described as: offn(...off2(off1(reg)))),
- * generates following code:
- *
- *  r7 <- fp
- *  r7 <- r7 - stack_offset  // Ideal code should initialize r7 using
- *                           // fp before generating args. However,
- *                           // eBPF won't regard r7 as stack pointer
- *                           // if it is generated by minus 8 from
- *                           // another stack pointer except fp.
- *                           // This is why we have to set r7
- *                           // to fp for each variable.
- *  r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx()
- *  (r7) <- r3       // skip following instructions for bare reg
- *  r3 <- r3 + off1  . // skip if off1 == 0
- *  r2 <- 8           \
- *  r1 <- r7           |-> generated by gen_read_mem()
- *  call probe_read    /
- *  jnei r0, 0, err  ./
- *  r3 <- (r7)
- *  r3 <- r3 + off2  . // skip if off2 == 0
- *  r2 <- 8           \  // r2 may be broken by probe_read, so set again
- *  r1 <- r7           |-> generated by gen_read_mem()
- *  call probe_read    /
- *  jnei r0, 0, err  ./
- *  ...
- */
-static int
-gen_prologue_slowpath(struct bpf_insn_pos *pos,
-		      struct probe_trace_arg *args, int nargs)
-{
-	int err, i, probeid;
-
-	for (i = 0; i < nargs; i++) {
-		struct probe_trace_arg *arg = &args[i];
-		const char *reg = arg->value;
-		struct probe_trace_arg_ref *ref = NULL;
-		int stack_offset = (i + 1) * -8;
-
-		pr_debug("prologue: fetch arg %d, base reg is %s\n",
-			 i, reg);
-
-		/* value of base register is stored into ARG3 */
-		err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg,
-					   BPF_REG_ARG3);
-		if (err) {
-			pr_err("prologue: failed to get offset of register %s\n",
-			       reg);
-			goto errout;
-		}
-
-		/* Make r7 the stack pointer. */
-		ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos);
-		/* r7 += -8 */
-		ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos);
-		/*
-		 * Store r3 (base register) onto stack
-		 * Ensure fp[offset] is set.
-		 * fp is the only valid base register when storing
-		 * into stack. We are not allowed to use r7 as base
-		 * register here.
-		 */
-		ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3,
-				stack_offset), pos);
-
-		ref = arg->ref;
-		probeid = BPF_FUNC_probe_read_kernel;
-		while (ref) {
-			pr_debug("prologue: arg %d: offset %ld\n",
-				 i, ref->offset);
-
-			if (ref->user_access)
-				probeid = BPF_FUNC_probe_read_user;
-
-			err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
-					   ref->offset, probeid);
-			if (err) {
-				pr_err("prologue: failed to generate probe_read function call\n");
-				goto errout;
-			}
-
-			ref = ref->next;
-			/*
-			 * Load previous result into ARG3. Use
-			 * BPF_REG_FP instead of r7 because verifier
-			 * allows FP based addressing only.
-			 */
-			if (ref)
-				ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3,
-						BPF_REG_FP, stack_offset), pos);
-		}
-	}
-
-	/* Final pass: read to registers */
-	for (i = 0; i < nargs; i++) {
-		int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW;
-
-		pr_debug("prologue: load arg %d, insn_sz is %s\n",
-			 i, insn_sz_to_str(insn_sz));
-		ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
-				BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
-	}
-
-	ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
-
-	return check_pos(pos);
-errout:
-	return err;
-}
-
-static int
-prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code,
-		  struct bpf_insn *success_code, struct bpf_insn *user_code)
-{
-	struct bpf_insn *insn;
-
-	if (check_pos(pos))
-		return -BPF_LOADER_ERRNO__PROLOGUE2BIG;
-
-	for (insn = pos->begin; insn < pos->pos; insn++) {
-		struct bpf_insn *target;
-		u8 class = BPF_CLASS(insn->code);
-		u8 opcode;
-
-		if (class != BPF_JMP)
-			continue;
-		opcode = BPF_OP(insn->code);
-		if (opcode == BPF_CALL)
-			continue;
-
-		switch (insn->off) {
-		case JMP_TO_ERROR_CODE:
-			target = error_code;
-			break;
-		case JMP_TO_SUCCESS_CODE:
-			target = success_code;
-			break;
-		case JMP_TO_USER_CODE:
-			target = user_code;
-			break;
-		default:
-			pr_err("bpf prologue: internal error: relocation failed\n");
-			return -BPF_LOADER_ERRNO__PROLOGUE;
-		}
-
-		insn->off = target - (insn + 1);
-	}
-	return 0;
-}
-
-int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
-		      struct bpf_insn *new_prog, size_t *new_cnt,
-		      size_t cnt_space)
-{
-	struct bpf_insn *success_code = NULL;
-	struct bpf_insn *error_code = NULL;
-	struct bpf_insn *user_code = NULL;
-	struct bpf_insn_pos pos;
-	bool fastpath = true;
-	int err = 0, i;
-
-	if (!new_prog || !new_cnt)
-		return -EINVAL;
-
-	if (cnt_space > BPF_MAXINSNS)
-		cnt_space = BPF_MAXINSNS;
-
-	pos.begin = new_prog;
-	pos.end = new_prog + cnt_space;
-	pos.pos = new_prog;
-
-	if (!nargs) {
-		ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0),
-		    &pos);
-
-		if (check_pos(&pos))
-			goto errout;
-
-		*new_cnt = pos_get_cnt(&pos);
-		return 0;
-	}
-
-	if (nargs > BPF_PROLOGUE_MAX_ARGS) {
-		pr_warning("bpf: prologue: %d arguments are dropped\n",
-			   nargs - BPF_PROLOGUE_MAX_ARGS);
-		nargs = BPF_PROLOGUE_MAX_ARGS;
-	}
-
-	/* First pass: validation */
-	for (i = 0; i < nargs; i++) {
-		struct probe_trace_arg_ref *ref = args[i].ref;
-
-		if (args[i].value[0] == '@') {
-			/* TODO: fetch global variable */
-			pr_err("bpf: prologue: global %s%+ld not support\n",
-				args[i].value, ref ? ref->offset : 0);
-			return -ENOTSUP;
-		}
-
-		while (ref) {
-			/* fastpath is true if all args has ref == NULL */
-			fastpath = false;
-
-			/*
-			 * Instruction encodes immediate value using
-			 * s32, ref->offset is long. On systems which
-			 * can't fill long in s32, refuse to process if
-			 * ref->offset too large (or small).
-			 */
-#ifdef __LP64__
-#define OFFSET_MAX	((1LL << 31) - 1)
-#define OFFSET_MIN	((1LL << 31) * -1)
-			if (ref->offset > OFFSET_MAX ||
-					ref->offset < OFFSET_MIN) {
-				pr_err("bpf: prologue: offset out of bound: %ld\n",
-				       ref->offset);
-				return -BPF_LOADER_ERRNO__PROLOGUEOOB;
-			}
-#endif
-			ref = ref->next;
-		}
-	}
-	pr_debug("prologue: pass validation\n");
-
-	if (fastpath) {
-		/* If all variables are registers... */
-		pr_debug("prologue: fast path\n");
-		err = gen_prologue_fastpath(&pos, args, nargs);
-		if (err)
-			goto errout;
-	} else {
-		pr_debug("prologue: slow path\n");
-
-		/* Initialization: move ctx to a callee saved register. */
-		ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos);
-
-		err = gen_prologue_slowpath(&pos, args, nargs);
-		if (err)
-			goto errout;
-		/*
-		 * start of ERROR_CODE (only slow pass needs error code)
-		 *   mov r2 <- 1  // r2 is error number
-		 *   mov r3 <- 0  // r3, r4... should be touched or
-		 *                // verifier would complain
-		 *   mov r4 <- 0
-		 *   ...
-		 *   goto usercode
-		 */
-		error_code = pos.pos;
-		ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1),
-		    &pos);
-
-		for (i = 0; i < nargs; i++)
-			ins(BPF_ALU64_IMM(BPF_MOV,
-					  BPF_PROLOGUE_START_ARG_REG + i,
-					  0),
-			    &pos);
-		ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE),
-				&pos);
-	}
-
-	/*
-	 * start of SUCCESS_CODE:
-	 *   mov r2 <- 0
-	 *   goto usercode  // skip
-	 */
-	success_code = pos.pos;
-	ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos);
-
-	/*
-	 * start of USER_CODE:
-	 *   Restore ctx to r1
-	 */
-	user_code = pos.pos;
-	if (!fastpath) {
-		/*
-		 * Only slow path needs restoring of ctx. In fast path,
-		 * register are loaded directly from r1.
-		 */
-		ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos);
-		err = prologue_relocate(&pos, error_code, success_code,
-					user_code);
-		if (err)
-			goto errout;
-	}
-
-	err = check_pos(&pos);
-	if (err)
-		goto errout;
-
-	*new_cnt = pos_get_cnt(&pos);
-	return 0;
-errout:
-	return err;
-}
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 6732cbbcf9b3..7a8af60e0f51 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -104,7 +104,7 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id)
 	struct bpf_prog_profiler_bpf *skel;
 	struct bpf_counter *counter;
 	struct bpf_program *prog;
-	char *prog_name;
+	char *prog_name = NULL;
 	int prog_fd;
 	int err;
 
@@ -155,10 +155,12 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id)
 	assert(skel != NULL);
 	counter->skel = skel;
 	list_add(&counter->list, &evsel->bpf_counter_list);
+	free(prog_name);
 	close(prog_fd);
 	return 0;
 err_out:
 	bpf_prog_profiler_bpf__destroy(skel);
+	free(prog_name);
 	free(counter);
 	close(prog_fd);
 	return -1;
@@ -180,6 +182,7 @@ static int bpf_program_profiler__load(struct evsel *evsel, struct target *target
 		    (*p != '\0' && *p != ',')) {
 			pr_err("Failed to parse bpf prog ids %s\n",
 			       target->bpf_str);
+			free(bpf_str_);
 			return -1;
 		}
 
@@ -452,7 +455,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 		return -1;
 
 	if (!all_cpu_map) {
-		all_cpu_map = perf_cpu_map__new(NULL);
+		all_cpu_map = perf_cpu_map__new_online_cpus();
 		if (!all_cpu_map)
 			return -1;
 	}
diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c
new file mode 100644
index 000000000000..035e02272790
--- /dev/null
+++ b/tools/perf/util/bpf_kwork_top.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * bpf_kwork_top.c
+ *
+ * Copyright (c) 2022  Huawei Inc,  Yang Jihong <yangjihong1@huawei.com>
+ */
+
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <linux/time64.h>
+
+#include "util/debug.h"
+#include "util/evsel.h"
+#include "util/kwork.h"
+
+#include <bpf/bpf.h>
+#include <perf/cpumap.h>
+
+#include "util/bpf_skel/kwork_top.skel.h"
+
+/*
+ * This should be in sync with "util/kwork_top.bpf.c"
+ */
+#define MAX_COMMAND_LEN 16
+
+struct time_data {
+	__u64 timestamp;
+};
+
+struct work_data {
+	__u64 runtime;
+};
+
+struct task_data {
+	__u32 tgid;
+	__u32 is_kthread;
+	char comm[MAX_COMMAND_LEN];
+};
+
+struct work_key {
+	__u32 type;
+	__u32 pid;
+	__u64 task_p;
+};
+
+struct task_key {
+	__u32 pid;
+	__u32 cpu;
+};
+
+struct kwork_class_bpf {
+	struct kwork_class *class;
+	void (*load_prepare)(void);
+};
+
+static struct kwork_top_bpf *skel;
+
+void perf_kwork__top_start(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	skel->bss->from_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec;
+	skel->bss->enabled = 1;
+	pr_debug("perf kwork top start at: %lld\n", skel->bss->from_timestamp);
+}
+
+void perf_kwork__top_finish(void)
+{
+	struct timespec ts;
+
+	skel->bss->enabled = 0;
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	skel->bss->to_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec;
+	pr_debug("perf kwork top finish at: %lld\n", skel->bss->to_timestamp);
+}
+
+static void irq_load_prepare(void)
+{
+	bpf_program__set_autoload(skel->progs.on_irq_handler_entry, true);
+	bpf_program__set_autoload(skel->progs.on_irq_handler_exit, true);
+}
+
+static struct kwork_class_bpf kwork_irq_bpf = {
+	.load_prepare = irq_load_prepare,
+};
+
+static void softirq_load_prepare(void)
+{
+	bpf_program__set_autoload(skel->progs.on_softirq_entry, true);
+	bpf_program__set_autoload(skel->progs.on_softirq_exit, true);
+}
+
+static struct kwork_class_bpf kwork_softirq_bpf = {
+	.load_prepare = softirq_load_prepare,
+};
+
+static void sched_load_prepare(void)
+{
+	bpf_program__set_autoload(skel->progs.on_switch, true);
+}
+
+static struct kwork_class_bpf kwork_sched_bpf = {
+	.load_prepare = sched_load_prepare,
+};
+
+static struct kwork_class_bpf *
+kwork_class_bpf_supported_list[KWORK_CLASS_MAX] = {
+	[KWORK_CLASS_IRQ]	= &kwork_irq_bpf,
+	[KWORK_CLASS_SOFTIRQ]	= &kwork_softirq_bpf,
+	[KWORK_CLASS_SCHED]	= &kwork_sched_bpf,
+};
+
+static bool valid_kwork_class_type(enum kwork_class_type type)
+{
+	return type >= 0 && type < KWORK_CLASS_MAX;
+}
+
+static int setup_filters(struct perf_kwork *kwork)
+{
+	u8 val = 1;
+	int i, nr_cpus, fd;
+	struct perf_cpu_map *map;
+
+	if (kwork->cpu_list) {
+		fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter);
+		if (fd < 0) {
+			pr_debug("Invalid cpu filter fd\n");
+			return -1;
+		}
+
+		map = perf_cpu_map__new(kwork->cpu_list);
+		if (!map) {
+			pr_debug("Invalid cpu_list\n");
+			return -1;
+		}
+
+		nr_cpus = libbpf_num_possible_cpus();
+		for (i = 0; i < perf_cpu_map__nr(map); i++) {
+			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+
+			if (cpu.cpu >= nr_cpus) {
+				perf_cpu_map__put(map);
+				pr_err("Requested cpu %d too large\n", cpu.cpu);
+				return -1;
+			}
+			bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);
+		}
+		perf_cpu_map__put(map);
+
+		skel->bss->has_cpu_filter = 1;
+	}
+
+	return 0;
+}
+
+int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	struct bpf_program *prog;
+	struct kwork_class *class;
+	struct kwork_class_bpf *class_bpf;
+	enum kwork_class_type type;
+
+	skel = kwork_top_bpf__open();
+	if (!skel) {
+		pr_debug("Failed to open kwork top skeleton\n");
+		return -1;
+	}
+
+	/*
+	 * set all progs to non-autoload,
+	 * then set corresponding progs according to config
+	 */
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	list_for_each_entry(class, &kwork->class_list, list) {
+		type = class->type;
+		if (!valid_kwork_class_type(type) ||
+		    !kwork_class_bpf_supported_list[type]) {
+			pr_err("Unsupported bpf trace class %s\n", class->name);
+			goto out;
+		}
+
+		class_bpf = kwork_class_bpf_supported_list[type];
+		class_bpf->class = class;
+
+		if (class_bpf->load_prepare)
+			class_bpf->load_prepare();
+	}
+
+	if (kwork_top_bpf__load(skel)) {
+		pr_debug("Failed to load kwork top skeleton\n");
+		goto out;
+	}
+
+	if (setup_filters(kwork))
+		goto out;
+
+	if (kwork_top_bpf__attach(skel)) {
+		pr_debug("Failed to attach kwork top skeleton\n");
+		goto out;
+	}
+
+	return 0;
+
+out:
+	kwork_top_bpf__destroy(skel);
+	return -1;
+}
+
+static void read_task_info(struct kwork_work *work)
+{
+	int fd;
+	struct task_data data;
+	struct task_key key = {
+		.pid = work->id,
+		.cpu = work->cpu,
+	};
+
+	fd = bpf_map__fd(skel->maps.kwork_top_tasks);
+	if (fd < 0) {
+		pr_debug("Invalid top tasks map fd\n");
+		return;
+	}
+
+	if (!bpf_map_lookup_elem(fd, &key, &data)) {
+		work->tgid = data.tgid;
+		work->is_kthread = data.is_kthread;
+		work->name = strdup(data.comm);
+	}
+}
+static int add_work(struct perf_kwork *kwork, struct work_key *key,
+		    struct work_data *data, int cpu)
+{
+	struct kwork_class_bpf *bpf_trace;
+	struct kwork_work *work;
+	struct kwork_work tmp = {
+		.id = key->pid,
+		.cpu = cpu,
+		.name = NULL,
+	};
+	enum kwork_class_type type = key->type;
+
+	if (!valid_kwork_class_type(type)) {
+		pr_debug("Invalid class type %d to add work\n", type);
+		return -1;
+	}
+
+	bpf_trace = kwork_class_bpf_supported_list[type];
+	tmp.class = bpf_trace->class;
+
+	work = perf_kwork_add_work(kwork, tmp.class, &tmp);
+	if (!work)
+		return -1;
+
+	work->total_runtime = data->runtime;
+	read_task_info(work);
+
+	return 0;
+}
+
+int perf_kwork__top_read_bpf(struct perf_kwork *kwork)
+{
+	int i, fd, nr_cpus;
+	struct work_data *data;
+	struct work_key key, prev;
+
+	fd = bpf_map__fd(skel->maps.kwork_top_works);
+	if (fd < 0) {
+		pr_debug("Invalid top runtime fd\n");
+		return -1;
+	}
+
+	nr_cpus = libbpf_num_possible_cpus();
+	data = calloc(nr_cpus, sizeof(struct work_data));
+	if (!data)
+		return -1;
+
+	memset(&prev, 0, sizeof(prev));
+	while (!bpf_map_get_next_key(fd, &prev, &key)) {
+		if ((bpf_map_lookup_elem(fd, &key, data)) != 0) {
+			pr_debug("Failed to lookup top elem\n");
+			return -1;
+		}
+
+		for (i = 0; i < nr_cpus; i++) {
+			if (data[i].runtime == 0)
+				continue;
+
+			if (add_work(kwork, &key, &data[i], i))
+				return -1;
+		}
+		prev = key;
+	}
+	free(data);
+
+	return 0;
+}
+
+void perf_kwork__top_cleanup_bpf(void)
+{
+	kwork_top_bpf__destroy(skel);
+}
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index e7dddf0127bc..b4cb3fe5cc25 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "util/cgroup.h"
 #include "util/debug.h"
 #include "util/evlist.h"
 #include "util/machine.h"
@@ -11,6 +12,7 @@
 #include <linux/zalloc.h>
 #include <linux/string.h>
 #include <bpf/bpf.h>
+#include <inttypes.h>
 
 #include "bpf_skel/lock_contention.skel.h"
 #include "bpf_skel/lock_data.h"
@@ -20,7 +22,7 @@ static struct lock_contention_bpf *skel;
 int lock_contention_prepare(struct lock_contention *con)
 {
 	int i, fd;
-	int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1;
+	int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1;
 	struct evlist *evlist = con->evlist;
 	struct target *target = con->target;
 
@@ -50,6 +52,8 @@ int lock_contention_prepare(struct lock_contention *con)
 		ntasks = perf_thread_map__nr(evlist->core.threads);
 	if (con->filters->nr_types)
 		ntypes = con->filters->nr_types;
+	if (con->filters->nr_cgrps)
+		ncgrps = con->filters->nr_cgrps;
 
 	/* resolve lock name filters to addr */
 	if (con->filters->nr_syms) {
@@ -84,6 +88,7 @@ int lock_contention_prepare(struct lock_contention *con)
 	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
 	bpf_map__set_max_entries(skel->maps.type_filter, ntypes);
 	bpf_map__set_max_entries(skel->maps.addr_filter, naddrs);
+	bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
 
 	if (lock_contention_bpf__load(skel) < 0) {
 		pr_err("Failed to load lock-contention BPF skeleton\n");
@@ -145,18 +150,152 @@ int lock_contention_prepare(struct lock_contention *con)
 			bpf_map_update_elem(fd, &con->filters->addrs[i], &val, BPF_ANY);
 	}
 
+	if (con->filters->nr_cgrps) {
+		u8 val = 1;
+
+		skel->bss->has_cgroup = 1;
+		fd = bpf_map__fd(skel->maps.cgroup_filter);
+
+		for (i = 0; i < con->filters->nr_cgrps; i++)
+			bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY);
+	}
+
 	/* these don't work well if in the rodata section */
 	skel->bss->stack_skip = con->stack_skip;
 	skel->bss->aggr_mode = con->aggr_mode;
 	skel->bss->needs_callstack = con->save_callstack;
 	skel->bss->lock_owner = con->owner;
 
+	if (con->aggr_mode == LOCK_AGGR_CGROUP) {
+		if (cgroup_is_v2("perf_event"))
+			skel->bss->use_cgroup_v2 = 1;
+
+		read_all_cgroups(&con->cgroups);
+	}
+
 	bpf_program__set_autoload(skel->progs.collect_lock_syms, false);
 
 	lock_contention_bpf__attach(skel);
 	return 0;
 }
 
+/*
+ * Run the BPF program directly using BPF_PROG_TEST_RUN to update the end
+ * timestamp in ktime so that it can calculate delta easily.
+ */
+static void mark_end_timestamp(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.flags = BPF_F_TEST_RUN_ON_CPU,
+	);
+	int prog_fd = bpf_program__fd(skel->progs.end_timestamp);
+
+	bpf_prog_test_run_opts(prog_fd, &opts);
+}
+
+static void update_lock_stat(int map_fd, int pid, u64 end_ts,
+			     enum lock_aggr_mode aggr_mode,
+			     struct tstamp_data *ts_data)
+{
+	u64 delta;
+	struct contention_key stat_key = {};
+	struct contention_data stat_data;
+
+	if (ts_data->timestamp >= end_ts)
+		return;
+
+	delta = end_ts - ts_data->timestamp;
+
+	switch (aggr_mode) {
+	case LOCK_AGGR_CALLER:
+		stat_key.stack_id = ts_data->stack_id;
+		break;
+	case LOCK_AGGR_TASK:
+		stat_key.pid = pid;
+		break;
+	case LOCK_AGGR_ADDR:
+		stat_key.lock_addr_or_cgroup = ts_data->lock;
+		break;
+	case LOCK_AGGR_CGROUP:
+		/* TODO */
+		return;
+	default:
+		return;
+	}
+
+	if (bpf_map_lookup_elem(map_fd, &stat_key, &stat_data) < 0)
+		return;
+
+	stat_data.total_time += delta;
+	stat_data.count++;
+
+	if (delta > stat_data.max_time)
+		stat_data.max_time = delta;
+	if (delta < stat_data.min_time)
+		stat_data.min_time = delta;
+
+	bpf_map_update_elem(map_fd, &stat_key, &stat_data, BPF_EXIST);
+}
+
+/*
+ * Account entries in the tstamp map (which didn't see the corresponding
+ * lock:contention_end tracepoint) using end_ts.
+ */
+static void account_end_timestamp(struct lock_contention *con)
+{
+	int ts_fd, stat_fd;
+	int *prev_key, key;
+	u64 end_ts = skel->bss->end_ts;
+	int total_cpus;
+	enum lock_aggr_mode aggr_mode = con->aggr_mode;
+	struct tstamp_data ts_data, *cpu_data;
+
+	/* Iterate per-task tstamp map (key = TID) */
+	ts_fd = bpf_map__fd(skel->maps.tstamp);
+	stat_fd = bpf_map__fd(skel->maps.lock_stat);
+
+	prev_key = NULL;
+	while (!bpf_map_get_next_key(ts_fd, prev_key, &key)) {
+		if (bpf_map_lookup_elem(ts_fd, &key, &ts_data) == 0) {
+			int pid = key;
+
+			if (aggr_mode == LOCK_AGGR_TASK && con->owner)
+				pid = ts_data.flags;
+
+			update_lock_stat(stat_fd, pid, end_ts, aggr_mode,
+					 &ts_data);
+		}
+
+		prev_key = &key;
+	}
+
+	/* Now it'll check per-cpu tstamp map which doesn't have TID. */
+	if (aggr_mode == LOCK_AGGR_TASK || aggr_mode == LOCK_AGGR_CGROUP)
+		return;
+
+	total_cpus = cpu__max_cpu().cpu;
+	ts_fd = bpf_map__fd(skel->maps.tstamp_cpu);
+
+	cpu_data = calloc(total_cpus, sizeof(*cpu_data));
+	if (cpu_data == NULL)
+		return;
+
+	prev_key = NULL;
+	while (!bpf_map_get_next_key(ts_fd, prev_key, &key)) {
+		if (bpf_map_lookup_elem(ts_fd, &key, cpu_data) < 0)
+			goto next;
+
+		for (int i = 0; i < total_cpus; i++) {
+			update_lock_stat(stat_fd, -1, end_ts, aggr_mode,
+					 &cpu_data[i]);
+		}
+
+next:
+		prev_key = &key;
+	}
+	free(cpu_data);
+}
+
 int lock_contention_start(void)
 {
 	skel->bss->enabled = 1;
@@ -166,6 +305,7 @@ int lock_contention_start(void)
 int lock_contention_stop(void)
 {
 	skel->bss->enabled = 0;
+	mark_end_timestamp();
 	return 0;
 }
 
@@ -188,7 +328,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 
 		/* do not update idle comm which contains CPU number */
 		if (pid) {
-			struct thread *t = __machine__findnew_thread(machine, /*pid=*/-1, pid);
+			struct thread *t = machine__findnew_thread(machine, /*pid=*/-1, pid);
 
 			if (t == NULL)
 				return name;
@@ -209,12 +349,12 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 			return "siglock";
 
 		/* global locks with symbols */
-		sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap);
+		sym = machine__find_kernel_symbol(machine, key->lock_addr_or_cgroup, &kmap);
 		if (sym)
 			return sym->name;
 
 		/* try semi-global locks collected separately */
-		if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr, &flags)) {
+		if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr_or_cgroup, &flags)) {
 			if (flags == LOCK_CLASS_RQLOCK)
 				return "rq_lock";
 		}
@@ -222,6 +362,17 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 		return "";
 	}
 
+	if (con->aggr_mode == LOCK_AGGR_CGROUP) {
+		u64 cgrp_id = key->lock_addr_or_cgroup;
+		struct cgroup *cgrp = __cgroup__find(&con->cgroups, cgrp_id);
+
+		if (cgrp)
+			return cgrp->name;
+
+		snprintf(name_buf, sizeof(name_buf), "cgroup:%" PRIu64 "", cgrp_id);
+		return name_buf;
+	}
+
 	/* LOCK_AGGR_CALLER: skip lock internal functions */
 	while (machine__is_lock_function(machine, stack_trace[idx]) &&
 	       idx < con->max_stack - 1)
@@ -268,8 +419,10 @@ int lock_contention_read(struct lock_contention *con)
 	if (stack_trace == NULL)
 		return -1;
 
+	account_end_timestamp(con);
+
 	if (con->aggr_mode == LOCK_AGGR_TASK) {
-		struct thread *idle = __machine__findnew_thread(machine,
+		struct thread *idle = machine__findnew_thread(machine,
 								/*pid=*/0,
 								/*tid=*/0);
 		thread__set_comm(idle, "swapper", /*timestamp=*/0);
@@ -285,7 +438,7 @@ int lock_contention_read(struct lock_contention *con)
 	}
 
 	/* make sure it loads the kernel map */
-	map__load(maps__first(machine->kmaps)->map);
+	maps__load_first(machine->kmaps);
 
 	prev_key = NULL;
 	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
@@ -313,7 +466,8 @@ int lock_contention_read(struct lock_contention *con)
 			ls_key = key.pid;
 			break;
 		case LOCK_AGGR_ADDR:
-			ls_key = key.lock_addr;
+		case LOCK_AGGR_CGROUP:
+			ls_key = key.lock_addr_or_cgroup;
 			break;
 		default:
 			goto next;
@@ -364,12 +518,20 @@ next:
 	return err;
 }
 
-int lock_contention_finish(void)
+int lock_contention_finish(struct lock_contention *con)
 {
 	if (skel) {
 		skel->bss->enabled = 0;
 		lock_contention_bpf__destroy(skel);
 	}
 
+	while (!RB_EMPTY_ROOT(&con->cgroups)) {
+		struct rb_node *node = rb_first(&con->cgroups);
+		struct cgroup *cgrp = rb_entry(node, struct cgroup, node);
+
+		rb_erase(node, &con->cgroups);
+		cgroup__put(cgrp);
+	}
+
 	return 0;
 }
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index 01f70b8e705a..6af36142dc5a 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -98,28 +98,31 @@ static void off_cpu_finish(void *arg __maybe_unused)
 /* v5.18 kernel added prev_state arg, so it needs to check the signature */
 static void check_sched_switch_args(void)
 {
-	const struct btf *btf = bpf_object__btf(skel->obj);
+	struct btf *btf = btf__load_vmlinux_btf();
 	const struct btf_type *t1, *t2, *t3;
 	u32 type_id;
 
 	type_id = btf__find_by_name_kind(btf, "btf_trace_sched_switch",
 					 BTF_KIND_TYPEDEF);
 	if ((s32)type_id < 0)
-		return;
+		goto cleanup;
 
 	t1 = btf__type_by_id(btf, type_id);
 	if (t1 == NULL)
-		return;
+		goto cleanup;
 
 	t2 = btf__type_by_id(btf, t1->type);
 	if (t2 == NULL || !btf_is_ptr(t2))
-		return;
+		goto cleanup;
 
 	t3 = btf__type_by_id(btf, t2->type);
-	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 4) {
+	/* btf_trace func proto has one more argument for the context */
+	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 5) {
 		/* new format: pass prev_state as 4th arg */
 		skel->rodata->has_prev_state = true;
 	}
+cleanup:
+	btf__free(btf);
 }
 
 int off_cpu_prepare(struct evlist *evlist, struct target *target,
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
new file mode 100644
index 000000000000..2872f9bc0785
--- /dev/null
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
+ *
+ * This exactly matches what is marshalled into the raw_syscall:sys_enter
+ * payload expected by the 'perf trace' beautifiers.
+ */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <linux/limits.h>
+
+/**
+ * is_power_of_2() - check if a value is a power of two
+ * @n: the value to check
+ *
+ * Determine whether some value is a power of two, where zero is *not*
+ * considered a power of two.  Return: true if @n is a power of 2, otherwise
+ * false.
+ */
+#define is_power_of_2(n) (n != 0 && ((n & (n - 1)) == 0))
+
+#define MAX_CPUS  4096
+
+/* bpf-output associated map */
+struct __augmented_syscalls__ {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__type(key, int);
+	__type(value, __u32);
+	__uint(max_entries, MAX_CPUS);
+} __augmented_syscalls__ SEC(".maps");
+
+/*
+ * What to augment at entry?
+ *
+ * Pointer arg payloads (filenames, etc) passed from userspace to the kernel
+ */
+struct syscalls_sys_enter {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 512);
+} syscalls_sys_enter SEC(".maps");
+
+/*
+ * What to augment at exit?
+ *
+ * Pointer arg payloads returned from the kernel (struct stat, etc) to userspace.
+ */
+struct syscalls_sys_exit {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 512);
+} syscalls_sys_exit SEC(".maps");
+
+struct syscall_enter_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	unsigned long	   args[6];
+};
+
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_arg {
+	unsigned int	size;
+	int		err;
+	char		value[PATH_MAX];
+};
+
+struct pids_filtered {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, pid_t);
+	__type(value, bool);
+	__uint(max_entries, 64);
+} pids_filtered SEC(".maps");
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define SS_MAXSIZE   128     /* Implementation specific max size */
+
+typedef unsigned short sa_family_t;
+
+/*
+ * FIXME: Should come from system headers
+ *
+ * The definition uses anonymous union and struct in order to control the
+ * default alignment.
+ */
+struct sockaddr_storage {
+	union {
+		struct {
+			sa_family_t    ss_family; /* address family */
+			/* Following field(s) are implementation specific */
+			char __data[SS_MAXSIZE - sizeof(unsigned short)];
+				/* space to achieve desired size, */
+				/* _SS_MAXSIZE value minus size of ss_family */
+		};
+		void *__align; /* implementation specific desired alignment */
+	};
+};
+
+struct augmented_args_payload {
+       struct syscall_enter_args args;
+       union {
+		struct {
+			struct augmented_arg arg, arg2;
+		};
+		struct sockaddr_storage saddr;
+		char   __data[sizeof(struct augmented_arg)];
+	};
+};
+
+// We need more tmp space than the BPF stack can give us
+struct augmented_args_tmp {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, int);
+	__type(value, struct augmented_args_payload);
+	__uint(max_entries, 1);
+} augmented_args_tmp SEC(".maps");
+
+static inline struct augmented_args_payload *augmented_args_payload(void)
+{
+	int key = 0;
+	return bpf_map_lookup_elem(&augmented_args_tmp, &key);
+}
+
+static inline int augmented__output(void *ctx, struct augmented_args_payload *args, int len)
+{
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
+	return bpf_perf_event_output(ctx, &__augmented_syscalls__, BPF_F_CURRENT_CPU, args, len);
+}
+
+static inline
+unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len)
+{
+	unsigned int augmented_len = sizeof(*augmented_arg);
+	int string_len = bpf_probe_read_user_str(&augmented_arg->value, arg_len, arg);
+
+	augmented_arg->size = augmented_arg->err = 0;
+	/*
+	 * probe_read_str may return < 0, e.g. -EFAULT
+	 * So we leave that in the augmented_arg->size that userspace will
+	 */
+	if (string_len > 0) {
+		augmented_len -= sizeof(augmented_arg->value) - string_len;
+		_Static_assert(is_power_of_2(sizeof(augmented_arg->value)), "sizeof(augmented_arg->value) needs to be a power of two");
+		augmented_len &= sizeof(augmented_arg->value) - 1;
+		augmented_arg->size = string_len;
+	} else {
+		/*
+		 * So that username notice the error while still being able
+		 * to skip this augmented arg record
+		 */
+		augmented_arg->err = string_len;
+		augmented_len = offsetof(struct augmented_arg, value);
+	}
+
+	return augmented_len;
+}
+
+SEC("tp/raw_syscalls/sys_enter")
+int syscall_unaugmented(struct syscall_enter_args *args)
+{
+	return 1;
+}
+
+/*
+ * These will be tail_called from SEC("raw_syscalls:sys_enter"), so will find in
+ * augmented_args_tmp what was read by that raw_syscalls:sys_enter and go
+ * on from there, reading the first syscall arg as a string, i.e. open's
+ * filename.
+ */
+SEC("tp/syscalls/sys_enter_connect")
+int sys_enter_connect(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *sockaddr_arg = (const void *)args->args[1];
+	unsigned int socklen = args->args[2];
+	unsigned int len = sizeof(augmented_args->args);
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	_Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two");
+	socklen &= sizeof(augmented_args->saddr) - 1;
+
+	bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
+
+	return augmented__output(args, augmented_args, len + socklen);
+}
+
+SEC("tp/syscalls/sys_enter_sendto")
+int sys_enter_sendto(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *sockaddr_arg = (const void *)args->args[4];
+	unsigned int socklen = args->args[5];
+	unsigned int len = sizeof(augmented_args->args);
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	socklen &= sizeof(augmented_args->saddr) - 1;
+
+	bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg);
+
+	return augmented__output(args, augmented_args, len + socklen);
+}
+
+SEC("tp/syscalls/sys_enter_open")
+int sys_enter_open(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *filename_arg = (const void *)args->args[0];
+	unsigned int len = sizeof(augmented_args->args);
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
+
+	return augmented__output(args, augmented_args, len);
+}
+
+SEC("tp/syscalls/sys_enter_openat")
+int sys_enter_openat(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *filename_arg = (const void *)args->args[1];
+	unsigned int len = sizeof(augmented_args->args);
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	len += augmented_arg__read_str(&augmented_args->arg, filename_arg, sizeof(augmented_args->arg.value));
+
+	return augmented__output(args, augmented_args, len);
+}
+
+SEC("tp/syscalls/sys_enter_rename")
+int sys_enter_rename(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *oldpath_arg = (const void *)args->args[0],
+		   *newpath_arg = (const void *)args->args[1];
+	unsigned int len = sizeof(augmented_args->args), oldpath_len;
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
+	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
+
+	return augmented__output(args, augmented_args, len);
+}
+
+SEC("tp/syscalls/sys_enter_renameat")
+int sys_enter_renameat(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *oldpath_arg = (const void *)args->args[1],
+		   *newpath_arg = (const void *)args->args[3];
+	unsigned int len = sizeof(augmented_args->args), oldpath_len;
+
+        if (augmented_args == NULL)
+                return 1; /* Failure: don't filter */
+
+	oldpath_len = augmented_arg__read_str(&augmented_args->arg, oldpath_arg, sizeof(augmented_args->arg.value));
+	len += oldpath_len + augmented_arg__read_str((void *)(&augmented_args->arg) + oldpath_len, newpath_arg, sizeof(augmented_args->arg.value));
+
+	return augmented__output(args, augmented_args, len);
+}
+
+#define PERF_ATTR_SIZE_VER0     64      /* sizeof first published struct */
+
+// we need just the start, get the size to then copy it
+struct perf_event_attr_size {
+        __u32                   type;
+        /*
+         * Size of the attr structure, for fwd/bwd compat.
+         */
+        __u32                   size;
+};
+
+SEC("tp/syscalls/sys_enter_perf_event_open")
+int sys_enter_perf_event_open(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const struct perf_event_attr_size *attr = (const struct perf_event_attr_size *)args->args[0], *attr_read;
+	unsigned int len = sizeof(augmented_args->args);
+
+        if (augmented_args == NULL)
+		goto failure;
+
+	if (bpf_probe_read_user(&augmented_args->__data, sizeof(*attr), attr) < 0)
+		goto failure;
+
+	attr_read = (const struct perf_event_attr_size *)augmented_args->__data;
+
+	__u32 size = attr_read->size;
+
+	if (!size)
+		size = PERF_ATTR_SIZE_VER0;
+
+	if (size > sizeof(augmented_args->__data))
+                goto failure;
+
+	// Now that we read attr->size and tested it against the size limits, read it completely
+	if (bpf_probe_read_user(&augmented_args->__data, size, attr) < 0)
+		goto failure;
+
+	return augmented__output(args, augmented_args, len + size);
+failure:
+	return 1; /* Failure: don't filter */
+}
+
+SEC("tp/syscalls/sys_enter_clock_nanosleep")
+int sys_enter_clock_nanosleep(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *rqtp_arg = (const void *)args->args[2];
+	unsigned int len = sizeof(augmented_args->args);
+	__u32 size = sizeof(struct timespec64);
+
+        if (augmented_args == NULL)
+		goto failure;
+
+	if (size > sizeof(augmented_args->__data))
+                goto failure;
+
+	bpf_probe_read_user(&augmented_args->__data, size, rqtp_arg);
+
+	return augmented__output(args, augmented_args, len + size);
+failure:
+	return 1; /* Failure: don't filter */
+}
+
+static pid_t getpid(void)
+{
+	return bpf_get_current_pid_tgid();
+}
+
+static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
+{
+	return bpf_map_lookup_elem(pids, &pid) != NULL;
+}
+
+SEC("tp/raw_syscalls/sys_enter")
+int sys_enter(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args;
+	/*
+	 * We start len, the amount of data that will be in the perf ring
+	 * buffer, if this is not filtered out by one of pid_filter__has(),
+	 * syscall->enabled, etc, with the non-augmented raw syscall payload,
+	 * i.e. sizeof(augmented_args->args).
+	 *
+	 * We'll add to this as we add augmented syscalls right after that
+	 * initial, non-augmented raw_syscalls:sys_enter payload.
+	 */
+
+	if (pid_filter__has(&pids_filtered, getpid()))
+		return 0;
+
+	augmented_args = augmented_args_payload();
+	if (augmented_args == NULL)
+		return 1;
+
+	bpf_probe_read_kernel(&augmented_args->args, sizeof(augmented_args->args), args);
+
+	/*
+	 * Jump to syscall specific augmenter, even if the default one,
+	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
+	 * unaugmented tracepoint payload.
+	 */
+	bpf_tail_call(args, &syscalls_sys_enter, augmented_args->args.syscall_nr);
+
+	// If not found on the PROG_ARRAY syscalls map, then we're filtering it:
+	return 0;
+}
+
+SEC("tp/raw_syscalls/sys_exit")
+int sys_exit(struct syscall_exit_args *args)
+{
+	struct syscall_exit_args exit_args;
+
+	if (pid_filter__has(&pids_filtered, getpid()))
+		return 0;
+
+	bpf_probe_read_kernel(&exit_args, sizeof(exit_args), args);
+	/*
+	 * Jump to syscall specific return augmenter, even if the default one,
+	 * "!raw_syscalls:unaugmented" that will just return 1 to return the
+	 * unaugmented tracepoint payload.
+	 */
+	bpf_tail_call(args, &syscalls_sys_exit, exit_args.syscall_nr);
+	/*
+	 * If not found on the PROG_ARRAY syscalls map, then we're filtering it:
+	 */
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
new file mode 100644
index 000000000000..2c55896bb33c
--- /dev/null
+++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2023 Red Hat
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+unsigned int nr_uprobes;
+
+SEC("uprobe")
+int BPF_UPROBE(empty)
+{
+       return 0;
+}
+
+SEC("uprobe")
+int BPF_UPROBE(trace_printk)
+{
+	char fmt[] = "perf bench uprobe %u";
+
+	bpf_trace_printk(fmt, sizeof(fmt), ++nr_uprobes);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c
new file mode 100644
index 000000000000..84c15ccbab44
--- /dev/null
+++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2022, Huawei
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+/*
+ * This should be in sync with "util/kwork.h"
+ */
+enum kwork_class_type {
+	KWORK_CLASS_IRQ,
+	KWORK_CLASS_SOFTIRQ,
+	KWORK_CLASS_WORKQUEUE,
+	KWORK_CLASS_SCHED,
+	KWORK_CLASS_MAX,
+};
+
+#define MAX_ENTRIES     102400
+#define MAX_NR_CPUS     2048
+#define PF_KTHREAD      0x00200000
+#define MAX_COMMAND_LEN 16
+
+struct time_data {
+	__u64 timestamp;
+};
+
+struct work_data {
+	__u64 runtime;
+};
+
+struct task_data {
+	__u32 tgid;
+	__u32 is_kthread;
+	char comm[MAX_COMMAND_LEN];
+};
+
+struct work_key {
+	__u32 type;
+	__u32 pid;
+	__u64 task_p;
+};
+
+struct task_key {
+	__u32 pid;
+	__u32 cpu;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct time_data);
+} kwork_top_task_time SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(struct work_key));
+	__uint(value_size, sizeof(struct time_data));
+	__uint(max_entries, MAX_ENTRIES);
+} kwork_top_irq_time SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct task_key));
+	__uint(value_size, sizeof(struct task_data));
+	__uint(max_entries, MAX_ENTRIES);
+} kwork_top_tasks SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(struct work_key));
+	__uint(value_size, sizeof(struct work_data));
+	__uint(max_entries, MAX_ENTRIES);
+} kwork_top_works SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u8));
+	__uint(max_entries, MAX_NR_CPUS);
+} kwork_top_cpu_filter SEC(".maps");
+
+int enabled = 0;
+
+int has_cpu_filter = 0;
+
+__u64 from_timestamp = 0;
+__u64 to_timestamp = 0;
+
+static __always_inline int cpu_is_filtered(__u32 cpu)
+{
+	__u8 *cpu_val;
+
+	if (has_cpu_filter) {
+		cpu_val = bpf_map_lookup_elem(&kwork_top_cpu_filter, &cpu);
+		if (!cpu_val)
+			return 1;
+	}
+
+	return 0;
+}
+
+static __always_inline void update_task_info(struct task_struct *task, __u32 cpu)
+{
+	struct task_key key = {
+		.pid = task->pid,
+		.cpu = cpu,
+	};
+
+	if (!bpf_map_lookup_elem(&kwork_top_tasks, &key)) {
+		struct task_data data = {
+			.tgid = task->tgid,
+			.is_kthread = task->flags & PF_KTHREAD ? 1 : 0,
+		};
+		BPF_CORE_READ_STR_INTO(&data.comm, task, comm);
+
+		bpf_map_update_elem(&kwork_top_tasks, &key, &data, BPF_ANY);
+	}
+}
+
+static __always_inline void update_work(struct work_key *key, __u64 delta)
+{
+	struct work_data *data;
+
+	data = bpf_map_lookup_elem(&kwork_top_works, key);
+	if (data) {
+		data->runtime += delta;
+	} else {
+		struct work_data new_data = {
+			.runtime = delta,
+		};
+
+		bpf_map_update_elem(&kwork_top_works, key, &new_data, BPF_ANY);
+	}
+}
+
+static void on_sched_out(struct task_struct *task, __u64 ts, __u32 cpu)
+{
+	__u64 delta;
+	struct time_data *pelem;
+
+	pelem = bpf_task_storage_get(&kwork_top_task_time, task, NULL, 0);
+	if (pelem)
+		delta = ts - pelem->timestamp;
+	else
+		delta = ts - from_timestamp;
+
+	struct work_key key = {
+		.type = KWORK_CLASS_SCHED,
+		.pid = task->pid,
+		.task_p = (__u64)task,
+	};
+
+	update_work(&key, delta);
+	update_task_info(task, cpu);
+}
+
+static void on_sched_in(struct task_struct *task, __u64 ts)
+{
+	struct time_data *pelem;
+
+	pelem = bpf_task_storage_get(&kwork_top_task_time, task, NULL,
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (pelem)
+		pelem->timestamp = ts;
+}
+
+SEC("tp_btf/sched_switch")
+int on_switch(u64 *ctx)
+{
+	struct task_struct *prev, *next;
+
+	prev = (struct task_struct *)ctx[1];
+	next = (struct task_struct *)ctx[2];
+
+	if (!enabled)
+		return 0;
+
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu_is_filtered(cpu))
+		return 0;
+
+	__u64 ts = bpf_ktime_get_ns();
+
+	on_sched_out(prev, ts, cpu);
+	on_sched_in(next, ts);
+
+	return 0;
+}
+
+SEC("tp_btf/irq_handler_entry")
+int on_irq_handler_entry(u64 *cxt)
+{
+	struct task_struct *task;
+
+	if (!enabled)
+		return 0;
+
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu_is_filtered(cpu))
+		return 0;
+
+	__u64 ts = bpf_ktime_get_ns();
+
+	task = (struct task_struct *)bpf_get_current_task();
+	if (!task)
+		return 0;
+
+	struct work_key key = {
+		.type = KWORK_CLASS_IRQ,
+		.pid = BPF_CORE_READ(task, pid),
+		.task_p = (__u64)task,
+	};
+
+	struct time_data data = {
+		.timestamp = ts,
+	};
+
+	bpf_map_update_elem(&kwork_top_irq_time, &key, &data, BPF_ANY);
+
+	return 0;
+}
+
+SEC("tp_btf/irq_handler_exit")
+int on_irq_handler_exit(u64 *cxt)
+{
+	__u64 delta;
+	struct task_struct *task;
+	struct time_data *pelem;
+
+	if (!enabled)
+		return 0;
+
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu_is_filtered(cpu))
+		return 0;
+
+	__u64 ts = bpf_ktime_get_ns();
+
+	task = (struct task_struct *)bpf_get_current_task();
+	if (!task)
+		return 0;
+
+	struct work_key key = {
+		.type = KWORK_CLASS_IRQ,
+		.pid = BPF_CORE_READ(task, pid),
+		.task_p = (__u64)task,
+	};
+
+	pelem = bpf_map_lookup_elem(&kwork_top_irq_time, &key);
+	if (pelem && pelem->timestamp != 0)
+		delta = ts - pelem->timestamp;
+	else
+		delta = ts - from_timestamp;
+
+	update_work(&key, delta);
+
+	return 0;
+}
+
+SEC("tp_btf/softirq_entry")
+int on_softirq_entry(u64 *cxt)
+{
+	struct task_struct *task;
+
+	if (!enabled)
+		return 0;
+
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu_is_filtered(cpu))
+		return 0;
+
+	__u64 ts = bpf_ktime_get_ns();
+
+	task = (struct task_struct *)bpf_get_current_task();
+	if (!task)
+		return 0;
+
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.pid = BPF_CORE_READ(task, pid),
+		.task_p = (__u64)task,
+	};
+
+	struct time_data data = {
+		.timestamp = ts,
+	};
+
+	bpf_map_update_elem(&kwork_top_irq_time, &key, &data, BPF_ANY);
+
+	return 0;
+}
+
+SEC("tp_btf/softirq_exit")
+int on_softirq_exit(u64 *cxt)
+{
+	__u64 delta;
+	struct task_struct *task;
+	struct time_data *pelem;
+
+	if (!enabled)
+		return 0;
+
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu_is_filtered(cpu))
+		return 0;
+
+	__u64 ts = bpf_ktime_get_ns();
+
+	task = (struct task_struct *)bpf_get_current_task();
+	if (!task)
+		return 0;
+
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.pid = BPF_CORE_READ(task, pid),
+		.task_p = (__u64)task,
+	};
+
+	pelem = bpf_map_lookup_elem(&kwork_top_irq_time, &key);
+	if (pelem)
+		delta = ts - pelem->timestamp;
+	else
+		delta = ts - from_timestamp;
+
+	update_work(&key, delta);
+
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 8d3cfbb3cc65..d931a898c434 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -19,13 +19,6 @@
 #define LCB_F_PERCPU	(1U << 4)
 #define LCB_F_MUTEX	(1U << 5)
 
-struct tstamp_data {
-	__u64 timestamp;
-	__u64 lock;
-	__u32 flags;
-	__s32 stack_id;
-};
-
 /* callstack storage  */
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
@@ -42,6 +35,14 @@ struct {
 	__uint(max_entries, MAX_ENTRIES);
 } tstamp SEC(".maps");
 
+/* maintain per-CPU timestamp at the beginning of contention */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct tstamp_data));
+	__uint(max_entries, 1);
+} tstamp_cpu SEC(".maps");
+
 /* actual lock contention statistics */
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
@@ -92,6 +93,13 @@ struct {
 	__uint(max_entries, 1);
 } addr_filter SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cgroup_filter SEC(".maps");
+
 struct rw_semaphore___old {
 	struct task_struct *owner;
 } __attribute__((preserve_access_index));
@@ -114,13 +122,19 @@ int has_cpu;
 int has_task;
 int has_type;
 int has_addr;
+int has_cgroup;
 int needs_callstack;
 int stack_skip;
 int lock_owner;
 
+int use_cgroup_v2;
+int perf_subsys_id = -1;
+
 /* determine the key of lock stat */
 int aggr_mode;
 
+__u64 end_ts;
+
 /* error stat */
 int task_fail;
 int stack_fail;
@@ -130,6 +144,29 @@ int data_fail;
 int task_map_full;
 int data_map_full;
 
+static inline __u64 get_current_cgroup_id(void)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (use_cgroup_v2)
+		return bpf_get_current_cgroup_id();
+
+	task = bpf_get_current_task_btf();
+
+	if (perf_subsys_id == -1) {
+#if __has_builtin(__builtin_preserve_enum_value)
+		perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id,
+						     perf_event_cgrp_id);
+#else
+		perf_subsys_id = perf_event_cgrp_id;
+#endif
+	}
+
+	cgrp = BPF_CORE_READ(task, cgroups, subsys[perf_subsys_id], cgroup);
+	return BPF_CORE_READ(cgrp, kn, id);
+}
+
 static inline int can_record(u64 *ctx)
 {
 	if (has_cpu) {
@@ -168,6 +205,15 @@ static inline int can_record(u64 *ctx)
 			return 0;
 	}
 
+	if (has_cgroup) {
+		__u8 *ok;
+		__u64 cgrp = get_current_cgroup_id();
+
+		ok = bpf_map_lookup_elem(&cgroup_filter, &cgrp);
+		if (!ok)
+			return 0;
+	}
+
 	return 1;
 }
 
@@ -238,6 +284,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
 	struct task_struct *curr;
 	struct mm_struct___old *mm_old;
 	struct mm_struct___new *mm_new;
+	struct sighand_struct *sighand;
 
 	switch (flags) {
 	case LCB_F_READ:  /* rwsem */
@@ -259,7 +306,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
 		break;
 	case LCB_F_SPIN:  /* spinlock */
 		curr = bpf_get_current_task_btf();
-		if (&curr->sighand->siglock == (void *)lock)
+		sighand = curr->sighand;
+
+		if (sighand && &sighand->siglock == (void *)lock)
 			return LCD_F_SIGHAND_LOCK;
 		break;
 	default:
@@ -268,30 +317,57 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
 	return 0;
 }
 
-SEC("tp_btf/contention_begin")
-int contention_begin(u64 *ctx)
+static inline struct tstamp_data *get_tstamp_elem(__u32 flags)
 {
 	__u32 pid;
 	struct tstamp_data *pelem;
 
-	if (!enabled || !can_record(ctx))
-		return 0;
+	/* Use per-cpu array map for spinlock and rwlock */
+	if (flags == (LCB_F_SPIN | LCB_F_READ) || flags == LCB_F_SPIN ||
+	    flags == (LCB_F_SPIN | LCB_F_WRITE)) {
+		__u32 idx = 0;
+
+		pelem = bpf_map_lookup_elem(&tstamp_cpu, &idx);
+		/* Do not update the element for nested locks */
+		if (pelem && pelem->lock)
+			pelem = NULL;
+		return pelem;
+	}
 
 	pid = bpf_get_current_pid_tgid();
 	pelem = bpf_map_lookup_elem(&tstamp, &pid);
+	/* Do not update the element for nested locks */
 	if (pelem && pelem->lock)
-		return 0;
+		return NULL;
 
 	if (pelem == NULL) {
 		struct tstamp_data zero = {};
 
-		bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY);
+		if (bpf_map_update_elem(&tstamp, &pid, &zero, BPF_NOEXIST) < 0) {
+			__sync_fetch_and_add(&task_fail, 1);
+			return NULL;
+		}
+
 		pelem = bpf_map_lookup_elem(&tstamp, &pid);
 		if (pelem == NULL) {
 			__sync_fetch_and_add(&task_fail, 1);
-			return 0;
+			return NULL;
 		}
 	}
+	return pelem;
+}
+
+SEC("tp_btf/contention_begin")
+int contention_begin(u64 *ctx)
+{
+	struct tstamp_data *pelem;
+
+	if (!enabled || !can_record(ctx))
+		return 0;
+
+	pelem = get_tstamp_elem(ctx[1]);
+	if (pelem == NULL)
+		return 0;
 
 	pelem->timestamp = bpf_ktime_get_ns();
 	pelem->lock = (__u64)ctx[0];
@@ -330,23 +406,42 @@ int contention_begin(u64 *ctx)
 SEC("tp_btf/contention_end")
 int contention_end(u64 *ctx)
 {
-	__u32 pid;
+	__u32 pid = 0, idx = 0;
 	struct tstamp_data *pelem;
 	struct contention_key key = {};
 	struct contention_data *data;
 	__u64 duration;
+	bool need_delete = false;
 
 	if (!enabled)
 		return 0;
 
-	pid = bpf_get_current_pid_tgid();
-	pelem = bpf_map_lookup_elem(&tstamp, &pid);
-	if (!pelem || pelem->lock != ctx[0])
-		return 0;
+	/*
+	 * For spinlock and rwlock, it needs to get the timestamp for the
+	 * per-cpu map.  However, contention_end does not have the flags
+	 * so it cannot know whether it reads percpu or hash map.
+	 *
+	 * Try per-cpu map first and check if there's active contention.
+	 * If it is, do not read hash map because it cannot go to sleeping
+	 * locks before releasing the spinning locks.
+	 */
+	pelem = bpf_map_lookup_elem(&tstamp_cpu, &idx);
+	if (pelem && pelem->lock) {
+		if (pelem->lock != ctx[0])
+			return 0;
+	} else {
+		pid = bpf_get_current_pid_tgid();
+		pelem = bpf_map_lookup_elem(&tstamp, &pid);
+		if (!pelem || pelem->lock != ctx[0])
+			return 0;
+		need_delete = true;
+	}
 
 	duration = bpf_ktime_get_ns() - pelem->timestamp;
 	if ((__s64)duration < 0) {
-		bpf_map_delete_elem(&tstamp, &pid);
+		pelem->lock = 0;
+		if (need_delete)
+			bpf_map_delete_elem(&tstamp, &pid);
 		__sync_fetch_and_add(&time_fail, 1);
 		return 0;
 	}
@@ -358,16 +453,22 @@ int contention_end(u64 *ctx)
 	case LOCK_AGGR_TASK:
 		if (lock_owner)
 			key.pid = pelem->flags;
-		else
+		else {
+			if (!need_delete)
+				pid = bpf_get_current_pid_tgid();
 			key.pid = pid;
+		}
 		if (needs_callstack)
 			key.stack_id = pelem->stack_id;
 		break;
 	case LOCK_AGGR_ADDR:
-		key.lock_addr = pelem->lock;
+		key.lock_addr_or_cgroup = pelem->lock;
 		if (needs_callstack)
 			key.stack_id = pelem->stack_id;
 		break;
+	case LOCK_AGGR_CGROUP:
+		key.lock_addr_or_cgroup = get_current_cgroup_id();
+		break;
 	default:
 		/* should not happen */
 		return 0;
@@ -376,7 +477,9 @@ int contention_end(u64 *ctx)
 	data = bpf_map_lookup_elem(&lock_stat, &key);
 	if (!data) {
 		if (data_map_full) {
-			bpf_map_delete_elem(&tstamp, &pid);
+			pelem->lock = 0;
+			if (need_delete)
+				bpf_map_delete_elem(&tstamp, &pid);
 			__sync_fetch_and_add(&data_fail, 1);
 			return 0;
 		}
@@ -399,7 +502,9 @@ int contention_end(u64 *ctx)
 				data_map_full = 1;
 			__sync_fetch_and_add(&data_fail, 1);
 		}
-		bpf_map_delete_elem(&tstamp, &pid);
+		pelem->lock = 0;
+		if (need_delete)
+			bpf_map_delete_elem(&tstamp, &pid);
 		return 0;
 	}
 
@@ -412,7 +517,9 @@ int contention_end(u64 *ctx)
 	if (data->min_time > duration)
 		data->min_time = duration;
 
-	bpf_map_delete_elem(&tstamp, &pid);
+	pelem->lock = 0;
+	if (need_delete)
+		bpf_map_delete_elem(&tstamp, &pid);
 	return 0;
 }
 
@@ -450,4 +557,11 @@ int BPF_PROG(collect_lock_syms)
 	return 0;
 }
 
+SEC("raw_tp/bpf_test_finish")
+int BPF_PROG(end_timestamp)
+{
+	end_ts = bpf_ktime_get_ns();
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index 260062a9f2ab..36af11faad03 100644
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -3,10 +3,17 @@
 #ifndef UTIL_BPF_SKEL_LOCK_DATA_H
 #define UTIL_BPF_SKEL_LOCK_DATA_H
 
+struct tstamp_data {
+	u64 timestamp;
+	u64 lock;
+	u32 flags;
+	u32 stack_id;
+};
+
 struct contention_key {
 	u32 stack_id;
 	u32 pid;
-	u64 lock_addr;
+	u64 lock_addr_or_cgroup;
 };
 
 #define TASK_COMM_LEN  16
@@ -39,6 +46,7 @@ enum lock_aggr_mode {
 	LOCK_AGGR_ADDR = 0,
 	LOCK_AGGR_TASK,
 	LOCK_AGGR_CALLER,
+	LOCK_AGGR_CGROUP,
 };
 
 enum lock_class_sym {
diff --git a/tools/perf/util/bpf_skel/vmlinux/.gitignore b/tools/perf/util/bpf_skel/vmlinux/.gitignore
new file mode 100644
index 000000000000..49502c04183a
--- /dev/null
+++ b/tools/perf/util/bpf_skel/vmlinux/.gitignore
@@ -0,0 +1 @@
+!vmlinux.h
diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
index ab84a6e1da5e..e9028235d771 100644
--- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
@@ -20,6 +20,13 @@ typedef __s64 s64;
 
 typedef int pid_t;
 
+typedef __s64 time64_t;
+
+struct timespec64 {
+        time64_t        tv_sec;
+        long int        tv_nsec;
+};
+
 enum cgroup_subsys_id {
 	perf_event_cgrp_id  = 8,
 };
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 378f16a24751..ab760e267d41 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -109,7 +109,7 @@ const char *get_branch_type(struct branch_entry *e)
 	return branch_type_name(e->flags.type);
 }
 
-void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
+void branch_type_stat_display(FILE *fp, const struct branch_type_stat *st)
 {
 	u64 total = 0;
 	int i;
@@ -171,7 +171,7 @@ static int count_str_scnprintf(int idx, const char *str, char *bf, int size)
 	return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str);
 }
 
-int branch_type_str(struct branch_type_stat *st, char *bf, int size)
+int branch_type_str(const struct branch_type_stat *st, char *bf, int size)
 {
 	int i, j = 0, printed = 0;
 	u64 total = 0;
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index e41bfffe2217..87704d713ff6 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -86,8 +86,8 @@ void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
 const char *branch_type_name(int type);
 const char *branch_new_type_name(int new_type);
 const char *get_branch_type(struct branch_entry *e);
-void branch_type_stat_display(FILE *fp, struct branch_type_stat *st);
-int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize);
+void branch_type_stat_display(FILE *fp, const struct branch_type_stat *st);
+int branch_type_str(const struct branch_type_stat *st, char *bf, int bfsize);
 
 const char *branch_spec_desc(int spec);
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 36728222a5b4..03c64b85383b 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -560,7 +560,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 			       struct nsinfo *nsi, bool is_kallsyms,
 			       bool is_vdso)
 {
-	char *realname = (char *)name, *filename;
+	char *realname = NULL, *filename;
 	bool slash = is_kallsyms || is_vdso;
 
 	if (!slash)
@@ -571,9 +571,7 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 		     sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
 		filename = NULL;
 
-	if (!slash)
-		free(realname);
-
+	free(realname);
 	return filename;
 }
 
diff --git a/tools/perf/util/c++/Build b/tools/perf/util/c++/Build
deleted file mode 100644
index 613ecfd76527..000000000000
--- a/tools/perf/util/c++/Build
+++ /dev/null
@@ -1,2 +0,0 @@
-perf-$(CONFIG_CLANGLLVM) += clang.o
-perf-$(CONFIG_CLANGLLVM) += clang-test.o
diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
deleted file mode 100644
index d3731a876b6c..000000000000
--- a/tools/perf/util/c++/clang-c.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef PERF_UTIL_CLANG_C_H
-#define PERF_UTIL_CLANG_C_H
-
-#include <stddef.h>	/* for size_t */
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#ifdef HAVE_LIBCLANGLLVM_SUPPORT
-extern void perf_clang__init(void);
-extern void perf_clang__cleanup(void);
-
-struct test_suite;
-extern int test__clang_to_IR(struct test_suite *test, int subtest);
-extern int test__clang_to_obj(struct test_suite *test, int subtest);
-
-extern int perf_clang__compile_bpf(const char *filename,
-				   void **p_obj_buf,
-				   size_t *p_obj_buf_sz);
-#else
-
-#include <errno.h>
-#include <linux/compiler.h>	/* for __maybe_unused */
-
-static inline void perf_clang__init(void) { }
-static inline void perf_clang__cleanup(void) { }
-
-static inline int
-perf_clang__compile_bpf(const char *filename __maybe_unused,
-			void **p_obj_buf __maybe_unused,
-			size_t *p_obj_buf_sz __maybe_unused)
-{
-	return -ENOTSUP;
-}
-
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-#endif
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
deleted file mode 100644
index a4683ca53697..000000000000
--- a/tools/perf/util/c++/clang-test.cpp
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "clang.h"
-#include "clang-c.h"
-extern "C" {
-#include "../util.h"
-}
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-
-#include <tests/llvm.h>
-#include <string>
-
-class perf_clang_scope {
-public:
-	explicit perf_clang_scope() {perf_clang__init();}
-	~perf_clang_scope() {perf_clang__cleanup();}
-};
-
-static std::unique_ptr<llvm::Module>
-__test__clang_to_IR(void)
-{
-	unsigned int kernel_version;
-
-	if (fetch_kernel_version(&kernel_version, NULL, 0))
-		return std::unique_ptr<llvm::Module>(nullptr);
-
-	std::string cflag_kver("-DLINUX_VERSION_CODE=" +
-				std::to_string(kernel_version));
-
-	std::unique_ptr<llvm::Module> M =
-		perf::getModuleFromSource({cflag_kver.c_str()},
-					  "perf-test.c",
-					  test_llvm__bpf_base_prog);
-	return M;
-}
-
-extern "C" {
-int test__clang_to_IR(struct test_suite *test __maybe_unused,
-                      int subtest __maybe_unused)
-{
-	perf_clang_scope _scope;
-
-	auto M = __test__clang_to_IR();
-	if (!M)
-		return -1;
-	for (llvm::Function& F : *M)
-		if (F.getName() == "bpf_func__SyS_epoll_pwait")
-			return 0;
-	return -1;
-}
-
-int test__clang_to_obj(struct test_suite *test __maybe_unused,
-                       int subtest __maybe_unused)
-{
-	perf_clang_scope _scope;
-
-	auto M = __test__clang_to_IR();
-	if (!M)
-		return -1;
-
-	auto Buffer = perf::getBPFObjectFromModule(&*M);
-	if (!Buffer)
-		return -1;
-	return 0;
-}
-
-}
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
deleted file mode 100644
index 1aad7d6d34aa..000000000000
--- a/tools/perf/util/c++/clang.cpp
+++ /dev/null
@@ -1,225 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * llvm C frontend for perf. Support dynamically compile C file
- *
- * Inspired by clang example code:
- * http://llvm.org/svn/llvm-project/cfe/trunk/examples/clang-interpreter/main.cpp
- *
- * Copyright (C) 2016 Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2016 Huawei Inc.
- */
-
-#include "clang/Basic/Version.h"
-#include "clang/CodeGen/CodeGenAction.h"
-#include "clang/Frontend/CompilerInvocation.h"
-#include "clang/Frontend/CompilerInstance.h"
-#include "clang/Frontend/TextDiagnosticPrinter.h"
-#include "clang/Tooling/Tooling.h"
-#include "llvm/IR/LegacyPassManager.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Option/Option.h"
-#include "llvm/Support/FileSystem.h"
-#include "llvm/Support/ManagedStatic.h"
-#if CLANG_VERSION_MAJOR >= 14
-#include "llvm/MC/TargetRegistry.h"
-#else
-#include "llvm/Support/TargetRegistry.h"
-#endif
-#include "llvm/Support/TargetSelect.h"
-#include "llvm/Target/TargetMachine.h"
-#include "llvm/Target/TargetOptions.h"
-#include <memory>
-
-#include "clang.h"
-#include "clang-c.h"
-
-namespace perf {
-
-static std::unique_ptr<llvm::LLVMContext> LLVMCtx;
-
-using namespace clang;
-
-static CompilerInvocation *
-createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path,
-			 DiagnosticsEngine& Diags)
-{
-	llvm::opt::ArgStringList CCArgs {
-		"-cc1",
-		"-triple", "bpf-pc-linux",
-		"-fsyntax-only",
-		"-O2",
-		"-nostdsysteminc",
-		"-nobuiltininc",
-		"-vectorize-loops",
-		"-vectorize-slp",
-		"-Wno-unused-value",
-		"-Wno-pointer-sign",
-		"-x", "c"};
-
-	CCArgs.append(CFlags.begin(), CFlags.end());
-	CompilerInvocation *CI = tooling::newInvocation(&Diags, CCArgs
-#if CLANG_VERSION_MAJOR >= 11
-                                                        ,/*BinaryName=*/nullptr
-#endif
-                                                        );
-
-	FrontendOptions& Opts = CI->getFrontendOpts();
-	Opts.Inputs.clear();
-	Opts.Inputs.emplace_back(Path,
-			FrontendOptions::getInputKindForExtension("c"));
-	return CI;
-}
-
-static std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags,
-		    StringRef Path, IntrusiveRefCntPtr<vfs::FileSystem> VFS)
-{
-	CompilerInstance Clang;
-	Clang.createDiagnostics();
-
-#if CLANG_VERSION_MAJOR < 9
-	Clang.setVirtualFileSystem(&*VFS);
-#else
-	Clang.createFileManager(&*VFS);
-#endif
-
-#if CLANG_VERSION_MAJOR < 4
-	IntrusiveRefCntPtr<CompilerInvocation> CI =
-		createCompilerInvocation(std::move(CFlags), Path,
-					 Clang.getDiagnostics());
-	Clang.setInvocation(&*CI);
-#else
-	std::shared_ptr<CompilerInvocation> CI(
-		createCompilerInvocation(std::move(CFlags), Path,
-					 Clang.getDiagnostics()));
-	Clang.setInvocation(CI);
-#endif
-
-	std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx));
-	if (!Clang.ExecuteAction(*Act))
-		return std::unique_ptr<llvm::Module>(nullptr);
-
-	return Act->takeModule();
-}
-
-std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags,
-		    StringRef Name, StringRef Content)
-{
-	using namespace vfs;
-
-	llvm::IntrusiveRefCntPtr<OverlayFileSystem> OverlayFS(
-			new OverlayFileSystem(getRealFileSystem()));
-	llvm::IntrusiveRefCntPtr<InMemoryFileSystem> MemFS(
-			new InMemoryFileSystem(true));
-
-	/*
-	 * pushOverlay helps setting working dir for MemFS. Must call
-	 * before addFile.
-	 */
-	OverlayFS->pushOverlay(MemFS);
-	MemFS->addFile(Twine(Name), 0, llvm::MemoryBuffer::getMemBuffer(Content));
-
-	return getModuleFromSource(std::move(CFlags), Name, OverlayFS);
-}
-
-std::unique_ptr<llvm::Module>
-getModuleFromSource(llvm::opt::ArgStringList CFlags, StringRef Path)
-{
-	IntrusiveRefCntPtr<vfs::FileSystem> VFS(vfs::getRealFileSystem());
-	return getModuleFromSource(std::move(CFlags), Path, VFS);
-}
-
-std::unique_ptr<llvm::SmallVectorImpl<char>>
-getBPFObjectFromModule(llvm::Module *Module)
-{
-	using namespace llvm;
-
-	std::string TargetTriple("bpf-pc-linux");
-	std::string Error;
-	const Target* Target = TargetRegistry::lookupTarget(TargetTriple, Error);
-	if (!Target) {
-		llvm::errs() << Error;
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
-	}
-
-	llvm::TargetOptions Opt;
-	TargetMachine *TargetMachine =
-		Target->createTargetMachine(TargetTriple,
-					    "generic", "",
-					    Opt, Reloc::Static);
-
-	Module->setDataLayout(TargetMachine->createDataLayout());
-	Module->setTargetTriple(TargetTriple);
-
-	std::unique_ptr<SmallVectorImpl<char>> Buffer(new SmallVector<char, 0>());
-	raw_svector_ostream ostream(*Buffer);
-
-	legacy::PassManager PM;
-	bool NotAdded;
-	NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream
-#if CLANG_VERSION_MAJOR >= 7
-                                                      , /*DwoOut=*/nullptr
-#endif
-#if CLANG_VERSION_MAJOR < 10
-                                                      , TargetMachine::CGFT_ObjectFile
-#else
-                                                      , llvm::CGFT_ObjectFile
-#endif
-                                                      );
-	if (NotAdded) {
-		llvm::errs() << "TargetMachine can't emit a file of this type\n";
-		return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);
-	}
-	PM.run(*Module);
-
-	return Buffer;
-}
-
-}
-
-extern "C" {
-void perf_clang__init(void)
-{
-	perf::LLVMCtx.reset(new llvm::LLVMContext());
-	LLVMInitializeBPFTargetInfo();
-	LLVMInitializeBPFTarget();
-	LLVMInitializeBPFTargetMC();
-	LLVMInitializeBPFAsmPrinter();
-}
-
-void perf_clang__cleanup(void)
-{
-	perf::LLVMCtx.reset(nullptr);
-	llvm::llvm_shutdown();
-}
-
-int perf_clang__compile_bpf(const char *filename,
-			    void **p_obj_buf,
-			    size_t *p_obj_buf_sz)
-{
-	using namespace perf;
-
-	if (!p_obj_buf || !p_obj_buf_sz)
-		return -EINVAL;
-
-	llvm::opt::ArgStringList CFlags;
-	auto M = getModuleFromSource(std::move(CFlags), filename);
-	if (!M)
-		return  -EINVAL;
-	auto O = getBPFObjectFromModule(&*M);
-	if (!O)
-		return -EINVAL;
-
-	size_t size = O->size_in_bytes();
-	void *buffer;
-
-	buffer = malloc(size);
-	if (!buffer)
-		return -ENOMEM;
-	memcpy(buffer, O->data(), size);
-	*p_obj_buf = buffer;
-	*p_obj_buf_sz = size;
-	return 0;
-}
-}
diff --git a/tools/perf/util/c++/clang.h b/tools/perf/util/c++/clang.h
deleted file mode 100644
index 6ce33e22f23c..000000000000
--- a/tools/perf/util/c++/clang.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef PERF_UTIL_CLANG_H
-#define PERF_UTIL_CLANG_H
-
-#include "llvm/ADT/StringRef.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Option/Option.h"
-#include <memory>
-
-namespace perf {
-
-using namespace llvm;
-
-std::unique_ptr<Module>
-getModuleFromSource(opt::ArgStringList CFlags,
-		    StringRef Name, StringRef Content);
-
-std::unique_ptr<Module>
-getModuleFromSource(opt::ArgStringList CFlags,
-		    StringRef Path);
-
-std::unique_ptr<llvm::SmallVectorImpl<char>>
-getBPFObjectFromModule(llvm::Module *Module);
-
-}
-#endif
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aee937d14fbb..7517d16c02ec 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -586,7 +586,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
-			return -1;
+			return -ENOMEM;
 		}
 		call->ip = cursor_node->ip;
 		call->ms = cursor_node->ms;
@@ -602,7 +602,15 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 				 * branch_from is set with value somewhere else
 				 * to imply it's "to" of a branch.
 				 */
-				call->brtype_stat.branch_to = true;
+				if (!call->brtype_stat) {
+					call->brtype_stat = zalloc(sizeof(*call->brtype_stat));
+					if (!call->brtype_stat) {
+						perror("not enough memory for the code path branch statistics");
+						free(call->brtype_stat);
+						return -ENOMEM;
+					}
+				}
+				call->brtype_stat->branch_to = true;
 
 				if (cursor_node->branch_flags.predicted)
 					call->predicted_count = 1;
@@ -610,7 +618,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 				if (cursor_node->branch_flags.abort)
 					call->abort_count = 1;
 
-				branch_type_count(&call->brtype_stat,
+				branch_type_count(call->brtype_stat,
 						  &cursor_node->branch_flags,
 						  cursor_node->branch_from,
 						  cursor_node->ip);
@@ -618,7 +626,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 				/*
 				 * It's "from" of a branch
 				 */
-				call->brtype_stat.branch_to = false;
+				if (call->brtype_stat && call->brtype_stat->branch_to)
+					call->brtype_stat->branch_to = false;
 				call->cycles_count =
 					cursor_node->branch_flags.cycles;
 				call->iter_count = cursor_node->nr_loop_iter;
@@ -650,8 +659,8 @@ add_child(struct callchain_node *parent,
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
 			list_del_init(&call->list);
-			map__zput(call->ms.map);
-			maps__zput(call->ms.maps);
+			map_symbol__exit(&call->ms);
+			zfree(&call->brtype_stat);
 			free(call);
 		}
 		free(new);
@@ -762,7 +771,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			/*
 			 * It's "to" of a branch
 			 */
-			cnode->brtype_stat.branch_to = true;
+			if (!cnode->brtype_stat) {
+				cnode->brtype_stat = zalloc(sizeof(*cnode->brtype_stat));
+				if (!cnode->brtype_stat) {
+					perror("not enough memory for the code path branch statistics");
+					return MATCH_ERROR;
+				}
+			}
+			cnode->brtype_stat->branch_to = true;
 
 			if (node->branch_flags.predicted)
 				cnode->predicted_count++;
@@ -770,7 +786,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			if (node->branch_flags.abort)
 				cnode->abort_count++;
 
-			branch_type_count(&cnode->brtype_stat,
+			branch_type_count(cnode->brtype_stat,
 					  &node->branch_flags,
 					  node->branch_from,
 					  node->ip);
@@ -778,7 +794,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			/*
 			 * It's "from" of a branch
 			 */
-			cnode->brtype_stat.branch_to = false;
+			if (cnode->brtype_stat && cnode->brtype_stat->branch_to)
+				cnode->brtype_stat->branch_to = false;
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
@@ -1022,10 +1039,9 @@ merge_chain_branch(struct callchain_cursor *cursor,
 		};
 		callchain_cursor_append(cursor, list->ip, &ms, false, NULL, 0, 0, 0, list->srcline);
 		list_del_init(&list->list);
-		map__zput(ms.map);
-		maps__zput(ms.maps);
-		map__zput(list->ms.map);
-		maps__zput(list->ms.maps);
+		map_symbol__exit(&ms);
+		map_symbol__exit(&list->ms);
+		zfree(&list->brtype_stat);
 		free(list);
 	}
 
@@ -1077,8 +1093,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	}
 
 	node->ip = ip;
-	maps__zput(node->ms.maps);
-	map__zput(node->ms.map);
+	map_symbol__exit(&node->ms);
 	node->ms = *ms;
 	node->ms.maps = maps__get(ms->maps);
 	node->ms.map = map__get(ms->map);
@@ -1142,7 +1157,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 		if (al->map == NULL)
 			goto out;
 	}
-	if (RC_CHK_ACCESS(al->maps) == RC_CHK_ACCESS(machine__kernel_maps(machine))) {
+	if (maps__equal(al->maps, machine__kernel_maps(machine))) {
 		if (machine__is_host(machine)) {
 			al->cpumode = PERF_RECORD_MISC_KERNEL;
 			al->level = 'k';
@@ -1339,7 +1354,7 @@ static int count_float_printf(int idx, const char *str, float value,
 static int branch_to_str(char *bf, int bfsize,
 			 u64 branch_count, u64 predicted_count,
 			 u64 abort_count,
-			 struct branch_type_stat *brtype_stat)
+			 const struct branch_type_stat *brtype_stat)
 {
 	int printed, i = 0;
 
@@ -1403,7 +1418,7 @@ static int counts_str_build(char *bf, int bfsize,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
 			     u64 from_count,
-			     struct branch_type_stat *brtype_stat)
+			     const struct branch_type_stat *brtype_stat)
 {
 	int printed;
 
@@ -1430,7 +1445,7 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
 				   u64 from_count,
-				   struct branch_type_stat *brtype_stat)
+				   const struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
@@ -1447,11 +1462,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 int callchain_list_counts__printf_value(struct callchain_list *clist,
 					FILE *fp, char *bf, int bfsize)
 {
+	static const struct branch_type_stat empty_brtype_stat = {};
+	const struct branch_type_stat *brtype_stat;
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
 	u64 from_count;
 
+	brtype_stat = clist->brtype_stat ?: &empty_brtype_stat;
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
 	abort_count = clist->abort_count;
@@ -1463,7 +1481,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       from_count, &clist->brtype_stat);
+				       from_count, brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
@@ -1474,15 +1492,15 @@ static void free_callchain_node(struct callchain_node *node)
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
 		list_del_init(&list->list);
-		map__zput(list->ms.map);
-		maps__zput(list->ms.maps);
+		map_symbol__exit(&list->ms);
+		zfree(&list->brtype_stat);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del_init(&list->list);
-		map__zput(list->ms.map);
-		maps__zput(list->ms.maps);
+		map_symbol__exit(&list->ms);
+		zfree(&list->brtype_stat);
 		free(list);
 	}
 
@@ -1567,8 +1585,8 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
 		list_del_init(&chain->list);
-		map__zput(chain->ms.map);
-		maps__zput(chain->ms.maps);
+		map_symbol__exit(&chain->ms);
+		zfree(&chain->brtype_stat);
 		free(chain);
 	}
 	return -ENOMEM;
@@ -1651,10 +1669,8 @@ void callchain_cursor_reset(struct callchain_cursor *cursor)
 	cursor->nr = 0;
 	cursor->last = &cursor->first;
 
-	for (node = cursor->first; node != NULL; node = node->next) {
-		map__zput(node->ms.map);
-		maps__zput(node->ms.maps);
-	}
+	for (node = cursor->first; node != NULL; node = node->next)
+		map_symbol__exit(&node->ms);
 }
 
 void callchain_param_setup(u64 sample_type, const char *arch)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d2618a47deca..d5c66345ae31 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -116,22 +116,22 @@ extern struct callchain_param callchain_param;
 extern struct callchain_param callchain_param_default;
 
 struct callchain_list {
+	struct list_head	list;
 	u64			ip;
 	struct map_symbol	ms;
-	struct /* for TUI */ {
-		bool		unfolded;
-		bool		has_children;
-	};
+	const char		*srcline;
 	u64			branch_count;
 	u64			from_count;
-	u64			predicted_count;
-	u64			abort_count;
 	u64			cycles_count;
 	u64			iter_count;
 	u64			iter_cycles;
-	struct branch_type_stat brtype_stat;
-	const char		*srcline;
-	struct list_head	list;
+	struct branch_type_stat *brtype_stat;
+	u64			predicted_count;
+	u64			abort_count;
+	struct /* for TUI */ {
+		bool		unfolded;
+		bool		has_children;
+	};
 };
 
 /*
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index bfb13306d82c..fcb509058499 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -48,28 +48,36 @@ static int open_cgroup(const char *name)
 }
 
 #ifdef HAVE_FILE_HANDLE
-int read_cgroup_id(struct cgroup *cgrp)
+static u64 __read_cgroup_id(const char *path)
 {
-	char path[PATH_MAX + 1];
-	char mnt[PATH_MAX + 1];
 	struct {
 		struct file_handle fh;
 		uint64_t cgroup_id;
 	} handle;
 	int mount_id;
 
+	handle.fh.handle_bytes = sizeof(handle.cgroup_id);
+	if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0)
+		return -1ULL;
+
+	return handle.cgroup_id;
+}
+
+int read_cgroup_id(struct cgroup *cgrp)
+{
+	char path[PATH_MAX + 1];
+	char mnt[PATH_MAX + 1];
+
 	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
 		return -1;
 
 	scnprintf(path, PATH_MAX, "%s/%s", mnt, cgrp->name);
 
-	handle.fh.handle_bytes = sizeof(handle.cgroup_id);
-	if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0)
-		return -1;
-
-	cgrp->id = handle.cgroup_id;
+	cgrp->id = __read_cgroup_id(path);
 	return 0;
 }
+#else
+static inline u64 __read_cgroup_id(const char *path __maybe_unused) { return -1ULL; }
 #endif  /* HAVE_FILE_HANDLE */
 
 #ifndef CGROUP2_SUPER_MAGIC
@@ -106,7 +114,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str
 	return NULL;
 }
 
-static struct cgroup *cgroup__new(const char *name, bool do_open)
+struct cgroup *cgroup__new(const char *name, bool do_open)
 {
 	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
@@ -562,6 +570,11 @@ struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id,
 	return cgrp;
 }
 
+struct cgroup *__cgroup__find(struct rb_root *root, uint64_t id)
+{
+	return __cgroup__findnew(root, id, /*create=*/false, /*path=*/NULL);
+}
+
 struct cgroup *cgroup__find(struct perf_env *env, uint64_t id)
 {
 	struct cgroup *cgrp;
@@ -587,3 +600,35 @@ void perf_env__purge_cgroups(struct perf_env *env)
 	}
 	up_write(&env->cgroups.lock);
 }
+
+void read_all_cgroups(struct rb_root *root)
+{
+	char mnt[PATH_MAX];
+	struct cgroup_name *cn;
+	int prefix_len;
+
+	if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event"))
+		return;
+
+	/* cgroup_name will have a full path, skip the root directory */
+	prefix_len = strlen(mnt);
+
+	/* collect all cgroups in the cgroup_list */
+	if (nftw(mnt, add_cgroup_name, 20, 0) < 0)
+		return;
+
+	list_for_each_entry(cn, &cgroup_list, list) {
+		const char *name;
+		u64 cgrp_id;
+
+		/* cgroup_name might have a full path, skip the prefix */
+		name = cn->name + prefix_len;
+		if (name[0] == '\0')
+			name = "/";
+
+		cgrp_id = __read_cgroup_id(cn->name);
+		__cgroup__findnew(root, cgrp_id, /*create=*/true, name);
+	}
+
+	release_cgroup_list();
+}
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 12256b78608c..de8882d6e8d3 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -26,6 +26,7 @@ void cgroup__put(struct cgroup *cgroup);
 struct evlist;
 struct rblist;
 
+struct cgroup *cgroup__new(const char *name, bool do_open);
 struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name);
 int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups,
 			  struct rblist *metric_events, bool open_cgroup);
@@ -37,6 +38,7 @@ int parse_cgroups(const struct option *opt, const char *str, int unset);
 struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id,
 			       const char *path);
 struct cgroup *cgroup__find(struct perf_env *env, uint64_t id);
+struct cgroup *__cgroup__find(struct rb_root *root, uint64_t id);
 
 void perf_env__purge_cgroups(struct perf_env *env);
 
@@ -49,6 +51,9 @@ static inline int read_cgroup_id(struct cgroup *cgrp __maybe_unused)
 }
 #endif  /* HAVE_FILE_HANDLE */
 
+/* read all cgroups in the system and save them in the rbtree */
+void read_all_cgroups(struct rb_root *root);
+
 int cgroup_is_v2(const char *subsys);
 
 #endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 0cd3369af2a4..b29109cd3609 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -3,6 +3,8 @@
 #define PERF_COMPRESS_H
 
 #include <stdbool.h>
+#include <stddef.h>
+#include <sys/types.h>
 #ifdef HAVE_ZSTD_SUPPORT
 #include <zstd.h>
 #endif
@@ -21,6 +23,7 @@ struct zstd_data {
 #ifdef HAVE_ZSTD_SUPPORT
 	ZSTD_CStream	*cstream;
 	ZSTD_DStream	*dstream;
+	int comp_level;
 #endif
 };
 
@@ -29,7 +32,7 @@ struct zstd_data {
 int zstd_init(struct zstd_data *data, int level);
 int zstd_fini(struct zstd_data *data);
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment));
 
@@ -48,7 +51,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused)
 }
 
 static inline
-size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
 				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
 				       void *src __maybe_unused, size_t src_size __maybe_unused,
 				       size_t max_record_size __maybe_unused,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 46f144c46827..7a650de0db83 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -16,7 +16,6 @@
 #include <subcmd/exec-cmd.h>
 #include "util/event.h"  /* proc_map_timeout */
 #include "util/hist.h"  /* perf_hist_config */
-#include "util/llvm-utils.h"   /* perf_llvm_config */
 #include "util/stat.h"  /* perf_stat__set_big_num */
 #include "util/evsel.h"  /* evsel__hw_names, evsel__use_bpf_counters */
 #include "util/srcline.h"  /* addr2line_timeout_ms */
@@ -486,9 +485,6 @@ int perf_default_config(const char *var, const char *value,
 	if (strstarts(var, "call-graph."))
 		return perf_callchain_config(var, value);
 
-	if (strstarts(var, "llvm."))
-		return perf_llvm_config(var, value);
-
 	if (strstarts(var, "buildid."))
 		return perf_buildid_config(var, value);
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0e090e8bc334..356e30c42cd8 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -222,6 +222,8 @@ static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer)
 		return a->socket - b->socket;
 	else if (a->die != b->die)
 		return a->die - b->die;
+	else if (a->cluster != b->cluster)
+		return a->cluster - b->cluster;
 	else if (a->cache_lvl != b->cache_lvl)
 		return a->cache_lvl - b->cache_lvl;
 	else if (a->cache != b->cache)
@@ -309,6 +311,30 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data)
 	return id;
 }
 
+int cpu__get_cluster_id(struct perf_cpu cpu)
+{
+	int value, ret = cpu__get_topology_int(cpu.cpu, "cluster_id", &value);
+
+	return ret ?: value;
+}
+
+struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data)
+{
+	int cluster = cpu__get_cluster_id(cpu);
+	struct aggr_cpu_id id;
+
+	/* There is no cluster_id on legacy system. */
+	if (cluster == -1)
+		cluster = 0;
+
+	id = aggr_cpu_id__die(cpu, data);
+	if (aggr_cpu_id__is_empty(&id))
+		return id;
+
+	id.cluster = cluster;
+	return id;
+}
+
 int cpu__get_core_id(struct perf_cpu cpu)
 {
 	int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value);
@@ -320,8 +346,8 @@ struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data)
 	struct aggr_cpu_id id;
 	int core = cpu__get_core_id(cpu);
 
-	/* aggr_cpu_id__die returns a struct with socket and die set. */
-	id = aggr_cpu_id__die(cpu, data);
+	/* aggr_cpu_id__die returns a struct with socket die, and cluster set. */
+	id = aggr_cpu_id__cluster(cpu, data);
 	if (aggr_cpu_id__is_empty(&id))
 		return id;
 
@@ -672,7 +698,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
 	static struct perf_cpu_map *online;
 
 	if (!online)
-		online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */
+		online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */
 
 	return online;
 }
@@ -683,6 +709,7 @@ bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b
 		a->node == b->node &&
 		a->socket == b->socket &&
 		a->die == b->die &&
+		a->cluster == b->cluster &&
 		a->cache_lvl == b->cache_lvl &&
 		a->cache == b->cache &&
 		a->core == b->core &&
@@ -695,6 +722,7 @@ bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a)
 		a->node == -1 &&
 		a->socket == -1 &&
 		a->die == -1 &&
+		a->cluster == -1 &&
 		a->cache_lvl == -1 &&
 		a->cache == -1 &&
 		a->core == -1 &&
@@ -708,6 +736,7 @@ struct aggr_cpu_id aggr_cpu_id__empty(void)
 		.node = -1,
 		.socket = -1,
 		.die = -1,
+		.cluster = -1,
 		.cache_lvl = -1,
 		.cache = -1,
 		.core = -1,
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 9df2aeb34d3d..26cf76c693f5 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -20,6 +20,8 @@ struct aggr_cpu_id {
 	int socket;
 	/** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */
 	int die;
+	/** The cluster id as read from /sys/devices/system/cpu/cpuX/topology/cluster_id */
+	int cluster;
 	/** The cache level as read from /sys/devices/system/cpu/cpuX/cache/indexY/level */
 	int cache_lvl;
 	/**
@@ -87,6 +89,11 @@ int cpu__get_socket_id(struct perf_cpu cpu);
  */
 int cpu__get_die_id(struct perf_cpu cpu);
 /**
+ * cpu__get_cluster_id - Returns the cluster id as read from
+ * /sys/devices/system/cpu/cpuX/topology/cluster_id for the given CPU
+ */
+int cpu__get_cluster_id(struct perf_cpu cpu);
+/**
  * cpu__get_core_id - Returns the core id as read from
  * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU.
  */
@@ -127,9 +134,15 @@ struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data);
  */
 struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data);
 /**
- * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket
- * populated with the core, die and socket for cpu. The function signature is
- * compatible with aggr_cpu_id_get_t.
+ * aggr_cpu_id__cluster - Create an aggr_cpu_id with cluster, die and socket
+ * populated with the cluster, die and socket for cpu. The function signature
+ * is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the core, cluster, die and
+ * socket populated with the core, die and socket for cpu. The function
+ * signature is compatible with aggr_cpu_id_get_t.
  */
 struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data);
 /**
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 81cfc85f4668..8bbeb2dc76fd 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -267,7 +267,7 @@ struct cpu_topology *cpu_topology__new(void)
 	ncpus = cpu__max_present_cpu().cpu;
 
 	/* build online CPU map */
-	map = perf_cpu_map__new(NULL);
+	map = perf_cpu_map__new_online_cpus();
 	if (map == NULL) {
 		pr_debug("failed to get system cpumap\n");
 		return NULL;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 1419b40dfbe8..d65d7485886c 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -6,10 +6,11 @@
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
  */
 
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/coresight-pmu.h>
 #include <linux/err.h>
-#include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/types.h>
 #include <linux/zalloc.h>
@@ -282,33 +283,31 @@ static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata)
 }
 
 /*
- * FIELD_GET (linux/bitfield.h) not available outside kernel code,
- * and the header contains too many dependencies to just copy over,
- * so roll our own based on the original
- */
-#define __bf_shf(x) (__builtin_ffsll(x) - 1)
-#define FIELD_GET(_mask, _reg)						\
-	({								\
-		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \
-	})
-
-/*
- * Get a metadata for a specific cpu from an array.
+ * Get a metadata index for a specific cpu from an array.
  *
  */
-static u64 *get_cpu_data(struct cs_etm_auxtrace *etm, int cpu)
+static int get_cpu_data_idx(struct cs_etm_auxtrace *etm, int cpu)
 {
 	int i;
-	u64 *metadata = NULL;
 
 	for (i = 0; i < etm->num_cpu; i++) {
 		if (etm->metadata[i][CS_ETM_CPU] == (u64)cpu) {
-			metadata = etm->metadata[i];
-			break;
+			return i;
 		}
 	}
 
-	return metadata;
+	return -1;
+}
+
+/*
+ * Get a metadata for a specific cpu from an array.
+ *
+ */
+static u64 *get_cpu_data(struct cs_etm_auxtrace *etm, int cpu)
+{
+	int idx = get_cpu_data_idx(etm, cpu);
+
+	return (idx != -1) ? etm->metadata[idx] : NULL;
 }
 
 /*
@@ -651,66 +650,80 @@ static void cs_etm__packet_dump(const char *pkt_string)
 }
 
 static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int idx,
-					  u32 etmidr)
+					  struct cs_etm_auxtrace *etm, int t_idx,
+					  int m_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];
+	t_params[t_idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
+	t_params[t_idx].etmv3.reg_ctrl = metadata[m_idx][CS_ETM_ETMCR];
+	t_params[t_idx].etmv3.reg_trc_id = metadata[m_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)
+					  struct cs_etm_auxtrace *etm, int t_idx,
+					  int m_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];
+	t_params[t_idx].protocol = CS_ETM_PROTO_ETMV4i;
+	t_params[t_idx].etmv4.reg_idr0 = metadata[m_idx][CS_ETMV4_TRCIDR0];
+	t_params[t_idx].etmv4.reg_idr1 = metadata[m_idx][CS_ETMV4_TRCIDR1];
+	t_params[t_idx].etmv4.reg_idr2 = metadata[m_idx][CS_ETMV4_TRCIDR2];
+	t_params[t_idx].etmv4.reg_idr8 = metadata[m_idx][CS_ETMV4_TRCIDR8];
+	t_params[t_idx].etmv4.reg_configr = metadata[m_idx][CS_ETMV4_TRCCONFIGR];
+	t_params[t_idx].etmv4.reg_traceidr = metadata[m_idx][CS_ETMV4_TRCTRACEIDR];
 }
 
 static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int idx)
+					  struct cs_etm_auxtrace *etm, int t_idx,
+					  int m_idx)
 {
 	u64 **metadata = etm->metadata;
 
-	t_params[idx].protocol = CS_ETM_PROTO_ETE;
-	t_params[idx].ete.reg_idr0 = metadata[idx][CS_ETE_TRCIDR0];
-	t_params[idx].ete.reg_idr1 = metadata[idx][CS_ETE_TRCIDR1];
-	t_params[idx].ete.reg_idr2 = metadata[idx][CS_ETE_TRCIDR2];
-	t_params[idx].ete.reg_idr8 = metadata[idx][CS_ETE_TRCIDR8];
-	t_params[idx].ete.reg_configr = metadata[idx][CS_ETE_TRCCONFIGR];
-	t_params[idx].ete.reg_traceidr = metadata[idx][CS_ETE_TRCTRACEIDR];
-	t_params[idx].ete.reg_devarch = metadata[idx][CS_ETE_TRCDEVARCH];
+	t_params[t_idx].protocol = CS_ETM_PROTO_ETE;
+	t_params[t_idx].ete.reg_idr0 = metadata[m_idx][CS_ETE_TRCIDR0];
+	t_params[t_idx].ete.reg_idr1 = metadata[m_idx][CS_ETE_TRCIDR1];
+	t_params[t_idx].ete.reg_idr2 = metadata[m_idx][CS_ETE_TRCIDR2];
+	t_params[t_idx].ete.reg_idr8 = metadata[m_idx][CS_ETE_TRCIDR8];
+	t_params[t_idx].ete.reg_configr = metadata[m_idx][CS_ETE_TRCCONFIGR];
+	t_params[t_idx].ete.reg_traceidr = metadata[m_idx][CS_ETE_TRCTRACEIDR];
+	t_params[t_idx].ete.reg_devarch = metadata[m_idx][CS_ETE_TRCDEVARCH];
 }
 
 static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
 				     struct cs_etm_auxtrace *etm,
+				     bool formatted,
+				     int sample_cpu,
 				     int decoders)
 {
-	int i;
+	int t_idx, m_idx;
 	u32 etmidr;
 	u64 architecture;
 
-	for (i = 0; i < decoders; i++) {
-		architecture = etm->metadata[i][CS_ETM_MAGIC];
+	for (t_idx = 0; t_idx < decoders; t_idx++) {
+		if (formatted)
+			m_idx = t_idx;
+		else {
+			m_idx = get_cpu_data_idx(etm, sample_cpu);
+			if (m_idx == -1) {
+				pr_warning("CS_ETM: unknown CPU, falling back to first metadata\n");
+				m_idx = 0;
+			}
+		}
+
+		architecture = etm->metadata[m_idx][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);
+			etmidr = etm->metadata[m_idx][CS_ETM_ETMIDR];
+			cs_etm__set_trace_param_etmv3(t_params, etm, t_idx, m_idx, etmidr);
 			break;
 		case __perf_cs_etmv4_magic:
-			cs_etm__set_trace_param_etmv4(t_params, etm, i);
+			cs_etm__set_trace_param_etmv4(t_params, etm, t_idx, m_idx);
 			break;
 		case __perf_cs_ete_magic:
-			cs_etm__set_trace_param_ete(t_params, etm, i);
+			cs_etm__set_trace_param_ete(t_params, etm, t_idx, m_idx);
 			break;
 		default:
 			return -EINVAL;
@@ -1026,7 +1039,7 @@ out:
 }
 
 static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
-						bool formatted)
+						bool formatted, int sample_cpu)
 {
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params  *t_params = NULL;
@@ -1051,7 +1064,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	if (!t_params)
 		goto out_free;
 
-	if (cs_etm__init_trace_params(t_params, etm, decoders))
+	if (cs_etm__init_trace_params(t_params, etm, formatted, sample_cpu, decoders))
 		goto out_free;
 
 	/* Set decoder parameters to decode trace packets */
@@ -1091,14 +1104,15 @@ out_free:
 static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_queue *queue,
 			       unsigned int queue_nr,
-			       bool formatted)
+			       bool formatted,
+			       int sample_cpu)
 {
 	struct cs_etm_queue *etmq = queue->priv;
 
 	if (list_empty(&queue->head) || etmq)
 		return 0;
 
-	etmq = cs_etm__alloc_queue(etm, formatted);
+	etmq = cs_etm__alloc_queue(etm, formatted, sample_cpu);
 
 	if (!etmq)
 		return -ENOMEM;
@@ -2826,7 +2840,7 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
 		 * formatted in piped mode (true).
 		 */
 		err = cs_etm__setup_queue(etm, &etm->queues.queue_array[idx],
-					  idx, true);
+					  idx, true, -1);
 		if (err)
 			return err;
 
@@ -3032,7 +3046,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
 		idx = auxtrace_event->idx;
 		formatted = !(aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW);
 		return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx],
-					   idx, formatted);
+					   idx, formatted, sample->cpu);
 	}
 
 	/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
@@ -3332,12 +3346,27 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->metadata = metadata;
 	etm->auxtrace_type = auxtrace_info->type;
 
-	/* Use virtual timestamps if all ETMs report ts_source = 1 */
-	etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
+	if (etm->synth_opts.use_timestamp)
+		/*
+		 * Prior to Armv8.4, Arm CPUs don't support FEAT_TRF feature,
+		 * therefore the decoder cannot know if the timestamp trace is
+		 * same with the kernel time.
+		 *
+		 * If a user has knowledge for the working platform and can
+		 * specify itrace option 'T' to tell decoder to forcely use the
+		 * traced timestamp as the kernel time.
+		 */
+		etm->has_virtual_ts = true;
+	else
+		/* Use virtual timestamps if all ETMs report ts_source = 1 */
+		etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu);
 
 	if (!etm->has_virtual_ts)
 		ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n"
-			    "The time field of the samples will not be set accurately.\n\n");
+			    "The time field of the samples will not be set accurately.\n"
+			    "For Arm CPUs prior to Armv8.4 or without support FEAT_TRF,\n"
+			    "you can specify the itrace option 'T' for timestamp decoding\n"
+			    "if the Coresight timestamp on the platform is same with the kernel time.\n\n");
 
 	etm->auxtrace.process_event = cs_etm__process_event;
 	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 7cca37887917..4696267a32f0 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -242,7 +242,7 @@ struct cs_etm_packet_queue {
 
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
-struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu);
+void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr);
 
 enum cs_etm_pid_fmt {
 	CS_ETM_PIDFMT_NONE,
diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
index 5bb3c2ba95ca..09d57efd2d9d 100644
--- a/tools/perf/util/data-convert-json.c
+++ b/tools/perf/util/data-convert-json.c
@@ -284,7 +284,9 @@ static void output_headers(struct perf_session *session, struct convert_json *c)
 	output_json_key_string(out, true, 2, "os-release", header->env.os_release);
 	output_json_key_string(out, true, 2, "arch", header->env.arch);
 
-	output_json_key_string(out, true, 2, "cpu-desc", header->env.cpu_desc);
+	if (header->env.cpu_desc)
+		output_json_key_string(out, true, 2, "cpu-desc", header->env.cpu_desc);
+
 	output_json_key_string(out, true, 2, "cpuid", header->env.cpuid);
 	output_json_key_format(out, true, 2, "nrcpus-online", "%u", header->env.nr_cpus_online);
 	output_json_key_format(out, true, 2, "nrcpus-avail", "%u", header->env.nr_cpus_avail);
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index fc16299c915f..08c4bfbd817f 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -17,6 +17,7 @@
 #include "util.h" // rm_rf_perf_data()
 #include "debug.h"
 #include "header.h"
+#include "rlimit.h"
 #include <internal/lib.h>
 
 static void close_dir(struct perf_data_file *files, int nr)
@@ -35,6 +36,7 @@ void perf_data__close_dir(struct perf_data *data)
 
 int perf_data__create_dir(struct perf_data *data, int nr)
 {
+	enum rlimit_action set_rlimit = NO_CHANGE;
 	struct perf_data_file *files = NULL;
 	int i, ret;
 
@@ -54,11 +56,21 @@ int perf_data__create_dir(struct perf_data *data, int nr)
 			goto out_err;
 		}
 
+retry_open:
 		ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
 		if (ret < 0) {
+			/*
+			 * If using parallel threads to collect data,
+			 * perf record needs at least 6 fds per CPU.
+			 * When we run out of them try to increase the limits.
+			 */
+			if (errno == EMFILE && rlimit__increase_nofile(&set_rlimit))
+				goto retry_open;
+
 			ret = -errno;
 			goto out_err;
 		}
+		set_rlimit = NO_CHANGE;
 
 		file->fd = ret;
 	}
@@ -401,7 +413,7 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 }
 
 ssize_t perf_data__write(struct perf_data *data,
-			      void *buf, size_t size)
+			 void *buf, size_t size)
 {
 	if (data->use_stdio) {
 		if (fwrite(buf, size, 1, data->file.fptr) == 1)
@@ -412,14 +424,12 @@ ssize_t perf_data__write(struct perf_data *data,
 }
 
 int perf_data__switch(struct perf_data *data,
-			   const char *postfix,
-			   size_t pos, bool at_exit,
-			   char **new_filepath)
+		      const char *postfix,
+		      size_t pos, bool at_exit,
+		      char **new_filepath)
 {
 	int ret;
 
-	if (check_pipe(data))
-		return -EINVAL;
 	if (perf_data__is_read(data))
 		return -EINVAL;
 
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index effcc195d7e9..110f3ebde30f 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -80,7 +80,7 @@ int perf_data__open(struct perf_data *data);
 void perf_data__close(struct perf_data *data);
 ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size);
 ssize_t perf_data__write(struct perf_data *data,
-			      void *buf, size_t size);
+			 void *buf, size_t size);
 ssize_t perf_data_file__write(struct perf_data_file *file,
 			      void *buf, size_t size);
 /*
@@ -91,8 +91,8 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
  * Return value is fd of new output.
  */
 int perf_data__switch(struct perf_data *data,
-			   const char *postfix,
-			   size_t pos, bool at_exit, char **new_filepath);
+		      const char *postfix,
+		      size_t pos, bool at_exit, char **new_filepath);
 
 int perf_data__create_dir(struct perf_data *data, int nr);
 int perf_data__open_dir(struct perf_data *data);
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b9fb71ab7a73..106429155c2e 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -253,8 +253,8 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		 */
 		addr_location__init(&al);
 		al.sym = node->ms.sym;
-		al.map = node->ms.map;
-		al.maps = thread__maps(thread);
+		al.map = map__get(node->ms.map);
+		al.maps = maps__get(thread__maps(thread));
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 88378c4c5dd9..c39ee0fcb8cf 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -33,17 +33,27 @@
 #endif
 
 int verbose;
+int debug_kmaps;
 int debug_peo_args;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
-static FILE *debug_file;
+static FILE *_debug_file;
 bool debug_display_time;
 
+FILE *debug_file(void)
+{
+	if (!_debug_file) {
+		pr_warning_once("debug_file not set");
+		debug_set_file(stderr);
+	}
+	return _debug_file;
+}
+
 void debug_set_file(FILE *file)
 {
-	debug_file = file;
+	_debug_file = file;
 }
 
 void debug_set_display_time(bool set)
@@ -78,8 +88,8 @@ int veprintf(int level, int var, const char *fmt, va_list args)
 		if (use_browser >= 1 && !redirect_to_stderr) {
 			ui_helpline__vshow(fmt, args);
 		} else {
-			ret = fprintf_time(debug_file);
-			ret += vfprintf(debug_file, fmt, args);
+			ret = fprintf_time(debug_file());
+			ret += vfprintf(debug_file(), fmt, args);
 		}
 	}
 
@@ -107,9 +117,8 @@ static int veprintf_time(u64 t, const char *fmt, va_list args)
 	nsecs -= secs  * NSEC_PER_SEC;
 	usecs  = nsecs / NSEC_PER_USEC;
 
-	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
-		      secs, usecs);
-	ret += vfprintf(stderr, fmt, args);
+	ret = fprintf(debug_file(), "[%13" PRIu64 ".%06" PRIu64 "] ", secs, usecs);
+	ret += vfprintf(debug_file(), fmt, args);
 	return ret;
 }
 
@@ -221,6 +230,7 @@ static struct sublevel_option debug_opts[] = {
 	{ .name = "stderr",		.value_ptr = &redirect_to_stderr},
 	{ .name = "data-convert",	.value_ptr = &debug_data_convert },
 	{ .name = "perf-event-open",	.value_ptr = &debug_peo_args },
+	{ .name = "kmaps",		.value_ptr = &debug_kmaps },
 	{ .name = NULL, }
 };
 
@@ -259,6 +269,7 @@ int perf_quiet_option(void)
 	/* For debug variables that are used as bool types, set to 0. */
 	redirect_to_stderr = 0;
 	debug_peo_args = 0;
+	debug_kmaps = 0;
 
 	return 0;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index f99468a7f681..35a7a5ae762e 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 
 extern int verbose;
+extern int debug_kmaps;
 extern int debug_peo_args;
 extern bool quiet, dump_trace;
 extern int debug_ordered_events;
@@ -77,6 +78,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5)
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+FILE *debug_file(void);
 void debug_set_file(FILE *file);
 void debug_set_display_time(bool set);
 void perf_debug_setup(void);
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
new file mode 100644
index 000000000000..19acf4775d35
--- /dev/null
+++ b/tools/perf/util/debuginfo.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DWARF debug information handling code.  Copied from probe-finder.c.
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/zalloc.h>
+
+#include "build-id.h"
+#include "dso.h"
+#include "debug.h"
+#include "debuginfo.h"
+#include "symbol.h"
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
+/* Dwarf FL wrappers */
+static char *debuginfo_path;	/* Currently dummy */
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.section_address = dwfl_offline_section_address,
+
+	/* We use this table for core files too.  */
+	.find_elf = dwfl_build_id_find_elf,
+};
+
+/* Get a Dwarf from offline image */
+static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
+					 const char *path)
+{
+	GElf_Addr dummy;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	dbg->dwfl = dwfl_begin(&offline_callbacks);
+	if (!dbg->dwfl)
+		goto error;
+
+	dwfl_report_begin(dbg->dwfl);
+	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
+	if (!dbg->mod)
+		goto error;
+
+	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
+	if (!dbg->dbg)
+		goto error;
+
+	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
+
+	dwfl_report_end(dbg->dwfl, NULL, NULL);
+
+	return 0;
+error:
+	if (dbg->dwfl)
+		dwfl_end(dbg->dwfl);
+	else
+		close(fd);
+	memset(dbg, 0, sizeof(*dbg));
+
+	return -ENOENT;
+}
+
+static struct debuginfo *__debuginfo__new(const char *path)
+{
+	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	if (!dbg)
+		return NULL;
+
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
+	return dbg;
+}
+
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
+
+struct debuginfo *debuginfo__new(const char *path)
+{
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+	struct build_id bid;
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
+
+	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
+	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
+		dso__set_build_id(dso, &bid);
+
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__put(dso);
+
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
+}
+
+void debuginfo__delete(struct debuginfo *dbg)
+{
+	if (dbg) {
+		if (dbg->dwfl)
+			dwfl_end(dbg->dwfl);
+		free(dbg);
+	}
+}
+
+/* For the kernel module, we need a special code to get a DIE */
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
+{
+	int n, i;
+	Elf32_Word shndx;
+	Elf_Scn *scn;
+	Elf *elf;
+	GElf_Shdr mem, *shdr;
+	const char *p;
+
+	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
+	if (!elf)
+		return -EINVAL;
+
+	/* Get the number of relocations */
+	n = dwfl_module_relocations(dbg->mod);
+	if (n < 0)
+		return -ENOENT;
+	/* Search the relocation related .text section */
+	for (i = 0; i < n; i++) {
+		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
+		if (strcmp(p, ".text") == 0) {
+			/* OK, get the section header */
+			scn = elf_getscn(elf, shndx);
+			if (!scn)
+				return -ENOENT;
+			shdr = gelf_getshdr(scn, &mem);
+			if (!shdr)
+				return -ENOENT;
+			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
+		}
+	}
+	return 0;
+}
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path,
+			       const char *sbuild_id, char **new_path)
+{
+	debuginfod_client *c = debuginfod_begin();
+	const char *p = raw_path;
+	int fd;
+
+	if (!c)
+		return -ENOMEM;
+
+	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
+				0, p, new_path);
+	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
+	if (fd >= 0)
+		close(fd);
+	debuginfod_end(c);
+	if (fd < 0) {
+		pr_debug("Failed to find %s in debuginfod (%s)\n",
+			raw_path, sbuild_id);
+		return -ENOENT;
+	}
+	pr_debug("Got a source %s\n", *new_path);
+
+	return 0;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
diff --git a/tools/perf/util/debuginfo.h b/tools/perf/util/debuginfo.h
new file mode 100644
index 000000000000..4d65b8c605fc
--- /dev/null
+++ b/tools/perf/util/debuginfo.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PERF_DEBUGINFO_H
+#define _PERF_DEBUGINFO_H
+
+#include <errno.h>
+#include <linux/compiler.h>
+
+#ifdef HAVE_DWARF_SUPPORT
+
+#include "dwarf-aux.h"
+
+/* debug information structure */
+struct debuginfo {
+	Dwarf		*dbg;
+	Dwfl_Module	*mod;
+	Dwfl		*dwfl;
+	Dwarf_Addr	bias;
+	const unsigned char	*build_id;
+};
+
+/* This also tries to open distro debuginfo */
+struct debuginfo *debuginfo__new(const char *path);
+void debuginfo__delete(struct debuginfo *dbg);
+
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+			       bool adjust_offset);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+/* dummy debug information structure */
+struct debuginfo {
+};
+
+static inline struct debuginfo *debuginfo__new(const char *path __maybe_unused)
+{
+	return NULL;
+}
+
+static inline void debuginfo__delete(struct debuginfo *dbg __maybe_unused)
+{
+}
+
+static inline int debuginfo__get_text_offset(struct debuginfo *dbg __maybe_unused,
+					     Dwarf_Addr *offs __maybe_unused,
+					     bool adjust_offset __maybe_unused)
+{
+	return -EINVAL;
+}
+
+#endif /* HAVE_DWARF_SUPPORT */
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path, const char *sbuild_id,
+			       char **new_path);
+#else /* HAVE_DEBUGINFOD_SUPPORT */
+static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
+					     const char *sbuild_id __maybe_unused,
+					     char **new_path __maybe_unused)
+{
+	return -ENOTSUP;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */
+
+#endif /* _PERF_DEBUGINFO_H */
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 46f74b2344db..908e16813722 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -10,6 +10,8 @@
 #include <subcmd/exec-cmd.h>
 #include <linux/zalloc.h>
 #include <linux/build_bug.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
 
 #include "debug.h"
 #include "event.h"
@@ -50,8 +52,10 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
 		d_al->sym_end = sym->end;
 		if (al->addr < sym->end)
 			d_al->symoff = al->addr - sym->start;
-		else
+		else if (al->map)
 			d_al->symoff = al->addr - map__start(al->map) - sym->start;
+		else
+			d_al->symoff = 0;
 		d_al->sym_binding = sym->binding;
 	} else {
 		d_al->sym = NULL;
@@ -63,6 +67,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
 	d_al->addr = al->addr;
 	d_al->comm = NULL;
 	d_al->filtered = 0;
+	d_al->priv = NULL;
 }
 
 static struct addr_location *get_al(struct dlfilter *d)
@@ -151,6 +156,11 @@ static char **dlfilter__args(void *ctx, int *dlargc)
 	return d->dlargv;
 }
 
+static bool has_priv(struct perf_dlfilter_al *d_al_p)
+{
+	return d_al_p->size >= offsetof(struct perf_dlfilter_al, priv) + sizeof(d_al_p->priv);
+}
+
 static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlfilter_al *d_al_p)
 {
 	struct dlfilter *d = (struct dlfilter *)ctx;
@@ -166,6 +176,7 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
 	if (!thread)
 		return -1;
 
+	addr_location__init(&al);
 	thread__find_symbol_fb(thread, d->sample->cpumode, address, &al);
 
 	al_to_d_al(&al, &d_al);
@@ -176,9 +187,31 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
 	memcpy(d_al_p, &d_al, min((size_t)sz, sizeof(d_al)));
 	d_al_p->size = sz;
 
+	if (has_priv(d_al_p))
+		d_al_p->priv = memdup(&al, sizeof(al));
+	else /* Avoid leak for v0 API */
+		addr_location__exit(&al);
+
 	return 0;
 }
 
+static void dlfilter__al_cleanup(void *ctx __maybe_unused, struct perf_dlfilter_al *d_al_p)
+{
+	struct addr_location *al;
+
+	/* Ensure backward compatibility */
+	if (!has_priv(d_al_p) || !d_al_p->priv)
+		return;
+
+	al = d_al_p->priv;
+
+	d_al_p->priv = NULL;
+
+	addr_location__exit(al);
+
+	free(al);
+}
+
 static const __u8 *dlfilter__insn(void *ctx, __u32 *len)
 {
 	struct dlfilter *d = (struct dlfilter *)ctx;
@@ -251,13 +284,21 @@ static struct perf_event_attr *dlfilter__attr(void *ctx)
 	return &d->evsel->core.attr;
 }
 
+static __s32 code_read(__u64 ip, struct map *map, struct machine *machine, void *buf, __u32 len)
+{
+	u64 offset = map__map_ip(map, ip);
+
+	if (ip + len >= map__end(map))
+		len = map__end(map) - ip;
+
+	return dso__data_read_offset(map__dso(map), machine, offset, buf, len);
+}
+
 static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len)
 {
 	struct dlfilter *d = (struct dlfilter *)ctx;
 	struct addr_location *al;
 	struct addr_location a;
-	struct map *map;
-	u64 offset;
 	__s32 ret;
 
 	if (!d->ctx_valid)
@@ -267,27 +308,17 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len)
 	if (!al)
 		return -1;
 
-	map = al->map;
-
-	if (map && ip >= map__start(map) && ip < map__end(map) &&
+	if (al->map && ip >= map__start(al->map) && ip < map__end(al->map) &&
 	    machine__kernel_ip(d->machine, ip) == machine__kernel_ip(d->machine, d->sample->ip))
-		goto have_map;
+		return code_read(ip, al->map, d->machine, buf, len);
 
 	addr_location__init(&a);
+
 	thread__find_map_fb(al->thread, d->sample->cpumode, ip, &a);
-	if (!a.map) {
-		ret = -1;
-		goto out;
-	}
+	ret = a.map ? code_read(ip, a.map, d->machine, buf, len) : -1;
 
-	map = a.map;
-have_map:
-	offset = map__map_ip(map, ip);
-	if (ip + len >= map__end(map))
-		len = map__end(map) - ip;
-	ret = dso__data_read_offset(map__dso(map), d->machine, offset, buf, len);
-out:
 	addr_location__exit(&a);
+
 	return ret;
 }
 
@@ -296,6 +327,7 @@ static const struct perf_dlfilter_fns perf_dlfilter_fns = {
 	.resolve_addr    = dlfilter__resolve_addr,
 	.args            = dlfilter__args,
 	.resolve_address = dlfilter__resolve_address,
+	.al_cleanup      = dlfilter__al_cleanup,
 	.insn            = dlfilter__insn,
 	.srcline         = dlfilter__srcline,
 	.attr            = dlfilter__attr,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index bdfead36b83a..22fd5fa806ed 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -31,6 +31,7 @@
 #include "debug.h"
 #include "string2.h"
 #include "vdso.h"
+#include "annotate-data.h"
 
 static const char * const debuglink_paths[] = {
 	"%.0s%s",
@@ -477,6 +478,7 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m,
 		dso->comp = m->comp;
 	}
 
+	dso->is_kmod = 1;
 	dso__set_short_name(dso, strdup(m->name), true);
 }
 
@@ -1326,6 +1328,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
+		dso->data_types = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1338,6 +1341,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->has_srcline = 1;
 		dso->a2l_fails = 1;
 		dso->kernel = DSO_SPACE__USER;
+		dso->is_kmod = 0;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		dso->comp = COMP_ID__NONE;
 		RB_CLEAR_NODE(&dso->rb_node);
@@ -1368,6 +1372,8 @@ void dso__delete(struct dso *dso)
 	symbols__delete(&dso->symbols);
 	dso->symbol_names_len = 0;
 	zfree(&dso->symbol_names);
+	annotated_data_type__tree_delete(&dso->data_types);
+
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
 		dso->short_name_allocated = false;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b41c9782c754..ce9f3849a773 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -154,6 +154,8 @@ struct dso {
 	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
+	struct rb_root	data_types;
+
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
@@ -162,6 +164,7 @@ struct dso {
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
 	enum dso_space_type	kernel;
+	bool			is_kmod;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
 	enum dso_binary_type	binary_type;
@@ -181,6 +184,7 @@ struct dso {
 	u8		 rel;
 	struct build_id	 bid;
 	u64		 text_offset;
+	u64		 text_end;
 	const char	 *short_name;
 	const char	 *long_name;
 	u16		 long_name_len;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2941d88f2199..2791126069b4 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -1051,32 +1051,28 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 }
 
 /**
- * die_get_typename - Get the name of given variable DIE
- * @vr_die: a variable DIE
+ * die_get_typename_from_type - Get the name of given type DIE
+ * @type_die: a type DIE
  * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * Get the name of @type_die and stores it to @buf. Return 0 if succeeded.
  * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf)
 {
-	Dwarf_Die type;
 	int tag, ret;
 	const char *tmp = "";
 
-	if (__die_get_real_type(vr_die, &type) == NULL)
-		return -ENOENT;
-
-	tag = dwarf_tag(&type);
+	tag = dwarf_tag(type_die);
 	if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
 		return strbuf_add(buf, "(function_type)", 15);
 	} else {
-		const char *name = dwarf_diename(&type);
+		const char *name = dwarf_diename(type_die);
 
 		if (tag == DW_TAG_union_type)
 			tmp = "union ";
@@ -1089,8 +1085,35 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 		/* Write a base name */
 		return strbuf_addf(buf, "%s%s", tmp, name ?: "");
 	}
-	ret = die_get_typename(&type, buf);
-	return ret ? ret : strbuf_addstr(buf, tmp);
+	ret = die_get_typename(type_die, buf);
+	if (ret < 0) {
+		/* void pointer has no type attribute */
+		if (tag == DW_TAG_pointer_type && ret == -ENOENT)
+			return strbuf_addf(buf, "void*");
+
+		return ret;
+	}
+	return strbuf_addstr(buf, tmp);
+}
+
+/**
+ * die_get_typename - Get the name of given variable DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for result type name
+ *
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
+ * Note that the result will stores typedef name if possible, and stores
+ * "*(function_type)" if the type is a function pointer.
+ */
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	Dwarf_Die type;
+
+	if (__die_get_real_type(vr_die, &type) == NULL)
+		return -ENOENT;
+
+	return die_get_typename_from_type(&type, buf);
 }
 
 /**
@@ -1238,14 +1261,292 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 out:
 	return ret;
 }
-#else
-int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
-		      Dwarf_Die *vr_die __maybe_unused,
-		      struct strbuf *buf __maybe_unused)
+
+/* Interval parameters for __die_find_var_reg_cb() */
+struct find_var_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Target memory address (for global data) */
+	Dwarf_Addr addr;
+	/* Target register */
+	unsigned reg;
+	/* Access offset, set for global data */
+	int offset;
+	/* True if the current register is the frame base */
+	bool is_fbreg;
+};
+
+/* Max number of registers DW_OP_regN supports */
+#define DWARF_OP_DIRECT_REGS  32
+
+static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
+			     u64 addr_offset, u64 addr_type)
+{
+	Dwarf_Die type_die;
+	Dwarf_Word size;
+
+	if (addr_offset == addr_type) {
+		/* Update offset relative to the start of the variable */
+		data->offset = 0;
+		return true;
+	}
+
+	if (die_get_real_type(die_mem, &type_die) == NULL)
+		return false;
+
+	if (dwarf_aggregate_size(&type_die, &size) < 0)
+		return false;
+
+	if (addr_offset >= addr_type + size)
+		return false;
+
+	/* Update offset relative to the start of the variable */
+	data->offset = addr_offset - addr_type;
+	return true;
+}
+
+static bool check_allowed_ops(Dwarf_Op *ops, size_t nops)
 {
-	return -ENOTSUP;
+	/* The first op is checked separately */
+	ops++;
+	nops--;
+
+	/*
+	 * It needs to make sure if the location expression matches to the given
+	 * register and offset exactly.  Thus it rejects any complex expressions
+	 * and only allows a few of selected operators that doesn't change the
+	 * location.
+	 */
+	while (nops) {
+		switch (ops->atom) {
+		case DW_OP_stack_value:
+		case DW_OP_deref_size:
+		case DW_OP_deref:
+		case DW_OP_piece:
+			break;
+		default:
+			return false;
+		}
+		ops++;
+		nops--;
+	}
+	return true;
 }
-#endif
+
+/* Only checks direct child DIEs in the given scope. */
+static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		/* Assuming the location list is sorted by address */
+		if (end < data->pc)
+			continue;
+		if (start > data->pc)
+			break;
+
+		/* Local variables accessed using frame base register */
+		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
+		    data->offset >= (int)ops->number &&
+		    check_allowed_ops(ops, nops) &&
+		    match_var_offset(die_mem, data, data->offset, ops->number))
+			return DIE_FIND_CB_END;
+
+		/* Only match with a simple case */
+		if (data->reg < DWARF_OP_DIRECT_REGS) {
+			/* pointer variables saved in a register 0 to 31 */
+			if (ops->atom == (DW_OP_reg0 + data->reg) &&
+			    check_allowed_ops(ops, nops))
+				return DIE_FIND_CB_END;
+
+			/* Local variables accessed by a register + offset */
+			if (ops->atom == (DW_OP_breg0 + data->reg) &&
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, ops->number))
+				return DIE_FIND_CB_END;
+		} else {
+			/* pointer variables saved in a register 32 or above */
+			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
+			    check_allowed_ops(ops, nops))
+				return DIE_FIND_CB_END;
+
+			/* Local variables accessed by a register + offset */
+			if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, ops->number2))
+				return DIE_FIND_CB_END;
+		}
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_reg - Find a variable saved in a register
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @reg: the register number to find
+ * @poffset: pointer to offset, will be updated for fbreg case
+ * @is_fbreg: boolean value if the current register is the frame base
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * Find the variable DIE accessed by the given register.  It'll update the @offset
+ * when the variable is in the stack.
+ */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    int *poffset, bool is_fbreg,
+				    Dwarf_Die *die_mem)
+{
+	struct find_var_data data = {
+		.pc = pc,
+		.reg = reg,
+		.offset = *poffset,
+		.is_fbreg = is_fbreg,
+	};
+	Dwarf_Die *result;
+
+	result = die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem);
+	if (result)
+		*poffset = data.offset;
+	return result;
+}
+
+/* Only checks direct child DIEs in the given scope */
+static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_var_data *data = arg;
+	int tag = dwarf_tag(die_mem);
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (tag != DW_TAG_variable)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		if (ops->atom != DW_OP_addr)
+			continue;
+
+		if (data->addr < ops->number)
+			continue;
+
+		if (check_allowed_ops(ops, nops) &&
+		    match_var_offset(die_mem, data, data->addr, ops->number))
+			return DIE_FIND_CB_END;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_variable_by_addr - Find variable located at given address
+ * @sc_die: a scope DIE
+ * @pc: the program address to find
+ * @addr: the data address to find
+ * @die_mem: a buffer to save the resulting DIE
+ * @offset: the offset in the resulting type
+ *
+ * Find the variable DIE located at the given address (in PC-relative mode).
+ * This is usually for global variables.
+ */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset)
+{
+	struct find_var_data data = {
+		.pc = pc,
+		.addr = addr,
+	};
+	Dwarf_Die *result;
+
+	result = die_find_child(sc_die, __die_find_var_addr_cb, &data, die_mem);
+	if (result)
+		*offset = data.offset;
+	return result;
+}
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+#ifdef HAVE_DWARF_CFI_SUPPORT
+static int reg_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+		return op->atom - DW_OP_reg0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->atom - DW_OP_breg0;
+	case DW_OP_regx:
+	case DW_OP_bregx:
+		return op->number;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static int offset_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+	case DW_OP_regx:
+		return 0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->number;
+	case DW_OP_bregx:
+		return op->number2;
+	default:
+		break;
+	}
+	return -1;
+}
+
+/**
+ * die_get_cfa - Get frame base information
+ * @dwarf: a Dwarf info
+ * @pc: program address
+ * @preg: pointer for saved register
+ * @poffset: pointer for saved offset
+ *
+ * This function gets register and offset for CFA (Canonical Frame Address)
+ * by searching the CIE/FDE info.  The CFA usually points to the start address
+ * of the current stack frame and local variables can be located using an offset
+ * from the CFA.  The @preg and @poffset will be updated if it returns 0.
+ */
+int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset)
+{
+	Dwarf_CFI *cfi;
+	Dwarf_Frame *frame = NULL;
+	Dwarf_Op *ops = NULL;
+	size_t nops;
+
+	cfi = dwarf_getcfi(dwarf);
+	if (cfi == NULL)
+		return -1;
+
+	if (!dwarf_cfi_addrframe(cfi, pc, &frame) &&
+	    !dwarf_frame_cfa(frame, &ops, &nops) &&
+	    check_allowed_ops(ops, nops)) {
+		*preg = reg_from_dwarf_op(ops);
+		*poffset = offset_from_dwarf_op(ops);
+		return 0;
+	}
+	return -1;
+}
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 /*
  * die_has_loclist - Check if DW_AT_location of @vr_die is a location list
@@ -1425,3 +1726,56 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 
 	*entrypc = postprologue_addr;
 }
+
+/* Internal parameters for __die_find_scope_cb() */
+struct find_scope_data {
+	/* Target instruction address */
+	Dwarf_Addr pc;
+	/* Number of scopes found [output] */
+	int nr;
+	/* Array of scopes found, 0 for the outermost one. [output] */
+	Dwarf_Die *scopes;
+};
+
+static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg)
+{
+	struct find_scope_data *data = arg;
+
+	if (dwarf_haspc(die_mem, data->pc)) {
+		Dwarf_Die *tmp;
+
+		tmp = realloc(data->scopes, (data->nr + 1) * sizeof(*tmp));
+		if (tmp == NULL)
+			return DIE_FIND_CB_END;
+
+		memcpy(tmp + data->nr, die_mem, sizeof(*die_mem));
+		data->scopes = tmp;
+		data->nr++;
+		return DIE_FIND_CB_CHILD;
+	}
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_scopes - Return a list of scopes including the address
+ * @cu_die: a compile unit DIE
+ * @pc: the address to find
+ * @scopes: the array of DIEs for scopes (result)
+ *
+ * This function does the same as the dwarf_getscopes() but doesn't follow
+ * the origins of inlined functions.  It returns the number of scopes saved
+ * in the @scopes argument.  The outer scope will be saved first (index 0) and
+ * the last one is the innermost scope at the @pc.
+ */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
+{
+	struct find_scope_data data = {
+		.pc = pc,
+	};
+	Dwarf_Die die_mem;
+
+	die_find_child(cu_die, __die_find_scope_cb, &data, &die_mem);
+
+	*scopes = data.scopes;
+	return data.nr;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 7ec8bc1083bb..85dd527ae1f7 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -116,12 +116,14 @@ Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
 Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 			   Dwarf_Die *die_mem);
 
+/* Get the name of given type DIE */
+int die_get_typename_from_type(Dwarf_Die *type_die, struct strbuf *buf);
+
 /* Get the name of given variable DIE */
 int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
 int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
-int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Check if target program is compiled with optimization */
 bool die_is_optimized_target(Dwarf_Die *cu_die);
@@ -130,4 +132,67 @@ bool die_is_optimized_target(Dwarf_Die *cu_die);
 void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 		       Dwarf_Addr *entrypc);
 
-#endif
+/* Get the list of including scopes */
+int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
+
+#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
+
+/* Get byte offset range of given variable DIE */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf);
+
+/* Find a variable saved in the 'reg' at given address */
+Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
+				    int *poffset, bool is_fbreg,
+				    Dwarf_Die *die_mem);
+
+/* Find a (global) variable located in the 'addr' */
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
+				     Dwarf_Addr addr, Dwarf_Die *die_mem,
+				     int *offset);
+
+#else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused,
+				    Dwarf_Die *vr_die __maybe_unused,
+				    struct strbuf *buf __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused,
+						  Dwarf_Addr pc __maybe_unused,
+						  int reg __maybe_unused,
+						  int *poffset __maybe_unused,
+						  bool is_fbreg __maybe_unused,
+						  Dwarf_Die *die_mem __maybe_unused)
+{
+	return NULL;
+}
+
+static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
+						   Dwarf_Addr pc __maybe_unused,
+						   Dwarf_Addr addr __maybe_unused,
+						   Dwarf_Die *die_mem __maybe_unused,
+						   int *offset __maybe_unused)
+{
+	return NULL;
+}
+
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
+
+#ifdef HAVE_DWARF_CFI_SUPPORT
+
+/* Get the frame base information from CFA */
+int die_get_cfa(Dwarf *dwarf, u64 pc, int *preg, int *poffset);
+
+#else /* HAVE_DWARF_CFI_SUPPORT */
+
+static inline int die_get_cfa(Dwarf *dwarf __maybe_unused, u64 pc __maybe_unused,
+			      int *preg __maybe_unused, int *poffset __maybe_unused)
+{
+	return -1;
+}
+
+#endif /* HAVE_DWARF_CFI_SUPPORT */
+
+#endif /* _DWARF_AUX_H */
diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c
index 69cfaa5953bf..5b7f86c0063f 100644
--- a/tools/perf/util/dwarf-regs.c
+++ b/tools/perf/util/dwarf-regs.c
@@ -5,9 +5,12 @@
  * Written by: Masami Hiramatsu <mhiramat@kernel.org>
  */
 
+#include <stdlib.h>
+#include <string.h>
 #include <debug.h>
 #include <dwarf-regs.h>
 #include <elf.h>
+#include <errno.h>
 #include <linux/kernel.h>
 
 #ifndef EM_AARCH64
@@ -68,3 +71,34 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine)
 	}
 	return NULL;
 }
+
+__weak int get_arch_regnum(const char *name __maybe_unused)
+{
+	return -ENOTSUP;
+}
+
+/* Return DWARF register number from architecture register name */
+int get_dwarf_regnum(const char *name, unsigned int machine)
+{
+	char *regname = strdup(name);
+	int reg = -1;
+	char *p;
+
+	if (regname == NULL)
+		return -EINVAL;
+
+	/* For convenience, remove trailing characters */
+	p = strpbrk(regname, " ,)");
+	if (p)
+		*p = '\0';
+
+	switch (machine) {
+	case EM_NONE:	/* Generic arch - use host arch */
+		reg = get_arch_regnum(regname);
+		break;
+	default:
+		pr_err("ELF MACHINE %x is not supported.\n", machine);
+	}
+	free(regname);
+	return reg;
+}
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 9eabf3ec56e9..a459374d0a1a 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include "env.h"
 #include "util/header.h"
+#include "linux/compiler.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 #include "cgroup.h"
@@ -12,6 +13,7 @@
 #include <string.h>
 #include "pmus.h"
 #include "strbuf.h"
+#include "trace/beauty/beauty.h"
 
 struct perf_env perf_env;
 
@@ -23,12 +25,18 @@ struct perf_env perf_env;
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node)
 {
+	down_write(&env->bpf_progs.lock);
+	__perf_env__insert_bpf_prog_info(env, info_node);
+	up_write(&env->bpf_progs.lock);
+}
+
+void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
+{
 	__u32 prog_id = info_node->info_linear->info.id;
 	struct bpf_prog_info_node *node;
 	struct rb_node *parent = NULL;
 	struct rb_node **p;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.infos.rb_node;
 
 	while (*p != NULL) {
@@ -40,15 +48,13 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env,
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated bpf prog info %u\n", prog_id);
-			goto out;
+			return;
 		}
 	}
 
 	rb_link_node(&info_node->rb_node, parent, p);
 	rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
 	env->bpf_progs.infos_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
 }
 
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
@@ -78,13 +84,21 @@ out:
 
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 {
+	bool ret;
+
+	down_write(&env->bpf_progs.lock);
+	ret = __perf_env__insert_btf(env, btf_node);
+	up_write(&env->bpf_progs.lock);
+	return ret;
+}
+
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+{
 	struct rb_node *parent = NULL;
 	__u32 btf_id = btf_node->id;
 	struct btf_node *node;
 	struct rb_node **p;
-	bool ret = true;
 
-	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.btfs.rb_node;
 
 	while (*p != NULL) {
@@ -96,25 +110,31 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated btf %u\n", btf_id);
-			ret = false;
-			goto out;
+			return false;
 		}
 	}
 
 	rb_link_node(&btf_node->rb_node, parent, p);
 	rb_insert_color(&btf_node->rb_node, &env->bpf_progs.btfs);
 	env->bpf_progs.btfs_cnt++;
-out:
-	up_write(&env->bpf_progs.lock);
-	return ret;
+	return true;
 }
 
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 {
+	struct btf_node *res;
+
+	down_read(&env->bpf_progs.lock);
+	res = __perf_env__find_btf(env, btf_id);
+	up_read(&env->bpf_progs.lock);
+	return res;
+}
+
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id)
+{
 	struct btf_node *node = NULL;
 	struct rb_node *n;
 
-	down_read(&env->bpf_progs.lock);
 	n = env->bpf_progs.btfs.rb_node;
 
 	while (n) {
@@ -124,13 +144,9 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			goto out;
+			return node;
 	}
-	node = NULL;
-
-out:
-	up_read(&env->bpf_progs.lock);
-	return node;
+	return NULL;
 }
 
 /* purge data in bpf_progs.infos tree */
@@ -324,11 +340,9 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 	u32 pmu_num = 0;
 	struct strbuf sb;
 
-	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
+	while ((pmu = perf_pmus__scan(pmu)))
 		pmu_num++;
-	}
+
 	if (!pmu_num) {
 		pr_debug("pmu mappings not available\n");
 		return -ENOENT;
@@ -339,8 +353,6 @@ int perf_env__read_pmu_mappings(struct perf_env *env)
 		return -ENOMEM;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
 		if (strbuf_addf(&sb, "%u:%s", pmu->type, pmu->name) < 0)
 			goto error;
 		/* include a NULL character at the end */
@@ -457,11 +469,23 @@ const char *perf_env__arch(struct perf_env *env)
 	return normalize_arch(arch_name);
 }
 
+const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused)
+{
+#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT)
+	if (env->arch_strerrno == NULL)
+		env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env));
+
+	return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function";
+#else
+	return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)";
+#endif
+}
+
 const char *perf_env__cpuid(struct perf_env *env)
 {
 	int status;
 
-	if (!env || !env->cpuid) { /* Assume local operation */
+	if (!env->cpuid) { /* Assume local operation */
 		status = perf_env__read_cpuid(env);
 		if (status)
 			return NULL;
@@ -474,7 +498,7 @@ int perf_env__nr_pmu_mappings(struct perf_env *env)
 {
 	int status;
 
-	if (!env || !env->nr_pmu_mappings) { /* Assume local operation */
+	if (!env->nr_pmu_mappings) { /* Assume local operation */
 		status = perf_env__read_pmu_mappings(env);
 		if (status)
 			return 0;
@@ -487,7 +511,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env)
 {
 	int status;
 
-	if (!env || !env->pmu_mappings) { /* Assume local operation */
+	if (!env->pmu_mappings) { /* Assume local operation */
 		status = perf_env__read_pmu_mappings(env);
 		if (status)
 			return NULL;
@@ -535,6 +559,24 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 	return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
 
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name)
+{
+	char *pmu_mapping = env->pmu_mappings, *colon;
+
+	for (int i = 0; i < env->nr_pmu_mappings; ++i) {
+		if (strtoul(pmu_mapping, &colon, 0) == ULONG_MAX || *colon != ':')
+			goto out_error;
+
+		pmu_mapping = colon + 1;
+		if (strcmp(pmu_mapping, pmu_name) == 0)
+			return true;
+
+		pmu_mapping += strlen(pmu_mapping) + 1;
+	}
+out_error:
+	return false;
+}
+
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap)
 {
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 4566c51f2fd9..2a2c37cc40b7 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -12,6 +12,7 @@ struct perf_cpu_map;
 struct cpu_topology_map {
 	int	socket_id;
 	int	die_id;
+	int	cluster_id;
 	int	core_id;
 };
 
@@ -46,10 +47,17 @@ struct hybrid_node {
 struct pmu_caps {
 	int		nr_caps;
 	unsigned int    max_branches;
+	unsigned int	br_cntr_nr;
+	unsigned int	br_cntr_width;
+
 	char            **caps;
 	char            *pmu_name;
 };
 
+typedef const char *(arch_syscalls__strerrno_t)(int err);
+
+arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch);
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -62,6 +70,8 @@ struct perf_env {
 	unsigned long long	total_mem;
 	unsigned int		msr_pmu_type;
 	unsigned int		max_branches;
+	unsigned int		br_cntr_nr;
+	unsigned int		br_cntr_width;
 	int			kernel_is_64_bit;
 
 	int			nr_cmdline;
@@ -130,6 +140,7 @@ struct perf_env {
 		 */
 		bool	enabled;
 	} clock;
+	arch_syscalls__strerrno_t *arch_strerrno;
 };
 
 enum perf_compress_type {
@@ -159,19 +170,26 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__arch_strerrno(struct perf_env *env, int err);
 const char *perf_env__cpuid(struct perf_env *env);
 const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
 void perf_env__init(struct perf_env *env);
+void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
 			     const char *cap);
+
+bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4cbb092e0684..198903157f9e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -93,8 +93,8 @@ struct process_symbol_args {
 	u64	   start;
 };
 
-static int find_symbol_cb(void *arg, const char *name, char type,
-			  u64 start)
+static int find_func_symbol_cb(void *arg, const char *name, char type,
+			       u64 start)
 {
 	struct process_symbol_args *args = arg;
 
@@ -110,12 +110,36 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	return 1;
 }
 
+static int find_any_symbol_cb(void *arg, const char *name,
+			      char type __maybe_unused, u64 start)
+{
+	struct process_symbol_args *args = arg;
+
+	if (strcmp(name, args->name))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr)
 {
 	struct process_symbol_args args = { .name = symbol_name, };
 
-	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+	if (kallsyms__parse(kallsyms_filename, &args, find_func_symbol_cb) <= 0)
+		return -1;
+
+	*addr = args.start;
+	return 0;
+}
+
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_any_symbol_cb) <= 0)
 		return -1;
 
 	*addr = args.start;
@@ -487,7 +511,7 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma
 		struct addr_location al;
 
 		addr_location__init(&al);
-		al.map = map__get(maps__find(machine__kernel_maps(machine), tp->addr));
+		al.map = maps__find(machine__kernel_maps(machine), tp->addr);
 		if (al.map && map__load(al.map) >= 0) {
 			al.addr = map__map_ip(al.map, tp->addr);
 			al.sym = map__find_symbol(al.map, al.addr);
@@ -593,13 +617,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
 		al->level = '.';
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
 		al->level = 'g';
 		maps = machine__kernel_maps(machine);
-		load_map = true;
+		load_map = !symbol_conf.lazy_load_kernel_maps;
 	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
 		al->level = 'u';
 	} else {
@@ -617,7 +641,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 		return NULL;
 	}
 	al->maps = maps__get(maps);
-	al->map = map__get(maps__find(maps, al->addr));
+	al->map = maps__find(maps, al->addr);
 	if (al->map != NULL) {
 		/*
 		 * Kernel maps might be changed when loading symbols so loading
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index de20e01c9d72..d8bcee2e9b93 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -360,6 +360,8 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name, u64 *addr);
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr);
 
 void event_attr_init(struct perf_event_attr *attr);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7ef43f72098e..55a300a0977b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -103,7 +103,14 @@ struct evlist *evlist__new_default(void)
 	err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu");
 	if (err) {
 		evlist__delete(evlist);
-		evlist = NULL;
+		return NULL;
+	}
+
+	if (evlist->core.nr_entries > 1) {
+		struct evsel *evsel;
+
+		evlist__for_each_entry(evlist, evsel)
+			evsel__set_sample_id(evsel, /*can_sample_identifier=*/false);
 	}
 
 	return evlist;
@@ -251,6 +258,9 @@ static struct evsel *evlist__dummy_event(struct evlist *evlist)
 		.type	= PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
+		/* Avoid frequency mode for dummy events to avoid associated timers. */
+		.freq = 0,
+		.sample_period = 1,
 	};
 
 	return evsel__new_idx(&attr, evlist->core.nr_entries);
@@ -277,8 +287,6 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
 	evsel->core.attr.exclude_kernel = 1;
 	evsel->core.attr.exclude_guest = 1;
 	evsel->core.attr.exclude_hv = 1;
-	evsel->core.attr.freq = 0;
-	evsel->core.attr.sample_period = 1;
 	evsel->core.system_wide = system_wide;
 	evsel->no_aux_samples = true;
 	evsel->name = strdup("dummy:u");
@@ -1055,7 +1063,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target)
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		cpus = perf_cpu_map__dummy_new();
+		cpus = perf_cpu_map__new_any_cpu();
 	else
 		cpus = perf_cpu_map__new(target->cpu_list);
 
@@ -1351,7 +1359,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		goto out;
 
@@ -1694,6 +1702,24 @@ void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_ev
 	tracking_evsel->tracking = true;
 }
 
+struct evsel *evlist__findnew_tracking_event(struct evlist *evlist, bool system_wide)
+{
+	struct evsel *evsel;
+
+	evsel = evlist__get_tracking_event(evlist);
+	if (!evsel__is_dummy_event(evsel)) {
+		evsel = evlist__add_aux_dummy(evlist, system_wide);
+		if (!evsel)
+			return NULL;
+
+		evlist__set_tracking_event(evlist, evsel);
+	} else if (system_wide) {
+		perf_evlist__go_system_wide(&evlist->core, &evsel->core);
+	}
+
+	return evsel;
+}
+
 struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str)
 {
 	struct evsel *evsel;
@@ -2499,3 +2525,33 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis
 	}
 	perf_cpu_map__put(user_requested_cpus);
 }
+
+void evlist__uniquify_name(struct evlist *evlist)
+{
+	char *new_name, empty_attributes[2] = ":", *attributes;
+	struct evsel *pos;
+
+	if (perf_pmus__num_core_pmus() == 1)
+		return;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (!evsel__is_hybrid(pos))
+			continue;
+
+		if (strchr(pos->name, '/'))
+			continue;
+
+		attributes = strchr(pos->name, ':');
+		if (attributes)
+			*attributes = '\0';
+		else
+			attributes = empty_attributes;
+
+		if (asprintf(&new_name, "%s/%s/%s", pos->pmu_name, pos->name, attributes + 1)) {
+			free(pos->name);
+			pos->name = new_name;
+		} else {
+			*attributes = ':';
+		}
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 664c6bf7b3e0..cb91dc9117a2 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -387,6 +387,7 @@ bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr);
 
 struct evsel *evlist__get_tracking_event(struct evlist *evlist);
 void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
+struct evsel *evlist__findnew_tracking_event(struct evlist *evlist, bool system_wide);
 
 struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
 
@@ -441,5 +442,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
 int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf);
 void evlist__check_mem_load_aux(struct evlist *evlist);
 void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list);
+void evlist__uniquify_name(struct evlist *evlist);
 
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 762e2b2634a5..3536404e9447 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -49,6 +49,7 @@
 #include "off_cpu.h"
 #include "pmu.h"
 #include "pmus.h"
+#include "rlimit.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include "util/bpf-filter.h"
@@ -845,6 +846,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 {
 	bool function = evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->core.attr;
+	const char *arch = perf_env__arch(evsel__env(evsel));
 
 	evsel__set_sample_bit(evsel, CALLCHAIN);
 
@@ -877,8 +879,9 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 		if (!function) {
 			evsel__set_sample_bit(evsel, REGS_USER);
 			evsel__set_sample_bit(evsel, STACK_USER);
-			if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
-				attr->sample_regs_user |= DWARF_MINIMAL_REGS;
+			if (opts->sample_user_regs &&
+			    DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) {
+				attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch);
 				pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
 					   "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
 					   "so the minimal registers set (IP, SP) is explicitly forced.\n");
@@ -1474,6 +1477,7 @@ void evsel__exit(struct evsel *evsel)
 	perf_thread_map__put(evsel->core.threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
+	zfree(&evsel->filter);
 	zfree(&evsel->pmu_name);
 	zfree(&evsel->group_pmu_name);
 	zfree(&evsel->unit);
@@ -1797,7 +1801,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 	if (cpus == NULL) {
 		if (empty_cpu_map == NULL) {
-			empty_cpu_map = perf_cpu_map__dummy_new();
+			empty_cpu_map = perf_cpu_map__new_any_cpu();
 			if (empty_cpu_map == NULL)
 				return -ENOMEM;
 		}
@@ -1828,6 +1832,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 
 static void evsel__disable_missing_features(struct evsel *evsel)
 {
+	if (perf_missing_features.branch_counters)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS;
 	if (perf_missing_features.read_lost)
 		evsel->core.attr.read_format &= ~PERF_FORMAT_LOST;
 	if (perf_missing_features.weight_struct) {
@@ -1881,7 +1887,12 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.read_lost &&
+	if (!perf_missing_features.branch_counters &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) {
+		perf_missing_features.branch_counters = true;
+		pr_debug2("switching off branch counters support\n");
+		return true;
+	} else if (!perf_missing_features.read_lost &&
 	    (evsel->core.attr.read_format & PERF_FORMAT_LOST)) {
 		perf_missing_features.read_lost = true;
 		pr_debug2("switching off PERF_FORMAT_LOST support\n");
@@ -1986,33 +1997,6 @@ bool evsel__detect_missing_features(struct evsel *evsel)
 	}
 }
 
-bool evsel__increase_rlimit(enum rlimit_action *set_rlimit)
-{
-	int old_errno;
-	struct rlimit l;
-
-	if (*set_rlimit < INCREASED_MAX) {
-		old_errno = errno;
-
-		if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
-			if (*set_rlimit == NO_CHANGE) {
-				l.rlim_cur = l.rlim_max;
-			} else {
-				l.rlim_cur = l.rlim_max + 1000;
-				l.rlim_max = l.rlim_cur;
-			}
-			if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
-				(*set_rlimit) += 1;
-				errno = old_errno;
-				return true;
-			}
-		}
-		errno = old_errno;
-	}
-
-	return false;
-}
-
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
 		int start_cpu_map_idx, int end_cpu_map_idx)
@@ -2140,7 +2124,7 @@ try_fallback:
 	 * perf stat needs between 5 and 22 fds per CPU. When we run out
 	 * of them try to increase the limits.
 	 */
-	if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
+	if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
 		goto retry_open;
 
 	if (err != -EINVAL || idx > 0 || thread > 0)
@@ -2341,6 +2325,22 @@ u64 evsel__bitfield_swap_branch_flags(u64 value)
 	return new_val;
 }
 
+static inline bool evsel__has_branch_counters(const struct evsel *evsel)
+{
+	struct evsel *cur, *leader = evsel__leader(evsel);
+
+	/* The branch counters feature only supports group */
+	if (!leader || !evsel->evlist)
+		return false;
+
+	evlist__for_each_entry(evsel->evlist, cur) {
+		if ((leader == evsel__leader(cur)) &&
+		    (cur->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			return true;
+	}
+	return false;
+}
+
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *data)
 {
@@ -2363,7 +2363,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	data->period = evsel->core.attr.sample_period;
 	data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	data->misc    = event->header.misc;
-	data->id = -1ULL;
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	data->vcpu = -1;
 
@@ -2574,6 +2573,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
+
+		if (evsel__has_branch_counters(evsel)) {
+			OVERFLOW_CHECK_u64(array);
+
+			data->branch_stack_cntr = (u64 *)array;
+			sz = data->branch_stack->nr * sizeof(u64);
+
+			OVERFLOW_CHECK(array, sz, max_size);
+			array = (void *)array + sz;
+		}
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
@@ -2763,6 +2772,11 @@ struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 	return tep_find_field(evsel->tp_format, name);
 }
 
+struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name)
+{
+	return tep_find_common_field(evsel->tp_format, name);
+}
+
 void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
 	struct tep_format_field *field = evsel__field(evsel, name);
@@ -2826,14 +2840,53 @@ u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *n
 {
 	struct tep_format_field *field = evsel__field(evsel, name);
 
-	if (!field)
-		return 0;
+	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
+}
+
+u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const char *name)
+{
+	struct tep_format_field *field = evsel__common_field(evsel, name);
 
 	return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
 }
+
+char evsel__taskstate(struct evsel *evsel, struct perf_sample *sample, const char *name)
+{
+	static struct tep_format_field *prev_state_field;
+	static const char *states;
+	struct tep_format_field *field;
+	unsigned long long val;
+	unsigned int bit;
+	char state = '?'; /* '?' denotes unknown task state */
+
+	field = evsel__field(evsel, name);
+
+	if (!field)
+		return state;
+
+	if (!states || field != prev_state_field) {
+		states = parse_task_states(field);
+		if (!states)
+			return state;
+		prev_state_field = field;
+	}
+
+	/*
+	 * Note since the kernel exposes TASK_REPORT_MAX to userspace
+	 * to denote the 'preempted' state, we might as welll report
+	 * 'R' for this case, which make senses to users as well.
+	 *
+	 * We can change this if we have a good reason in the future.
+	 */
+	val = evsel__intval(evsel, sample, name);
+	bit = val ? ffs(val) : 0;
+	state = (!bit || bit > strlen(states)) ? 'R' : states[bit-1];
+	return state;
+}
 #endif
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize)
 {
 	int paranoid;
 
@@ -2841,18 +2894,19 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize)
 	    evsel->core.attr.type   == PERF_TYPE_HARDWARE &&
 	    evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 		/*
-		 * If it's cycles then fall back to hrtimer based
-		 * cpu-clock-tick sw counter, which is always available even if
-		 * no PMU support.
+		 * If it's cycles then fall back to hrtimer based cpu-clock sw
+		 * counter, which is always available even if no PMU support.
 		 *
 		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
 		 * b0a873e).
 		 */
-		scnprintf(msg, msgsize, "%s",
-"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
-
 		evsel->core.attr.type   = PERF_TYPE_SOFTWARE;
-		evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK;
+		evsel->core.attr.config = target__has_cpu(target)
+			? PERF_COUNT_SW_CPU_CLOCK
+			: PERF_COUNT_SW_TASK_CLOCK;
+		scnprintf(msg, msgsize,
+			"The cycles event is not supported, trying to fall back to %s",
+			target__has_cpu(target) ? "cpu-clock" : "task-clock");
 
 		zfree(&evsel->name);
 		return true;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 848534ec74fa..517cff431de2 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -191,6 +191,7 @@ struct perf_missing_features {
 	bool code_page_size;
 	bool weight_struct;
 	bool read_lost;
+	bool branch_counters;
 };
 
 extern struct perf_missing_features perf_missing_features;
@@ -330,9 +331,6 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads);
 bool evsel__detect_missing_features(struct evsel *evsel);
 
-enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX };
-bool evsel__increase_rlimit(enum rlimit_action *set_rlimit);
-
 bool evsel__precise_ip_fallback(struct evsel *evsel);
 
 struct perf_sample;
@@ -340,6 +338,8 @@ struct perf_sample;
 #ifdef HAVE_LIBTRACEEVENT
 void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name);
 u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name);
+u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const char *name);
+char evsel__taskstate(struct evsel *evsel, struct perf_sample *sample, const char *name);
 
 static inline char *evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name)
 {
@@ -352,6 +352,7 @@ struct tep_format_field;
 u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap);
 
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name);
+struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name);
 
 static inline bool __evsel__match(const struct evsel *evsel, u32 type, u64 config)
 {
@@ -460,7 +461,8 @@ static inline bool evsel__is_clock(const struct evsel *evsel)
 	       evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
-bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize);
+bool evsel__fallback(struct evsel *evsel, struct target *target, int err,
+		     char *msg, size_t msgsize);
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size);
 
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 4814262e3805..b8875aac8f87 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -10,9 +10,11 @@
 #include "debug.h"
 #include "evlist.h"
 #include "expr.h"
-#include "expr-bison.h"
-#include "expr-flex.h"
+#include <util/expr-bison.h>
+#include <util/expr-flex.h>
 #include "util/hashmap.h"
+#include "util/header.h"
+#include "util/pmu.h"
 #include "smt.h"
 #include "tsc.h"
 #include <api/fs/fs.h>
@@ -425,6 +427,13 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
 		result = cpu__max_present_cpu().cpu;
 		goto out;
 	}
+	if (!strcmp("#num_cpus_online", literal)) {
+		struct perf_cpu_map *online = cpu_map__online();
+
+		if (online)
+			result = perf_cpu_map__nr(online);
+		goto out;
+	}
 
 	if (!strcasecmp("#system_tsc_freq", literal)) {
 		result = arch_get_tsc_freq();
@@ -491,7 +500,41 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const
 	tmp = evlist__new();
 	if (!tmp)
 		return NAN;
-	ret = parse_event(tmp, id) ? 0 : 1;
+
+	if (strchr(id, '@')) {
+		char *tmp_id, *p;
+
+		tmp_id = strdup(id);
+		if (!tmp_id) {
+			ret = NAN;
+			goto out;
+		}
+		p = strchr(tmp_id, '@');
+		*p = '/';
+		p = strrchr(tmp_id, '@');
+		*p = '/';
+		ret = parse_event(tmp, tmp_id) ? 0 : 1;
+		free(tmp_id);
+	} else {
+		ret = parse_event(tmp, id) ? 0 : 1;
+	}
+out:
 	evlist__delete(tmp);
 	return ret;
 }
+
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused,
+		       bool compute_ids __maybe_unused, const char *test_id)
+{
+	double ret;
+	struct perf_pmu *pmu = perf_pmus__find_core_pmu();
+	char *cpuid = perf_pmu__getcpuid(pmu);
+
+	if (!cpuid)
+		return NAN;
+
+	ret = !strcmp_cpuid_str(test_id, cpuid);
+
+	free(cpuid);
+	return ret;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 3c1e49b3e35d..c0cec29ddc29 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -55,5 +55,6 @@ double expr_id_data__value(const struct expr_id_data *data);
 double expr_id_data__source_count(const struct expr_id_data *data);
 double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
 double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index dbb117414710..a2fc43159ee9 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -94,6 +94,14 @@ static int literal(yyscan_t scanner, const struct expr_scanner_ctx *sctx)
 	}
 	return LITERAL;
 }
+
+static int nan_value(yyscan_t scanner)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+
+	yylval->num = NAN;
+	return NUMBER;
+}
 %}
 
 number		([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)(e-?[0-9]+)?
@@ -114,6 +122,8 @@ if		{ return IF; }
 else		{ return ELSE; }
 source_count	{ return SOURCE_COUNT; }
 has_event	{ return HAS_EVENT; }
+strcmp_cpuid_str	{ return STRCMP_CPUID_STR; }
+NaN		{ return nan_value(yyscanner); }
 {literal}	{ return literal(yyscanner, sctx); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index dd504afd8f36..e364790babb5 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -1,12 +1,16 @@
 /* Simple expression parser */
 %{
+#ifndef NDEBUG
 #define YYDEBUG 1
+#endif
 #include <assert.h>
 #include <math.h>
 #include <stdlib.h>
 #include "util/debug.h"
 #define IN_EXPR_Y 1
 #include "expr.h"
+#include "expr-bison.h"
+int expr_lex(YYSTYPE * yylval_param , void *yyscanner);
 %}
 
 %define api.pure full
@@ -37,7 +41,7 @@
 	} ids;
 }
 
-%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR
+%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT STRCMP_CPUID_STR EXPR_ERROR
 %left MIN MAX IF
 %left '|'
 %left '^'
@@ -56,7 +60,7 @@
 static void expr_error(double *final_val __maybe_unused,
 		       struct expr_parse_ctx *ctx __maybe_unused,
 		       bool compute_ids __maybe_unused,
-		       void *scanner,
+		       void *scanner __maybe_unused,
 		       const char *s)
 {
 	pr_debug("%s\n", s);
@@ -205,6 +209,12 @@ expr: NUMBER
 	$$.ids = NULL;
 	free($3);
 }
+| STRCMP_CPUID_STR '(' ID ')'
+{
+	$$.val = expr__strcmp_cpuid_str(ctx, compute_ids, $3);
+	$$.ids = NULL;
+	free($3);
+}
 | expr '|' expr
 {
 	if (is_const($1.val) && is_const($3.val)) {
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index fefc72066c4e..ac17a3cb59dc 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	 */
 	phdr = elf_newphdr(e, 1);
 	phdr[0].p_type = PT_LOAD;
-	phdr[0].p_offset = 0;
-	phdr[0].p_vaddr = 0;
-	phdr[0].p_paddr = 0;
+	phdr[0].p_offset = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET;
 	phdr[0].p_filesz = csize;
 	phdr[0].p_memsz = csize;
 	phdr[0].p_flags = PF_X | PF_R;
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index 0a5bf1937a7c..c12f8320e668 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -80,16 +80,6 @@ struct hashmap {
 	size_t sz;
 };
 
-#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
-	.hash_fn = (hash_fn),			\
-	.equal_fn = (equal_fn),			\
-	.ctx = (ctx),				\
-	.buckets = NULL,			\
-	.cap = 0,				\
-	.cap_bits = 0,				\
-	.sz = 0,				\
-}
-
 void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
 		   hashmap_equal_fn equal_fn, void *ctx);
 struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 52fbf526fe74..3fe28edc3d01 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -456,6 +456,8 @@ static int write_cpudesc(struct feat_fd *ff,
 #define CPUINFO_PROC	{ "Processor", }
 #elif defined(__xtensa__)
 #define CPUINFO_PROC	{ "core ID", }
+#elif defined(__loongarch__)
+#define CPUINFO_PROC	{ "Model Name", }
 #else
 #define CPUINFO_PROC	{ "model name", }
 #endif
@@ -746,20 +748,14 @@ static int write_pmu_mappings(struct feat_fd *ff,
 	 * Do a first pass to count number of pmu to avoid lseek so this
 	 * works in pipe mode as well.
 	 */
-	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
+	while ((pmu = perf_pmus__scan(pmu)))
 		pmu_num++;
-	}
 
 	ret = do_write(ff, &pmu_num, sizeof(pmu_num));
 	if (ret < 0)
 		return ret;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name)
-			continue;
-
 		ret = do_write(ff, &pmu->type, sizeof(pmu->type));
 		if (ret < 0)
 			return ret;
@@ -1448,7 +1444,9 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp)
 			nodes = new_nodes;
 			size += 4;
 		}
-		ret = memory_node__read(&nodes[cnt++], idx);
+		ret = memory_node__read(&nodes[cnt], idx);
+		if (!ret)
+			cnt += 1;
 	}
 out:
 	closedir(dir);
@@ -1605,8 +1603,15 @@ static int write_pmu_caps(struct feat_fd *ff,
 	int ret;
 
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (!pmu->name || !strcmp(pmu->name, "cpu") ||
-		    perf_pmu__caps_parse(pmu) <= 0)
+		if (!strcmp(pmu->name, "cpu")) {
+			/*
+			 * The "cpu" PMU is special and covered by
+			 * HEADER_CPU_PMU_CAPS. Note, core PMUs are
+			 * counted/written here for ARM, s390 and Intel hybrid.
+			 */
+			continue;
+		}
+		if (perf_pmu__caps_parse(pmu) <= 0)
 			continue;
 		nr_pmu++;
 	}
@@ -1619,23 +1624,17 @@ static int write_pmu_caps(struct feat_fd *ff,
 		return 0;
 
 	/*
-	 * Write hybrid pmu caps first to maintain compatibility with
-	 * older perf tool.
+	 * Note older perf tools assume core PMUs come first, this is a property
+	 * of perf_pmus__scan.
 	 */
-	if (perf_pmus__num_core_pmus() > 1) {
-		pmu = NULL;
-		while ((pmu = perf_pmus__scan_core(pmu))) {
-			ret = __write_pmu_caps(ff, pmu, true);
-			if (ret < 0)
-				return ret;
-		}
-	}
-
 	pmu = NULL;
 	while ((pmu = perf_pmus__scan(pmu))) {
-		if (pmu->is_core || !pmu->nr_caps)
+		if (!strcmp(pmu->name, "cpu")) {
+			/* Skip as above. */
+			continue;
+		}
+		if (perf_pmu__caps_parse(pmu) <= 0)
 			continue;
-
 		ret = __write_pmu_caps(ff, pmu, true);
 		if (ret < 0)
 			return ret;
@@ -1850,8 +1849,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		bpf_event__print_bpf_prog_info(&node->info_linear->info,
-					       env, fp);
+		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
+						 env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -2148,6 +2147,14 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp)
 		__print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps,
 				 pmu_caps->pmu_name);
 	}
+
+	if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 &&
+	    perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) {
+		char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise");
+
+		if (max_precise != NULL && atoi(max_precise) == 0)
+			fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n");
+	}
 }
 
 static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
@@ -2576,7 +2583,7 @@ error:
 static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 {
 	u32 nr, i;
-	char *str;
+	char *str = NULL;
 	struct strbuf sb;
 	int cpu_nr = ff->ph->env.nr_cpus_avail;
 	u64 size = 0;
@@ -2604,7 +2611,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
 			goto error;
 		size += string_size(str);
-		free(str);
+		zfree(&str);
 	}
 	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
 
@@ -2623,7 +2630,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
 			goto error;
 		size += string_size(str);
-		free(str);
+		zfree(&str);
 	}
 	ph->env.sibling_threads = strbuf_detach(&sb, NULL);
 
@@ -2687,7 +2694,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 		if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
 			goto error;
 		size += string_size(str);
-		free(str);
+		zfree(&str);
 	}
 	ph->env.sibling_dies = strbuf_detach(&sb, NULL);
 
@@ -2702,6 +2709,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 
 error:
 	strbuf_release(&sb);
+	zfree(&str);
 free_cpu:
 	zfree(&ph->env.cpu);
 	return -1;
@@ -2739,10 +2747,9 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused)
 			goto error;
 
 		n->map = perf_cpu_map__new(str);
+		free(str);
 		if (!n->map)
 			goto error;
-
-		free(str);
 	}
 	ff->ph->env.nr_numa_nodes = nr;
 	ff->ph->env.numa_nodes = nodes;
@@ -2916,10 +2923,10 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused)
 		return -1;
 
 	for (i = 0; i < cnt; i++) {
-		struct cpu_cache_level c;
+		struct cpu_cache_level *c = &caches[i];
 
 		#define _R(v)						\
-			if (do_read_u32(ff, &c.v))\
+			if (do_read_u32(ff, &c->v))			\
 				goto out_free_caches;			\
 
 		_R(level)
@@ -2929,22 +2936,25 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused)
 		#undef _R
 
 		#define _R(v)					\
-			c.v = do_read_string(ff);		\
-			if (!c.v)				\
-				goto out_free_caches;
+			c->v = do_read_string(ff);		\
+			if (!c->v)				\
+				goto out_free_caches;		\
 
 		_R(type)
 		_R(size)
 		_R(map)
 		#undef _R
-
-		caches[i] = c;
 	}
 
 	ff->ph->env.caches = caches;
 	ff->ph->env.caches_cnt = cnt;
 	return 0;
 out_free_caches:
+	for (i = 0; i < cnt; i++) {
+		free(caches[i].type);
+		free(caches[i].size);
+		free(caches[i].map);
+	}
 	free(caches);
 	return -1;
 }
@@ -3178,7 +3188,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		/* after reading from file, translate offset to address */
 		bpil_offs_to_addr(info_linear);
 		info_node->info_linear = info_linear;
-		perf_env__insert_bpf_prog_info(env, info_node);
+		__perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
 	up_write(&env->bpf_progs.lock);
@@ -3225,7 +3235,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 		if (__do_read(ff, node->data, data_size))
 			goto out;
 
-		perf_env__insert_btf(env, node);
+		__perf_env__insert_btf(env, node);
 		node = NULL;
 	}
 
@@ -3259,7 +3269,9 @@ static int process_compressed(struct feat_fd *ff,
 }
 
 static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
-			      char ***caps, unsigned int *max_branches)
+			      char ***caps, unsigned int *max_branches,
+			      unsigned int *br_cntr_nr,
+			      unsigned int *br_cntr_width)
 {
 	char *name, *value, *ptr;
 	u32 nr_pmu_caps, i;
@@ -3294,6 +3306,12 @@ static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
 		if (!strcmp(name, "branches"))
 			*max_branches = atoi(value);
 
+		if (!strcmp(name, "branch_counter_nr"))
+			*br_cntr_nr = atoi(value);
+
+		if (!strcmp(name, "branch_counter_width"))
+			*br_cntr_width = atoi(value);
+
 		free(value);
 		free(name);
 	}
@@ -3318,7 +3336,9 @@ static int process_cpu_pmu_caps(struct feat_fd *ff,
 {
 	int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps,
 				     &ff->ph->env.cpu_pmu_caps,
-				     &ff->ph->env.max_branches);
+				     &ff->ph->env.max_branches,
+				     &ff->ph->env.br_cntr_nr,
+				     &ff->ph->env.br_cntr_width);
 
 	if (!ret && !ff->ph->env.cpu_pmu_caps)
 		pr_debug("cpu pmu capabilities not available\n");
@@ -3347,7 +3367,9 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused)
 	for (i = 0; i < nr_pmu; i++) {
 		ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps,
 					 &pmu_caps[i].caps,
-					 &pmu_caps[i].max_branches);
+					 &pmu_caps[i].max_branches,
+					 &pmu_caps[i].br_cntr_nr,
+					 &pmu_caps[i].br_cntr_width);
 		if (ret)
 			goto err;
 
@@ -3588,18 +3610,16 @@ static int perf_header__adds_write(struct perf_header *header,
 				   struct feat_copier *fc)
 {
 	int nr_sections;
-	struct feat_fd ff;
+	struct feat_fd ff = {
+		.fd  = fd,
+		.ph = header,
+	};
 	struct perf_file_section *feat_sec, *p;
 	int sec_size;
 	u64 sec_start;
 	int feat;
 	int err;
 
-	ff = (struct feat_fd){
-		.fd  = fd,
-		.ph = header,
-	};
-
 	nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
 	if (!nr_sections)
 		return 0;
@@ -3626,6 +3646,7 @@ static int perf_header__adds_write(struct perf_header *header,
 	err = do_write(&ff, feat_sec, sec_size);
 	if (err < 0)
 		pr_debug("failed to write feature section\n");
+	free(ff.buf); /* TODO: added to silence clang-tidy. */
 	free(feat_sec);
 	return err;
 }
@@ -3633,11 +3654,11 @@ static int perf_header__adds_write(struct perf_header *header,
 int perf_header__write_pipe(int fd)
 {
 	struct perf_pipe_file_header f_header;
-	struct feat_fd ff;
+	struct feat_fd ff = {
+		.fd = fd,
+	};
 	int err;
 
-	ff = (struct feat_fd){ .fd = fd };
-
 	f_header = (struct perf_pipe_file_header){
 		.magic	   = PERF_MAGIC,
 		.size	   = sizeof(f_header),
@@ -3648,7 +3669,7 @@ int perf_header__write_pipe(int fd)
 		pr_debug("failed to write perf pipe header\n");
 		return err;
 	}
-
+	free(ff.buf);
 	return 0;
 }
 
@@ -3661,11 +3682,12 @@ static int perf_session__do_write_header(struct perf_session *session,
 	struct perf_file_attr   f_attr;
 	struct perf_header *header = &session->header;
 	struct evsel *evsel;
-	struct feat_fd ff;
+	struct feat_fd ff = {
+		.fd = fd,
+	};
 	u64 attr_offset;
 	int err;
 
-	ff = (struct feat_fd){ .fd = fd};
 	lseek(fd, sizeof(f_header), SEEK_SET);
 
 	evlist__for_each_entry(session->evlist, evsel) {
@@ -3673,6 +3695,7 @@ static int perf_session__do_write_header(struct perf_session *session,
 		err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64));
 		if (err < 0) {
 			pr_debug("failed to write perf header\n");
+			free(ff.buf);
 			return err;
 		}
 	}
@@ -3698,6 +3721,7 @@ static int perf_session__do_write_header(struct perf_session *session,
 		err = do_write(&ff, &f_attr, sizeof(f_attr));
 		if (err < 0) {
 			pr_debug("failed to write perf header attribute\n");
+			free(ff.buf);
 			return err;
 		}
 	}
@@ -3708,8 +3732,10 @@ static int perf_session__do_write_header(struct perf_session *session,
 
 	if (at_exit) {
 		err = perf_header__adds_write(header, evlist, fd, fc);
-		if (err < 0)
+		if (err < 0) {
+			free(ff.buf);
 			return err;
+		}
 	}
 
 	f_header = (struct perf_file_header){
@@ -3731,6 +3757,7 @@ static int perf_session__do_write_header(struct perf_session *session,
 
 	lseek(fd, 0, SEEK_SET);
 	err = do_write(&ff, &f_header, sizeof(f_header));
+	free(ff.buf);
 	if (err < 0) {
 		pr_debug("failed to write perf header\n");
 		return err;
@@ -4364,9 +4391,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 		ret += fprintf(fp, "... ");
 
 		map = cpu_map__new_data(&ev->cpus.cpus);
-		if (map)
+		if (map) {
 			ret += cpu_map__fprintf(map, fp);
-		else
+			perf_cpu_map__put(map);
+		} else
 			ret += fprintf(fp, "failed to get cpus\n");
 		break;
 	default:
@@ -4381,7 +4409,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct evlist **pevlist)
 {
-	u32 i, ids, n_ids;
+	u32 i, n_ids;
+	u64 *ids;
 	struct evsel *evsel;
 	struct evlist *evlist = *pevlist;
 
@@ -4397,9 +4426,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 
 	evlist__add(evlist, evsel);
 
-	ids = event->header.size;
-	ids -= (void *)&event->attr.id - (void *)event;
-	n_ids = ids / sizeof(u64);
+	n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+	n_ids = n_ids / sizeof(u64);
 	/*
 	 * We don't have the cpu and thread maps on the header, so
 	 * for allocating the perf_sample_id table we fake 1 cpu and
@@ -4408,8 +4436,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 	if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
 		return -ENOMEM;
 
+	ids = perf_record_header_attr_id(event);
 	for (i = 0; i < n_ids; i++) {
-		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+		perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
 	}
 
 	return 0;
diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c
index 45b614bb73bf..52d0ce302ca0 100644
--- a/tools/perf/util/hisi-ptt.c
+++ b/tools/perf/util/hisi-ptt.c
@@ -108,8 +108,10 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
 		data_offset = 0;
 	} else {
 		data_offset = lseek(fd, 0, SEEK_CUR);
-		if (data_offset == -1)
+		if (data_offset == -1) {
+			free(data);
 			return -errno;
+		}
 	}
 
 	err = readn(fd, data, size);
@@ -121,6 +123,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
 	if (dump_trace)
 		hisi_ptt_dump_event(ptt, data, size);
 
+	free(data);
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 3dc8a4968beb..fa359180ebf8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -491,8 +491,8 @@ static int hist_entry__init(struct hist_entry *he,
 	}
 
 	if (symbol_conf.res_sample) {
-		he->res_samples = calloc(sizeof(struct res_sample),
-					symbol_conf.res_sample);
+		he->res_samples = calloc(symbol_conf.res_sample,
+					sizeof(struct res_sample));
 		if (!he->res_samples)
 			goto err_srcline;
 	}
@@ -515,17 +515,16 @@ err_rawdata:
 
 err_infos:
 	if (he->branch_info) {
-		map__put(he->branch_info->from.ms.map);
-		map__put(he->branch_info->to.ms.map);
+		map_symbol__exit(&he->branch_info->from.ms);
+		map_symbol__exit(&he->branch_info->to.ms);
 		zfree(&he->branch_info);
 	}
 	if (he->mem_info) {
-		map__put(he->mem_info->iaddr.ms.map);
-		map__put(he->mem_info->daddr.ms.map);
+		map_symbol__exit(&he->mem_info->iaddr.ms);
+		map_symbol__exit(&he->mem_info->daddr.ms);
 	}
 err:
-	maps__zput(he->ms.maps);
-	map__zput(he->ms.map);
+	map_symbol__exit(&he->ms);
 	zfree(&he->stat_acc);
 	return -ENOMEM;
 }
@@ -1317,20 +1316,19 @@ void hist_entry__delete(struct hist_entry *he)
 	struct hist_entry_ops *ops = he->ops;
 
 	thread__zput(he->thread);
-	maps__zput(he->ms.maps);
-	map__zput(he->ms.map);
+	map_symbol__exit(&he->ms);
 
 	if (he->branch_info) {
-		map__zput(he->branch_info->from.ms.map);
-		map__zput(he->branch_info->to.ms.map);
+		map_symbol__exit(&he->branch_info->from.ms);
+		map_symbol__exit(&he->branch_info->to.ms);
 		zfree_srcline(&he->branch_info->srcline_from);
 		zfree_srcline(&he->branch_info->srcline_to);
 		zfree(&he->branch_info);
 	}
 
 	if (he->mem_info) {
-		map__zput(he->mem_info->iaddr.ms.map);
-		map__zput(he->mem_info->daddr.ms.map);
+		map_symbol__exit(&he->mem_info->iaddr.ms);
+		map_symbol__exit(&he->mem_info->daddr.ms);
 		mem_info__zput(he->mem_info);
 	}
 
@@ -2142,7 +2140,7 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he)
 {
 	if (hists->thread_filter != NULL &&
-	    RC_CHK_ACCESS(he->thread) != RC_CHK_ACCESS(hists->thread_filter)) {
+	    !RC_CHK_EQUAL(he->thread, hists->thread_filter)) {
 		he->filtered |= (1 << HIST_FILTER__THREAD);
 		return true;
 	}
@@ -2676,8 +2674,6 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 
 	/* If we have branch cycles always annotate them. */
 	if (bs && bs->nr && entries[0].flags.cycles) {
-		int i;
-
 		bi = sample__resolve_bstack(sample, al);
 		if (bi) {
 			struct addr_map_symbol *prev = NULL;
@@ -2692,7 +2688,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			 * Note that perf stores branches reversed from
 			 * program order!
 			 */
-			for (i = bs->nr - 1; i >= 0; i--) {
+			for (int i = bs->nr - 1; i >= 0; i--) {
 				addr_map_symbol__account_cycles(&bi[i].from,
 					nonany_branch_mode ? NULL : prev,
 					bi[i].flags.cycles);
@@ -2701,6 +2697,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 				if (total_cycles)
 					*total_cycles += bi[i].flags.cycles;
 			}
+			for (unsigned int i = 0; i < bs->nr; i++) {
+				map_symbol__exit(&bi[i].to.ms);
+				map_symbol__exit(&bi[i].from.ms);
+			}
 			free(bi);
 		}
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index afc9f1c7f4dc..4a0aea0c9e00 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -82,6 +82,9 @@ enum hist_column {
 	HISTC_ADDR_TO,
 	HISTC_ADDR,
 	HISTC_SIMD,
+	HISTC_TYPE,
+	HISTC_TYPE_OFFSET,
+	HISTC_SYMBOL_OFFSET,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -457,7 +460,6 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-struct annotation_options;
 struct res_sample;
 
 enum rstype {
@@ -473,16 +475,13 @@ struct block_hist;
 void attr_to_script(char *buf, struct perf_event_attr *attr);
 
 int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
-			     struct hist_browser_timer *hbt,
-			     struct annotation_options *annotation_opts);
+			     struct hist_browser_timer *hbt);
 
 int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
-			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
-			     struct annotation_options *annotation_options);
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event);
 
 int script_browse(const char *script_opt, struct evsel *evsel);
 
@@ -492,8 +491,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
 void res_sample_init(void);
 
 int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
-			   float min_percent, struct perf_env *env,
-			   struct annotation_options *annotation_opts);
+			   float min_percent, struct perf_env *env);
 #else
 static inline
 int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
@@ -501,23 +499,20 @@ int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
 			     struct hist_browser_timer *hbt __maybe_unused,
 			     float min_pcnt __maybe_unused,
 			     struct perf_env *env __maybe_unused,
-			     bool warn_lost_event __maybe_unused,
-			     struct annotation_options *annotation_options __maybe_unused)
+			     bool warn_lost_event __maybe_unused)
 {
 	return 0;
 }
 static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_options __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
 
 static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,
 					   struct evsel *evsel __maybe_unused,
-					   struct hist_browser_timer *hbt __maybe_unused,
-					   struct annotation_options *annotation_opts __maybe_unused)
+					   struct hist_browser_timer *hbt __maybe_unused)
 {
 	return 0;
 }
@@ -541,8 +536,7 @@ static inline void res_sample_init(void) {}
 static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused,
 					 struct evsel *evsel __maybe_unused,
 					 float min_percent __maybe_unused,
-					 struct perf_env *env __maybe_unused,
-					 struct annotation_options *annotation_opts __maybe_unused)
+					 struct perf_env *env __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/include/dwarf-regs.h b/tools/perf/util/include/dwarf-regs.h
index 7d99a084e82d..01fb25a1150a 100644
--- a/tools/perf/util/include/dwarf-regs.h
+++ b/tools/perf/util/include/dwarf-regs.h
@@ -2,6 +2,9 @@
 #ifndef _PERF_DWARF_REGS_H_
 #define _PERF_DWARF_REGS_H_
 
+#define DWARF_REG_PC  0xd3af9c /* random number */
+#define DWARF_REG_FB  0xd3affb /* random number */
+
 #ifdef HAVE_DWARF_SUPPORT
 const char *get_arch_regstr(unsigned int n);
 /*
@@ -10,6 +13,22 @@ const char *get_arch_regstr(unsigned int n);
  * machine: ELF machine signature (EM_*)
  */
 const char *get_dwarf_regstr(unsigned int n, unsigned int machine);
+
+int get_arch_regnum(const char *name);
+/*
+ * get_dwarf_regnum - Returns DWARF regnum from register name
+ * name: architecture register name
+ * machine: ELF machine signature (EM_*)
+ */
+int get_dwarf_regnum(const char *name, unsigned int machine);
+
+#else /* HAVE_DWARF_SUPPORT */
+
+static inline int get_dwarf_regnum(const char *name __maybe_unused,
+				   unsigned int machine __maybe_unused)
+{
+	return -1;
+}
 #endif
 
 #ifdef HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 75e2248416f5..178b00205fe6 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -115,6 +115,10 @@
 	SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
 #endif
 
+#ifndef SYM_FUNC_ALIAS_MEMFUNC
+#define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
 // In the kernel sources (include/linux/cfi_types.h), this has a different
 // definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
 // definition:
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index af9710622a1f..bccb988a7a44 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -8,7 +8,9 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/kernel.h>
 #include <linux/compiler.h>
+#include <asm-generic/unaligned.h>
 
 #include "intel-pt-pkt-decoder.h"
 
@@ -17,17 +19,11 @@
 #define BIT63		((uint64_t)1 << 63)
 
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-#define le16_to_cpu bswap_16
-#define le32_to_cpu bswap_32
-#define le64_to_cpu bswap_64
 #define memcpy_le64(d, s, n) do { \
 	memcpy((d), (s), (n));    \
 	*(d) = le64_to_cpu(*(d)); \
 } while (0)
 #else
-#define le16_to_cpu
-#define le32_to_cpu
-#define le64_to_cpu
 #define memcpy_le64 memcpy
 #endif
 
@@ -83,7 +79,7 @@ static int intel_pt_get_long_tnt(const unsigned char *buf, size_t len,
 	if (len < 8)
 		return INTEL_PT_NEED_MORE_BYTES;
 
-	payload = le64_to_cpu(*(uint64_t *)buf);
+	payload = get_unaligned_le64(buf);
 
 	for (count = 47; count; count--) {
 		if (payload & BIT63)
@@ -124,26 +120,21 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len,
 	if (len < 4)
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_CBR;
-	packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2));
+	packet->payload = get_unaligned_le16(buf + 2);
 	return 4;
 }
 
 static int intel_pt_get_vmcs(const unsigned char *buf, size_t len,
 			     struct intel_pt_pkt *packet)
 {
-	unsigned int count = (52 - 5) >> 3;
-
-	if (count < 1 || count > 7)
-		return INTEL_PT_BAD_PACKET;
-
-	if (len < count + 2)
+	if (len < 7)
 		return INTEL_PT_NEED_MORE_BYTES;
 
 	packet->type = INTEL_PT_VMCS;
-	packet->count = count;
-	memcpy_le64(&packet->payload, buf + 2, count);
+	packet->count = 5;
+	memcpy_le64(&packet->payload, buf + 2, 5);
 
-	return count + 2;
+	return 7;
 }
 
 static int intel_pt_get_ovf(struct intel_pt_pkt *packet)
@@ -199,7 +190,7 @@ static int intel_pt_get_mnt(const unsigned char *buf, size_t len,
 	if (len < 11)
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_MNT;
-	memcpy_le64(&packet->payload, buf + 3, 8);
+	packet->payload = get_unaligned_le64(buf + 3);
 	return 11;
 }
 
@@ -228,12 +219,12 @@ static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len,
 	case 0:
 		if (len < 6)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2));
+		packet->payload = get_unaligned_le32(buf + 2);
 		return 6;
 	case 1:
 		if (len < 10)
 			return INTEL_PT_NEED_MORE_BYTES;
-		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2));
+		packet->payload = get_unaligned_le64(buf + 2);
 		return 10;
 	default:
 		return INTEL_PT_BAD_PACKET;
@@ -258,7 +249,7 @@ static int intel_pt_get_mwait(const unsigned char *buf, size_t len,
 	if (len < 10)
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_MWAIT;
-	packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2));
+	packet->payload = get_unaligned_le64(buf + 2);
 	return 10;
 }
 
@@ -311,7 +302,7 @@ static int intel_pt_get_bip_8(const unsigned char *buf, size_t len,
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_BIP;
 	packet->count = buf[0] >> 3;
-	memcpy_le64(&packet->payload, buf + 1, 8);
+	packet->payload = get_unaligned_le64(buf + 1);
 	return 9;
 }
 
@@ -350,7 +341,7 @@ static int intel_pt_get_evd(const unsigned char *buf, size_t len,
 	packet->type = INTEL_PT_EVD;
 	packet->count = buf[2] & 0x3f;
 	packet->payload = buf[3];
-	memcpy_le64(&packet->payload, buf + 3, 8);
+	packet->payload = get_unaligned_le64(buf + 3);
 	return 11;
 }
 
@@ -465,13 +456,13 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
 		if (len < 3)
 			return INTEL_PT_NEED_MORE_BYTES;
 		ip_len = 2;
-		packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+		packet->payload = get_unaligned_le16(buf + 1);
 		break;
 	case 2:
 		if (len < 5)
 			return INTEL_PT_NEED_MORE_BYTES;
 		ip_len = 4;
-		packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
+		packet->payload = get_unaligned_le32(buf + 1);
 		break;
 	case 3:
 	case 4:
@@ -484,7 +475,7 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
 		if (len < 9)
 			return INTEL_PT_NEED_MORE_BYTES;
 		ip_len = 8;
-		packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+		packet->payload = get_unaligned_le64(buf + 1);
 		break;
 	default:
 		return INTEL_PT_BAD_PACKET;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index dbf0bc71a63b..f38893e0b036 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1512,9 +1512,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
 	} else if (ptq->state->flags & INTEL_PT_ASYNC) {
 		if (!ptq->state->to_ip)
 			ptq->flags = PERF_IP_FLAG_BRANCH |
+				     PERF_IP_FLAG_ASYNC |
 				     PERF_IP_FLAG_TRACE_END;
 		else if (ptq->state->from_nr && !ptq->state->to_nr)
 			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+				     PERF_IP_FLAG_ASYNC |
 				     PERF_IP_FLAG_VMEXIT;
 		else
 			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h
index c7d6068e3a6b..18fd0be52e6c 100644
--- a/tools/perf/util/intel-pt.h
+++ b/tools/perf/util/intel-pt.h
@@ -42,6 +42,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err);
 int intel_pt_process_auxtrace_info(union perf_event *event,
 				   struct perf_session *session);
 
-struct perf_event_attr *intel_pt_pmu_default_config(struct perf_pmu *pmu);
+void intel_pt_pmu_default_config(const struct perf_pmu *intel_pt_pmu,
+				 struct perf_event_attr *attr);
 
 #endif
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 6b2b96c16ccd..1f657ef8975f 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -675,6 +675,7 @@ jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr)
 	jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size;
 	jd->unwinding_size = jr->unwinding.unwinding_size;
 	jd->unwinding_mapped_size = jr->unwinding.mapped_size;
+	free(jd->unwinding_data);
 	jd->unwinding_data = unwinding_data;
 
 	return 0;
diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h
index 53b7327550b8..76fe2a821bcf 100644
--- a/tools/perf/util/kwork.h
+++ b/tools/perf/util/kwork.h
@@ -16,6 +16,7 @@ enum kwork_class_type {
 	KWORK_CLASS_IRQ,
 	KWORK_CLASS_SOFTIRQ,
 	KWORK_CLASS_WORKQUEUE,
+	KWORK_CLASS_SCHED,
 	KWORK_CLASS_MAX,
 };
 
@@ -23,6 +24,7 @@ enum kwork_report_type {
 	KWORK_REPORT_RUNTIME,
 	KWORK_REPORT_LATENCY,
 	KWORK_REPORT_TIMEHIST,
+	KWORK_REPORT_TOP,
 };
 
 enum kwork_trace_type {
@@ -91,6 +93,7 @@ struct kwork_atom_page {
 	DECLARE_BITMAP(bitmap, NR_ATOM_PER_PAGE);
 };
 
+struct perf_kwork;
 struct kwork_class;
 struct kwork_work {
 	/*
@@ -127,6 +130,13 @@ struct kwork_work {
 	u64 max_latency_start;
 	u64 max_latency_end;
 	u64 total_latency;
+
+	/*
+	 * top report
+	 */
+	u32 cpu_usage;
+	u32 tgid;
+	bool is_kthread;
 };
 
 struct kwork_class {
@@ -142,8 +152,10 @@ struct kwork_class {
 	int (*class_init)(struct kwork_class *class,
 			  struct perf_session *session);
 
-	void (*work_init)(struct kwork_class *class,
+	void (*work_init)(struct perf_kwork *kwork,
+			  struct kwork_class *class,
 			  struct kwork_work *work,
+			  enum kwork_trace_type src_type,
 			  struct evsel *evsel,
 			  struct perf_sample *sample,
 			  struct machine *machine);
@@ -152,7 +164,6 @@ struct kwork_class {
 			  char *buf, int len);
 };
 
-struct perf_kwork;
 struct trace_kwork_handler {
 	int (*raise_event)(struct perf_kwork *kwork,
 			   struct kwork_class *class, struct evsel *evsel,
@@ -165,6 +176,23 @@ struct trace_kwork_handler {
 	int (*exit_event)(struct perf_kwork *kwork,
 			  struct kwork_class *class, struct evsel *evsel,
 			  struct perf_sample *sample, struct machine *machine);
+
+	int (*sched_switch_event)(struct perf_kwork *kwork,
+				  struct kwork_class *class, struct evsel *evsel,
+				  struct perf_sample *sample, struct machine *machine);
+};
+
+struct __top_cpus_runtime {
+	u64 load;
+	u64 idle;
+	u64 irq;
+	u64 softirq;
+	u64 total;
+};
+
+struct kwork_top_stat {
+	DECLARE_BITMAP(all_cpus_bitmap, MAX_NR_CPUS);
+	struct __top_cpus_runtime *cpus_runtime;
 };
 
 struct perf_kwork {
@@ -218,6 +246,11 @@ struct perf_kwork {
 	u64 all_runtime;
 	u64 all_count;
 	u64 nr_skipped_events[KWORK_TRACE_MAX + 1];
+
+	/*
+	 * perf kwork top data
+	 */
+	struct kwork_top_stat top_stat;
 };
 
 struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork,
@@ -233,6 +266,13 @@ void perf_kwork__report_cleanup_bpf(void);
 void perf_kwork__trace_start(void);
 void perf_kwork__trace_finish(void);
 
+int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork);
+int perf_kwork__top_read_bpf(struct perf_kwork *kwork);
+void perf_kwork__top_cleanup_bpf(void);
+
+void perf_kwork__top_start(void);
+void perf_kwork__top_finish(void);
+
 #else  /* !HAVE_BPF_SKEL */
 
 static inline int
@@ -252,6 +292,23 @@ static inline void perf_kwork__report_cleanup_bpf(void) {}
 static inline void perf_kwork__trace_start(void) {}
 static inline void perf_kwork__trace_finish(void) {}
 
+static inline int
+perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_kwork__top_read_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline void perf_kwork__top_cleanup_bpf(void) {}
+
+static inline void perf_kwork__top_start(void) {}
+static inline void perf_kwork__top_finish(void) {}
+
 #endif  /* HAVE_BPF_SKEL */
 
 #endif  /* PERF_UTIL_KWORK_H */
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 014d82159656..37ecef0c53b9 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -18,8 +18,6 @@
  * defined before including "unwind.h"
  */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum)
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
 
 #include "unwind.h"
 #include "libunwind-aarch64.h"
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
index b2b92d030aef..1697dece1b74 100644
--- a/tools/perf/util/libunwind/x86_32.c
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -18,8 +18,6 @@
  * defined before including "unwind.h"
  */
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum)
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
 
 #include "unwind.h"
 #include "libunwind-x86.h"
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
deleted file mode 100644
index c6c9c2228578..000000000000
--- a/tools/perf/util/llvm-utils.c
+++ /dev/null
@@ -1,612 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-
-#include <errno.h>
-#include <limits.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <linux/err.h>
-#include <linux/string.h>
-#include <linux/zalloc.h>
-#include "debug.h"
-#include "llvm-utils.h"
-#include "config.h"
-#include "util.h"
-#include <sys/wait.h>
-#include <subcmd/exec-cmd.h>
-
-#define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
-		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
-		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
-		"-Wno-unused-value -Wno-pointer-sign "		\
-		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
-
-struct llvm_param llvm_param = {
-	.clang_path = "clang",
-	.llc_path = "llc",
-	.clang_bpf_cmd_template = CLANG_BPF_CMD_DEFAULT_TEMPLATE,
-	.clang_opt = NULL,
-	.opts = NULL,
-	.kbuild_dir = NULL,
-	.kbuild_opts = NULL,
-	.user_set_param = false,
-};
-
-static void version_notice(void);
-
-int perf_llvm_config(const char *var, const char *value)
-{
-	if (!strstarts(var, "llvm."))
-		return 0;
-	var += sizeof("llvm.") - 1;
-
-	if (!strcmp(var, "clang-path"))
-		llvm_param.clang_path = strdup(value);
-	else if (!strcmp(var, "clang-bpf-cmd-template"))
-		llvm_param.clang_bpf_cmd_template = strdup(value);
-	else if (!strcmp(var, "clang-opt"))
-		llvm_param.clang_opt = strdup(value);
-	else if (!strcmp(var, "kbuild-dir"))
-		llvm_param.kbuild_dir = strdup(value);
-	else if (!strcmp(var, "kbuild-opts"))
-		llvm_param.kbuild_opts = strdup(value);
-	else if (!strcmp(var, "dump-obj"))
-		llvm_param.dump_obj = !!perf_config_bool(var, value);
-	else if (!strcmp(var, "opts"))
-		llvm_param.opts = strdup(value);
-	else {
-		pr_debug("Invalid LLVM config option: %s\n", value);
-		return -1;
-	}
-	llvm_param.user_set_param = true;
-	return 0;
-}
-
-static int
-search_program(const char *def, const char *name,
-	       char *output)
-{
-	char *env, *path, *tmp = NULL;
-	char buf[PATH_MAX];
-	int ret;
-
-	output[0] = '\0';
-	if (def && def[0] != '\0') {
-		if (def[0] == '/') {
-			if (access(def, F_OK) == 0) {
-				strlcpy(output, def, PATH_MAX);
-				return 0;
-			}
-		} else if (def[0] != '\0')
-			name = def;
-	}
-
-	env = getenv("PATH");
-	if (!env)
-		return -1;
-	env = strdup(env);
-	if (!env)
-		return -1;
-
-	ret = -ENOENT;
-	path = strtok_r(env, ":",  &tmp);
-	while (path) {
-		scnprintf(buf, sizeof(buf), "%s/%s", path, name);
-		if (access(buf, F_OK) == 0) {
-			strlcpy(output, buf, PATH_MAX);
-			ret = 0;
-			break;
-		}
-		path = strtok_r(NULL, ":", &tmp);
-	}
-
-	free(env);
-	return ret;
-}
-
-static int search_program_and_warn(const char *def, const char *name,
-				   char *output)
-{
-	int ret = search_program(def, name, output);
-
-	if (ret) {
-		pr_err("ERROR:\tunable to find %s.\n"
-		       "Hint:\tTry to install latest clang/llvm to support BPF. Check your $PATH\n"
-		       "     \tand '%s-path' option in [llvm] section of ~/.perfconfig.\n",
-		       name, name);
-		version_notice();
-	}
-	return ret;
-}
-
-#define READ_SIZE	4096
-static int
-read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
-{
-	int err = 0;
-	void *buf = NULL;
-	FILE *file = NULL;
-	size_t read_sz = 0, buf_sz = 0;
-	char serr[STRERR_BUFSIZE];
-
-	file = popen(cmd, "r");
-	if (!file) {
-		pr_err("ERROR: unable to popen cmd: %s\n",
-		       str_error_r(errno, serr, sizeof(serr)));
-		return -EINVAL;
-	}
-
-	while (!feof(file) && !ferror(file)) {
-		/*
-		 * Make buf_sz always have obe byte extra space so we
-		 * can put '\0' there.
-		 */
-		if (buf_sz - read_sz < READ_SIZE + 1) {
-			void *new_buf;
-
-			buf_sz = read_sz + READ_SIZE + 1;
-			new_buf = realloc(buf, buf_sz);
-
-			if (!new_buf) {
-				pr_err("ERROR: failed to realloc memory\n");
-				err = -ENOMEM;
-				goto errout;
-			}
-
-			buf = new_buf;
-		}
-		read_sz += fread(buf + read_sz, 1, READ_SIZE, file);
-	}
-
-	if (buf_sz - read_sz < 1) {
-		pr_err("ERROR: internal error\n");
-		err = -EINVAL;
-		goto errout;
-	}
-
-	if (ferror(file)) {
-		pr_err("ERROR: error occurred when reading from pipe: %s\n",
-		       str_error_r(errno, serr, sizeof(serr)));
-		err = -EIO;
-		goto errout;
-	}
-
-	err = WEXITSTATUS(pclose(file));
-	file = NULL;
-	if (err) {
-		err = -EINVAL;
-		goto errout;
-	}
-
-	/*
-	 * If buf is string, give it terminal '\0' to make our life
-	 * easier. If buf is not string, that '\0' is out of space
-	 * indicated by read_sz so caller won't even notice it.
-	 */
-	((char *)buf)[read_sz] = '\0';
-
-	if (!p_buf)
-		free(buf);
-	else
-		*p_buf = buf;
-
-	if (p_read_sz)
-		*p_read_sz = read_sz;
-	return 0;
-
-errout:
-	if (file)
-		pclose(file);
-	free(buf);
-	if (p_buf)
-		*p_buf = NULL;
-	if (p_read_sz)
-		*p_read_sz = 0;
-	return err;
-}
-
-static inline void
-force_set_env(const char *var, const char *value)
-{
-	if (value) {
-		setenv(var, value, 1);
-		pr_debug("set env: %s=%s\n", var, value);
-	} else {
-		unsetenv(var);
-		pr_debug("unset env: %s\n", var);
-	}
-}
-
-static void
-version_notice(void)
-{
-	pr_err(
-"     \tLLVM 3.7 or newer is required. Which can be found from http://llvm.org\n"
-"     \tYou may want to try git trunk:\n"
-"     \t\tgit clone http://llvm.org/git/llvm.git\n"
-"     \t\t     and\n"
-"     \t\tgit clone http://llvm.org/git/clang.git\n\n"
-"     \tOr fetch the latest clang/llvm 3.7 from pre-built llvm packages for\n"
-"     \tdebian/ubuntu:\n"
-"     \t\thttps://apt.llvm.org/\n\n"
-"     \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
-"     \toption in [llvm] section of ~/.perfconfig to:\n\n"
-"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
-"     \t     -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
-"     \t     -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
-"     \t(Replace /path/to/llc with path to your llc)\n\n"
-);
-}
-
-static int detect_kbuild_dir(char **kbuild_dir)
-{
-	const char *test_dir = llvm_param.kbuild_dir;
-	const char *prefix_dir = "";
-	const char *suffix_dir = "";
-
-	/* _UTSNAME_LENGTH is 65 */
-	char release[128];
-
-	char *autoconf_path;
-
-	int err;
-
-	if (!test_dir) {
-		err = fetch_kernel_version(NULL, release,
-					   sizeof(release));
-		if (err)
-			return -EINVAL;
-
-		test_dir = release;
-		prefix_dir = "/lib/modules/";
-		suffix_dir = "/build";
-	}
-
-	err = asprintf(&autoconf_path, "%s%s%s/include/generated/autoconf.h",
-		       prefix_dir, test_dir, suffix_dir);
-	if (err < 0)
-		return -ENOMEM;
-
-	if (access(autoconf_path, R_OK) == 0) {
-		free(autoconf_path);
-
-		err = asprintf(kbuild_dir, "%s%s%s", prefix_dir, test_dir,
-			       suffix_dir);
-		if (err < 0)
-			return -ENOMEM;
-		return 0;
-	}
-	pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
-		 __func__, autoconf_path);
-	free(autoconf_path);
-	return -ENOENT;
-}
-
-static const char *kinc_fetch_script =
-"#!/usr/bin/env sh\n"
-"if ! test -d \"$KBUILD_DIR\"\n"
-"then\n"
-"	exit 1\n"
-"fi\n"
-"if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
-"then\n"
-"	exit 1\n"
-"fi\n"
-"TMPDIR=`mktemp -d`\n"
-"if test -z \"$TMPDIR\"\n"
-"then\n"
-"    exit 1\n"
-"fi\n"
-"cat << EOF > $TMPDIR/Makefile\n"
-"obj-y := dummy.o\n"
-"\\$(obj)/%.o: \\$(src)/%.c\n"
-"\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n"
-"\t\\$(CC) -c -o \\$@ \\$<\n"
-"EOF\n"
-"touch $TMPDIR/dummy.c\n"
-"make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n"
-"RET=$?\n"
-"rm -rf $TMPDIR\n"
-"exit $RET\n";
-
-void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
-{
-	static char *saved_kbuild_dir;
-	static char *saved_kbuild_include_opts;
-	int err;
-
-	if (!kbuild_dir || !kbuild_include_opts)
-		return;
-
-	*kbuild_dir = NULL;
-	*kbuild_include_opts = NULL;
-
-	if (saved_kbuild_dir && saved_kbuild_include_opts &&
-	    !IS_ERR(saved_kbuild_dir) && !IS_ERR(saved_kbuild_include_opts)) {
-		*kbuild_dir = strdup(saved_kbuild_dir);
-		*kbuild_include_opts = strdup(saved_kbuild_include_opts);
-
-		if (*kbuild_dir && *kbuild_include_opts)
-			return;
-
-		zfree(kbuild_dir);
-		zfree(kbuild_include_opts);
-		/*
-		 * Don't fall through: it may breaks saved_kbuild_dir and
-		 * saved_kbuild_include_opts if detect them again when
-		 * memory is low.
-		 */
-		return;
-	}
-
-	if (llvm_param.kbuild_dir && !llvm_param.kbuild_dir[0]) {
-		pr_debug("[llvm.kbuild-dir] is set to \"\" deliberately.\n");
-		pr_debug("Skip kbuild options detection.\n");
-		goto errout;
-	}
-
-	err = detect_kbuild_dir(kbuild_dir);
-	if (err) {
-		pr_warning(
-"WARNING:\tunable to get correct kernel building directory.\n"
-"Hint:\tSet correct kbuild directory using 'kbuild-dir' option in [llvm]\n"
-"     \tsection of ~/.perfconfig or set it to \"\" to suppress kbuild\n"
-"     \tdetection.\n\n");
-		goto errout;
-	}
-
-	pr_debug("Kernel build dir is set to %s\n", *kbuild_dir);
-	force_set_env("KBUILD_DIR", *kbuild_dir);
-	force_set_env("KBUILD_OPTS", llvm_param.kbuild_opts);
-	err = read_from_pipe(kinc_fetch_script,
-			     (void **)kbuild_include_opts,
-			     NULL);
-	if (err) {
-		pr_warning(
-"WARNING:\tunable to get kernel include directories from '%s'\n"
-"Hint:\tTry set clang include options using 'clang-bpf-cmd-template'\n"
-"     \toption in [llvm] section of ~/.perfconfig and set 'kbuild-dir'\n"
-"     \toption in [llvm] to \"\" to suppress this detection.\n\n",
-			*kbuild_dir);
-
-		zfree(kbuild_dir);
-		goto errout;
-	}
-
-	pr_debug("include option is set to %s\n", *kbuild_include_opts);
-
-	saved_kbuild_dir = strdup(*kbuild_dir);
-	saved_kbuild_include_opts = strdup(*kbuild_include_opts);
-
-	if (!saved_kbuild_dir || !saved_kbuild_include_opts) {
-		zfree(&saved_kbuild_dir);
-		zfree(&saved_kbuild_include_opts);
-	}
-	return;
-errout:
-	saved_kbuild_dir = ERR_PTR(-EINVAL);
-	saved_kbuild_include_opts = ERR_PTR(-EINVAL);
-}
-
-int llvm__get_nr_cpus(void)
-{
-	static int nr_cpus_avail = 0;
-	char serr[STRERR_BUFSIZE];
-
-	if (nr_cpus_avail > 0)
-		return nr_cpus_avail;
-
-	nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
-	if (nr_cpus_avail <= 0) {
-		pr_err(
-"WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr)));
-		nr_cpus_avail = 128;
-	}
-	return nr_cpus_avail;
-}
-
-void llvm__dump_obj(const char *path, void *obj_buf, size_t size)
-{
-	char *obj_path = strdup(path);
-	FILE *fp;
-	char *p;
-
-	if (!obj_path) {
-		pr_warning("WARNING: Not enough memory, skip object dumping\n");
-		return;
-	}
-
-	p = strrchr(obj_path, '.');
-	if (!p || (strcmp(p, ".c") != 0)) {
-		pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n",
-			   obj_path);
-		goto out;
-	}
-
-	p[1] = 'o';
-	fp = fopen(obj_path, "wb");
-	if (!fp) {
-		pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n",
-			   obj_path, strerror(errno));
-		goto out;
-	}
-
-	pr_debug("LLVM: dumping %s\n", obj_path);
-	if (fwrite(obj_buf, size, 1, fp) != 1)
-		pr_debug("WARNING: failed to write to file '%s': %s, skip object dumping\n", obj_path, strerror(errno));
-	fclose(fp);
-out:
-	free(obj_path);
-}
-
-int llvm__compile_bpf(const char *path, void **p_obj_buf,
-		      size_t *p_obj_buf_sz)
-{
-	size_t obj_buf_sz;
-	void *obj_buf = NULL;
-	int err, nr_cpus_avail;
-	unsigned int kernel_version;
-	char linux_version_code_str[64];
-	const char *clang_opt = llvm_param.clang_opt;
-	char clang_path[PATH_MAX], llc_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
-	char serr[STRERR_BUFSIZE];
-	char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
-	     *perf_bpf_include_opts = NULL;
-	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *pipe_template = NULL;
-	const char *opts = llvm_param.opts;
-	char *command_echo = NULL, *command_out;
-	char *libbpf_include_dir = system_path(LIBBPF_INCLUDE_DIR);
-
-	if (path[0] != '-' && realpath(path, abspath) == NULL) {
-		err = errno;
-		pr_err("ERROR: problems with path %s: %s\n",
-		       path, str_error_r(err, serr, sizeof(serr)));
-		return -err;
-	}
-
-	if (!template)
-		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
-
-	err = search_program_and_warn(llvm_param.clang_path,
-			     "clang", clang_path);
-	if (err)
-		return -ENOENT;
-
-	/*
-	 * This is an optional work. Even it fail we can continue our
-	 * work. Needn't check error return.
-	 */
-	llvm__get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
-
-	nr_cpus_avail = llvm__get_nr_cpus();
-	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
-		 nr_cpus_avail);
-
-	if (fetch_kernel_version(&kernel_version, NULL, 0))
-		kernel_version = 0;
-
-	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
-		 "0x%x", kernel_version);
-	if (asprintf(&perf_bpf_include_opts, "-I%s/", libbpf_include_dir) < 0)
-		goto errout;
-	force_set_env("NR_CPUS", nr_cpus_avail_str);
-	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
-	force_set_env("CLANG_EXEC", clang_path);
-	force_set_env("CLANG_OPTIONS", clang_opt);
-	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
-	force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
-	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
-
-	if (opts) {
-		err = search_program_and_warn(llvm_param.llc_path, "llc", llc_path);
-		if (err)
-			goto errout;
-
-		err = -ENOMEM;
-		if (asprintf(&pipe_template, "%s -emit-llvm | %s -march=bpf %s -filetype=obj -o -",
-			      template, llc_path, opts) < 0) {
-			pr_err("ERROR:\tnot enough memory to setup command line\n");
-			goto errout;
-		}
-
-		template = pipe_template;
-
-	}
-
-	/*
-	 * Since we may reset clang's working dir, path of source file
-	 * should be transferred into absolute path, except we want
-	 * stdin to be source file (testing).
-	 */
-	force_set_env("CLANG_SOURCE",
-		      (path[0] == '-') ? path : abspath);
-
-	pr_debug("llvm compiling command template: %s\n", template);
-
-	/*
-	 * Below, substitute control characters for values that can cause the
-	 * echo to misbehave, then substitute the values back.
-	 */
-	err = -ENOMEM;
-	if (asprintf(&command_echo, "echo -n \a%s\a", template) < 0)
-		goto errout;
-
-#define SWAP_CHAR(a, b) do { if (*p == a) *p = b; } while (0)
-	for (char *p = command_echo; *p; p++) {
-		SWAP_CHAR('<', '\001');
-		SWAP_CHAR('>', '\002');
-		SWAP_CHAR('"', '\003');
-		SWAP_CHAR('\'', '\004');
-		SWAP_CHAR('|', '\005');
-		SWAP_CHAR('&', '\006');
-		SWAP_CHAR('\a', '"');
-	}
-	err = read_from_pipe(command_echo, (void **) &command_out, NULL);
-	if (err)
-		goto errout;
-
-	for (char *p = command_out; *p; p++) {
-		SWAP_CHAR('\001', '<');
-		SWAP_CHAR('\002', '>');
-		SWAP_CHAR('\003', '"');
-		SWAP_CHAR('\004', '\'');
-		SWAP_CHAR('\005', '|');
-		SWAP_CHAR('\006', '&');
-	}
-#undef SWAP_CHAR
-	pr_debug("llvm compiling command : %s\n", command_out);
-
-	err = read_from_pipe(template, &obj_buf, &obj_buf_sz);
-	if (err) {
-		pr_err("ERROR:\tunable to compile %s\n", path);
-		pr_err("Hint:\tCheck error message shown above.\n");
-		pr_err("Hint:\tYou can also pre-compile it into .o using:\n");
-		pr_err("     \t\tclang --target=bpf -O2 -c %s\n", path);
-		pr_err("     \twith proper -I and -D options.\n");
-		goto errout;
-	}
-
-	free(command_echo);
-	free(command_out);
-	free(kbuild_dir);
-	free(kbuild_include_opts);
-	free(perf_bpf_include_opts);
-	free(libbpf_include_dir);
-
-	if (!p_obj_buf)
-		free(obj_buf);
-	else
-		*p_obj_buf = obj_buf;
-
-	if (p_obj_buf_sz)
-		*p_obj_buf_sz = obj_buf_sz;
-	return 0;
-errout:
-	free(command_echo);
-	free(kbuild_dir);
-	free(kbuild_include_opts);
-	free(obj_buf);
-	free(perf_bpf_include_opts);
-	free(libbpf_include_dir);
-	free(pipe_template);
-	if (p_obj_buf)
-		*p_obj_buf = NULL;
-	if (p_obj_buf_sz)
-		*p_obj_buf_sz = 0;
-	return err;
-}
-
-int llvm__search_clang(void)
-{
-	char clang_path[PATH_MAX];
-
-	return search_program_and_warn(llvm_param.clang_path, "clang", clang_path);
-}
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
deleted file mode 100644
index 7878a0e3fa98..000000000000
--- a/tools/perf/util/llvm-utils.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2015, Wang Nan <wangnan0@huawei.com>
- * Copyright (C) 2015, Huawei Inc.
- */
-#ifndef __LLVM_UTILS_H
-#define __LLVM_UTILS_H
-
-#include <stdbool.h>
-
-struct llvm_param {
-	/* Path of clang executable */
-	const char *clang_path;
-	/* Path of llc executable */
-	const char *llc_path;
-	/*
-	 * Template of clang bpf compiling. 5 env variables
-	 * can be used:
-	 *   $CLANG_EXEC:		Path to clang.
-	 *   $CLANG_OPTIONS:		Extra options to clang.
-	 *   $KERNEL_INC_OPTIONS:	Kernel include directories.
-	 *   $WORKING_DIR:		Kernel source directory.
-	 *   $CLANG_SOURCE:		Source file to be compiled.
-	 */
-	const char *clang_bpf_cmd_template;
-	/* Will be filled in $CLANG_OPTIONS */
-	const char *clang_opt;
-	/*
-	 * If present it'll add -emit-llvm to $CLANG_OPTIONS to pipe
-	 * the clang output to llc, useful for new llvm options not
-	 * yet selectable via 'clang -mllvm option', such as -mattr=dwarfris
-	 * in clang 6.0/llvm 7
-	 */
-	const char *opts;
-	/* Where to find kbuild system */
-	const char *kbuild_dir;
-	/*
-	 * Arguments passed to make, like 'ARCH=arm' if doing cross
-	 * compiling. Should not be used for dynamic compiling.
-	 */
-	const char *kbuild_opts;
-	/*
-	 * Default is false. If set to true, write compiling result
-	 * to object file.
-	 */
-	bool dump_obj;
-	/*
-	 * Default is false. If one of the above fields is set by user
-	 * explicitly then user_set_llvm is set to true. This is used
-	 * for perf test. If user doesn't set anything in .perfconfig
-	 * and clang is not found, don't trigger llvm test.
-	 */
-	bool user_set_param;
-};
-
-extern struct llvm_param llvm_param;
-int perf_llvm_config(const char *var, const char *value);
-
-int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz);
-
-/* This function is for test__llvm() use only */
-int llvm__search_clang(void);
-
-/* Following functions are reused by builtin clang support */
-void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts);
-int llvm__get_nr_cpus(void);
-
-void llvm__dump_obj(const char *path, void *obj_buf, size_t size);
-#endif
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
index fa16532c971c..1a7248ff3889 100644
--- a/tools/perf/util/lock-contention.h
+++ b/tools/perf/util/lock-contention.h
@@ -9,9 +9,11 @@ struct lock_filter {
 	int			nr_types;
 	int			nr_addrs;
 	int			nr_syms;
+	int			nr_cgrps;
 	unsigned int		*types;
 	unsigned long		*addrs;
 	char			**syms;
+	u64			*cgrps;
 };
 
 struct lock_stat {
@@ -136,6 +138,7 @@ struct lock_contention {
 	struct hlist_head *result;
 	struct lock_filter *filters;
 	struct lock_contention_fails fails;
+	struct rb_root cgroups;
 	unsigned long map_nr_entries;
 	int max_stack;
 	int stack_skip;
@@ -151,7 +154,7 @@ int lock_contention_prepare(struct lock_contention *con);
 int lock_contention_start(void);
 int lock_contention_stop(void);
 int lock_contention_read(struct lock_contention *con);
-int lock_contention_finish(void);
+int lock_contention_finish(struct lock_contention *con);
 
 #else  /* !HAVE_BPF_SKEL */
 
@@ -162,7 +165,10 @@ static inline int lock_contention_prepare(struct lock_contention *con __maybe_un
 
 static inline int lock_contention_start(void) { return 0; }
 static inline int lock_contention_stop(void) { return 0; }
-static inline int lock_contention_finish(void) { return 0; }
+static inline int lock_contention_finish(struct lock_contention *con __maybe_unused)
+{
+	return 0;
+}
 
 static inline int lock_contention_read(struct lock_contention *con __maybe_unused)
 {
diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
index 51424cdc3b68..af9a97612f9d 100644
--- a/tools/perf/util/lzma.c
+++ b/tools/perf/util/lzma.c
@@ -45,15 +45,13 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 
 	infile = fopen(input, "rb");
 	if (!infile) {
-		pr_err("lzma: fopen failed on %s: '%s'\n",
-		       input, strerror(errno));
+		pr_debug("lzma: fopen failed on %s: '%s'\n", input, strerror(errno));
 		return -1;
 	}
 
 	ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED);
 	if (ret != LZMA_OK) {
-		pr_err("lzma: lzma_stream_decoder failed %s (%d)\n",
-			lzma_strerror(ret), ret);
+		pr_debug("lzma: lzma_stream_decoder failed %s (%d)\n", lzma_strerror(ret), ret);
 		goto err_fclose;
 	}
 
@@ -68,7 +66,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			strm.avail_in = fread(buf_in, 1, sizeof(buf_in), infile);
 
 			if (ferror(infile)) {
-				pr_err("lzma: read error: %s\n", strerror(errno));
+				pr_debug("lzma: read error: %s\n", strerror(errno));
 				goto err_lzma_end;
 			}
 
@@ -82,7 +80,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			ssize_t write_size = sizeof(buf_out) - strm.avail_out;
 
 			if (writen(output_fd, buf_out, write_size) != write_size) {
-				pr_err("lzma: write error: %s\n", strerror(errno));
+				pr_debug("lzma: write error: %s\n", strerror(errno));
 				goto err_lzma_end;
 			}
 
@@ -94,7 +92,7 @@ int lzma_decompress_to_file(const char *input, int output_fd)
 			if (ret == LZMA_STREAM_END)
 				break;
 
-			pr_err("lzma: failed %s\n", lzma_strerror(ret));
+			pr_debug("lzma: failed %s\n", lzma_strerror(ret));
 			goto err_lzma_end;
 		}
 	}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f4cb41ee23cd..527517db3182 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -43,9 +43,6 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
-static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd,
-				     struct thread *th, bool lock);
-
 static struct dso *machine__kernel_dso(struct machine *machine)
 {
 	return map__dso(machine->vmlinux_map);
@@ -58,36 +55,6 @@ static void dsos__init(struct dsos *dsos)
 	init_rwsem(&dsos->lock);
 }
 
-static void machine__threads_init(struct machine *machine)
-{
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-		threads->entries = RB_ROOT_CACHED;
-		init_rwsem(&threads->lock);
-		threads->nr = 0;
-		INIT_LIST_HEAD(&threads->dead);
-		threads->last_match = NULL;
-	}
-}
-
-static int thread_rb_node__cmp_tid(const void *key, const struct rb_node *nd)
-{
-	int to_find = (int) *((pid_t *)key);
-
-	return to_find - (int)thread__tid(rb_entry(nd, struct thread_rb_node, rb_node)->thread);
-}
-
-static struct thread_rb_node *thread_rb_node__find(const struct thread *th,
-						   struct rb_root *tree)
-{
-	pid_t to_find = thread__tid(th);
-	struct rb_node *nd = rb_find(&to_find, tree, thread_rb_node__cmp_tid);
-
-	return rb_entry(nd, struct thread_rb_node, rb_node);
-}
-
 static int machine__set_mmap_name(struct machine *machine)
 {
 	if (machine__is_host(machine))
@@ -121,7 +88,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
 
-	machine__threads_init(machine);
+	threads__init(&machine->threads);
 
 	machine->vdso_info = NULL;
 	machine->env = NULL;
@@ -222,27 +189,11 @@ static void dsos__exit(struct dsos *dsos)
 
 void machine__delete_threads(struct machine *machine)
 {
-	struct rb_node *nd;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-		down_write(&threads->lock);
-		nd = rb_first_cached(&threads->entries);
-		while (nd) {
-			struct thread_rb_node *trb = rb_entry(nd, struct thread_rb_node, rb_node);
-
-			nd = rb_next(nd);
-			__machine__remove_thread(machine, trb, trb->thread, false);
-		}
-		up_write(&threads->lock);
-	}
+	threads__remove_all_threads(&machine->threads);
 }
 
 void machine__exit(struct machine *machine)
 {
-	int i;
-
 	if (machine == NULL)
 		return;
 
@@ -255,12 +206,7 @@ void machine__exit(struct machine *machine)
 	zfree(&machine->current_tid);
 	zfree(&machine->kallsyms_filename);
 
-	machine__delete_threads(machine);
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-
-		exit_rwsem(&threads->lock);
-	}
+	threads__exit(&machine->threads);
 }
 
 void machine__delete(struct machine *machine)
@@ -441,7 +387,7 @@ static struct thread *findnew_guest_code(struct machine *machine,
 		return NULL;
 
 	/* Assume maps are set up if there are any */
-	if (maps__nr_maps(thread__maps(thread)))
+	if (!maps__empty(thread__maps(thread)))
 		return thread;
 
 	host_thread = machine__find_thread(host_machine, -1, pid);
@@ -454,7 +400,7 @@ static struct thread *findnew_guest_code(struct machine *machine,
 	 * Guest code can be found in hypervisor process at the same address
 	 * so copy host maps.
 	 */
-	err = maps__clone(thread, thread__maps(host_thread));
+	err = maps__copy_from(thread__maps(thread), thread__maps(host_thread));
 	thread__put(host_thread);
 	if (err)
 		goto out_err;
@@ -527,7 +473,7 @@ static void machine__update_thread_pid(struct machine *machine,
 	if (thread__pid(th) == thread__tid(th))
 		return;
 
-	leader = __machine__findnew_thread(machine, thread__pid(th), thread__pid(th));
+	leader = machine__findnew_thread(machine, thread__pid(th), thread__pid(th));
 	if (!leader)
 		goto out_err;
 
@@ -562,159 +508,55 @@ out_err:
 }
 
 /*
- * Front-end cache - TID lookups come in blocks,
- * so most of the time we dont have to look up
- * the full rbtree:
- */
-static struct thread*
-__threads__get_last_match(struct threads *threads, struct machine *machine,
-			  int pid, int tid)
-{
-	struct thread *th;
-
-	th = threads->last_match;
-	if (th != NULL) {
-		if (thread__tid(th) == tid) {
-			machine__update_thread_pid(machine, th, pid);
-			return thread__get(th);
-		}
-		thread__put(threads->last_match);
-		threads->last_match = NULL;
-	}
-
-	return NULL;
-}
-
-static struct thread*
-threads__get_last_match(struct threads *threads, struct machine *machine,
-			int pid, int tid)
-{
-	struct thread *th = NULL;
-
-	if (perf_singlethreaded)
-		th = __threads__get_last_match(threads, machine, pid, tid);
-
-	return th;
-}
-
-static void
-__threads__set_last_match(struct threads *threads, struct thread *th)
-{
-	thread__put(threads->last_match);
-	threads->last_match = thread__get(th);
-}
-
-static void
-threads__set_last_match(struct threads *threads, struct thread *th)
-{
-	if (perf_singlethreaded)
-		__threads__set_last_match(threads, th);
-}
-
-/*
  * Caller must eventually drop thread->refcnt returned with a successful
  * lookup/new thread inserted.
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread *__machine__findnew_thread(struct machine *machine,
+						pid_t pid,
+						pid_t tid,
+						bool create)
 {
-	struct rb_node **p = &threads->entries.rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct thread *th;
-	struct thread_rb_node *nd;
-	bool leftmost = true;
+	struct thread *th = threads__find(&machine->threads, tid);
+	bool created;
 
-	th = threads__get_last_match(threads, machine, pid, tid);
-	if (th)
+	if (th) {
+		machine__update_thread_pid(machine, th, pid);
 		return th;
-
-	while (*p != NULL) {
-		parent = *p;
-		th = rb_entry(parent, struct thread_rb_node, rb_node)->thread;
-
-		if (thread__tid(th) == tid) {
-			threads__set_last_match(threads, th);
-			machine__update_thread_pid(machine, th, pid);
-			return thread__get(th);
-		}
-
-		if (tid < thread__tid(th))
-			p = &(*p)->rb_left;
-		else {
-			p = &(*p)->rb_right;
-			leftmost = false;
-		}
 	}
-
 	if (!create)
 		return NULL;
 
-	th = thread__new(pid, tid);
-	if (th == NULL)
-		return NULL;
-
-	nd = malloc(sizeof(*nd));
-	if (nd == NULL) {
-		thread__put(th);
-		return NULL;
-	}
-	nd->thread = th;
-
-	rb_link_node(&nd->rb_node, parent, p);
-	rb_insert_color_cached(&nd->rb_node, &threads->entries, leftmost);
-	/*
-	 * We have to initialize maps separately after rb tree is updated.
-	 *
-	 * The reason is that we call machine__findnew_thread within
-	 * thread__init_maps to find the thread leader and that would screwed
-	 * the rb tree.
-	 */
-	if (thread__init_maps(th, machine)) {
-		pr_err("Thread init failed thread %d\n", pid);
-		rb_erase_cached(&nd->rb_node, &threads->entries);
-		RB_CLEAR_NODE(&nd->rb_node);
-		free(nd);
-		thread__put(th);
-		return NULL;
-	}
-	/*
-	 * It is now in the rbtree, get a ref
-	 */
-	threads__set_last_match(threads, th);
-	++threads->nr;
-
-	return thread__get(th);
-}
+	th = threads__findnew(&machine->threads, pid, tid, &created);
+	if (created) {
+		/*
+		 * We have to initialize maps separately after rb tree is
+		 * updated.
+		 *
+		 * The reason is that we call machine__findnew_thread within
+		 * thread__init_maps to find the thread leader and that would
+		 * screwed the rb tree.
+		 */
+		if (thread__init_maps(th, machine)) {
+			pr_err("Thread init failed thread %d\n", pid);
+			threads__remove(&machine->threads, th);
+			thread__put(th);
+			return NULL;
+		}
+	} else
+		machine__update_thread_pid(machine, th, pid);
 
-struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
-{
-	return ____machine__findnew_thread(machine, machine__threads(machine, tid), pid, tid, true);
+	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
-				       pid_t tid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
 {
-	struct threads *threads = machine__threads(machine, tid);
-	struct thread *th;
-
-	down_write(&threads->lock);
-	th = __machine__findnew_thread(machine, pid, tid);
-	up_write(&threads->lock);
-	return th;
+	return __machine__findnew_thread(machine, pid, tid, /*create=*/true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
-	struct threads *threads = machine__threads(machine, tid);
-	struct thread *th;
-
-	down_read(&threads->lock);
-	th =  ____machine__findnew_thread(machine, threads, pid, tid, false);
-	up_read(&threads->lock);
-	return th;
+	return __machine__findnew_thread(machine, pid, tid, /*create=*/false);
 }
 
 /*
@@ -897,7 +739,6 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	struct symbol *sym;
 	struct dso *dso;
 	struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr);
-	bool put_map = false;
 	int err = 0;
 
 	if (!map) {
@@ -914,12 +755,6 @@ static int machine__process_ksymbol_register(struct machine *machine,
 			err = -ENOMEM;
 			goto out;
 		}
-		/*
-		 * The inserted map has a get on it, we need to put to release
-		 * the reference count here, but do it after all accesses are
-		 * done.
-		 */
-		put_map = true;
 		if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) {
 			dso->binary_type = DSO_BINARY_TYPE__OOL;
 			dso->data.file_size = event->ksymbol.len;
@@ -953,8 +788,7 @@ static int machine__process_ksymbol_register(struct machine *machine,
 	}
 	dso__insert_symbol(dso, sym);
 out:
-	if (put_map)
-		map__put(map);
+	map__put(map);
 	return err;
 }
 
@@ -969,7 +803,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 	if (!map)
 		return 0;
 
-	if (RC_CHK_ACCESS(map) != RC_CHK_ACCESS(machine->vmlinux_map))
+	if (!RC_CHK_EQUAL(map, machine->vmlinux_map))
 		maps__remove(machine__kernel_maps(machine), map);
 	else {
 		struct dso *dso = map__dso(map);
@@ -978,7 +812,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 		if (sym)
 			dso__delete_symbol(dso, sym);
 	}
-
+	map__put(map);
 	return 0;
 }
 
@@ -1006,11 +840,11 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 		perf_event__fprintf_text_poke(event, machine, stdout);
 
 	if (!event->text_poke.new_len)
-		return 0;
+		goto out;
 
 	if (cpumode != PERF_RECORD_MISC_KERNEL) {
 		pr_debug("%s: unsupported cpumode - ignoring\n", __func__);
-		return 0;
+		goto out;
 	}
 
 	if (dso) {
@@ -1033,7 +867,8 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event,
 		pr_debug("Failed to find kernel text poke address map for %#" PRI_lx64 "\n",
 			 event->text_poke.addr);
 	}
-
+out:
+	map__put(map);
 	return 0;
 }
 
@@ -1121,29 +956,30 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 	return printed;
 }
 
-size_t machine__fprintf(struct machine *machine, FILE *fp)
-{
-	struct rb_node *nd;
-	size_t ret;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		struct threads *threads = &machine->threads[i];
-
-		down_read(&threads->lock);
+struct machine_fprintf_cb_args {
+	FILE *fp;
+	size_t printed;
+};
 
-		ret = fprintf(fp, "Threads: %u\n", threads->nr);
+static int machine_fprintf_cb(struct thread *thread, void *data)
+{
+	struct machine_fprintf_cb_args *args = data;
 
-		for (nd = rb_first_cached(&threads->entries); nd;
-		     nd = rb_next(nd)) {
-			struct thread *pos = rb_entry(nd, struct thread_rb_node, rb_node)->thread;
+	/* TODO: handle fprintf errors. */
+	args->printed += thread__fprintf(thread, args->fp);
+	return 0;
+}
 
-			ret += thread__fprintf(pos, fp);
-		}
+size_t machine__fprintf(struct machine *machine, FILE *fp)
+{
+	struct machine_fprintf_cb_args args = {
+		.fp = fp,
+		.printed = 0,
+	};
+	size_t ret = fprintf(fp, "Threads: %zu\n", threads__nr(&machine->threads));
 
-		up_read(&threads->lock);
-	}
-	return ret;
+	machine__for_each_thread(machine, machine_fprintf_cb, &args);
+	return ret + args.printed;
 }
 
 static struct dso *machine__get_kernel(struct machine *machine)
@@ -1215,7 +1051,9 @@ static int machine__get_running_kernel_start(struct machine *machine,
 
 	*start = addr;
 
-	err = kallsyms__get_function_start(filename, "_etext", &addr);
+	err = kallsyms__get_symbol_start(filename, "_edata", &addr);
+	if (err)
+		err = kallsyms__get_function_start(filename, "_etext", &addr);
 	if (!err)
 		*end = addr;
 
@@ -1284,33 +1122,47 @@ static u64 find_entry_trampoline(struct dso *dso)
 #define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
 #define X86_64_ENTRY_TRAMPOLINE		0x6000
 
+struct machine__map_x86_64_entry_trampolines_args {
+	struct maps *kmaps;
+	bool found;
+};
+
+static int machine__map_x86_64_entry_trampolines_cb(struct map *map, void *data)
+{
+	struct machine__map_x86_64_entry_trampolines_args *args = data;
+	struct map *dest_map;
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap || !is_entry_trampoline(kmap->name))
+		return 0;
+
+	dest_map = maps__find(args->kmaps, map__pgoff(map));
+	if (RC_CHK_ACCESS(dest_map) != RC_CHK_ACCESS(map))
+		map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
+
+	map__put(dest_map);
+	args->found = true;
+	return 0;
+}
+
 /* Map x86_64 PTI entry trampolines */
 int machine__map_x86_64_entry_trampolines(struct machine *machine,
 					  struct dso *kernel)
 {
-	struct maps *kmaps = machine__kernel_maps(machine);
+	struct machine__map_x86_64_entry_trampolines_args args = {
+		.kmaps = machine__kernel_maps(machine),
+		.found = false,
+	};
 	int nr_cpus_avail, cpu;
-	bool found = false;
-	struct map_rb_node *rb_node;
 	u64 pgoff;
 
 	/*
 	 * In the vmlinux case, pgoff is a virtual address which must now be
 	 * mapped to a vmlinux offset.
 	 */
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *dest_map, *map = rb_node->map;
-		struct kmap *kmap = __map__kmap(map);
+	maps__for_each_map(args.kmaps, machine__map_x86_64_entry_trampolines_cb, &args);
 
-		if (!kmap || !is_entry_trampoline(kmap->name))
-			continue;
-
-		dest_map = maps__find(kmaps, map__pgoff(map));
-		if (dest_map != map)
-			map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map)));
-		found = true;
-	}
-	if (found || machine->trampolines_mapped)
+	if (args.found || machine->trampolines_mapped)
 		return 0;
 
 	pgoff = find_entry_trampoline(kernel);
@@ -1358,8 +1210,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 	if (machine->vmlinux_map == NULL)
 		return -ENOMEM;
 
-	map__set_map_ip(machine->vmlinux_map, identity__map_ip);
-	map__set_unmap_ip(machine->vmlinux_map, identity__map_ip);
+	map__set_mapping_type(machine->vmlinux_map, MAPPING_TYPE__IDENTITY);
 	return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
 }
 
@@ -1530,8 +1381,10 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 		return 0;
 
 	long_name = strdup(path);
-	if (long_name == NULL)
+	if (long_name == NULL) {
+		map__put(map);
 		return -ENOMEM;
+	}
 
 	dso = map__dso(map);
 	dso__set_long_name(dso, long_name, true);
@@ -1545,7 +1398,7 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo
 		dso->symtab_type++;
 		dso->comp = m->comp;
 	}
-
+	map__put(map);
 	return 0;
 }
 
@@ -1749,12 +1602,13 @@ int machine__create_kernel_maps(struct machine *machine)
 
 	if (end == ~0ULL) {
 		/* update end address of the kernel map using adjacent module address */
-		struct map_rb_node *rb_node = maps__find_node(machine__kernel_maps(machine),
-							machine__kernel_map(machine));
-		struct map_rb_node *next = map_rb_node__next(rb_node);
+		struct map *next = maps__find_next_entry(machine__kernel_maps(machine),
+							 machine__kernel_map(machine));
 
-		if (next)
-			machine__set_kernel_mmap(machine, start, map__start(next->map));
+		if (next) {
+			machine__set_kernel_mmap(machine, start, map__start(next));
+			map__put(next);
+		}
 	}
 
 out_put:
@@ -2048,36 +1902,9 @@ out_problem:
 	return 0;
 }
 
-static void __machine__remove_thread(struct machine *machine, struct thread_rb_node *nd,
-				     struct thread *th, bool lock)
-{
-	struct threads *threads = machine__threads(machine, thread__tid(th));
-
-	if (!nd)
-		nd = thread_rb_node__find(th, &threads->entries.rb_root);
-
-	if (threads->last_match && RC_CHK_ACCESS(threads->last_match) == RC_CHK_ACCESS(th))
-		threads__set_last_match(threads, NULL);
-
-	if (lock)
-		down_write(&threads->lock);
-
-	BUG_ON(refcount_read(thread__refcnt(th)) == 0);
-
-	thread__put(nd->thread);
-	rb_erase_cached(&nd->rb_node, &threads->entries);
-	RB_CLEAR_NODE(&nd->rb_node);
-	--threads->nr;
-
-	free(nd);
-
-	if (lock)
-		up_write(&threads->lock);
-}
-
 void machine__remove_thread(struct machine *machine, struct thread *th)
 {
-	return __machine__remove_thread(machine, NULL, th, true);
+	return threads__remove(&machine->threads, th);
 }
 
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
@@ -2156,9 +1983,13 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
-		thread__put(thread);
-
+	if (thread != NULL) {
+		if (symbol_conf.keep_exited_threads)
+			thread__set_exited(thread, /*exited=*/true);
+		else
+			machine__remove_thread(machine, thread);
+	}
+	thread__put(thread);
 	return 0;
 }
 
@@ -2211,9 +2042,7 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 
 static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-	if (!regexec(regex, sym->name, 0, NULL, 0))
-		return true;
-	return false;
+	return regexec(regex, sym->name, 0, NULL, 0) == 0;
 }
 
 static void ip__resolve_ams(struct thread *thread,
@@ -2390,8 +2219,7 @@ static int add_callchain_ip(struct thread *thread,
 				      iter_cycles, branch_from, srcline);
 out:
 	addr_location__exit(&al);
-	maps__put(ms.maps);
-	map__put(ms.map);
+	map_symbol__exit(&ms);
 	return err;
 }
 
@@ -2622,16 +2450,18 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread,
 		save_lbr_cursor_node(thread, cursor, i);
 	}
 
-	/* Add LBR ip from first entries.to */
-	ip = entries[0].to;
-	flags = &entries[0].flags;
-	*branch_from = entries[0].from;
-	err = add_callchain_ip(thread, cursor, parent,
-			       root_al, &cpumode, ip,
-			       true, flags, NULL,
-			       *branch_from);
-	if (err)
-		return err;
+	if (lbr_nr > 0) {
+		/* Add LBR ip from first entries.to */
+		ip = entries[0].to;
+		flags = &entries[0].flags;
+		*branch_from = entries[0].from;
+		err = add_callchain_ip(thread, cursor, parent,
+				root_al, &cpumode, ip,
+				true, flags, NULL,
+				*branch_from);
+		if (err)
+			return err;
+	}
 
 	return 0;
 }
@@ -3115,8 +2945,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms
 		if (ret != 0)
 			return ret;
 	}
-	map__put(ilist_ms.map);
-	maps__put(ilist_ms.maps);
+	map_symbol__exit(&ilist_ms);
 
 	return ret;
 }
@@ -3209,23 +3038,7 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv)
 {
-	struct threads *threads;
-	struct rb_node *nd;
-	int rc = 0;
-	int i;
-
-	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
-		threads = &machine->threads[i];
-		for (nd = rb_first_cached(&threads->entries); nd;
-		     nd = rb_next(nd)) {
-			struct thread_rb_node *trb = rb_entry(nd, struct thread_rb_node, rb_node);
-
-			rc = fn(trb->thread, priv);
-			if (rc != 0)
-				return rc;
-		}
-	}
-	return rc;
+	return threads__for_each_thread(&machine->threads, fn, priv);
 }
 
 int machines__for_each_thread(struct machines *machines,
@@ -3249,6 +3062,36 @@ int machines__for_each_thread(struct machines *machines,
 	return rc;
 }
 
+
+static int thread_list_cb(struct thread *thread, void *data)
+{
+	struct list_head *list = data;
+	struct thread_list *entry = malloc(sizeof(*entry));
+
+	if (!entry)
+		return -ENOMEM;
+
+	entry->thread = thread__get(thread);
+	list_add_tail(&entry->list, list);
+	return 0;
+}
+
+int machine__thread_list(struct machine *machine, struct list_head *list)
+{
+	return machine__for_each_thread(machine, thread_list_cb, list);
+}
+
+void thread_list__delete(struct list_head *list)
+{
+	struct thread_list *pos, *next;
+
+	list_for_each_entry_safe(pos, next, list, list) {
+		thread__zput(pos->thread);
+		list_del(&pos->list);
+		free(pos);
+	}
+}
+
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
 	if (cpu < 0 || (size_t)cpu >= machine->current_tid_sz)
@@ -3396,16 +3239,8 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
 {
 	struct maps *maps = machine__kernel_maps(machine);
-	struct map_rb_node *pos;
-	int err = 0;
 
-	maps__for_each_entry(maps, pos) {
-		err = fn(pos->map, priv);
-		if (err != 0) {
-			break;
-		}
-	}
-	return err;
+	return maps__for_each_map(maps, fn, priv);
 }
 
 bool machine__is_lock_function(struct machine *machine, u64 addr)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index d034ecaf89c1..e28c787616fe 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -7,6 +7,7 @@
 #include "maps.h"
 #include "dsos.h"
 #include "rwsem.h"
+#include "threads.h"
 
 struct addr_location;
 struct branch_stack;
@@ -28,17 +29,6 @@ extern const char *ref_reloc_sym_names[];
 
 struct vdso_info;
 
-#define THREADS__TABLE_BITS	8
-#define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
-
-struct threads {
-	struct rb_root_cached  entries;
-	struct rw_semaphore    lock;
-	unsigned int	       nr;
-	struct list_head       dead;
-	struct thread	       *last_match;
-};
-
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -49,7 +39,7 @@ struct machine {
 	char		  *root_dir;
 	char		  *mmap_name;
 	char		  *kallsyms_filename;
-	struct threads    threads[THREADS__TABLE_SIZE];
+	struct threads    threads;
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
 	struct dsos	  dsos;
@@ -70,12 +60,6 @@ struct machine {
 	bool		  trampolines_mapped;
 };
 
-static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
-{
-	/* Cast it to handle tid == -1 */
-	return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
-}
-
 /*
  * The main kernel (vmlinux) map
  */
@@ -221,7 +205,6 @@ bool machine__is(struct machine *machine, const char *arch);
 bool machine__normalized_is(struct machine *machine, const char *arch);
 int machine__nr_cpus_avail(struct machine *machine);
 
-struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 
 struct dso *machine__findnew_dso_id(struct machine *machine, const char *filename, struct dso_id *id);
@@ -281,6 +264,16 @@ int machines__for_each_thread(struct machines *machines,
 			      int (*fn)(struct thread *thread, void *p),
 			      void *priv);
 
+struct thread_list {
+	struct list_head	 list;
+	struct thread		*thread;
+};
+
+/* Make a list of struct thread_list based on threads in the machine. */
+int machine__thread_list(struct machine *machine, struct list_head *list);
+/* Free up the nodes within the thread_list list. */
+void thread_list__delete(struct list_head *list);
+
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
 int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f64b83004421..14a5ea70d81e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -109,8 +109,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
 	map__set_pgoff(map, pgoff);
 	map__set_reloc(map, 0);
 	map__set_dso(map, dso__get(dso));
-	map__set_map_ip(map, map__dso_map_ip);
-	map__set_unmap_ip(map, map__dso_unmap_ip);
+	map__set_mapping_type(map, MAPPING_TYPE__DSO);
 	map__set_erange_warned(map, false);
 	refcount_set(map__refcnt(map), 1);
 }
@@ -169,10 +168,11 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
+		assert(!dso->kernel);
 		map__init(result, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			map->map_ip = map->unmap_ip = identity__map_ip;
+			map->mapping_type = MAPPING_TYPE__IDENTITY;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -553,10 +553,6 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 	if (dso->rel)
 		return rip - map__pgoff(map);
 
-	/*
-	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
-	 * but all kernel modules are ET_REL, so won't get here.
-	 */
 	if (dso->kernel == DSO_SPACE__USER)
 		return rip + dso->text_offset;
 
@@ -585,10 +581,6 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	if (dso->rel)
 		return map__unmap_ip(map, ip + map__pgoff(map));
 
-	/*
-	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
-	 * but all kernel modules are ET_REL, so won't get here.
-	 */
 	if (dso->kernel == DSO_SPACE__USER)
 		return map__unmap_ip(map, ip - dso->text_offset);
 
@@ -630,18 +622,3 @@ struct maps *map__kmaps(struct map *map)
 	}
 	return kmap->kmaps;
 }
-
-u64 map__dso_map_ip(const struct map *map, u64 ip)
-{
-	return ip - map__start(map) + map__pgoff(map);
-}
-
-u64 map__dso_unmap_ip(const struct map *map, u64 ip)
-{
-	return ip + map__start(map) - map__pgoff(map);
-}
-
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip)
-{
-	return ip;
-}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 1b53d53adc86..49756716cb13 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -16,23 +16,25 @@ struct dso;
 struct maps;
 struct machine;
 
+enum mapping_type {
+	/* map__map_ip/map__unmap_ip are given as offsets in the DSO. */
+	MAPPING_TYPE__DSO,
+	/* map__map_ip/map__unmap_ip are just the given ip value. */
+	MAPPING_TYPE__IDENTITY,
+};
+
 DECLARE_RC_STRUCT(map) {
 	u64			start;
 	u64			end;
-	bool			erange_warned:1;
-	bool			priv:1;
-	u32			prot;
 	u64			pgoff;
 	u64			reloc;
-
-	/* ip -> dso rip */
-	u64			(*map_ip)(const struct map *, u64);
-	/* dso rip -> ip */
-	u64			(*unmap_ip)(const struct map *, u64);
-
 	struct dso		*dso;
 	refcount_t		refcnt;
+	u32			prot;
 	u32			flags;
+	enum mapping_type	mapping_type:8;
+	bool			erange_warned;
+	bool			priv;
 };
 
 struct kmap;
@@ -41,38 +43,11 @@ struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct maps *map__kmaps(struct map *map);
 
-/* ip -> dso rip */
-u64 map__dso_map_ip(const struct map *map, u64 ip);
-/* dso rip -> ip */
-u64 map__dso_unmap_ip(const struct map *map, u64 ip);
-/* Returns ip */
-u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip);
-
 static inline struct dso *map__dso(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->dso;
 }
 
-static inline u64 map__map_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->map_ip(map, ip);
-}
-
-static inline u64 map__unmap_ip(const struct map *map, u64 ip)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip(map, ip);
-}
-
-static inline void *map__map_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->map_ip;
-}
-
-static inline void* map__unmap_ip_ptr(struct map *map)
-{
-	return RC_CHK_ACCESS(map)->unmap_ip;
-}
-
 static inline u64 map__start(const struct map *map)
 {
 	return RC_CHK_ACCESS(map)->start;
@@ -123,6 +98,34 @@ static inline size_t map__size(const struct map *map)
 	return map__end(map) - map__start(map);
 }
 
+/* ip -> dso rip */
+static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
+{
+	return ip - map__start(map) + map__pgoff(map);
+}
+
+/* dso rip -> ip */
+static inline u64 map__dso_unmap_ip(const struct map *map, u64 rip)
+{
+	return rip + map__start(map) - map__pgoff(map);
+}
+
+static inline u64 map__map_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_map_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
+static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip)
+{
+	if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
+		return map__dso_unmap_ip(map, ip_or_rip);
+	else
+		return ip_or_rip;
+}
+
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
 
@@ -294,13 +297,13 @@ static inline void map__set_dso(struct map *map, struct dso *dso)
 	RC_CHK_ACCESS(map)->dso = dso;
 }
 
-static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip))
+static inline void map__set_mapping_type(struct map *map, enum mapping_type type)
 {
-	RC_CHK_ACCESS(map)->map_ip = map_ip;
+	RC_CHK_ACCESS(map)->mapping_type = type;
 }
 
-static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip))
+static inline enum mapping_type map__mapping_type(struct map *map)
 {
-	RC_CHK_ACCESS(map)->unmap_ip = unmap_ip;
+	return RC_CHK_ACCESS(map)->mapping_type;
 }
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/map_symbol.c b/tools/perf/util/map_symbol.c
new file mode 100644
index 000000000000..bef5079f2403
--- /dev/null
+++ b/tools/perf/util/map_symbol.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "map_symbol.h"
+#include "maps.h"
+#include "map.h"
+
+void map_symbol__exit(struct map_symbol *ms)
+{
+	maps__zput(ms->maps);
+	map__zput(ms->map);
+}
+
+void addr_map_symbol__exit(struct addr_map_symbol *ams)
+{
+	map_symbol__exit(&ams->ms);
+}
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
index e08817b0c30f..72d5ed938ed6 100644
--- a/tools/perf/util/map_symbol.h
+++ b/tools/perf/util/map_symbol.h
@@ -22,4 +22,8 @@ struct addr_map_symbol {
 	u64	      phys_addr;
 	u64	      data_page_size;
 };
+
+void map_symbol__exit(struct map_symbol *ms);
+void addr_map_symbol__exit(struct addr_map_symbol *ams);
+
 #endif // __PERF_MAP_SYMBOL
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 233438c95b53..ce13145a9f8e 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -6,158 +6,250 @@
 #include "dso.h"
 #include "map.h"
 #include "maps.h"
+#include "rwsem.h"
 #include "thread.h"
 #include "ui/ui.h"
 #include "unwind.h"
+#include <internal/rc_check.h>
 
-static void maps__init(struct maps *maps, struct machine *machine)
+/*
+ * Locking/sorting note:
+ *
+ * Sorting is done with the write lock, iteration and binary searching happens
+ * under the read lock requiring being sorted. There is a race between sorting
+ * releasing the write lock and acquiring the read lock for iteration/searching
+ * where another thread could insert and break the sorting of the maps. In
+ * practice inserting maps should be rare meaning that the race shouldn't lead
+ * to live lock. Removal of maps doesn't break being sorted.
+ */
+
+DECLARE_RC_STRUCT(maps) {
+	struct rw_semaphore lock;
+	/**
+	 * @maps_by_address: array of maps sorted by their starting address if
+	 * maps_by_address_sorted is true.
+	 */
+	struct map	 **maps_by_address;
+	/**
+	 * @maps_by_name: optional array of maps sorted by their dso name if
+	 * maps_by_name_sorted is true.
+	 */
+	struct map	 **maps_by_name;
+	struct machine	 *machine;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	void		*addr_space;
+	const struct unwind_libunwind_ops *unwind_libunwind_ops;
+#endif
+	refcount_t	 refcnt;
+	/**
+	 * @nr_maps: number of maps_by_address, and possibly maps_by_name,
+	 * entries that contain maps.
+	 */
+	unsigned int	 nr_maps;
+	/**
+	 * @nr_maps_allocated: number of entries in maps_by_address and possibly
+	 * maps_by_name.
+	 */
+	unsigned int	 nr_maps_allocated;
+	/**
+	 * @last_search_by_name_idx: cache of last found by name entry's index
+	 * as frequent searches for the same dso name are common.
+	 */
+	unsigned int	 last_search_by_name_idx;
+	/** @maps_by_address_sorted: is maps_by_address sorted. */
+	bool		 maps_by_address_sorted;
+	/** @maps_by_name_sorted: is maps_by_name sorted. */
+	bool		 maps_by_name_sorted;
+	/** @ends_broken: does the map contain a map where end values are unset/unsorted? */
+	bool		 ends_broken;
+};
+
+static void check_invariants(const struct maps *maps __maybe_unused)
 {
-	refcount_set(maps__refcnt(maps), 1);
-	init_rwsem(maps__lock(maps));
-	RC_CHK_ACCESS(maps)->entries = RB_ROOT;
-	RC_CHK_ACCESS(maps)->machine = machine;
-	RC_CHK_ACCESS(maps)->last_search_by_name = NULL;
-	RC_CHK_ACCESS(maps)->nr_maps = 0;
-	RC_CHK_ACCESS(maps)->maps_by_name = NULL;
+#ifndef NDEBUG
+	assert(RC_CHK_ACCESS(maps)->nr_maps <= RC_CHK_ACCESS(maps)->nr_maps_allocated);
+	for (unsigned int i = 0; i < RC_CHK_ACCESS(maps)->nr_maps; i++) {
+		struct map *map = RC_CHK_ACCESS(maps)->maps_by_address[i];
+
+		/* Check map is well-formed. */
+		assert(map__end(map) == 0 || map__start(map) <= map__end(map));
+		/* Expect at least 1 reference count. */
+		assert(refcount_read(map__refcnt(map)) > 0);
+
+		if (map__dso(map) && map__dso(map)->kernel)
+			assert(RC_CHK_EQUAL(map__kmap(map)->kmaps, maps));
+
+		if (i > 0) {
+			struct map *prev = RC_CHK_ACCESS(maps)->maps_by_address[i - 1];
+
+			/* If addresses are sorted... */
+			if (RC_CHK_ACCESS(maps)->maps_by_address_sorted) {
+				/* Maps should be in start address order. */
+				assert(map__start(prev) <= map__start(map));
+				/*
+				 * If the ends of maps aren't broken (during
+				 * construction) then they should be ordered
+				 * too.
+				 */
+				if (!RC_CHK_ACCESS(maps)->ends_broken) {
+					assert(map__end(prev) <= map__end(map));
+					assert(map__end(prev) <= map__start(map) ||
+					       map__start(prev) == map__start(map));
+				}
+			}
+		}
+	}
+	if (RC_CHK_ACCESS(maps)->maps_by_name) {
+		for (unsigned int i = 0; i < RC_CHK_ACCESS(maps)->nr_maps; i++) {
+			struct map *map = RC_CHK_ACCESS(maps)->maps_by_name[i];
+
+			/*
+			 * Maps by name maps should be in maps_by_address, so
+			 * the reference count should be higher.
+			 */
+			assert(refcount_read(map__refcnt(map)) > 1);
+		}
+	}
+#endif
 }
 
-static void __maps__free_maps_by_name(struct maps *maps)
+static struct map **maps__maps_by_address(const struct maps *maps)
 {
-	/*
-	 * Free everything to try to do it from the rbtree in the next search
-	 */
-	for (unsigned int i = 0; i < maps__nr_maps(maps); i++)
-		map__put(maps__maps_by_name(maps)[i]);
-
-	zfree(&RC_CHK_ACCESS(maps)->maps_by_name);
-	RC_CHK_ACCESS(maps)->nr_maps_allocated = 0;
+	return RC_CHK_ACCESS(maps)->maps_by_address;
 }
 
-static int __maps__insert(struct maps *maps, struct map *map)
+static void maps__set_maps_by_address(struct maps *maps, struct map **new)
 {
-	struct rb_node **p = &maps__entries(maps)->rb_node;
-	struct rb_node *parent = NULL;
-	const u64 ip = map__start(map);
-	struct map_rb_node *m, *new_rb_node;
+	RC_CHK_ACCESS(maps)->maps_by_address = new;
 
-	new_rb_node = malloc(sizeof(*new_rb_node));
-	if (!new_rb_node)
-		return -ENOMEM;
+}
 
-	RB_CLEAR_NODE(&new_rb_node->rb_node);
-	new_rb_node->map = map__get(map);
+static struct map ***maps__maps_by_name_addr(struct maps *maps)
+{
+	return &RC_CHK_ACCESS(maps)->maps_by_name;
+}
 
-	while (*p != NULL) {
-		parent = *p;
-		m = rb_entry(parent, struct map_rb_node, rb_node);
-		if (ip < map__start(m->map))
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
+static void maps__set_nr_maps_allocated(struct maps *maps, unsigned int nr_maps_allocated)
+{
+	RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_maps_allocated;
+}
 
-	rb_link_node(&new_rb_node->rb_node, parent, p);
-	rb_insert_color(&new_rb_node->rb_node, maps__entries(maps));
-	return 0;
+static void maps__set_nr_maps(struct maps *maps, unsigned int nr_maps)
+{
+	RC_CHK_ACCESS(maps)->nr_maps = nr_maps;
 }
 
-int maps__insert(struct maps *maps, struct map *map)
+/* Not in the header, to aid reference counting. */
+static struct map **maps__maps_by_name(const struct maps *maps)
 {
-	int err;
-	const struct dso *dso = map__dso(map);
+	return RC_CHK_ACCESS(maps)->maps_by_name;
 
-	down_write(maps__lock(maps));
-	err = __maps__insert(maps, map);
-	if (err)
-		goto out;
+}
 
-	++RC_CHK_ACCESS(maps)->nr_maps;
+static void maps__set_maps_by_name(struct maps *maps, struct map **new)
+{
+	RC_CHK_ACCESS(maps)->maps_by_name = new;
 
-	if (dso && dso->kernel) {
-		struct kmap *kmap = map__kmap(map);
+}
 
-		if (kmap)
-			kmap->kmaps = maps;
-		else
-			pr_err("Internal error: kernel dso with non kernel map\n");
-	}
+static bool maps__maps_by_address_sorted(const struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->maps_by_address_sorted;
+}
 
+static void maps__set_maps_by_address_sorted(struct maps *maps, bool value)
+{
+	RC_CHK_ACCESS(maps)->maps_by_address_sorted = value;
+}
 
-	/*
-	 * If we already performed some search by name, then we need to add the just
-	 * inserted map and resort.
-	 */
-	if (maps__maps_by_name(maps)) {
-		if (maps__nr_maps(maps) > RC_CHK_ACCESS(maps)->nr_maps_allocated) {
-			int nr_allocate = maps__nr_maps(maps) * 2;
-			struct map **maps_by_name = realloc(maps__maps_by_name(maps),
-							    nr_allocate * sizeof(map));
+static bool maps__maps_by_name_sorted(const struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->maps_by_name_sorted;
+}
 
-			if (maps_by_name == NULL) {
-				__maps__free_maps_by_name(maps);
-				err = -ENOMEM;
-				goto out;
-			}
+static void maps__set_maps_by_name_sorted(struct maps *maps, bool value)
+{
+	RC_CHK_ACCESS(maps)->maps_by_name_sorted = value;
+}
 
-			RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
-			RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_allocate;
-		}
-		maps__maps_by_name(maps)[maps__nr_maps(maps) - 1] = map__get(map);
-		__maps__sort_by_name(maps);
-	}
- out:
-	up_write(maps__lock(maps));
-	return err;
+struct machine *maps__machine(const struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->machine;
 }
 
-static void __maps__remove(struct maps *maps, struct map_rb_node *rb_node)
+unsigned int maps__nr_maps(const struct maps *maps)
 {
-	rb_erase_init(&rb_node->rb_node, maps__entries(maps));
-	map__put(rb_node->map);
-	free(rb_node);
+	return RC_CHK_ACCESS(maps)->nr_maps;
 }
 
-void maps__remove(struct maps *maps, struct map *map)
+refcount_t *maps__refcnt(struct maps *maps)
 {
-	struct map_rb_node *rb_node;
+	return &RC_CHK_ACCESS(maps)->refcnt;
+}
 
-	down_write(maps__lock(maps));
-	if (RC_CHK_ACCESS(maps)->last_search_by_name == map)
-		RC_CHK_ACCESS(maps)->last_search_by_name = NULL;
-
-	rb_node = maps__find_node(maps, map);
-	assert(rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map));
-	__maps__remove(maps, rb_node);
-	if (maps__maps_by_name(maps))
-		__maps__free_maps_by_name(maps);
-	--RC_CHK_ACCESS(maps)->nr_maps;
-	up_write(maps__lock(maps));
+#ifdef HAVE_LIBUNWIND_SUPPORT
+void *maps__addr_space(const struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->addr_space;
 }
 
-static void __maps__purge(struct maps *maps)
+void maps__set_addr_space(struct maps *maps, void *addr_space)
 {
-	struct map_rb_node *pos, *next;
+	RC_CHK_ACCESS(maps)->addr_space = addr_space;
+}
 
-	if (maps__maps_by_name(maps))
-		__maps__free_maps_by_name(maps);
+const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps)
+{
+	return RC_CHK_ACCESS(maps)->unwind_libunwind_ops;
+}
 
-	maps__for_each_entry_safe(maps, pos, next) {
-		rb_erase_init(&pos->rb_node,  maps__entries(maps));
-		map__put(pos->map);
-		free(pos);
-	}
+void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libunwind_ops *ops)
+{
+	RC_CHK_ACCESS(maps)->unwind_libunwind_ops = ops;
 }
+#endif
 
-static void maps__exit(struct maps *maps)
+static struct rw_semaphore *maps__lock(struct maps *maps)
 {
-	down_write(maps__lock(maps));
-	__maps__purge(maps);
-	up_write(maps__lock(maps));
+	/*
+	 * When the lock is acquired or released the maps invariants should
+	 * hold.
+	 */
+	check_invariants(maps);
+	return &RC_CHK_ACCESS(maps)->lock;
 }
 
-bool maps__empty(struct maps *maps)
+static void maps__init(struct maps *maps, struct machine *machine)
+{
+	init_rwsem(maps__lock(maps));
+	RC_CHK_ACCESS(maps)->maps_by_address = NULL;
+	RC_CHK_ACCESS(maps)->maps_by_name = NULL;
+	RC_CHK_ACCESS(maps)->machine = machine;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+	RC_CHK_ACCESS(maps)->addr_space = NULL;
+	RC_CHK_ACCESS(maps)->unwind_libunwind_ops = NULL;
+#endif
+	refcount_set(maps__refcnt(maps), 1);
+	RC_CHK_ACCESS(maps)->nr_maps = 0;
+	RC_CHK_ACCESS(maps)->nr_maps_allocated = 0;
+	RC_CHK_ACCESS(maps)->last_search_by_name_idx = 0;
+	RC_CHK_ACCESS(maps)->maps_by_address_sorted = true;
+	RC_CHK_ACCESS(maps)->maps_by_name_sorted = false;
+}
+
+static void maps__exit(struct maps *maps)
 {
-	return !maps__first(maps);
+	struct map **maps_by_address = maps__maps_by_address(maps);
+	struct map **maps_by_name = maps__maps_by_name(maps);
+
+	for (unsigned int i = 0; i < maps__nr_maps(maps); i++) {
+		map__zput(maps_by_address[i]);
+		if (maps_by_name)
+			map__zput(maps_by_name[i]);
+	}
+	zfree(&maps_by_address);
+	zfree(&maps_by_name);
+	unwind__finish_access(maps);
 }
 
 struct maps *maps__new(struct machine *machine)
@@ -174,7 +266,6 @@ struct maps *maps__new(struct machine *machine)
 static void maps__delete(struct maps *maps)
 {
 	maps__exit(maps);
-	unwind__finish_access(maps);
 	RC_CHK_FREE(maps);
 }
 
@@ -196,45 +287,375 @@ void maps__put(struct maps *maps)
 		RC_CHK_PUT(maps);
 }
 
-struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
+static void __maps__free_maps_by_name(struct maps *maps)
 {
-	struct map *map = maps__find(maps, addr);
+	/*
+	 * Free everything to try to do it from the rbtree in the next search
+	 */
+	for (unsigned int i = 0; i < maps__nr_maps(maps); i++)
+		map__put(maps__maps_by_name(maps)[i]);
 
-	/* Ensure map is loaded before using map->map_ip */
-	if (map != NULL && map__load(map) >= 0) {
-		if (mapp != NULL)
-			*mapp = map;
-		return map__find_symbol(map, map__map_ip(map, addr));
+	zfree(&RC_CHK_ACCESS(maps)->maps_by_name);
+}
+
+static int map__start_cmp(const void *a, const void *b)
+{
+	const struct map *map_a = *(const struct map * const *)a;
+	const struct map *map_b = *(const struct map * const *)b;
+	u64 map_a_start = map__start(map_a);
+	u64 map_b_start = map__start(map_b);
+
+	if (map_a_start == map_b_start) {
+		u64 map_a_end = map__end(map_a);
+		u64 map_b_end = map__end(map_b);
+
+		if  (map_a_end == map_b_end) {
+			/* Ensure maps with the same addresses have a fixed order. */
+			if (RC_CHK_ACCESS(map_a) == RC_CHK_ACCESS(map_b))
+				return 0;
+			return (intptr_t)RC_CHK_ACCESS(map_a) > (intptr_t)RC_CHK_ACCESS(map_b)
+				? 1 : -1;
+		}
+		return map_a_end > map_b_end ? 1 : -1;
 	}
+	return map_a_start > map_b_start ? 1 : -1;
+}
 
-	return NULL;
+static void __maps__sort_by_address(struct maps *maps)
+{
+	if (maps__maps_by_address_sorted(maps))
+		return;
+
+	qsort(maps__maps_by_address(maps),
+		maps__nr_maps(maps),
+		sizeof(struct map *),
+		map__start_cmp);
+	maps__set_maps_by_address_sorted(maps, true);
 }
 
-struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
+static void maps__sort_by_address(struct maps *maps)
 {
-	struct symbol *sym;
-	struct map_rb_node *pos;
+	down_write(maps__lock(maps));
+	__maps__sort_by_address(maps);
+	up_write(maps__lock(maps));
+}
 
-	down_read(maps__lock(maps));
+static int map__strcmp(const void *a, const void *b)
+{
+	const struct map *map_a = *(const struct map * const *)a;
+	const struct map *map_b = *(const struct map * const *)b;
+	const struct dso *dso_a = map__dso(map_a);
+	const struct dso *dso_b = map__dso(map_b);
+	int ret = strcmp(dso_a->short_name, dso_b->short_name);
+
+	if (ret == 0 && RC_CHK_ACCESS(map_a) != RC_CHK_ACCESS(map_b)) {
+		/* Ensure distinct but name equal maps have an order. */
+		return map__start_cmp(a, b);
+	}
+	return ret;
+}
+
+static int maps__sort_by_name(struct maps *maps)
+{
+	int err = 0;
+	down_write(maps__lock(maps));
+	if (!maps__maps_by_name_sorted(maps)) {
+		struct map **maps_by_name = maps__maps_by_name(maps);
+
+		if (!maps_by_name) {
+			maps_by_name = malloc(RC_CHK_ACCESS(maps)->nr_maps_allocated *
+					sizeof(*maps_by_name));
+			if (!maps_by_name)
+				err = -ENOMEM;
+			else {
+				struct map **maps_by_address = maps__maps_by_address(maps);
+				unsigned int n = maps__nr_maps(maps);
+
+				maps__set_maps_by_name(maps, maps_by_name);
+				for (unsigned int i = 0; i < n; i++)
+					maps_by_name[i] = map__get(maps_by_address[i]);
+			}
+		}
+		if (!err) {
+			qsort(maps_by_name,
+				maps__nr_maps(maps),
+				sizeof(struct map *),
+				map__strcmp);
+			maps__set_maps_by_name_sorted(maps, true);
+		}
+	}
+	up_write(maps__lock(maps));
+	return err;
+}
+
+static unsigned int maps__by_address_index(const struct maps *maps, const struct map *map)
+{
+	struct map **maps_by_address = maps__maps_by_address(maps);
+
+	if (maps__maps_by_address_sorted(maps)) {
+		struct map **mapp =
+			bsearch(&map, maps__maps_by_address(maps), maps__nr_maps(maps),
+				sizeof(*mapp), map__start_cmp);
+
+		if (mapp)
+			return mapp - maps_by_address;
+	} else {
+		for (unsigned int i = 0; i < maps__nr_maps(maps); i++) {
+			if (RC_CHK_ACCESS(maps_by_address[i]) == RC_CHK_ACCESS(map))
+				return i;
+		}
+	}
+	pr_err("Map missing from maps");
+	return -1;
+}
 
-	maps__for_each_entry(maps, pos) {
-		sym = map__find_symbol_by_name(pos->map, name);
+static unsigned int maps__by_name_index(const struct maps *maps, const struct map *map)
+{
+	struct map **maps_by_name = maps__maps_by_name(maps);
+
+	if (maps__maps_by_name_sorted(maps)) {
+		struct map **mapp =
+			bsearch(&map, maps_by_name, maps__nr_maps(maps),
+				sizeof(*mapp), map__strcmp);
+
+		if (mapp)
+			return mapp - maps_by_name;
+	} else {
+		for (unsigned int i = 0; i < maps__nr_maps(maps); i++) {
+			if (RC_CHK_ACCESS(maps_by_name[i]) == RC_CHK_ACCESS(map))
+				return i;
+		}
+	}
+	pr_err("Map missing from maps");
+	return -1;
+}
 
-		if (sym == NULL)
-			continue;
-		if (!map__contains_symbol(pos->map, sym)) {
-			sym = NULL;
-			continue;
+static int __maps__insert(struct maps *maps, struct map *new)
+{
+	struct map **maps_by_address = maps__maps_by_address(maps);
+	struct map **maps_by_name = maps__maps_by_name(maps);
+	const struct dso *dso = map__dso(new);
+	unsigned int nr_maps = maps__nr_maps(maps);
+	unsigned int nr_allocate = RC_CHK_ACCESS(maps)->nr_maps_allocated;
+
+	if (nr_maps + 1 > nr_allocate) {
+		nr_allocate = !nr_allocate ? 32 : nr_allocate * 2;
+
+		maps_by_address = realloc(maps_by_address, nr_allocate * sizeof(new));
+		if (!maps_by_address)
+			return -ENOMEM;
+
+		maps__set_maps_by_address(maps, maps_by_address);
+		if (maps_by_name) {
+			maps_by_name = realloc(maps_by_name, nr_allocate * sizeof(new));
+			if (!maps_by_name) {
+				/*
+				 * If by name fails, just disable by name and it will
+				 * recompute next time it is required.
+				 */
+				__maps__free_maps_by_name(maps);
+			}
+			maps__set_maps_by_name(maps, maps_by_name);
 		}
-		if (mapp != NULL)
-			*mapp = pos->map;
-		goto out;
+		RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_allocate;
+	}
+	/* Insert the value at the end. */
+	maps_by_address[nr_maps] = map__get(new);
+	if (maps_by_name)
+		maps_by_name[nr_maps] = map__get(new);
+
+	nr_maps++;
+	RC_CHK_ACCESS(maps)->nr_maps = nr_maps;
+
+	/*
+	 * Recompute if things are sorted. If things are inserted in a sorted
+	 * manner, for example by processing /proc/pid/maps, then no
+	 * sorting/resorting will be necessary.
+	 */
+	if (nr_maps == 1) {
+		/* If there's just 1 entry then maps are sorted. */
+		maps__set_maps_by_address_sorted(maps, true);
+		maps__set_maps_by_name_sorted(maps, maps_by_name != NULL);
+	} else {
+		/* Sorted if maps were already sorted and this map starts after the last one. */
+		maps__set_maps_by_address_sorted(maps,
+			maps__maps_by_address_sorted(maps) &&
+			map__end(maps_by_address[nr_maps - 2]) <= map__start(new));
+		maps__set_maps_by_name_sorted(maps, false);
+	}
+	if (map__end(new) < map__start(new))
+		RC_CHK_ACCESS(maps)->ends_broken = true;
+	if (dso && dso->kernel) {
+		struct kmap *kmap = map__kmap(new);
+
+		if (kmap)
+			kmap->kmaps = maps;
+		else
+			pr_err("Internal error: kernel dso with non kernel map\n");
+	}
+	return 0;
+}
+
+int maps__insert(struct maps *maps, struct map *map)
+{
+	int ret;
+
+	down_write(maps__lock(maps));
+	ret = __maps__insert(maps, map);
+	up_write(maps__lock(maps));
+	return ret;
+}
+
+static void __maps__remove(struct maps *maps, struct map *map)
+{
+	struct map **maps_by_address = maps__maps_by_address(maps);
+	struct map **maps_by_name = maps__maps_by_name(maps);
+	unsigned int nr_maps = maps__nr_maps(maps);
+	unsigned int address_idx;
+
+	/* Slide later mappings over the one to remove */
+	address_idx = maps__by_address_index(maps, map);
+	map__put(maps_by_address[address_idx]);
+	memmove(&maps_by_address[address_idx],
+		&maps_by_address[address_idx + 1],
+		(nr_maps - address_idx - 1) * sizeof(*maps_by_address));
+
+	if (maps_by_name) {
+		unsigned int name_idx = maps__by_name_index(maps, map);
+
+		map__put(maps_by_name[name_idx]);
+		memmove(&maps_by_name[name_idx],
+			&maps_by_name[name_idx + 1],
+			(nr_maps - name_idx - 1) *  sizeof(*maps_by_name));
 	}
 
-	sym = NULL;
-out:
+	--RC_CHK_ACCESS(maps)->nr_maps;
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	down_write(maps__lock(maps));
+	__maps__remove(maps, map);
+	up_write(maps__lock(maps));
+}
+
+bool maps__empty(struct maps *maps)
+{
+	bool res;
+
+	down_read(maps__lock(maps));
+	res = maps__nr_maps(maps) == 0;
 	up_read(maps__lock(maps));
-	return sym;
+
+	return res;
+}
+
+bool maps__equal(struct maps *a, struct maps *b)
+{
+	return RC_CHK_EQUAL(a, b);
+}
+
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data)
+{
+	bool done = false;
+	int ret = 0;
+
+	/* See locking/sorting note. */
+	while (!done) {
+		down_read(maps__lock(maps));
+		if (maps__maps_by_address_sorted(maps)) {
+			/*
+			 * maps__for_each_map callbacks may buggily/unsafely
+			 * insert into maps_by_address. Deliberately reload
+			 * maps__nr_maps and maps_by_address on each iteration
+			 * to avoid using memory freed by maps__insert growing
+			 * the array - this may cause maps to be skipped or
+			 * repeated.
+			 */
+			for (unsigned int i = 0; i < maps__nr_maps(maps); i++) {
+				struct map **maps_by_address = maps__maps_by_address(maps);
+				struct map *map = maps_by_address[i];
+
+				ret = cb(map, data);
+				if (ret)
+					break;
+			}
+			done = true;
+		}
+		up_read(maps__lock(maps));
+		if (!done)
+			maps__sort_by_address(maps);
+	}
+	return ret;
+}
+
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data)
+{
+	struct map **maps_by_address;
+
+	down_write(maps__lock(maps));
+
+	maps_by_address = maps__maps_by_address(maps);
+	for (unsigned int i = 0; i < maps__nr_maps(maps);) {
+		if (cb(maps_by_address[i], data))
+			__maps__remove(maps, maps_by_address[i]);
+		else
+			i++;
+	}
+	up_write(maps__lock(maps));
+}
+
+struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
+{
+	struct map *map = maps__find(maps, addr);
+	struct symbol *result = NULL;
+
+	/* Ensure map is loaded before using map->map_ip */
+	if (map != NULL && map__load(map) >= 0)
+		result = map__find_symbol(map, map__map_ip(map, addr));
+
+	if (mapp)
+		*mapp = map;
+	else
+		map__put(map);
+
+	return result;
+}
+
+struct maps__find_symbol_by_name_args {
+	struct map **mapp;
+	const char *name;
+	struct symbol *sym;
+};
+
+static int maps__find_symbol_by_name_cb(struct map *map, void *data)
+{
+	struct maps__find_symbol_by_name_args *args = data;
+
+	args->sym = map__find_symbol_by_name(map, args->name);
+	if (!args->sym)
+		return 0;
+
+	if (!map__contains_symbol(map, args->sym)) {
+		args->sym = NULL;
+		return 0;
+	}
+
+	if (args->mapp != NULL)
+		*args->mapp = map__get(map);
+	return 1;
+}
+
+struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
+{
+	struct maps__find_symbol_by_name_args args = {
+		.mapp = mapp,
+		.name = name,
+		.sym = NULL,
+	};
+
+	maps__for_each_map(maps, maps__find_symbol_by_name_cb, &args);
+	return args.sym;
 }
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
@@ -253,225 +674,526 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
 	return ams->ms.sym ? 0 : -1;
 }
 
-size_t maps__fprintf(struct maps *maps, FILE *fp)
-{
-	size_t printed = 0;
-	struct map_rb_node *pos;
+struct maps__fprintf_args {
+	FILE *fp;
+	size_t printed;
+};
 
-	down_read(maps__lock(maps));
+static int maps__fprintf_cb(struct map *map, void *data)
+{
+	struct maps__fprintf_args *args = data;
 
-	maps__for_each_entry(maps, pos) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos->map, fp);
-		if (verbose > 2) {
-			printed += dso__fprintf(map__dso(pos->map), fp);
-			printed += fprintf(fp, "--\n");
-		}
+	args->printed += fprintf(args->fp, "Map:");
+	args->printed += map__fprintf(map, args->fp);
+	if (verbose > 2) {
+		args->printed += dso__fprintf(map__dso(map), args->fp);
+		args->printed += fprintf(args->fp, "--\n");
 	}
+	return 0;
+}
 
-	up_read(maps__lock(maps));
+size_t maps__fprintf(struct maps *maps, FILE *fp)
+{
+	struct maps__fprintf_args args = {
+		.fp = fp,
+		.printed = 0,
+	};
+
+	maps__for_each_map(maps, maps__fprintf_cb, &args);
 
-	return printed;
+	return args.printed;
 }
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
+/*
+ * Find first map where end > map->start.
+ * Same as find_vma() in kernel.
+ */
+static unsigned int first_ending_after(struct maps *maps, const struct map *map)
 {
-	struct rb_root *root;
-	struct rb_node *next, *first;
-	int err = 0;
+	struct map **maps_by_address = maps__maps_by_address(maps);
+	int low = 0, high = (int)maps__nr_maps(maps) - 1, first = high + 1;
 
-	down_write(maps__lock(maps));
+	assert(maps__maps_by_address_sorted(maps));
+	if (low <= high && map__end(maps_by_address[0]) > map__start(map))
+		return 0;
 
-	root = maps__entries(maps);
+	while (low <= high) {
+		int mid = (low + high) / 2;
+		struct map *pos = maps_by_address[mid];
 
-	/*
-	 * Find first map where end > map->start.
-	 * Same as find_vma() in kernel.
-	 */
-	next = root->rb_node;
-	first = NULL;
-	while (next) {
-		struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node);
-
-		if (map__end(pos->map) > map__start(map)) {
-			first = next;
-			if (map__start(pos->map) <= map__start(map))
+		if (map__end(pos) > map__start(map)) {
+			first = mid;
+			if (map__start(pos) <= map__start(map)) {
+				/* Entry overlaps map. */
 				break;
-			next = next->rb_left;
+			}
+			high = mid - 1;
 		} else
-			next = next->rb_right;
+			low = mid + 1;
 	}
+	return first;
+}
+
+/*
+ * Adds new to maps, if new overlaps existing entries then the existing maps are
+ * adjusted or removed so that new fits without overlapping any entries.
+ */
+static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+{
+	struct map **maps_by_address;
+	int err = 0;
+	FILE *fp = debug_file();
+
+sort_again:
+	if (!maps__maps_by_address_sorted(maps))
+		__maps__sort_by_address(maps);
 
-	next = first;
-	while (next && !err) {
-		struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node);
-		next = rb_next(&pos->rb_node);
+	maps_by_address = maps__maps_by_address(maps);
+	/*
+	 * Iterate through entries where the end of the existing entry is
+	 * greater-than the new map's start.
+	 */
+	for (unsigned int i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) {
+		struct map *pos = maps_by_address[i];
+		struct map *before = NULL, *after = NULL;
 
 		/*
 		 * Stop if current map starts after map->end.
 		 * Maps are ordered by start: next will not overlap for sure.
 		 */
-		if (map__start(pos->map) >= map__end(map))
+		if (map__start(pos) >= map__end(new))
 			break;
 
-		if (verbose >= 2) {
-
-			if (use_browser) {
-				pr_debug("overlapping maps in %s (disable tui for more info)\n",
-					 map__dso(map)->name);
-			} else {
-				fputs("overlapping maps:\n", fp);
-				map__fprintf(map, fp);
-				map__fprintf(pos->map, fp);
-			}
+		if (use_browser) {
+			pr_debug("overlapping maps in %s (disable tui for more info)\n",
+				map__dso(new)->name);
+		} else if (verbose >= 2) {
+			pr_debug("overlapping maps:\n");
+			map__fprintf(new, fp);
+			map__fprintf(pos, fp);
 		}
 
-		rb_erase_init(&pos->rb_node, root);
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
 		 */
-		if (map__start(map) > map__start(pos->map)) {
-			struct map *before = map__clone(pos->map);
+		if (map__start(new) > map__start(pos)) {
+			/* Map starts within existing map. Need to shorten the existing map. */
+			before = map__clone(pos);
 
 			if (before == NULL) {
 				err = -ENOMEM;
-				goto put_map;
-			}
-
-			map__set_end(before, map__start(map));
-			err = __maps__insert(maps, before);
-			if (err) {
-				map__put(before);
-				goto put_map;
+				goto out_err;
 			}
+			map__set_end(before, map__start(new));
 
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(before, fp);
-			map__put(before);
 		}
-
-		if (map__end(map) < map__end(pos->map)) {
-			struct map *after = map__clone(pos->map);
+		if (map__end(new) < map__end(pos)) {
+			/* The new map isn't as long as the existing map. */
+			after = map__clone(pos);
 
 			if (after == NULL) {
+				map__zput(before);
 				err = -ENOMEM;
-				goto put_map;
+				goto out_err;
 			}
 
-			map__set_start(after, map__end(map));
-			map__add_pgoff(after, map__end(map) - map__start(pos->map));
-			assert(map__map_ip(pos->map, map__end(map)) ==
-				map__map_ip(after, map__end(map)));
-			err = __maps__insert(maps, after);
-			if (err) {
-				map__put(after);
-				goto put_map;
-			}
+			map__set_start(after, map__end(new));
+			map__add_pgoff(after, map__end(new) - map__start(pos));
+			assert(map__map_ip(pos, map__end(new)) ==
+			       map__map_ip(after, map__end(new)));
+
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
-			map__put(after);
 		}
-put_map:
-		map__put(pos->map);
-		free(pos);
+		/*
+		 * If adding one entry, for `before` or `after`, we can replace
+		 * the existing entry. If both `before` and `after` are
+		 * necessary than an insert is needed. If the existing entry
+		 * entirely overlaps the existing entry it can just be removed.
+		 */
+		if (before) {
+			map__put(maps_by_address[i]);
+			maps_by_address[i] = before;
+			/* Maps are still ordered, go to next one. */
+			i++;
+			if (after) {
+				__maps__insert(maps, after);
+				map__put(after);
+				if (!maps__maps_by_address_sorted(maps)) {
+					/*
+					 * Sorting broken so invariants don't
+					 * hold, sort and go again.
+					 */
+					goto sort_again;
+				}
+				/*
+				 * Maps are still ordered, skip after and go to
+				 * next one (terminate loop).
+				 */
+				i++;
+			}
+		} else if (after) {
+			map__put(maps_by_address[i]);
+			maps_by_address[i] = after;
+			/* Maps are ordered, go to next one. */
+			i++;
+		} else {
+			__maps__remove(maps, pos);
+			/*
+			 * Maps are ordered but no need to increase `i` as the
+			 * later maps were moved down.
+			 */
+		}
+		check_invariants(maps);
 	}
-	up_write(maps__lock(maps));
+	/* Add the map. */
+	__maps__insert(maps, new);
+out_err:
 	return err;
 }
 
-/*
- * XXX This should not really _copy_ te maps, but refcount them.
- */
-int maps__clone(struct thread *thread, struct maps *parent)
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
 {
-	struct maps *maps = thread__maps(thread);
 	int err;
-	struct map_rb_node *rb_node;
 
+	down_write(maps__lock(maps));
+	err =  __maps__fixup_overlap_and_insert(maps, new);
+	up_write(maps__lock(maps));
+	return err;
+}
+
+int maps__copy_from(struct maps *dest, struct maps *parent)
+{
+	/* Note, if struct map were immutable then cloning could use ref counts. */
+	struct map **parent_maps_by_address;
+	int err = 0;
+	unsigned int n;
+
+	down_write(maps__lock(dest));
 	down_read(maps__lock(parent));
 
-	maps__for_each_entry(parent, rb_node) {
-		struct map *new = map__clone(rb_node->map);
+	parent_maps_by_address = maps__maps_by_address(parent);
+	n = maps__nr_maps(parent);
+	if (maps__nr_maps(dest) == 0) {
+		/* No existing mappings so just copy from parent to avoid reallocs in insert. */
+		unsigned int nr_maps_allocated = RC_CHK_ACCESS(parent)->nr_maps_allocated;
+		struct map **dest_maps_by_address =
+			malloc(nr_maps_allocated * sizeof(struct map *));
+		struct map **dest_maps_by_name = NULL;
 
-		if (new == NULL) {
+		if (!dest_maps_by_address)
 			err = -ENOMEM;
-			goto out_unlock;
+		else {
+			if (maps__maps_by_name(parent)) {
+				dest_maps_by_name =
+					malloc(nr_maps_allocated * sizeof(struct map *));
+			}
+
+			RC_CHK_ACCESS(dest)->maps_by_address = dest_maps_by_address;
+			RC_CHK_ACCESS(dest)->maps_by_name = dest_maps_by_name;
+			RC_CHK_ACCESS(dest)->nr_maps_allocated = nr_maps_allocated;
 		}
 
-		err = unwind__prepare_access(maps, new, NULL);
-		if (err)
-			goto out_unlock;
+		for (unsigned int i = 0; !err && i < n; i++) {
+			struct map *pos = parent_maps_by_address[i];
+			struct map *new = map__clone(pos);
 
-		err = maps__insert(maps, new);
-		if (err)
-			goto out_unlock;
+			if (!new)
+				err = -ENOMEM;
+			else {
+				err = unwind__prepare_access(dest, new, NULL);
+				if (!err) {
+					dest_maps_by_address[i] = new;
+					if (dest_maps_by_name)
+						dest_maps_by_name[i] = map__get(new);
+					RC_CHK_ACCESS(dest)->nr_maps = i + 1;
+				}
+			}
+			if (err)
+				map__put(new);
+		}
+		maps__set_maps_by_address_sorted(dest, maps__maps_by_address_sorted(parent));
+		if (!err) {
+			RC_CHK_ACCESS(dest)->last_search_by_name_idx =
+				RC_CHK_ACCESS(parent)->last_search_by_name_idx;
+			maps__set_maps_by_name_sorted(dest,
+						dest_maps_by_name &&
+						maps__maps_by_name_sorted(parent));
+		} else {
+			RC_CHK_ACCESS(dest)->last_search_by_name_idx = 0;
+			maps__set_maps_by_name_sorted(dest, false);
+		}
+	} else {
+		/* Unexpected copying to a maps containing entries. */
+		for (unsigned int i = 0; !err && i < n; i++) {
+			struct map *pos = parent_maps_by_address[i];
+			struct map *new = map__clone(pos);
 
-		map__put(new);
+			if (!new)
+				err = -ENOMEM;
+			else {
+				err = unwind__prepare_access(dest, new, NULL);
+				if (!err)
+					err = __maps__insert(dest, new);
+			}
+			map__put(new);
+		}
 	}
-
-	err = 0;
-out_unlock:
 	up_read(maps__lock(parent));
+	up_write(maps__lock(dest));
 	return err;
 }
 
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map)
+static int map__addr_cmp(const void *key, const void *entry)
 {
-	struct map_rb_node *rb_node;
+	const u64 ip = *(const u64 *)key;
+	const struct map *map = *(const struct map * const *)entry;
 
-	maps__for_each_entry(maps, rb_node) {
-		if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map))
-			return rb_node;
-	}
-	return NULL;
+	if (ip < map__start(map))
+		return -1;
+	if (ip >= map__end(map))
+		return 1;
+	return 0;
 }
 
 struct map *maps__find(struct maps *maps, u64 ip)
 {
-	struct rb_node *p;
-	struct map_rb_node *m;
+	struct map *result = NULL;
+	bool done = false;
+
+	/* See locking/sorting note. */
+	while (!done) {
+		down_read(maps__lock(maps));
+		if (maps__maps_by_address_sorted(maps)) {
+			struct map **mapp =
+				bsearch(&ip, maps__maps_by_address(maps), maps__nr_maps(maps),
+					sizeof(*mapp), map__addr_cmp);
+
+			if (mapp)
+				result = map__get(*mapp);
+			done = true;
+		}
+		up_read(maps__lock(maps));
+		if (!done)
+			maps__sort_by_address(maps);
+	}
+	return result;
+}
+
+static int map__strcmp_name(const void *name, const void *b)
+{
+	const struct dso *dso = map__dso(*(const struct map **)b);
 
+	return strcmp(name, dso->short_name);
+}
 
-	down_read(maps__lock(maps));
+struct map *maps__find_by_name(struct maps *maps, const char *name)
+{
+	struct map *result = NULL;
+	bool done = false;
 
-	p = maps__entries(maps)->rb_node;
-	while (p != NULL) {
-		m = rb_entry(p, struct map_rb_node, rb_node);
-		if (ip < map__start(m->map))
-			p = p->rb_left;
-		else if (ip >= map__end(m->map))
-			p = p->rb_right;
-		else
-			goto out;
+	/* See locking/sorting note. */
+	while (!done) {
+		unsigned int i;
+
+		down_read(maps__lock(maps));
+
+		/* First check last found entry. */
+		i = RC_CHK_ACCESS(maps)->last_search_by_name_idx;
+		if (i < maps__nr_maps(maps) && maps__maps_by_name(maps)) {
+			struct dso *dso = map__dso(maps__maps_by_name(maps)[i]);
+
+			if (dso && strcmp(dso->short_name, name) == 0) {
+				result = map__get(maps__maps_by_name(maps)[i]);
+				done = true;
+			}
+		}
+
+		/* Second search sorted array. */
+		if (!done && maps__maps_by_name_sorted(maps)) {
+			struct map **mapp =
+				bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
+					sizeof(*mapp), map__strcmp_name);
+
+			if (mapp) {
+				result = map__get(*mapp);
+				i = mapp - maps__maps_by_name(maps);
+				RC_CHK_ACCESS(maps)->last_search_by_name_idx = i;
+			}
+			done = true;
+		}
+		up_read(maps__lock(maps));
+		if (!done) {
+			/* Sort and retry binary search. */
+			if (maps__sort_by_name(maps)) {
+				/*
+				 * Memory allocation failed do linear search
+				 * through address sorted maps.
+				 */
+				struct map **maps_by_address;
+				unsigned int n;
+
+				down_read(maps__lock(maps));
+				maps_by_address =  maps__maps_by_address(maps);
+				n = maps__nr_maps(maps);
+				for (i = 0; i < n; i++) {
+					struct map *pos = maps_by_address[i];
+					struct dso *dso = map__dso(pos);
+
+					if (dso && strcmp(dso->short_name, name) == 0) {
+						result = map__get(pos);
+						break;
+					}
+				}
+				up_read(maps__lock(maps));
+				done = true;
+			}
+		}
 	}
+	return result;
+}
+
+struct map *maps__find_next_entry(struct maps *maps, struct map *map)
+{
+	unsigned int i;
+	struct map *result = NULL;
+
+	down_read(maps__lock(maps));
+	i = maps__by_address_index(maps, map);
+	if (i < maps__nr_maps(maps))
+		result = map__get(maps__maps_by_address(maps)[i]);
 
-	m = NULL;
-out:
 	up_read(maps__lock(maps));
-	return m ? m->map : NULL;
+	return result;
 }
 
-struct map_rb_node *maps__first(struct maps *maps)
+void maps__fixup_end(struct maps *maps)
 {
-	struct rb_node *first = rb_first(maps__entries(maps));
+	struct map **maps_by_address;
+	unsigned int n;
+
+	down_write(maps__lock(maps));
+	if (!maps__maps_by_address_sorted(maps))
+		__maps__sort_by_address(maps);
+
+	maps_by_address = maps__maps_by_address(maps);
+	n = maps__nr_maps(maps);
+	for (unsigned int i = 1; i < n; i++) {
+		struct map *prev = maps_by_address[i - 1];
+		struct map *curr = maps_by_address[i];
+
+		if (!map__end(prev) || map__end(prev) > map__start(curr))
+			map__set_end(prev, map__start(curr));
+	}
+
+	/*
+	 * We still haven't the actual symbols, so guess the
+	 * last map final address.
+	 */
+	if (n > 0 && !map__end(maps_by_address[n - 1]))
+		map__set_end(maps_by_address[n - 1], ~0ULL);
 
-	if (first)
-		return rb_entry(first, struct map_rb_node, rb_node);
-	return NULL;
+	RC_CHK_ACCESS(maps)->ends_broken = false;
+
+	up_write(maps__lock(maps));
 }
 
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node)
+/*
+ * Merges map into maps by splitting the new map within the existing map
+ * regions.
+ */
+int maps__merge_in(struct maps *kmaps, struct map *new_map)
 {
-	struct rb_node *next;
+	unsigned int first_after_, kmaps__nr_maps;
+	struct map **kmaps_maps_by_address;
+	struct map **merged_maps_by_address;
+	unsigned int merged_nr_maps_allocated;
+
+	/* First try under a read lock. */
+	while (true) {
+		down_read(maps__lock(kmaps));
+		if (maps__maps_by_address_sorted(kmaps))
+			break;
+
+		up_read(maps__lock(kmaps));
+
+		/* First after binary search requires sorted maps. Sort and try again. */
+		maps__sort_by_address(kmaps);
+	}
+	first_after_ = first_ending_after(kmaps, new_map);
+	kmaps_maps_by_address = maps__maps_by_address(kmaps);
+
+	if (first_after_ >= maps__nr_maps(kmaps) ||
+	    map__start(kmaps_maps_by_address[first_after_]) >= map__end(new_map)) {
+		/* No overlap so regular insert suffices. */
+		up_read(maps__lock(kmaps));
+		return maps__insert(kmaps, new_map);
+	}
+	up_read(maps__lock(kmaps));
+
+	/* Plain insert with a read-lock failed, try again now with the write lock. */
+	down_write(maps__lock(kmaps));
+	if (!maps__maps_by_address_sorted(kmaps))
+		__maps__sort_by_address(kmaps);
+
+	first_after_ = first_ending_after(kmaps, new_map);
+	kmaps_maps_by_address = maps__maps_by_address(kmaps);
+	kmaps__nr_maps = maps__nr_maps(kmaps);
+
+	if (first_after_ >= kmaps__nr_maps ||
+	    map__start(kmaps_maps_by_address[first_after_]) >= map__end(new_map)) {
+		/* No overlap so regular insert suffices. */
+		int ret = __maps__insert(kmaps, new_map);
+		up_write(maps__lock(kmaps));
+		return ret;
+	}
+	/* Array to merge into, possibly 1 more for the sake of new_map. */
+	merged_nr_maps_allocated = RC_CHK_ACCESS(kmaps)->nr_maps_allocated;
+	if (kmaps__nr_maps + 1 == merged_nr_maps_allocated)
+		merged_nr_maps_allocated++;
+
+	merged_maps_by_address = malloc(merged_nr_maps_allocated * sizeof(*merged_maps_by_address));
+	if (!merged_maps_by_address) {
+		up_write(maps__lock(kmaps));
+		return -ENOMEM;
+	}
+	maps__set_maps_by_address(kmaps, merged_maps_by_address);
+	maps__set_maps_by_address_sorted(kmaps, true);
+	zfree(maps__maps_by_name_addr(kmaps));
+	maps__set_maps_by_name_sorted(kmaps, true);
+	maps__set_nr_maps_allocated(kmaps, merged_nr_maps_allocated);
+
+	/* Copy entries before the new_map that can't overlap. */
+	for (unsigned int i = 0; i < first_after_; i++)
+		merged_maps_by_address[i] = map__get(kmaps_maps_by_address[i]);
+
+	maps__set_nr_maps(kmaps, first_after_);
 
-	if (!node)
-		return NULL;
+	/* Add the new map, it will be split when the later overlapping mappings are added. */
+	__maps__insert(kmaps, new_map);
 
-	next = rb_next(&node->rb_node);
+	/* Insert mappings after new_map, splitting new_map in the process. */
+	for (unsigned int i = first_after_; i < kmaps__nr_maps; i++)
+		__maps__fixup_overlap_and_insert(kmaps, kmaps_maps_by_address[i]);
 
-	if (!next)
-		return NULL;
+	/* Copy the maps from merged into kmaps. */
+	for (unsigned int i = 0; i < kmaps__nr_maps; i++)
+		map__zput(kmaps_maps_by_address[i]);
+
+	free(kmaps_maps_by_address);
+	up_write(maps__lock(kmaps));
+	return 0;
+}
 
-	return rb_entry(next, struct map_rb_node, rb_node);
+void maps__load_first(struct maps *maps)
+{
+	down_read(maps__lock(maps));
+
+	if (maps__nr_maps(maps) > 0)
+		map__load(maps__maps_by_address(maps)[0]);
+
+	up_read(maps__lock(maps));
 }
diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index 83144e0645ed..d9aa62ed968a 100644
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -3,50 +3,14 @@
 #define __PERF_MAPS_H
 
 #include <linux/refcount.h>
-#include <linux/rbtree.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
-#include "rwsem.h"
-#include <internal/rc_check.h>
 
 struct ref_reloc_sym;
 struct machine;
 struct map;
 struct maps;
-struct thread;
-
-struct map_rb_node {
-	struct rb_node rb_node;
-	struct map *map;
-};
-
-struct map_rb_node *maps__first(struct maps *maps);
-struct map_rb_node *map_rb_node__next(struct map_rb_node *node);
-struct map_rb_node *maps__find_node(struct maps *maps, struct map *map);
-struct map *maps__find(struct maps *maps, u64 addr);
-
-#define maps__for_each_entry(maps, map) \
-	for (map = maps__first(maps); map; map = map_rb_node__next(map))
-
-#define maps__for_each_entry_safe(maps, map, next) \
-	for (map = maps__first(maps), next = map_rb_node__next(map); map; \
-	     map = next, next = map_rb_node__next(map))
-
-DECLARE_RC_STRUCT(maps) {
-	struct rb_root      entries;
-	struct rw_semaphore lock;
-	struct machine	 *machine;
-	struct map	 *last_search_by_name;
-	struct map	 **maps_by_name;
-	refcount_t	 refcnt;
-	unsigned int	 nr_maps;
-	unsigned int	 nr_maps_allocated;
-#ifdef HAVE_LIBUNWIND_SUPPORT
-	void				*addr_space;
-	const struct unwind_libunwind_ops *unwind_libunwind_ops;
-#endif
-};
 
 #define KMAP_NAME_LEN 256
 
@@ -58,7 +22,7 @@ struct kmap {
 
 struct maps *maps__new(struct machine *machine);
 bool maps__empty(struct maps *maps);
-int maps__clone(struct thread *thread, struct maps *parent);
+int maps__copy_from(struct maps *maps, struct maps *parent);
 
 struct maps *maps__get(struct maps *maps);
 void maps__put(struct maps *maps);
@@ -71,46 +35,22 @@ static inline void __maps__zput(struct maps **map)
 
 #define maps__zput(map) __maps__zput(&map)
 
-static inline struct rb_root *maps__entries(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->entries;
-}
+bool maps__equal(struct maps *a, struct maps *b);
 
-static inline struct machine *maps__machine(struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->machine;
-}
+/* Iterate over map calling cb for each entry. */
+int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data);
+/* Iterate over map removing an entry if cb returns true. */
+void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data);
 
-static inline struct rw_semaphore *maps__lock(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->lock;
-}
-
-static inline struct map **maps__maps_by_name(struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->maps_by_name;
-}
-
-static inline unsigned int maps__nr_maps(const struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->nr_maps;
-}
-
-static inline refcount_t *maps__refcnt(struct maps *maps)
-{
-	return &RC_CHK_ACCESS(maps)->refcnt;
-}
+struct machine *maps__machine(const struct maps *maps);
+unsigned int maps__nr_maps(const struct maps *maps); /* Test only. */
+refcount_t *maps__refcnt(struct maps *maps); /* Test only. */
 
 #ifdef HAVE_LIBUNWIND_SUPPORT
-static inline void *maps__addr_space(struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->addr_space;
-}
-
-static inline const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps)
-{
-	return RC_CHK_ACCESS(maps)->unwind_libunwind_ops;
-}
+void *maps__addr_space(const struct maps *maps);
+void maps__set_addr_space(struct maps *maps, void *addr_space);
+const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps);
+void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libunwind_ops *ops);
 #endif
 
 size_t maps__fprintf(struct maps *maps, FILE *fp);
@@ -118,6 +58,7 @@ size_t maps__fprintf(struct maps *maps, FILE *fp);
 int 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 symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp);
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp);
 
@@ -125,12 +66,16 @@ struct addr_map_symbol;
 
 int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams);
 
-int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp);
+int maps__fixup_overlap_and_insert(struct maps *maps, struct map *new);
 
 struct map *maps__find_by_name(struct maps *maps, const char *name);
 
+struct map *maps__find_next_entry(struct maps *maps, struct map *map);
+
 int maps__merge_in(struct maps *kmaps, struct map *new_map);
 
-void __maps__sort_by_name(struct maps *maps);
+void maps__fixup_end(struct maps *maps);
+
+void maps__load_first(struct maps *maps);
 
 #endif // __PERF_MAPS_H
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index c07fe3a90722..637cbd4a7bfb 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -17,51 +17,126 @@
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 
-#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a }
 
-static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"cpu/events/mem-loads"),
-	E("ldlat-stores",	"cpu/mem-stores/P",		"cpu/events/mem-stores"),
-	E(NULL,			NULL,				NULL),
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"mem-loads",	true,	0),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
 };
 #undef E
 
 static char mem_loads_name[100];
-static bool mem_loads_name__init;
+static char mem_stores_name[100];
 
-struct perf_mem_event * __weak perf_mem_events__ptr(int i)
+struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i)
 {
-	if (i >= PERF_MEM_EVENTS__MAX)
+	if (i >= PERF_MEM_EVENTS__MAX || !pmu)
 		return NULL;
 
-	return &perf_mem_events[i];
+	return &pmu->mem_events[i];
 }
 
-char * __weak perf_mem_events__name(int i, char *pmu_name  __maybe_unused)
+static struct perf_pmu *perf_pmus__scan_mem(struct perf_pmu *pmu)
 {
-	struct perf_mem_event *e = perf_mem_events__ptr(i);
+	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
+		if (pmu->mem_events)
+			return pmu;
+	}
+	return NULL;
+}
+
+struct perf_pmu *perf_mem_events_find_pmu(void)
+{
+	/*
+	 * The current perf mem doesn't support per-PMU configuration.
+	 * The exact same configuration is applied to all the
+	 * mem_events supported PMUs.
+	 * Return the first mem_events supported PMU.
+	 *
+	 * Notes: The only case which may support multiple mem_events
+	 * supported PMUs is Intel hybrid. The exact same mem_events
+	 * is shared among the PMUs. Only configure the first PMU
+	 * is good enough as well.
+	 */
+	return perf_pmus__scan_mem(NULL);
+}
+
+/**
+ * perf_pmu__mem_events_num_mem_pmus - Get the number of mem PMUs since the given pmu
+ * @pmu: Start pmu. If it's NULL, search the entire PMU list.
+ */
+int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu)
+{
+	int num = 0;
+
+	while ((pmu = perf_pmus__scan_mem(pmu)) != NULL)
+		num++;
+
+	return num;
+}
+
+static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu)
+{
+	struct perf_mem_event *e;
 
+	if (i >= PERF_MEM_EVENTS__MAX || !pmu)
+		return NULL;
+
+	e = &pmu->mem_events[i];
 	if (!e)
 		return NULL;
 
-	if (i == PERF_MEM_EVENTS__LOAD) {
-		if (!mem_loads_name__init) {
-			mem_loads_name__init = true;
-			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, perf_mem_events__loads_ldlat);
+	if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) {
+		if (e->ldlat) {
+			if (!e->aux_event) {
+				/* ARM and Most of Intel */
+				scnprintf(mem_loads_name, sizeof(mem_loads_name),
+					  e->name, pmu->name,
+					  perf_mem_events__loads_ldlat);
+			} else {
+				/* Intel with mem-loads-aux event */
+				scnprintf(mem_loads_name, sizeof(mem_loads_name),
+					  e->name, pmu->name, pmu->name,
+					  perf_mem_events__loads_ldlat);
+			}
+		} else {
+			if (!e->aux_event) {
+				/* AMD and POWER */
+				scnprintf(mem_loads_name, sizeof(mem_loads_name),
+					  e->name, pmu->name);
+			} else
+				return NULL;
 		}
+
 		return mem_loads_name;
 	}
 
-	return (char *)e->name;
+	if (i == PERF_MEM_EVENTS__STORE) {
+		scnprintf(mem_stores_name, sizeof(mem_stores_name),
+			  e->name, pmu->name);
+		return mem_stores_name;
+	}
+
+	return NULL;
 }
 
-__weak bool is_mem_loads_aux_event(struct evsel *leader __maybe_unused)
+bool is_mem_loads_aux_event(struct evsel *leader)
 {
-	return false;
+	struct perf_pmu *pmu = leader->pmu;
+	struct perf_mem_event *e;
+
+	if (!pmu || !pmu->mem_events)
+		return false;
+
+	e = &pmu->mem_events[PERF_MEM_EVENTS__LOAD];
+	if (!e->aux_event)
+		return false;
+
+	return leader->core.attr.config == e->aux_event;
 }
 
-int perf_mem_events__parse(const char *str)
+int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str)
 {
 	char *tok, *saveptr = NULL;
 	bool found = false;
@@ -79,7 +154,7 @@ int perf_mem_events__parse(const char *str)
 
 	while (tok) {
 		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-			struct perf_mem_event *e = perf_mem_events__ptr(j);
+			struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
 
 			if (!e->tag)
 				continue;
@@ -100,16 +175,21 @@ int perf_mem_events__parse(const char *str)
 	return -1;
 }
 
-static bool perf_mem_event__supported(const char *mnt, char *sysfs_name)
+static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu,
+				      struct perf_mem_event *e)
 {
 	char path[PATH_MAX];
 	struct stat st;
 
-	scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, sysfs_name);
+	if (!e->event_name)
+		return true;
+
+	scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name);
+
 	return !stat(path, &st);
 }
 
-int perf_mem_events__init(void)
+int perf_pmu__mem_events_init(struct perf_pmu *pmu)
 {
 	const char *mnt = sysfs__mount();
 	bool found = false;
@@ -119,9 +199,7 @@ int perf_mem_events__init(void)
 		return -ENOENT;
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		struct perf_mem_event *e = perf_mem_events__ptr(j);
-		char sysfs_name[100];
-		struct perf_pmu *pmu = NULL;
+		struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
 
 		/*
 		 * If the event entry isn't valid, skip initialization
@@ -130,16 +208,7 @@ int perf_mem_events__init(void)
 		if (!e->tag)
 			continue;
 
-		/*
-		 * Scan all PMUs not just core ones, since perf mem/c2c on
-		 * platforms like AMD uses IBS OP PMU which is independent
-		 * of core PMU.
-		 */
-		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
-			e->supported |= perf_mem_event__supported(mnt, sysfs_name);
-		}
-
+		e->supported |= perf_pmu__mem_events_supported(mnt, pmu, e);
 		if (e->supported)
 			found = true;
 	}
@@ -147,84 +216,58 @@ int perf_mem_events__init(void)
 	return found ? 0 : -ENOENT;
 }
 
-void perf_mem_events__list(void)
+void perf_pmu__mem_events_list(struct perf_pmu *pmu)
 {
 	int j;
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		struct perf_mem_event *e = perf_mem_events__ptr(j);
+		struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
 
 		fprintf(stderr, "%-*s%-*s%s",
 			e->tag ? 13 : 0,
 			e->tag ? : "",
 			e->tag && verbose > 0 ? 25 : 0,
-			e->tag && verbose > 0 ? perf_mem_events__name(j, NULL) : "",
+			e->tag && verbose > 0 ? perf_pmu__mem_events_name(j, pmu) : "",
 			e->supported ? ": available\n" : "");
 	}
 }
 
-static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
-						    int idx)
+int perf_mem_events__record_args(const char **rec_argv, int *argv_nr)
 {
 	const char *mnt = sysfs__mount();
-	char sysfs_name[100];
 	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name,
-			  pmu->name);
-		if (!perf_mem_event__supported(mnt, sysfs_name)) {
-			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events__name(idx, pmu->name));
-		}
-	}
-}
-
-int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
-				 char **rec_tmp, int *tmp_nr)
-{
-	int i = *argv_nr, k = 0;
 	struct perf_mem_event *e;
-	struct perf_pmu *pmu;
-	char *s;
+	int i = *argv_nr;
+	const char *s;
+	char *copy;
 
-	for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		e = perf_mem_events__ptr(j);
-		if (!e->record)
-			continue;
+	while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) {
+		for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			e = perf_pmu__mem_events_ptr(pmu, j);
+
+			if (!e->record)
+				continue;
 
-		if (perf_pmus__num_mem_pmus() == 1) {
 			if (!e->supported) {
 				pr_err("failed: event '%s' not supported\n",
-				       perf_mem_events__name(j, NULL));
+					perf_pmu__mem_events_name(j, pmu));
 				return -1;
 			}
 
-			rec_argv[i++] = "-e";
-			rec_argv[i++] = perf_mem_events__name(j, NULL);
-		} else {
-			if (!e->supported) {
-				perf_mem_events__print_unsupport_hybrid(e, j);
+			s = perf_pmu__mem_events_name(j, pmu);
+			if (!s || !perf_pmu__mem_events_supported(mnt, pmu, e))
+				continue;
+
+			copy = strdup(s);
+			if (!copy)
 				return -1;
-			}
 
-			while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-				rec_argv[i++] = "-e";
-				s = perf_mem_events__name(j, pmu->name);
-				if (s) {
-					s = strdup(s);
-					if (!s)
-						return -1;
-
-					rec_argv[i++] = s;
-					rec_tmp[k++] = s;
-				}
-			}
+			rec_argv[i++] = "-e";
+			rec_argv[i++] = copy;
 		}
 	}
 
 	*argv_nr = i;
-	*tmp_nr = k;
 	return 0;
 }
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 12372309d60e..15d5f0320d27 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -14,9 +14,11 @@
 struct perf_mem_event {
 	bool		record;
 	bool		supported;
+	bool		ldlat;
+	u32		aux_event;
 	const char	*tag;
 	const char	*name;
-	const char	*sysfs_name;
+	const char	*event_name;
 };
 
 struct mem_info {
@@ -34,17 +36,18 @@ enum {
 };
 
 extern unsigned int perf_mem_events__loads_ldlat;
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
-int perf_mem_events__parse(const char *str);
-int perf_mem_events__init(void);
+int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str);
+int perf_pmu__mem_events_init(struct perf_pmu *pmu);
 
-char *perf_mem_events__name(int i, char *pmu_name);
-struct perf_mem_event *perf_mem_events__ptr(int i);
+struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i);
+struct perf_pmu *perf_mem_events_find_pmu(void);
+int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu);
 bool is_mem_loads_aux_event(struct evsel *leader);
 
-void perf_mem_events__list(void);
-int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
-				 char **rec_tmp, int *tmp_nr);
+void perf_pmu__mem_events_list(struct perf_pmu *pmu);
+int perf_mem_events__record_args(const char **rec_argv, int *argv_nr);
 
 int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index a6a5ed44a679..79ef6095ab28 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -44,6 +44,8 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 	if (!metric_events)
 		return NULL;
 
+	if (evsel && evsel->metric_leader)
+		me.evsel = evsel->metric_leader;
 	nd = rblist__find(metric_events, &me);
 	if (nd)
 		return container_of(nd, struct metric_event, nd);
@@ -225,7 +227,7 @@ static struct metric *metric__new(const struct pmu_metric *pm,
 
 	m->pmu = pm->pmu ?: "cpu";
 	m->metric_name = pm->metric_name;
-	m->default_metricgroup_name = pm->default_metricgroup_name;
+	m->default_metricgroup_name = pm->default_metricgroup_name ?: "";
 	m->modifier = NULL;
 	if (modifier) {
 		m->modifier = strdup(modifier);
@@ -286,7 +288,7 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	*out_metric_events = NULL;
 	ids_size = hashmap__size(ids);
 
-	metric_events = calloc(sizeof(void *), ids_size + 1);
+	metric_events = calloc(ids_size + 1, sizeof(void *));
 	if (!metric_events)
 		return -ENOMEM;
 
@@ -350,25 +352,23 @@ static int setup_metric_events(const char *pmu, struct hashmap *ids,
 	return 0;
 }
 
-static bool match_metric(const char *n, const char *list)
+static bool match_metric(const char *metric_or_groups, const char *sought)
 {
 	int len;
 	char *m;
 
-	if (!list)
+	if (!sought)
 		return false;
-	if (!strcmp(list, "all"))
+	if (!strcmp(sought, "all"))
 		return true;
-	if (!n)
-		return !strcasecmp(list, "No_group");
-	len = strlen(list);
-	m = strcasestr(n, list);
-	if (!m)
-		return false;
-	if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
-	    (m[len] == 0 || m[len] == ';'))
+	if (!metric_or_groups)
+		return !strcasecmp(sought, "No_group");
+	len = strlen(sought);
+	if (!strncasecmp(metric_or_groups, sought, len) &&
+	    (metric_or_groups[len] == 0 || metric_or_groups[len] == ';'))
 		return true;
-	return false;
+	m = strchr(metric_or_groups, ';');
+	return m && match_metric(m + 1, sought);
 }
 
 static bool match_pm_metric(const struct pmu_metric *pm, const char *pmu, const char *metric)
@@ -498,7 +498,7 @@ static int metricgroup__sys_event_iter(const struct pmu_metric *pm,
 
 	while ((pmu = perf_pmus__scan(pmu))) {
 
-		if (!pmu->id || strcmp(pmu->id, pm->compat))
+		if (!pmu->id || !pmu_uncore_identifier_match(pm->compat, pmu->id))
 			continue;
 
 		return d->fn(pm, table, d->data);
@@ -527,7 +527,7 @@ void metricgroup__print(const struct print_callbacks *print_cb, void *print_stat
 	groups.node_delete = mep_delete;
 	table = pmu_metrics_table__find();
 	if (table) {
-		pmu_metrics_table_for_each_metric(table,
+		pmu_metrics_table__for_each_metric(table,
 						 metricgroup__add_to_mep_groups_callback,
 						 &groups);
 	}
@@ -1069,7 +1069,7 @@ static bool metricgroup__find_metric(const char *pmu,
 		.pm = pm,
 	};
 
-	return pmu_metrics_table_for_each_metric(table, metricgroup__find_metric_callback, &data)
+	return pmu_metrics_table__for_each_metric(table, metricgroup__find_metric_callback, &data)
 		? true : false;
 }
 
@@ -1255,7 +1255,7 @@ static int metricgroup__add_metric(const char *pmu, const char *metric_name, con
 		 * Iterate over all metrics seeing if metric matches either the
 		 * name or group. When it does add the metric to the list.
 		 */
-		ret = pmu_metrics_table_for_each_metric(table, metricgroup__add_metric_callback,
+		ret = pmu_metrics_table__for_each_metric(table, metricgroup__add_metric_callback,
 						       &data);
 		if (ret)
 			goto out;
@@ -1740,7 +1740,7 @@ bool metricgroup__has_metric(const char *pmu, const char *metric)
 	if (!table)
 		return false;
 
-	return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, &data)
+	return pmu_metrics_table__for_each_metric(table, metricgroup__has_metric_callback, &data)
 		? true : false;
 }
 
@@ -1770,7 +1770,7 @@ unsigned int metricgroups__topdown_max_level(void)
 	if (!table)
 		return false;
 
-	pmu_metrics_table_for_each_metric(table, metricgroup__topdown_max_level_callback,
+	pmu_metrics_table__for_each_metric(table, metricgroup__topdown_max_level_callback,
 					  &max_level);
 	return max_level;
 }
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 49093b21ee2d..122ee198a86e 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 
 	map->core.flush = mp->flush;
 
-	map->comp_level = mp->comp_level;
 #ifndef PYTHON_PERF
-	if (zstd_init(&map->zstd_data, map->comp_level)) {
+	if (zstd_init(&map->zstd_data, mp->comp_level)) {
 		pr_debug2("failed to init mmap compressor, error %d\n", errno);
 		return -1;
 	}
 #endif
 
-	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+	if (mp->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index f944c3cd5efa..0df6e1621c7e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,7 +39,6 @@ struct mmap {
 #endif
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
-	int		comp_level;
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 };
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index fd67d204d720..f7f7aff3d85a 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -36,6 +36,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_OPT("hw_index", PERF_SAMPLE_BRANCH_HW_INDEX),
 	BRANCH_OPT("priv", PERF_SAMPLE_BRANCH_PRIV_SAVE),
+	BRANCH_OPT("counter", PERF_SAMPLE_BRANCH_COUNTERS),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c9ec0cafb69d..6f8b0fa17689 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -13,13 +13,12 @@
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "string2.h"
-#include "strlist.h"
-#include "bpf-loader.h"
+#include "strbuf.h"
 #include "debug.h"
 #include <api/fs/tracing_path.h>
 #include <perf/cpumap.h>
-#include "parse-events-bison.h"
-#include "parse-events-flex.h"
+#include <util/parse-events-bison.h>
+#include <util/parse-events-flex.h>
 #include "pmu.h"
 #include "pmus.h"
 #include "asm/bug.h"
@@ -35,9 +34,9 @@
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-int parse_events_parse(void *parse_state, void *scanner);
-static int get_config_terms(struct list_head *head_config,
-			    struct list_head *head_terms __maybe_unused);
+static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms);
+static int parse_events_terms__copy(const struct parse_events_terms *src,
+				    struct parse_events_terms *dest);
 
 struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
@@ -155,26 +154,27 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-static char *get_config_str(struct list_head *head_terms, int type_term)
+static char *get_config_str(struct parse_events_terms *head_terms,
+			    enum parse_events__term_type type_term)
 {
 	struct parse_events_term *term;
 
 	if (!head_terms)
 		return NULL;
 
-	list_for_each_entry(term, head_terms, list)
+	list_for_each_entry(term, &head_terms->terms, list)
 		if (term->type_term == type_term)
 			return term->val.str;
 
 	return NULL;
 }
 
-static char *get_config_metric_id(struct list_head *head_terms)
+static char *get_config_metric_id(struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_METRIC_ID);
 }
 
-static char *get_config_name(struct list_head *head_terms)
+static char *get_config_name(struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME);
 }
@@ -190,43 +190,36 @@ static char *get_config_name(struct list_head *head_terms)
  * @config_terms: the list of terms that may contain a raw term.
  * @pmu: the PMU to scan for events from.
  */
-static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu)
+static void fix_raw(struct parse_events_terms *config_terms, struct perf_pmu *pmu)
 {
 	struct parse_events_term *term;
 
-	list_for_each_entry(term, config_terms, list) {
-		struct perf_pmu_alias *alias;
-		bool matched = false;
+	list_for_each_entry(term, &config_terms->terms, list) {
+		u64 num;
 
 		if (term->type_term != PARSE_EVENTS__TERM_TYPE_RAW)
 			continue;
 
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcmp(alias->name, term->val.str)) {
-				free(term->config);
-				term->config = term->val.str;
-				term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
-				term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
-				term->val.num = 1;
-				term->no_value = true;
-				matched = true;
-				break;
-			}
-		}
-		if (!matched) {
-			u64 num;
-
-			free(term->config);
-			term->config = strdup("config");
-			errno = 0;
-			num = strtoull(term->val.str + 1, NULL, 16);
-			assert(errno == 0);
-			free(term->val.str);
+		if (perf_pmu__have_event(pmu, term->val.str)) {
+			zfree(&term->config);
+			term->config = term->val.str;
 			term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
-			term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG;
-			term->val.num = num;
-			term->no_value = false;
+			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->val.num = 1;
+			term->no_value = true;
+			continue;
 		}
+
+		zfree(&term->config);
+		term->config = strdup("config");
+		errno = 0;
+		num = strtoull(term->val.str + 1, NULL, 16);
+		assert(errno == 0);
+		free(term->val.str);
+		term->type_val = PARSE_EVENTS__TERM_TYPE_NUM;
+		term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG;
+		term->val.num = num;
+		term->no_value = false;
 	}
 }
 
@@ -271,7 +264,7 @@ __add_event(struct list_head *list, int *idx,
 	evsel->core.is_pmu_core = pmu ? pmu->is_core : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 	evsel->pmu = pmu;
-	evsel->pmu_name = pmu && pmu->name ? strdup(pmu->name) : NULL;
+	evsel->pmu_name = pmu ? strdup(pmu->name) : NULL;
 
 	if (name)
 		evsel->name = strdup(name);
@@ -365,7 +358,7 @@ static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
 			      struct parse_events_error *err);
 static int config_attr(struct perf_event_attr *attr,
-		       struct list_head *head,
+		       struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term);
 
@@ -446,15 +439,12 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	if (parse_state->pmu_filter == NULL)
 		return false;
 
-	if (pmu->name == NULL)
-		return true;
-
 	return strcmp(parse_state->pmu_filter, pmu->name) != 0;
 }
 
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct list_head *head_config)
+			   struct parse_events_terms *head_config)
 {
 	struct perf_pmu *pmu = NULL;
 	bool found_supported = false;
@@ -499,7 +489,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 #ifdef HAVE_LIBTRACEEVENT
 static void tracepoint_error(struct parse_events_error *e, int err,
-			     const char *sys, const char *name)
+			     const char *sys, const char *name, int column)
 {
 	const char *str;
 	char help[BUFSIZ];
@@ -526,18 +516,19 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 	}
 
 	tracing_path__strerror_open_tp(err, help, sizeof(help), sys, name);
-	parse_events_error__handle(e, 0, strdup(str), strdup(help));
+	parse_events_error__handle(e, column, strdup(str), strdup(help));
 }
 
 static int add_tracepoint(struct list_head *list, int *idx,
 			  const char *sys_name, const char *evt_name,
 			  struct parse_events_error *err,
-			  struct list_head *head_config)
+			  struct parse_events_terms *head_config, void *loc_)
 {
+	YYLTYPE *loc = loc_;
 	struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, (*idx)++);
 
 	if (IS_ERR(evsel)) {
-		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name);
+		tracepoint_error(err, PTR_ERR(evsel), sys_name, evt_name, loc->first_column);
 		return PTR_ERR(evsel);
 	}
 
@@ -556,7 +547,7 @@ static int add_tracepoint(struct list_head *list, int *idx,
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      const char *sys_name, const char *evt_name,
 				      struct parse_events_error *err,
-				      struct list_head *head_config)
+				      struct parse_events_terms *head_config, YYLTYPE *loc)
 {
 	char *evt_path;
 	struct dirent *evt_ent;
@@ -565,13 +556,13 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 
 	evt_path = get_events_file(sys_name);
 	if (!evt_path) {
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
 		put_events_file(evt_path);
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 
@@ -588,11 +579,11 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		found++;
 
 		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name,
-				     err, head_config);
+				     err, head_config, loc);
 	}
 
 	if (!found) {
-		tracepoint_error(err, ENOENT, sys_name, evt_name);
+		tracepoint_error(err, ENOENT, sys_name, evt_name, loc->first_column);
 		ret = -1;
 	}
 
@@ -604,19 +595,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 static int add_tracepoint_event(struct list_head *list, int *idx,
 				const char *sys_name, const char *evt_name,
 				struct parse_events_error *err,
-				struct list_head *head_config)
+				struct parse_events_terms *head_config, YYLTYPE *loc)
 {
 	return strpbrk(evt_name, "*?") ?
-	       add_tracepoint_multi_event(list, idx, sys_name, evt_name,
-					  err, head_config) :
-	       add_tracepoint(list, idx, sys_name, evt_name,
-			      err, head_config);
+		add_tracepoint_multi_event(list, idx, sys_name, evt_name,
+					   err, head_config, loc) :
+		add_tracepoint(list, idx, sys_name, evt_name,
+			       err, head_config, loc);
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 				    const char *sys_name, const char *evt_name,
 				    struct parse_events_error *err,
-				    struct list_head *head_config)
+				    struct parse_events_terms *head_config, YYLTYPE *loc)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
@@ -624,7 +615,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 
 	events_dir = tracing_events__opendir();
 	if (!events_dir) {
-		tracepoint_error(err, errno, sys_name, evt_name);
+		tracepoint_error(err, errno, sys_name, evt_name, loc->first_column);
 		return -1;
 	}
 
@@ -640,7 +631,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 			continue;
 
 		ret = add_tracepoint_event(list, idx, events_ent->d_name,
-					   evt_name, err, head_config);
+					   evt_name, err, head_config, loc);
 	}
 
 	closedir(events_dir);
@@ -648,264 +639,6 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 }
 #endif /* HAVE_LIBTRACEEVENT */
 
-#ifdef HAVE_LIBBPF_SUPPORT
-struct __add_bpf_event_param {
-	struct parse_events_state *parse_state;
-	struct list_head *list;
-	struct list_head *head_config;
-};
-
-static int add_bpf_event(const char *group, const char *event, int fd, struct bpf_object *obj,
-			 void *_param)
-{
-	LIST_HEAD(new_evsels);
-	struct __add_bpf_event_param *param = _param;
-	struct parse_events_state *parse_state = param->parse_state;
-	struct list_head *list = param->list;
-	struct evsel *pos;
-	int err;
-	/*
-	 * Check if we should add the event, i.e. if it is a TP but starts with a '!',
-	 * then don't add the tracepoint, this will be used for something else, like
-	 * adding to a BPF_MAP_TYPE_PROG_ARRAY.
-	 *
-	 * See tools/perf/examples/bpf/augmented_raw_syscalls.c
-	 */
-	if (group[0] == '!')
-		return 0;
-
-	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
-		 group, event, fd);
-
-	err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group,
-					  event, parse_state->error,
-					  param->head_config);
-	if (err) {
-		struct evsel *evsel, *tmp;
-
-		pr_debug("Failed to add BPF event %s:%s\n",
-			 group, event);
-		list_for_each_entry_safe(evsel, tmp, &new_evsels, core.node) {
-			list_del_init(&evsel->core.node);
-			evsel__delete(evsel);
-		}
-		return err;
-	}
-	pr_debug("adding %s:%s\n", group, event);
-
-	list_for_each_entry(pos, &new_evsels, core.node) {
-		pr_debug("adding %s:%s to %p\n",
-			 group, event, pos);
-		pos->bpf_fd = fd;
-		pos->bpf_obj = obj;
-	}
-	list_splice(&new_evsels, list);
-	return 0;
-}
-
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list,
-			      struct bpf_object *obj,
-			      struct list_head *head_config)
-{
-	int err;
-	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {parse_state, list, head_config};
-	static bool registered_unprobe_atexit = false;
-
-	if (IS_ERR(obj) || !obj) {
-		snprintf(errbuf, sizeof(errbuf),
-			 "Internal error: load bpf obj with NULL");
-		err = -EINVAL;
-		goto errout;
-	}
-
-	/*
-	 * Register atexit handler before calling bpf__probe() so
-	 * bpf__probe() don't need to unprobe probe points its already
-	 * created when failure.
-	 */
-	if (!registered_unprobe_atexit) {
-		atexit(bpf__clear);
-		registered_unprobe_atexit = true;
-	}
-
-	err = bpf__probe(obj);
-	if (err) {
-		bpf__strerror_probe(obj, err, errbuf, sizeof(errbuf));
-		goto errout;
-	}
-
-	err = bpf__load(obj);
-	if (err) {
-		bpf__strerror_load(obj, err, errbuf, sizeof(errbuf));
-		goto errout;
-	}
-
-	err = bpf__foreach_event(obj, add_bpf_event, &param);
-	if (err) {
-		snprintf(errbuf, sizeof(errbuf),
-			 "Attach events in BPF object failed");
-		goto errout;
-	}
-
-	return 0;
-errout:
-	parse_events_error__handle(parse_state->error, 0,
-				strdup(errbuf), strdup("(add -v to see detail)"));
-	return err;
-}
-
-static int
-parse_events_config_bpf(struct parse_events_state *parse_state,
-			struct bpf_object *obj,
-			struct list_head *head_config)
-{
-	struct parse_events_term *term;
-	int error_pos;
-
-	if (!head_config || list_empty(head_config))
-		return 0;
-
-	list_for_each_entry(term, head_config, list) {
-		int err;
-
-		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
-			parse_events_error__handle(parse_state->error, term->err_term,
-						strdup("Invalid config term for BPF object"),
-						NULL);
-			return -EINVAL;
-		}
-
-		err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos);
-		if (err) {
-			char errbuf[BUFSIZ];
-			int idx;
-
-			bpf__strerror_config_obj(obj, term, parse_state->evlist,
-						 &error_pos, err, errbuf,
-						 sizeof(errbuf));
-
-			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
-				idx = term->err_val;
-			else
-				idx = term->err_term + error_pos;
-
-			parse_events_error__handle(parse_state->error, idx,
-						strdup(errbuf),
-						strdup(
-"Hint:\tValid config terms:\n"
-"     \tmap:[<arraymap>].value<indices>=[value]\n"
-"     \tmap:[<eventmap>].event<indices>=[event]\n"
-"\n"
-"     \twhere <indices> is something like [0,3...5] or [all]\n"
-"     \t(add -v to see detail)"));
-			return err;
-		}
-	}
-	return 0;
-}
-
-/*
- * Split config terms:
- * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
- *  'call-graph=fp' is 'evt config', should be applied to each
- *  events in bpf.c.
- * 'map:array.value[0]=1' is 'obj config', should be processed
- * with parse_events_config_bpf.
- *
- * Move object config terms from the first list to obj_head_config.
- */
-static void
-split_bpf_config_terms(struct list_head *evt_head_config,
-		       struct list_head *obj_head_config)
-{
-	struct parse_events_term *term, *temp;
-
-	/*
-	 * Currently, all possible user config term
-	 * belong to bpf object. parse_events__is_hardcoded_term()
-	 * happens to be a good flag.
-	 *
-	 * See parse_events_config_bpf() and
-	 * config_term_tracepoint().
-	 */
-	list_for_each_entry_safe(term, temp, evt_head_config, list)
-		if (!parse_events__is_hardcoded_term(term))
-			list_move_tail(&term->list, obj_head_config);
-}
-
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  char *bpf_file_name,
-			  bool source,
-			  struct list_head *head_config)
-{
-	int err;
-	struct bpf_object *obj;
-	LIST_HEAD(obj_head_config);
-
-	if (head_config)
-		split_bpf_config_terms(head_config, &obj_head_config);
-
-	obj = bpf__prepare_load(bpf_file_name, source);
-	if (IS_ERR(obj)) {
-		char errbuf[BUFSIZ];
-
-		err = PTR_ERR(obj);
-
-		if (err == -ENOTSUP)
-			snprintf(errbuf, sizeof(errbuf),
-				 "BPF support is not compiled");
-		else
-			bpf__strerror_prepare_load(bpf_file_name,
-						   source,
-						   -err, errbuf,
-						   sizeof(errbuf));
-
-		parse_events_error__handle(parse_state->error, 0,
-					strdup(errbuf), strdup("(add -v to see detail)"));
-		return err;
-	}
-
-	err = parse_events_load_bpf_obj(parse_state, list, obj, head_config);
-	if (err)
-		return err;
-	err = parse_events_config_bpf(parse_state, obj, &obj_head_config);
-
-	/*
-	 * Caller doesn't know anything about obj_head_config,
-	 * so combine them together again before returning.
-	 */
-	if (head_config)
-		list_splice_tail(&obj_head_config, head_config);
-	return err;
-}
-#else // HAVE_LIBBPF_SUPPORT
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list __maybe_unused,
-			      struct bpf_object *obj __maybe_unused,
-			      struct list_head *head_config __maybe_unused)
-{
-	parse_events_error__handle(parse_state->error, 0,
-				   strdup("BPF support is not compiled"),
-				   strdup("Make sure libbpf-devel is available at build time."));
-	return -ENOTSUP;
-}
-
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list __maybe_unused,
-			  char *bpf_file_name __maybe_unused,
-			  bool source __maybe_unused,
-			  struct list_head *head_config __maybe_unused)
-{
-	parse_events_error__handle(parse_state->error, 0,
-				   strdup("BPF support is not compiled"),
-				   strdup("Make sure libbpf-devel is available at build time."));
-	return -ENOTSUP;
-}
-#endif // HAVE_LIBBPF_SUPPORT
-
 static int
 parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
 {
@@ -949,7 +682,7 @@ do {					\
 int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 				struct list_head *list,
 				u64 addr, char *type, u64 len,
-				struct list_head *head_config __maybe_unused)
+				struct parse_events_terms *head_config)
 {
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
@@ -991,7 +724,7 @@ int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 
 static int check_type_val(struct parse_events_term *term,
 			  struct parse_events_error *err,
-			  int type)
+			  enum parse_events__term_val_type type)
 {
 	if (type == term->type_val)
 		return 0;
@@ -1006,42 +739,49 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-/*
- * Update according to parse-events.l
- */
-static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
-	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
-	[PARSE_EVENTS__TERM_TYPE_CONFIG3]		= "config3",
-	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
-	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
-	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
-	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
-	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
-	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
-	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
-	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
-	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
-	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
-	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
-	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
-	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
-	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
-	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
-	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
-	[PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE]	= "aux-sample-size",
-	[PARSE_EVENTS__TERM_TYPE_METRIC_ID]		= "metric-id",
-	[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
-	[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
-	[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
-};
-
 static bool config_term_shrinked;
 
+static const char *config_term_name(enum parse_events__term_type term_type)
+{
+	/*
+	 * Update according to parse-events.l
+	 */
+	static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+		[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+		[PARSE_EVENTS__TERM_TYPE_CONFIG3]		= "config3",
+		[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+		[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+		[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+		[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+		[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+		[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+		[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+		[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+		[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+		[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+		[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
+		[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
+		[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
+		[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
+		[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+		[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
+		[PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE]	= "aux-sample-size",
+		[PARSE_EVENTS__TERM_TYPE_METRIC_ID]		= "metric-id",
+		[PARSE_EVENTS__TERM_TYPE_RAW]                   = "raw",
+		[PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE]          = "legacy-cache",
+		[PARSE_EVENTS__TERM_TYPE_HARDWARE]              = "hardware",
+	};
+	if ((unsigned int)term_type >= __PARSE_EVENTS__TERM_TYPE_NR)
+		return "unknown term";
+
+	return config_term_names[term_type];
+}
+
 static bool
-config_term_avail(int term_type, struct parse_events_error *err)
+config_term_avail(enum parse_events__term_type term_type, struct parse_events_error *err)
 {
 	char *err_str;
 
@@ -1063,13 +803,31 @@ config_term_avail(int term_type, struct parse_events_error *err)
 	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 	case PARSE_EVENTS__TERM_TYPE_PERCORE:
 		return true;
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_TIME:
+	case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+	case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+	case PARSE_EVENTS__TERM_TYPE_INHERIT:
+	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+	case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
+	case PARSE_EVENTS__TERM_TYPE_RAW:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		if (!err)
 			return false;
 
 		/* term_type is validated so indexing is safe */
 		if (asprintf(&err_str, "'%s' is not usable in 'perf stat'",
-				config_term_names[term_type]) >= 0)
+			     config_term_name(term_type)) >= 0)
 			parse_events_error__handle(err, -1, err_str, NULL);
 		return false;
 	}
@@ -1187,10 +945,14 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		parse_events_error__handle(err, term->err_term,
-				strdup("unknown term"),
-				parse_events_formats_error_string(NULL));
+					strdup(config_term_name(term->type_term)),
+					parse_events_formats_error_string(NULL));
 		return -EINVAL;
 	}
 
@@ -1214,7 +976,7 @@ static int config_term_pmu(struct perf_event_attr *attr,
 			   struct parse_events_error *err)
 {
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -1224,15 +986,23 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		if (perf_pmu__supports_legacy_cache(pmu)) {
+		/*
+		 * Rewrite the PMU event to a legacy cache one unless the PMU
+		 * doesn't support legacy cache events or the event is present
+		 * within the PMU.
+		 */
+		if (perf_pmu__supports_legacy_cache(pmu) &&
+		    !perf_pmu__have_event(pmu, term->config)) {
 			attr->type = PERF_TYPE_HW_CACHE;
 			return parse_events__decode_legacy_cache(term->config, pmu->type,
 								 &attr->config);
-		} else
+		} else {
 			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		}
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) {
-		const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
+		struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 
 		if (!pmu) {
 			char *err_str;
@@ -1242,10 +1012,19 @@ static int config_term_pmu(struct perf_event_attr *attr,
 							   err_str, /*help=*/NULL);
 			return -EINVAL;
 		}
-		attr->type = PERF_TYPE_HARDWARE;
-		attr->config = term->val.num;
-		if (perf_pmus__supports_extended_type())
-			attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		/*
+		 * If the PMU has a sysfs or json event prefer it over
+		 * legacy. ARM requires this.
+		 */
+		if (perf_pmu__have_event(pmu, term->config)) {
+			term->type_term = PARSE_EVENTS__TERM_TYPE_USER;
+			term->no_value = true;
+		} else {
+			attr->type = PERF_TYPE_HARDWARE;
+			attr->config = term->val.num;
+			if (perf_pmus__supports_extended_type())
+				attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+		}
 		return 0;
 	}
 	if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER ||
@@ -1276,10 +1055,26 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 	case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
 		return config_term_common(attr, term, err);
+	case PARSE_EVENTS__TERM_TYPE_USER:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+	case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+	case PARSE_EVENTS__TERM_TYPE_TIME:
+	case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+	case PARSE_EVENTS__TERM_TYPE_PERCORE:
+	case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+	case PARSE_EVENTS__TERM_TYPE_RAW:
+	case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+	case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 	default:
 		if (err) {
 			parse_events_error__handle(err, term->err_term,
-				strdup("unknown term"),
+						   strdup(config_term_name(term->type_term)),
 				strdup("valid terms: call-graph,stack-size\n"));
 		}
 		return -EINVAL;
@@ -1290,21 +1085,20 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 #endif
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct list_head *head,
+		       struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term)
 {
 	struct parse_events_term *term;
 
-	list_for_each_entry(term, head, list)
+	list_for_each_entry(term, &head->terms, list)
 		if (config_term(attr, term, err))
 			return -EINVAL;
 
 	return 0;
 }
 
-static int get_config_terms(struct list_head *head_config,
-			    struct list_head *head_terms __maybe_unused)
+static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms)
 {
 #define ADD_CONFIG_TERM(__type, __weak)				\
 	struct evsel_config_term *__t;			\
@@ -1337,7 +1131,7 @@ do {								\
 
 	struct parse_events_term *term;
 
-	list_for_each_entry(term, head_config, list) {
+	list_for_each_entry(term, &head_config->terms, list) {
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 			ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak);
@@ -1397,6 +1191,16 @@ do {								\
 			ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size,
 					    term->val.num, term->weak);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_USER:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+		case PARSE_EVENTS__TERM_TYPE_NAME:
+		case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+		case PARSE_EVENTS__TERM_TYPE_RAW:
+		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 		default:
 			break;
 		}
@@ -1408,24 +1212,48 @@ do {								\
  * Add EVSEL__CONFIG_TERM_CFG_CHG where cfg_chg will have a bit set for
  * each bit of attr->config that the user has changed.
  */
-static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
+static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head_config,
 			   struct list_head *head_terms)
 {
 	struct parse_events_term *term;
 	u64 bits = 0;
 	int type;
 
-	list_for_each_entry(term, head_config, list) {
+	list_for_each_entry(term, &head_config->terms, list) {
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_USER:
-			type = perf_pmu__format_type(&pmu->format, term->config);
+			type = perf_pmu__format_type(pmu, term->config);
 			if (type != PERF_PMU_FORMAT_VALUE_CONFIG)
 				continue;
-			bits |= perf_pmu__format_bits(&pmu->format, term->config);
+			bits |= perf_pmu__format_bits(pmu, term->config);
 			break;
 		case PARSE_EVENTS__TERM_TYPE_CONFIG:
 			bits = ~(u64)0;
 			break;
+		case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+		case PARSE_EVENTS__TERM_TYPE_CONFIG3:
+		case PARSE_EVENTS__TERM_TYPE_NAME:
+		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
+		case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ:
+		case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE:
+		case PARSE_EVENTS__TERM_TYPE_TIME:
+		case PARSE_EVENTS__TERM_TYPE_CALLGRAPH:
+		case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
+		case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+		case PARSE_EVENTS__TERM_TYPE_INHERIT:
+		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+		case PARSE_EVENTS__TERM_TYPE_DRV_CFG:
+		case PARSE_EVENTS__TERM_TYPE_PERCORE:
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE:
+		case PARSE_EVENTS__TERM_TYPE_METRIC_ID:
+		case PARSE_EVENTS__TERM_TYPE_RAW:
+		case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE:
+		case PARSE_EVENTS__TERM_TYPE_HARDWARE:
 		default:
 			break;
 		}
@@ -1441,8 +1269,9 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config,
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *err,
-				struct list_head *head_config)
+				struct parse_events_terms *head_config, void *loc_)
 {
+	YYLTYPE *loc = loc_;
 #ifdef HAVE_LIBTRACEEVENT
 	if (head_config) {
 		struct perf_event_attr attr;
@@ -1454,17 +1283,17 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 
 	if (strpbrk(sys, "*?"))
 		return add_tracepoint_multi_sys(list, idx, sys, event,
-						err, head_config);
+						err, head_config, loc);
 	else
 		return add_tracepoint_event(list, idx, sys, event,
-					    err, head_config);
+					    err, head_config, loc);
 #else
 	(void)list;
 	(void)idx;
 	(void)sys;
 	(void)event;
 	(void)head_config;
-	parse_events_error__handle(err, 0, strdup("unsupported tracepoint"),
+	parse_events_error__handle(err, loc->first_column, strdup("unsupported tracepoint"),
 				strdup("libtraceevent is necessary for tracepoint support"));
 	return -1;
 #endif
@@ -1473,7 +1302,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 				struct list_head *list,
 				struct perf_pmu *pmu, u32 type, u32 extended_type,
-				u64 config, struct list_head *head_config)
+				u64 config, struct parse_events_terms *head_config)
 {
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
@@ -1509,7 +1338,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct list_head *head_config,
+			     struct parse_events_terms *head_config,
 			     bool wildcard)
 {
 	struct perf_pmu *pmu = NULL;
@@ -1557,53 +1386,63 @@ static bool config_term_percore(struct list_head *config_terms)
 }
 
 int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
-			 struct list_head *head_config,
-			 bool auto_merge_stats)
+			 struct list_head *list, const char *name,
+			 const struct parse_events_terms *const_parsed_terms,
+			 bool auto_merge_stats, void *loc_)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
+	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
+	struct parse_events_terms parsed_terms;
+	bool alias_rewrote_terms = false;
 
 	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
 
-	if (verbose > 1 && !(pmu && pmu->selectable)) {
-		fprintf(stderr, "Attempting to add event pmu '%s' with '",
-			name);
-		if (head_config) {
-			struct parse_events_term *term;
-
-			list_for_each_entry(term, head_config, list) {
-				fprintf(stderr, "%s,", term->config);
-			}
-		}
-		fprintf(stderr, "' that may result in non-fatal errors\n");
-	}
-
 	if (!pmu) {
 		char *err_str;
 
 		if (asprintf(&err_str,
 				"Cannot find PMU `%s'. Missing kernel support?",
 				name) >= 0)
-			parse_events_error__handle(err, 0, err_str, NULL);
+			parse_events_error__handle(err, loc->first_column, err_str, NULL);
 		return -EINVAL;
 	}
-	if (head_config)
-		fix_raw(head_config, pmu);
 
-	if (pmu->default_config) {
-		memcpy(&attr, pmu->default_config,
-		       sizeof(struct perf_event_attr));
-	} else {
-		memset(&attr, 0, sizeof(attr));
+	parse_events_terms__init(&parsed_terms);
+	if (const_parsed_terms) {
+		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
+
+		if (ret)
+			return ret;
 	}
+
+	if (verbose > 1) {
+		struct strbuf sb;
+
+		strbuf_init(&sb, /*hint=*/ 0);
+		if (pmu->selectable && list_empty(&parsed_terms.terms)) {
+			strbuf_addf(&sb, "%s//", name);
+		} else {
+			strbuf_addf(&sb, "%s/", name);
+			parse_events_terms__to_strbuf(&parsed_terms, &sb);
+			strbuf_addch(&sb, '/');
+		}
+		fprintf(stderr, "Attempt to add: %s\n", sb.buf);
+		strbuf_release(&sb);
+	}
+	fix_raw(&parsed_terms, pmu);
+
+	memset(&attr, 0, sizeof(attr));
+	if (pmu->perf_event_attr_init_default)
+		pmu->perf_event_attr_init_default(pmu, &attr);
+
 	attr.type = pmu->type;
 
-	if (!head_config) {
+	if (list_empty(&parsed_terms.terms)) {
 		evsel = __add_event(list, &parse_state->idx, &attr,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
@@ -1612,59 +1451,77 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
-	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info))
+	/* Configure attr/terms with a known PMU, this will set hardcoded terms. */
+	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+		parse_events_terms__exit(&parsed_terms);
+		return -EINVAL;
+	}
+
+	/* Look for event names in the terms and rewrite into format based terms. */
+	if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms,
+							    &info, &alias_rewrote_terms, err)) {
+		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
+	}
 
 	if (verbose > 1) {
-		fprintf(stderr, "After aliases, add event pmu '%s' with '",
-			name);
-		if (head_config) {
-			struct parse_events_term *term;
+		struct strbuf sb;
 
-			list_for_each_entry(term, head_config, list) {
-				fprintf(stderr, "%s,", term->config);
-			}
-		}
-		fprintf(stderr, "' that may result in non-fatal errors\n");
+		strbuf_init(&sb, /*hint=*/ 0);
+		parse_events_terms__to_strbuf(&parsed_terms, &sb);
+		fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf);
+		strbuf_release(&sb);
 	}
 
-	/*
-	 * Configure hardcoded terms first, no need to check
-	 * return value when called with fail == 0 ;)
-	 */
-	if (config_attr(&attr, head_config, parse_state->error, config_term_pmu))
+	/* Configure attr/terms again if an alias was expanded. */
+	if (alias_rewrote_terms &&
+	    config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
+		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
+	}
 
-	if (get_config_terms(head_config, &config_terms))
+	if (get_config_terms(&parsed_terms, &config_terms)) {
+		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
+	}
 
 	/*
 	 * When using default config, record which bits of attr->config were
 	 * changed by the user.
 	 */
-	if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms))
+	if (pmu->perf_event_attr_init_default &&
+	    get_config_chgs(pmu, &parsed_terms, &config_terms)) {
+		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
+	}
 
-	if (!parse_state->fake_pmu && perf_pmu__config(pmu, &attr, head_config, parse_state->error)) {
+	if (!parse_state->fake_pmu &&
+	    perf_pmu__config(pmu, &attr, &parsed_terms, parse_state->error)) {
 		free_config_terms(&config_terms);
+		parse_events_terms__exit(&parsed_terms);
 		return -EINVAL;
 	}
 
 	evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true,
-			    get_config_name(head_config),
-			    get_config_metric_id(head_config), pmu,
+			    get_config_name(&parsed_terms),
+			    get_config_metric_id(&parsed_terms), pmu,
 			    &config_terms, auto_merge_stats, /*cpu_list=*/NULL);
-	if (!evsel)
+	if (!evsel) {
+		parse_events_terms__exit(&parsed_terms);
 		return -ENOMEM;
+	}
 
 	if (evsel->name)
 		evsel->use_config_name = true;
 
 	evsel->percore = config_term_percore(&evsel->config_terms);
 
-	if (parse_state->fake_pmu)
+	if (parse_state->fake_pmu) {
+		parse_events_terms__exit(&parsed_terms);
 		return 0;
+	}
 
+	parse_events_terms__exit(&parsed_terms);
 	free((char *)evsel->unit);
 	evsel->unit = strdup(info.unit);
 	evsel->scale = info.scale;
@@ -1674,37 +1531,40 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       char *str, struct list_head *head,
-			       struct list_head **listp)
+			       const char *event_name,
+			       const struct parse_events_terms *const_parsed_terms,
+			       struct list_head **listp, void *loc_)
 {
 	struct parse_events_term *term;
 	struct list_head *list = NULL;
-	struct list_head *orig_head = NULL;
 	struct perf_pmu *pmu = NULL;
+	YYLTYPE *loc = loc_;
 	int ok = 0;
-	char *config;
+	const char *config;
+	struct parse_events_terms parsed_terms;
 
 	*listp = NULL;
 
-	if (!head) {
-		head = malloc(sizeof(struct list_head));
-		if (!head)
-			goto out_err;
+	parse_events_terms__init(&parsed_terms);
+	if (const_parsed_terms) {
+		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
 
-		INIT_LIST_HEAD(head);
+		if (ret)
+			return ret;
 	}
-	config = strdup(str);
+
+	config = strdup(event_name);
 	if (!config)
 		goto out_err;
 
 	if (parse_events_term__num(&term,
 				   PARSE_EVENTS__TERM_TYPE_USER,
-				   config, 1, false, NULL,
-					NULL) < 0) {
-		free(config);
+				   config, /*num=*/1, /*novalue=*/true,
+				   loc, /*loc_val=*/NULL) < 0) {
+		zfree(&config);
 		goto out_err;
 	}
-	list_add_tail(&term->list, head);
+	list_add_tail(&term->list, &parsed_terms.terms);
 
 	/* Add it for all PMUs that support the alias */
 	list = malloc(sizeof(struct list_head));
@@ -1714,44 +1574,47 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	INIT_LIST_HEAD(list);
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		struct perf_pmu_alias *alias;
 		bool auto_merge_stats;
 
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
 
-		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+		if (!perf_pmu__have_event(pmu, event_name))
+			continue;
 
-		list_for_each_entry(alias, &pmu->aliases, list) {
-			if (!strcasecmp(alias->name, str)) {
-				parse_events_copy_term_list(head, &orig_head);
-				if (!parse_events_add_pmu(parse_state, list,
-							  pmu->name, orig_head,
-							  auto_merge_stats)) {
-					pr_debug("%s -> %s/%s/\n", str,
-						 pmu->name, alias->str);
-					ok++;
-				}
-				parse_events_terms__delete(orig_head);
-			}
+		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+		if (!parse_events_add_pmu(parse_state, list, pmu->name,
+					  &parsed_terms, auto_merge_stats, loc)) {
+			struct strbuf sb;
+
+			strbuf_init(&sb, /*hint=*/ 0);
+			parse_events_terms__to_strbuf(&parsed_terms, &sb);
+			pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf);
+			strbuf_release(&sb);
+			ok++;
 		}
 	}
 
 	if (parse_state->fake_pmu) {
-		if (!parse_events_add_pmu(parse_state, list, str, head,
-					  /*auto_merge_stats=*/true)) {
-			pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str);
+		if (!parse_events_add_pmu(parse_state, list, event_name, &parsed_terms,
+					  /*auto_merge_stats=*/true, loc)) {
+			struct strbuf sb;
+
+			strbuf_init(&sb, /*hint=*/ 0);
+			parse_events_terms__to_strbuf(&parsed_terms, &sb);
+			pr_debug("%s -> %s/%s/\n", event_name, "fake_pmu", sb.buf);
+			strbuf_release(&sb);
 			ok++;
 		}
 	}
 
 out_err:
+	parse_events_terms__exit(&parsed_terms);
 	if (ok)
 		*listp = list;
 	else
 		free(list);
 
-	parse_events_terms__delete(head);
 	return ok ? 0 : -1;
 }
 
@@ -1972,14 +1835,18 @@ int parse_events_name(struct list_head *list, const char *name)
 	struct evsel *evsel;
 
 	__evlist__for_each_entry(list, evsel) {
-		if (!evsel->name)
+		if (!evsel->name) {
 			evsel->name = strdup(name);
+			if (!evsel->name)
+				return -ENOMEM;
+		}
 	}
 
 	return 0;
 }
 
 static int parse_events__scanner(const char *str,
+				 FILE *input,
 				 struct parse_events_state *parse_state)
 {
 	YY_BUFFER_STATE buffer;
@@ -1990,7 +1857,10 @@ static int parse_events__scanner(const char *str,
 	if (ret)
 		return ret;
 
-	buffer = parse_events__scan_string(str, scanner);
+	if (str)
+		buffer = parse_events__scan_string(str, scanner);
+	else
+	        parse_events_set_in(input, scanner);
 
 #ifdef PARSER_DEBUG
 	parse_events_debug = 1;
@@ -1998,8 +1868,10 @@ static int parse_events__scanner(const char *str,
 #endif
 	ret = parse_events_parse(parse_state, scanner);
 
-	parse_events__flush_buffer(buffer, scanner);
-	parse_events__delete_buffer(buffer, scanner);
+	if (str) {
+		parse_events__flush_buffer(buffer, scanner);
+		parse_events__delete_buffer(buffer, scanner);
+	}
 	parse_events_lex_destroy(scanner);
 	return ret;
 }
@@ -2007,7 +1879,7 @@ static int parse_events__scanner(const char *str,
 /*
  * parse event config string, return a list of event terms.
  */
-int parse_events_terms(struct list_head *terms, const char *str)
+int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input)
 {
 	struct parse_events_state parse_state = {
 		.terms  = NULL,
@@ -2015,15 +1887,11 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	};
 	int ret;
 
-	ret = parse_events__scanner(str, &parse_state);
-
-	if (!ret) {
-		list_splice(parse_state.terms, terms);
-		zfree(&parse_state.terms);
-		return 0;
-	}
+	ret = parse_events__scanner(str, input, &parse_state);
+	if (!ret)
+		list_splice(&parse_state.terms->terms, &terms->terms);
 
-	parse_events_terms__delete(parse_state.terms);
+	zfree(&parse_state.terms);
 	return ret;
 }
 
@@ -2259,7 +2127,6 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 		.list	  = LIST_HEAD_INIT(parse_state.list),
 		.idx	  = evlist->core.nr_entries,
 		.error	  = err,
-		.evlist	  = evlist,
 		.stoken	  = PE_START_EVENTS,
 		.fake_pmu = fake_pmu,
 		.pmu_filter = pmu_filter,
@@ -2267,7 +2134,7 @@ int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filte
 	};
 	int ret, ret2;
 
-	ret = parse_events__scanner(str, &parse_state);
+	ret = parse_events__scanner(str, /*input=*/ NULL, &parse_state);
 
 	if (!ret && list_empty(&parse_state.list)) {
 		WARN_ONCE(true, "WARNING: event parser found nothing\n");
@@ -2314,50 +2181,53 @@ int parse_event(struct evlist *evlist, const char *str)
 	return ret;
 }
 
+struct parse_events_error_entry {
+	/** @list: The list the error is part of. */
+	struct list_head list;
+	/** @idx: index in the parsed string */
+	int   idx;
+	/** @str: string to display at the index */
+	char *str;
+	/** @help: optional help string */
+	char *help;
+};
+
 void parse_events_error__init(struct parse_events_error *err)
 {
-	bzero(err, sizeof(*err));
+	INIT_LIST_HEAD(&err->list);
 }
 
 void parse_events_error__exit(struct parse_events_error *err)
 {
-	zfree(&err->str);
-	zfree(&err->help);
-	zfree(&err->first_str);
-	zfree(&err->first_help);
+	struct parse_events_error_entry *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &err->list, list) {
+		zfree(&pos->str);
+		zfree(&pos->help);
+		list_del_init(&pos->list);
+		free(pos);
+	}
 }
 
 void parse_events_error__handle(struct parse_events_error *err, int idx,
 				char *str, char *help)
 {
+	struct parse_events_error_entry *entry;
+
 	if (WARN(!str || !err, "WARNING: failed to provide error string or struct\n"))
 		goto out_free;
-	switch (err->num_errors) {
-	case 0:
-		err->idx = idx;
-		err->str = str;
-		err->help = help;
-		break;
-	case 1:
-		err->first_idx = err->idx;
-		err->idx = idx;
-		err->first_str = err->str;
-		err->str = str;
-		err->first_help = err->help;
-		err->help = help;
-		break;
-	default:
-		pr_debug("Multiple errors dropping message: %s (%s)\n",
-			err->str, err->help);
-		free(err->str);
-		err->str = str;
-		free(err->help);
-		err->help = help;
-		break;
+
+	entry = zalloc(sizeof(*entry));
+	if (!entry) {
+		pr_err("Failed to allocate memory for event parsing error: %s (%s)\n",
+			str, help ?: "<no help>");
+		goto out_free;
 	}
-	err->num_errors++;
+	entry->idx = idx;
+	entry->str = str;
+	entry->help = help;
+	list_add(&entry->list, &err->list);
 	return;
-
 out_free:
 	free(str);
 	free(help);
@@ -2427,19 +2297,34 @@ static void __parse_events_error__print(int err_idx, const char *err_str,
 	}
 }
 
-void parse_events_error__print(struct parse_events_error *err,
+void parse_events_error__print(const struct parse_events_error *err,
 			       const char *event)
 {
-	if (!err->num_errors)
-		return;
+	struct parse_events_error_entry *pos;
+	bool first = true;
 
-	__parse_events_error__print(err->idx, err->str, err->help, event);
+	list_for_each_entry(pos, &err->list, list) {
+		if (!first)
+			fputs("\n", stderr);
+		__parse_events_error__print(pos->idx, pos->str, pos->help, event);
+		first = false;
+	}
+}
 
-	if (err->num_errors > 1) {
-		fputs("\nInitial error:\n", stderr);
-		__parse_events_error__print(err->first_idx, err->first_str,
-					err->first_help, event);
+/*
+ * In the list of errors err, do any of the error strings (str) contain the
+ * given needle string?
+ */
+bool parse_events_error__contains(const struct parse_events_error *err,
+				  const char *needle)
+{
+	struct parse_events_error_entry *pos;
+
+	list_for_each_entry(pos, &err->list, list) {
+		if (strstr(pos->str, needle) != NULL)
+			return true;
 	}
+	return false;
 }
 
 #undef MAX_WIDTH
@@ -2641,7 +2526,8 @@ static int new_term(struct parse_events_term **_term,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num,
+			   enum parse_events__term_type type_term,
+			   const char *config, u64 num,
 			   bool no_value,
 			   void *loc_term_, void *loc_val_)
 {
@@ -2651,17 +2537,18 @@ int parse_events_term__num(struct parse_events_term **term,
 	struct parse_events_term temp = {
 		.type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
 		.type_term = type_term,
-		.config    = config ? : strdup(config_term_names[type_term]),
+		.config    = config ? : strdup(config_term_name(type_term)),
 		.no_value  = no_value,
 		.err_term  = loc_term ? loc_term->first_column : 0,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
 	};
 
-	return new_term(term, &temp, NULL, num);
+	return new_term(term, &temp, /*str=*/NULL, num);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str,
+			   enum parse_events__term_type type_term,
+			   char *config, char *str,
 			   void *loc_term_, void *loc_val_)
 {
 	YYLTYPE *loc_term = loc_term_;
@@ -2675,15 +2562,16 @@ int parse_events_term__str(struct parse_events_term **term,
 		.err_val   = loc_val  ? loc_val->first_column  : 0,
 	};
 
-	return new_term(term, &temp, str, 0);
+	return new_term(term, &temp, str, /*num=*/0);
 }
 
 int parse_events_term__term(struct parse_events_term **term,
-			    int term_lhs, int term_rhs,
+			    enum parse_events__term_type term_lhs,
+			    enum parse_events__term_type term_rhs,
 			    void *loc_term, void *loc_val)
 {
 	return parse_events_term__str(term, term_lhs, NULL,
-				      strdup(config_term_names[term_rhs]),
+				      strdup(config_term_name(term_rhs)),
 				      loc_term, loc_val);
 }
 
@@ -2691,33 +2579,27 @@ int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
 	char *str;
-	struct parse_events_term temp = {
-		.type_val  = term->type_val,
-		.type_term = term->type_term,
-		.config    = NULL,
-		.err_term  = term->err_term,
-		.err_val   = term->err_val,
-	};
+	struct parse_events_term temp = *term;
 
+	temp.used = false;
 	if (term->config) {
 		temp.config = strdup(term->config);
 		if (!temp.config)
 			return -ENOMEM;
 	}
 	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-		return new_term(new, &temp, NULL, term->val.num);
+		return new_term(new, &temp, /*str=*/NULL, term->val.num);
 
 	str = strdup(term->val.str);
-	if (!str)
+	if (!str) {
+		zfree(&temp.config);
 		return -ENOMEM;
-	return new_term(new, &temp, str, 0);
+	}
+	return new_term(new, &temp, str, /*num=*/0);
 }
 
 void parse_events_term__delete(struct parse_events_term *term)
 {
-	if (term->array.nr_ranges)
-		zfree(&term->array.ranges);
-
 	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM)
 		zfree(&term->val.str);
 
@@ -2725,52 +2607,88 @@ void parse_events_term__delete(struct parse_events_term *term)
 	free(term);
 }
 
-int parse_events_copy_term_list(struct list_head *old,
-				 struct list_head **new)
+static int parse_events_terms__copy(const struct parse_events_terms *src,
+				    struct parse_events_terms *dest)
 {
-	struct parse_events_term *term, *n;
-	int ret;
-
-	if (!old) {
-		*new = NULL;
-		return 0;
-	}
+	struct parse_events_term *term;
 
-	*new = malloc(sizeof(struct list_head));
-	if (!*new)
-		return -ENOMEM;
-	INIT_LIST_HEAD(*new);
+	list_for_each_entry (term, &src->terms, list) {
+		struct parse_events_term *n;
+		int ret;
 
-	list_for_each_entry (term, old, list) {
 		ret = parse_events_term__clone(&n, term);
 		if (ret)
 			return ret;
-		list_add_tail(&n->list, *new);
+
+		list_add_tail(&n->list, &dest->terms);
 	}
 	return 0;
 }
 
-void parse_events_terms__purge(struct list_head *terms)
+void parse_events_terms__init(struct parse_events_terms *terms)
+{
+	INIT_LIST_HEAD(&terms->terms);
+}
+
+void parse_events_terms__exit(struct parse_events_terms *terms)
 {
 	struct parse_events_term *term, *h;
 
-	list_for_each_entry_safe(term, h, terms, list) {
+	list_for_each_entry_safe(term, h, &terms->terms, list) {
 		list_del_init(&term->list);
 		parse_events_term__delete(term);
 	}
 }
 
-void parse_events_terms__delete(struct list_head *terms)
+void parse_events_terms__delete(struct parse_events_terms *terms)
 {
 	if (!terms)
 		return;
-	parse_events_terms__purge(terms);
+	parse_events_terms__exit(terms);
 	free(terms);
 }
 
-void parse_events__clear_array(struct parse_events_array *a)
+int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb)
 {
-	zfree(&a->ranges);
+	struct parse_events_term *term;
+	bool first = true;
+
+	if (!terms)
+		return 0;
+
+	list_for_each_entry(term, &terms->terms, list) {
+		int ret;
+
+		if (!first) {
+			ret = strbuf_addch(sb, ',');
+			if (ret < 0)
+				return ret;
+		}
+		first = false;
+
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+			if (term->no_value) {
+				assert(term->val.num == 1);
+				ret = strbuf_addf(sb, "%s", term->config);
+			} else
+				ret = strbuf_addf(sb, "%s=%#"PRIx64, term->config, term->val.num);
+		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+			if (term->config) {
+				ret = strbuf_addf(sb, "%s=", term->config);
+				if (ret < 0)
+					return ret;
+			} else if ((unsigned int)term->type_term < __PARSE_EVENTS__TERM_TYPE_NR) {
+				ret = strbuf_addf(sb, "%s=", config_term_name(term->type_term));
+				if (ret < 0)
+					return ret;
+			}
+			assert(!term->no_value);
+			ret = strbuf_addf(sb, "%s", term->val.str);
+		}
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
 }
 
 void parse_events_evlist_error(struct parse_events_state *parse_state,
@@ -2789,7 +2707,7 @@ static void config_terms_list(char *buf, size_t buf_sz)
 
 	buf[0] = '\0';
 	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
-		const char *name = config_term_names[i];
+		const char *name = config_term_name(i);
 
 		if (!config_term_avail(i, NULL))
 			continue;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b0eb95f93e9c..809359e8544e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -9,6 +9,7 @@
 #include <stdbool.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <stdio.h>
 #include <string.h>
 
 struct evsel;
@@ -17,6 +18,7 @@ struct parse_events_error;
 
 struct option;
 struct perf_pmu;
+struct strbuf;
 
 const char *event_type(int type);
 
@@ -42,16 +44,15 @@ static inline int parse_events(struct evlist *evlist, const char *str,
 
 int parse_event(struct evlist *evlist, const char *str);
 
-int parse_events_terms(struct list_head *terms, const char *str);
 int parse_filter(const struct option *opt, const char *str, int unset);
 int exclude_perf(const struct option *opt, const char *arg, int unset);
 
-enum {
+enum parse_events__term_val_type {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
 };
 
-enum {
+enum parse_events__term_type {
 	PARSE_EVENTS__TERM_TYPE_USER,
 	PARSE_EVENTS__TERM_TYPE_CONFIG,
 	PARSE_EVENTS__TERM_TYPE_CONFIG1,
@@ -78,60 +79,84 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_RAW,
 	PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
 	PARSE_EVENTS__TERM_TYPE_HARDWARE,
-	__PARSE_EVENTS__TERM_TYPE_NR,
-};
-
-struct parse_events_array {
-	size_t nr_ranges;
-	struct {
-		unsigned int start;
-		size_t length;
-	} *ranges;
+#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_HARDWARE + 1)
 };
 
 struct parse_events_term {
-	char *config;
-	struct parse_events_array array;
+	/** @list: The term list the term is a part of. */
+	struct list_head list;
+	/**
+	 * @config: The left-hand side of a term assignment, so the term
+	 * "event=8" would have the config be "event"
+	 */
+	const char *config;
+	/**
+	 * @val: The right-hand side of a term assignment that can either be a
+	 * string or a number depending on type_val.
+	 */
 	union {
 		char *str;
 		u64  num;
 	} val;
-	int type_val;
-	int type_term;
-	struct list_head list;
-	bool used;
-	bool no_value;
-
-	/* error string indexes for within parsed string */
+	/** @type_val: The union variable in val to be used for the term. */
+	enum parse_events__term_val_type type_val;
+	/**
+	 * @type_term: A predefined term type or PARSE_EVENTS__TERM_TYPE_USER
+	 * when not inbuilt.
+	 */
+	enum parse_events__term_type type_term;
+	/**
+	 * @err_term: The column index of the term from parsing, used during
+	 * error output.
+	 */
 	int err_term;
+	/**
+	 * @err_val: The column index of the val from parsing, used during error
+	 * output.
+	 */
 	int err_val;
-
-	/* Coming from implicit alias */
+	/** @used: Was the term used during parameterized-eval. */
+	bool used;
+	/**
+	 * @weak: A term from the sysfs or json encoding of an event that
+	 * shouldn't override terms coming from the command line.
+	 */
 	bool weak;
+	/**
+	 * @no_value: Is there no value. If a numeric term has no value then the
+	 * value is assumed to be 1. An event name also has no value.
+	 */
+	bool no_value;
 };
 
 struct parse_events_error {
-	int   num_errors;       /* number of errors encountered */
-	int   idx;	/* index in the parsed string */
-	char *str;      /* string to display at the index */
-	char *help;	/* optional help string */
-	int   first_idx;/* as above, but for the first encountered error */
-	char *first_str;
-	char *first_help;
+	/** @list: The head of a list of errors. */
+	struct list_head list;
+};
+
+/* A wrapper around a list of terms for the sake of better type safety. */
+struct parse_events_terms {
+	struct list_head terms;
 };
 
 struct parse_events_state {
+	/* The list parsed events are placed on. */
 	struct list_head	   list;
+	/* The updated index used by entries as they are added. */
 	int			   idx;
+	/* Error information. */
 	struct parse_events_error *error;
-	struct evlist		  *evlist;
-	struct list_head	  *terms;
+	/* Holds returned terms for term parsing. */
+	struct parse_events_terms *terms;
+	/* Start token. */
 	int			   stoken;
+	/* Special fake PMU marker for testing. */
 	struct perf_pmu		  *fake_pmu;
 	/* If non-null, when wildcard matching only match the given PMU. */
 	const char		  *pmu_filter;
 	/* Should PE_LEGACY_NAME tokens be generated for config terms? */
 	bool			   match_legacy_cache_terms;
+	/* Were multiple PMUs scanned to find events? */
 	bool			   wild_card_pmus;
 };
 
@@ -140,71 +165,63 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num,
+			   enum parse_events__term_type type_term,
+			   const char *config, u64 num,
 			   bool novalue,
 			   void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str,
+			   enum parse_events__term_type type_term,
+			   char *config, char *str,
 			   void *loc_term, void *loc_val);
 int parse_events_term__term(struct parse_events_term **term,
-			    int term_lhs, int term_rhs,
+			    enum parse_events__term_type term_lhs,
+			    enum parse_events__term_type term_rhs,
 			    void *loc_term, void *loc_val);
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
 void parse_events_term__delete(struct parse_events_term *term);
-void parse_events_terms__delete(struct list_head *terms);
-void parse_events_terms__purge(struct list_head *terms);
-void parse_events__clear_array(struct parse_events_array *a);
+
+void parse_events_terms__delete(struct parse_events_terms *terms);
+void parse_events_terms__init(struct parse_events_terms *terms);
+void parse_events_terms__exit(struct parse_events_terms *terms);
+int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input);
+int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, const char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *error,
-				struct list_head *head_config);
-int parse_events_load_bpf(struct parse_events_state *parse_state,
-			  struct list_head *list,
-			  char *bpf_file_name,
-			  bool source,
-			  struct list_head *head_config);
-/* Provide this function for perf test */
-struct bpf_object;
-int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
-			      struct list_head *list,
-			      struct bpf_object *obj,
-			      struct list_head *head_config);
+				struct parse_events_terms *head_config, void *loc);
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct list_head *head_config,
+			     struct parse_events_terms *head_config,
 			     bool wildcard);
 int parse_events_add_tool(struct parse_events_state *parse_state,
 			  struct list_head *list,
 			  int tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct list_head *head_config);
+			   struct parse_events_terms *head_config);
 int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
 int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 				struct list_head *list,
 				u64 addr, char *type, u64 len,
-				struct list_head *head_config);
+				struct parse_events_terms *head_config);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
-			 struct list_head *head_config,
-			 bool auto_merge_stats);
+			 struct list_head *list, const char *name,
+			 const struct parse_events_terms *const_parsed_terms,
+			bool auto_merge_stats, void *loc);
 
 struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 				      const char *name, const char *metric_id,
 				      struct perf_pmu *pmu);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       char *str,
-			       struct list_head *head_config,
-			       struct list_head **listp);
-
-int parse_events_copy_term_list(struct list_head *old,
-				 struct list_head **new);
+			       const char *event_name,
+			       const struct parse_events_terms *const_parsed_terms,
+			       struct list_head **listp, void *loc);
 
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
@@ -225,9 +242,10 @@ void parse_events_error__init(struct parse_events_error *err);
 void parse_events_error__exit(struct parse_events_error *err);
 void parse_events_error__handle(struct parse_events_error *err, int idx,
 				char *str, char *help);
-void parse_events_error__print(struct parse_events_error *err,
+void parse_events_error__print(const struct parse_events_error *err,
 			       const char *event);
-
+bool parse_events_error__contains(const struct parse_events_error *err,
+				  const char *needle);
 #ifdef HAVE_LIBELF_SUPPORT
 /*
  * If the probe point starts with '%',
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 99335ec586ae..e86c45675e1d 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -68,31 +68,6 @@ static int lc_str(yyscan_t scanner, const struct parse_events_state *state)
 	return str(scanner, state->match_legacy_cache_terms ? PE_LEGACY_CACHE : PE_NAME);
 }
 
-static bool isbpf_suffix(char *text)
-{
-	int len = strlen(text);
-
-	if (len < 2)
-		return false;
-	if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
-	    text[len - 2] == '.')
-		return true;
-	if (len > 4 && !strcmp(text + len - 4, ".obj"))
-		return true;
-	return false;
-}
-
-static bool isbpf(yyscan_t scanner)
-{
-	char *text = parse_events_get_text(scanner);
-	struct stat st;
-
-	if (!isbpf_suffix(text))
-		return false;
-
-	return stat(text, &st) == 0;
-}
-
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -141,11 +116,11 @@ static int tool(yyscan_t scanner, enum perf_tool_event event)
 	return PE_VALUE_SYM_TOOL;
 }
 
-static int term(yyscan_t scanner, int type)
+static int term(yyscan_t scanner, enum parse_events__term_type type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
-	yylval->num = type;
+	yylval->term_type = type;
 	return PE_TERM;
 }
 
@@ -175,17 +150,14 @@ do {							\
 %x mem
 %s config
 %x event
-%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
 event		[^,{}/]+
-bpf_object	[^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
-bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec		[0-9]+
-num_hex		0x[a-fA-F0-9]+
-num_raw_hex	[a-fA-F0-9]+
+num_hex		0x[a-fA-F0-9]{1,16}
+num_raw_hex	[a-fA-F0-9]{1,16}
 name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]*
 name_tag	[\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
@@ -234,8 +206,6 @@ non_digit	[^0-9]
 		}
 
 {event_pmu}	|
-{bpf_object}	|
-{bpf_source}	|
 {event}		{
 			BEGIN(INITIAL);
 			REWIND(1);
@@ -251,14 +221,6 @@ non_digit	[^0-9]
 		}
 }
 
-<array>{
-"]"			{ BEGIN(config); return ']'; }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
-,			{ return ','; }
-"\.\.\."		{ return PE_ARRAY_RANGE; }
-}
-
 <config>{
 	/*
 	 * Please update config_term_names when new static term is added.
@@ -302,8 +264,6 @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 {lc_type}-{lc_op_result}	{ return lc_str(yyscanner, _parse_state); }
 {lc_type}-{lc_op_result}-{lc_op_result}	{ return lc_str(yyscanner, _parse_state); }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
-\[all\]			{ return PE_ARRAY_ALL; }
-"["			{ BEGIN(array); return '['; }
 @{drv_cfg_term}		{ return drv_str(yyscanner, PE_DRV_CFG_TERM); }
 }
 
@@ -374,8 +334,6 @@ r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
 {name}			{ return str(yyscanner, PE_NAME); }
 {name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9f28d4b5502f..d70f5d84af92 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -6,26 +6,27 @@
 
 %{
 
+#ifndef NDEBUG
 #define YYDEBUG 1
+#endif
 
 #include <errno.h>
-#include <fnmatch.h>
-#include <stdio.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/zalloc.h>
 #include "pmu.h"
 #include "pmus.h"
 #include "evsel.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
+int parse_events_lex(YYSTYPE * yylval_param, YYLTYPE * yylloc_param , void *yyscanner);
 void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg);
 
-#define ABORT_ON(val) \
+#define PE_ABORT(val) \
 do { \
-	if (val) \
-		YYABORT; \
+	if (val == -ENOMEM) \
+		YYNOMEM; \
+	YYABORT; \
 } while (0)
 
 static struct list_head* alloc_list(void)
@@ -58,32 +59,26 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
-%token PE_BPF_OBJECT PE_BPF_SOURCE
 %token PE_MODIFIER_EVENT PE_MODIFIER_BP PE_BP_COLON PE_BP_SLASH
 %token PE_LEGACY_CACHE
-%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
+%token PE_PREFIX_MEM
 %token PE_ERROR
-%token PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
-%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
 %type <num> PE_VALUE_SYM_TOOL
-%type <num> PE_TERM
+%type <term_type> PE_TERM
 %type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
-%type <str> PE_BPF_OBJECT
-%type <str> PE_BPF_SOURCE
 %type <str> PE_LEGACY_CACHE
 %type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
-%type <str> PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
 %type <str> PE_DRV_CFG_TERM
-%type <str> name_or_raw name_or_legacy
+%type <str> name_or_raw
 %destructor { free ($$); } <str>
 %type <term> event_term
 %destructor { parse_events_term__delete ($$); } <term>
@@ -98,7 +93,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_evsel> event_legacy_tracepoint
 %type <list_evsel> event_legacy_numeric
 %type <list_evsel> event_legacy_raw
-%type <list_evsel> event_bpf_file
 %type <list_evsel> event_def
 %type <list_evsel> event_mod
 %type <list_evsel> event_name
@@ -110,10 +104,6 @@ static void free_list_evsel(struct list_head* list_evsel)
 %destructor { free_list_evsel ($$); } <list_evsel>
 %type <tracepoint_name> tracepoint_name
 %destructor { free ($$.sys); free ($$.event); } <tracepoint_name>
-%type <array> array
-%type <array> array_term
-%type <array> array_terms
-%destructor { free ($$.ranges); } <array>
 %type <hardware_term> PE_TERM_HW
 %destructor { free ($$.str); } <hardware_term>
 
@@ -121,14 +111,14 @@ static void free_list_evsel(struct list_head* list_evsel)
 {
 	char *str;
 	u64 num;
+	enum parse_events__term_type term_type;
 	struct list_head *list_evsel;
-	struct list_head *list_terms;
+	struct parse_events_terms *list_terms;
 	struct parse_events_term *term;
 	struct tracepoint_name {
 		char *sys;
 		char *event;
 	} tracepoint_name;
-	struct parse_events_array array;
 	struct hardware_term {
 		char *str;
 		u64 num;
@@ -265,7 +255,7 @@ PE_EVENT_NAME event_def
 	free($1);
 	if (err) {
 		free_list_evsel($2);
-		YYABORT;
+		YYNOMEM;
 	}
 	$$ = $2;
 }
@@ -278,47 +268,42 @@ event_def: event_pmu |
 	   event_legacy_mem sep_dc |
 	   event_legacy_tracepoint sep_dc |
 	   event_legacy_numeric sep_dc |
-	   event_legacy_raw sep_dc |
-	   event_bpf_file
+	   event_legacy_raw sep_dc
 
 event_pmu:
 PE_NAME opt_pmu_config
 {
 	struct parse_events_state *parse_state = _parse_state;
-	struct parse_events_error *error = parse_state->error;
-	struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL;
+	/* List of created evsels. */
+	struct list_head *list = NULL;
 	char *pattern = NULL;
 
-#define CLEANUP_YYABORT					\
+#define CLEANUP						\
 	do {						\
 		parse_events_terms__delete($2);		\
-		parse_events_terms__delete(orig_terms);	\
 		free(list);				\
 		free($1);				\
 		free(pattern);				\
-		YYABORT;				\
 	} while(0)
 
-	if (parse_events_copy_term_list($2, &orig_terms))
-		CLEANUP_YYABORT;
-
-	if (error)
-		error->idx = @1.first_column;
-
 	list = alloc_list();
-	if (!list)
-		CLEANUP_YYABORT;
+	if (!list) {
+		CLEANUP;
+		YYNOMEM;
+	}
 	/* Attempt to add to list assuming $1 is a PMU name. */
-	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) {
+	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false, &@1)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 
 		/* Failure to add, try wildcard expansion of $1 as a PMU name. */
-		if (asprintf(&pattern, "%s*", $1) < 0)
-			CLEANUP_YYABORT;
+		if (asprintf(&pattern, "%s*", $1) < 0) {
+			CLEANUP;
+			YYNOMEM;
+		}
 
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			char *name = pmu->name;
+			const char *name = pmu->name;
 
 			if (parse_events__filter_pmu(parse_state, pmu))
 				continue;
@@ -330,44 +315,36 @@ PE_NAME opt_pmu_config
 			    !perf_pmu__match(pattern, pmu->alias_name, $1)) {
 				bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
 
-				if (parse_events_copy_term_list(orig_terms, &terms))
-					CLEANUP_YYABORT;
-				if (!parse_events_add_pmu(parse_state, list, pmu->name, terms,
-							  auto_merge_stats)) {
+				if (!parse_events_add_pmu(parse_state, list, pmu->name, $2,
+							  auto_merge_stats, &@1)) {
 					ok++;
 					parse_state->wild_card_pmus = true;
 				}
-				parse_events_terms__delete(terms);
 			}
 		}
 
 		if (!ok) {
 			/* Failure to add, assume $1 is an event name. */
 			zfree(&list);
-			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list);
-			$2 = NULL;
+			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1);
+		}
+		if (!ok) {
+			struct parse_events_error *error = parse_state->error;
+			char *help;
+
+			if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", $1) < 0)
+				help = NULL;
+			parse_events_error__handle(error, @1.first_column,
+						   strdup("Bad event or PMU"),
+						   help);
+			CLEANUP;
+			YYABORT;
 		}
-		if (!ok)
-			CLEANUP_YYABORT;
 	}
-	parse_events_terms__delete($2);
-	parse_events_terms__delete(orig_terms);
-	free(pattern);
-	free($1);
-	$$ = list;
-#undef CLEANUP_YYABORT
-}
-|
-PE_KERNEL_PMU_EVENT sep_dc
-{
-	struct list_head *list;
-	int err;
-
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
-	free($1);
-	if (err < 0)
-		YYABORT;
 	$$ = list;
+	list = NULL;
+	CLEANUP;
+#undef CLEANUP
 }
 |
 PE_NAME sep_dc
@@ -375,61 +352,19 @@ PE_NAME sep_dc
 	struct list_head *list;
 	int err;
 
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
-	free($1);
-	if (err < 0)
-		YYABORT;
-	$$ = list;
-}
-|
-PE_KERNEL_PMU_EVENT opt_pmu_config
-{
-	struct list_head *list;
-	int err;
-
-	/* frees $2 */
-	err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list);
-	free($1);
-	if (err < 0)
-		YYABORT;
-	$$ = list;
-}
-|
-PE_PMU_EVENT_FAKE sep_dc
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYABORT;
-
-	err = parse_events_add_pmu(_parse_state, list, $1, /*head_config=*/NULL,
-				   /*auto_merge_stats=*/false);
-	free($1);
+	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1);
 	if (err < 0) {
-		free(list);
-		YYABORT;
-	}
-	$$ = list;
-}
-|
-PE_PMU_EVENT_FAKE opt_pmu_config
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	if (!list)
-		YYABORT;
+		struct parse_events_state *parse_state = _parse_state;
+		struct parse_events_error *error = parse_state->error;
+		char *help;
 
-	err = parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false);
-	free($1);
-	parse_events_terms__delete($2);
-	if (err < 0) {
-		free(list);
-		YYABORT;
+		if (asprintf(&help, "Unable to find event on a PMU of '%s'", $1) < 0)
+			help = NULL;
+		parse_events_error__handle(error, @1.first_column, strdup("Bad event name"), help);
+		free($1);
+		PE_ABORT(err);
 	}
+	free($1);
 	$$ = list;
 }
 
@@ -448,12 +383,13 @@ value_sym '/' event_config '/'
 	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
 	parse_events_terms__delete($3);
 	if (err) {
 		free_list_evsel(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -464,21 +400,28 @@ value_sym sep_slash_slash_dc
 	int type = $1 >> 16;
 	int config = $1 & 255;
 	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
+	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
-	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config,
-					  /*head_config=*/NULL, wildcard));
+	if (!list)
+		YYNOMEM;
+	err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+	if (err)
+		PE_ABORT(err);
 	$$ = list;
 }
 |
 PE_VALUE_SYM_TOOL sep_slash_slash_dc
 {
 	struct list_head *list;
+	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
-	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+	if (!list)
+		YYNOMEM;
+	err = parse_events_add_tool(_parse_state, list, $1);
+	if (err)
+		YYNOMEM;
 	$$ = list;
 }
 
@@ -490,14 +433,16 @@ PE_LEGACY_CACHE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2);
 
 	parse_events_terms__delete($2);
 	free($1);
 	if (err) {
 		free_list_evsel(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -509,14 +454,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, $6, $4, $7);
 	parse_events_terms__delete($7);
 	free($6);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -527,13 +474,15 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, NULL, $4, $5);
 	parse_events_terms__delete($5);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -544,14 +493,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
+
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, $4, 0, $5);
 	parse_events_terms__delete($5);
 	free($4);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -562,13 +513,14 @@ PE_PREFIX_MEM PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_breakpoint(_parse_state, list,
 					  $2, NULL, 0, $3);
 	parse_events_terms__delete($3);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -582,19 +534,18 @@ tracepoint_name opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
-	if (error)
-		error->idx = @1.first_column;
+	if (!list)
+		YYNOMEM;
 
 	err = parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event,
-					error, $2);
+					error, $2, &@1);
 
 	parse_events_terms__delete($2);
 	free($1.sys);
 	free($1.event);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -614,13 +565,14 @@ PE_VALUE ':' PE_VALUE opt_event_config
 	int err;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4,
 				       /*wildcard=*/false);
 	parse_events_terms__delete($4);
 	if (err) {
 		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -633,52 +585,20 @@ PE_RAW opt_event_config
 	u64 num;
 
 	list = alloc_list();
-	ABORT_ON(!list);
+	if (!list)
+		YYNOMEM;
 	errno = 0;
 	num = strtoull($1 + 1, NULL, 16);
-	ABORT_ON(errno);
+	/* Given the lexer will only give [a-fA-F0-9]+ a failure here should be impossible. */
+	if (errno)
+		YYABORT;
 	free($1);
 	err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, num, $2,
 				       /*wildcard=*/false);
 	parse_events_terms__delete($2);
 	if (err) {
 		free(list);
-		YYABORT;
-	}
-	$$ = list;
-}
-
-event_bpf_file:
-PE_BPF_OBJECT opt_event_config
-{
-	struct parse_events_state *parse_state = _parse_state;
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	ABORT_ON(!list);
-	err = parse_events_load_bpf(parse_state, list, $1, false, $2);
-	parse_events_terms__delete($2);
-	free($1);
-	if (err) {
-		free(list);
-		YYABORT;
-	}
-	$$ = list;
-}
-|
-PE_BPF_SOURCE opt_event_config
-{
-	struct list_head *list;
-	int err;
-
-	list = alloc_list();
-	ABORT_ON(!list);
-	err = parse_events_load_bpf(_parse_state, list, $1, true, $2);
-	parse_events_terms__delete($2);
-	if (err) {
-		free(list);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = list;
 }
@@ -722,54 +642,54 @@ start_terms: event_config
 event_config:
 event_config ',' event_term
 {
-	struct list_head *head = $1;
+	struct parse_events_terms *head = $1;
 	struct parse_events_term *term = $3;
 
 	if (!head) {
 		parse_events_term__delete(term);
 		YYABORT;
 	}
-	list_add_tail(&term->list, head);
+	list_add_tail(&term->list, &head->terms);
 	$$ = $1;
 }
 |
 event_term
 {
-	struct list_head *head = malloc(sizeof(*head));
+	struct parse_events_terms *head = malloc(sizeof(*head));
 	struct parse_events_term *term = $1;
 
-	ABORT_ON(!head);
-	INIT_LIST_HEAD(head);
-	list_add_tail(&term->list, head);
+	if (!head)
+		YYNOMEM;
+	parse_events_terms__init(head);
+	list_add_tail(&term->list, &head->terms);
 	$$ = head;
 }
 
 name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE
 
-name_or_legacy: PE_NAME | PE_LEGACY_CACHE
-
 event_term:
 PE_RAW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
+					 strdup("raw"), $1, &@1, &@1);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
-					strdup("raw"), $1, &@1, &@1)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
 |
-name_or_raw '=' name_or_legacy
+name_or_raw '=' name_or_raw
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3, &@1, &@3);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3, &@1, &@3)) {
+	if (err) {
 		free($1);
 		free($3);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -777,11 +697,12 @@ name_or_raw '=' name_or_legacy
 name_or_raw '=' PE_VALUE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, $3, /*novalue=*/false, &@1, &@3);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3, false, &@1, &@3)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -789,12 +710,13 @@ name_or_raw '=' PE_VALUE
 name_or_raw '=' PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, $3.str, &@1, &@3);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3.str, &@1, &@3)) {
+	if (err) {
 		free($1);
 		free($3.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -802,11 +724,12 @@ name_or_raw '=' PE_TERM_HW
 PE_LEGACY_CACHE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
+					 $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
-					$1, 1, true, &@1, NULL)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -814,11 +737,12 @@ PE_LEGACY_CACHE
 PE_NAME
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					 $1, /*num=*/1, /*novalue=*/true, &@1, /*loc_val=*/NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, true, &@1, NULL)) {
+	if (err) {
 		free($1);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -826,22 +750,25 @@ PE_NAME
 PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
+					 $1.str, $1.num & 255, /*novalue=*/false,
+					 &@1, /*loc_val=*/NULL);
 
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
-				   $1.str, $1.num & 255, false, &@1, NULL)) {
+	if (err) {
 		free($1.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
 |
-PE_TERM '=' name_or_legacy
+PE_TERM '=' name_or_raw
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3, &@1, &@3);
 
-	if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) {
+	if (err) {
 		free($3);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -849,10 +776,11 @@ PE_TERM '=' name_or_legacy
 PE_TERM '=' PE_TERM_HW
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3.str, &@1, &@3);
 
-	if (parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3)) {
+	if (err) {
 		free($3.str);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
@@ -860,53 +788,37 @@ PE_TERM '=' PE_TERM_HW
 PE_TERM '=' PE_TERM
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__term(&term, $1, $3, &@1, &@3);
+
+	if (err)
+		PE_ABORT(err);
 
-	ABORT_ON(parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3));
 	$$ = term;
 }
 |
 PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, $1,
+					 /*config=*/NULL, $3, /*novalue=*/false,
+					 &@1, &@3);
+
+	if (err)
+		PE_ABORT(err);
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
 	$$ = term;
 }
 |
 PE_TERM
 {
 	struct parse_events_term *term;
+	int err = parse_events_term__num(&term, $1,
+					 /*config=*/NULL, /*num=*/1, /*novalue=*/true,
+					 &@1, /*loc_val=*/NULL);
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
-	$$ = term;
-}
-|
-name_or_raw array '=' name_or_legacy
-{
-	struct parse_events_term *term;
+	if (err)
+		PE_ABORT(err);
 
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $4, &@1, &@4)) {
-		free($1);
-		free($4);
-		free($2.ranges);
-		YYABORT;
-	}
-	term->array = $2;
-	$$ = term;
-}
-|
-name_or_raw array '=' PE_VALUE
-{
-	struct parse_events_term *term;
-
-	if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $4, false, &@1, &@4)) {
-		free($1);
-		free($2.ranges);
-		YYABORT;
-	}
-	term->array = $2;
 	$$ = term;
 }
 |
@@ -914,73 +826,19 @@ PE_DRV_CFG_TERM
 {
 	struct parse_events_term *term;
 	char *config = strdup($1);
+	int err;
 
-	ABORT_ON(!config);
-	if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG,
-					config, $1, &@1, NULL)) {
+	if (!config)
+		YYNOMEM;
+	err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL);
+	if (err) {
 		free($1);
 		free(config);
-		YYABORT;
+		PE_ABORT(err);
 	}
 	$$ = term;
 }
 
-array:
-'[' array_terms ']'
-{
-	$$ = $2;
-}
-|
-PE_ARRAY_ALL
-{
-	$$.nr_ranges = 0;
-	$$.ranges = NULL;
-}
-
-array_terms:
-array_terms ',' array_term
-{
-	struct parse_events_array new_array;
-
-	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
-	new_array.ranges = realloc($1.ranges,
-				sizeof(new_array.ranges[0]) *
-				new_array.nr_ranges);
-	ABORT_ON(!new_array.ranges);
-	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
-	       $3.nr_ranges * sizeof(new_array.ranges[0]));
-	free($3.ranges);
-	$$ = new_array;
-}
-|
-array_term
-
-array_term:
-PE_VALUE
-{
-	struct parse_events_array array;
-
-	array.nr_ranges = 1;
-	array.ranges = malloc(sizeof(array.ranges[0]));
-	ABORT_ON(!array.ranges);
-	array.ranges[0].start = $1;
-	array.ranges[0].length = 1;
-	$$ = array;
-}
-|
-PE_VALUE PE_ARRAY_RANGE PE_VALUE
-{
-	struct parse_events_array array;
-
-	ABORT_ON($3 < $1);
-	array.nr_ranges = 1;
-	array.ranges = malloc(sizeof(array.ranges[0]));
-	ABORT_ON(!array.ranges);
-	array.ranges[0].start = $1;
-	array.ranges[0].length = $3 - $1 + 1;
-	$$ = array;
-}
-
 sep_dc: ':' |
 
 sep_slash_slash_dc: '/' '/' | ':' |
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index a4a100425b3a..cda1c620968e 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -46,22 +46,18 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
 
 			if (!strcmp(s, "?")) {
 				fprintf(stderr, "available registers: ");
-#ifdef HAVE_PERF_REGS_SUPPORT
-				for (r = sample_reg_masks; r->name; r++) {
+				for (r = arch__sample_reg_masks(); r->name; r++) {
 					if (r->mask & mask)
 						fprintf(stderr, "%s ", r->name);
 				}
-#endif
 				fputc('\n', stderr);
 				/* just printing available regs */
 				goto error;
 			}
-#ifdef HAVE_PERF_REGS_SUPPORT
-			for (r = sample_reg_masks; r->name; r++) {
+			for (r = arch__sample_reg_masks(); r->name; r++) {
 				if ((r->mask & mask) && !strcasecmp(s, r->name))
 					break;
 			}
-#endif
 			if (!r || !r->name) {
 				ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n",
 					    s, intr ? "-I" : "--user-regs=");
diff --git a/tools/perf/util/perf-regs-arch/Build b/tools/perf/util/perf-regs-arch/Build
new file mode 100644
index 000000000000..d9d596d330a7
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/Build
@@ -0,0 +1,9 @@
+perf-y += perf_regs_aarch64.o
+perf-y += perf_regs_arm.o
+perf-y += perf_regs_csky.o
+perf-y += perf_regs_loongarch.o
+perf-y += perf_regs_mips.o
+perf-y += perf_regs_powerpc.o
+perf-y += perf_regs_riscv.o
+perf-y += perf_regs_s390.o
+perf-y += perf_regs_x86.o
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
new file mode 100644
index 000000000000..9dcda80d310f
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_aarch64.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/arm64/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_arm64(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	case PERF_REG_ARM64_VG:
+		return "vg";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_arm64(void)
+{
+	return PERF_REG_ARM64_PC;
+}
+
+uint64_t __perf_reg_sp_arm64(void)
+{
+	return PERF_REG_ARM64_SP;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_arm.c b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
new file mode 100644
index 000000000000..e29d130a587a
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_arm.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/arm/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_arm(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_arm(void)
+{
+	return PERF_REG_ARM_PC;
+}
+
+uint64_t __perf_reg_sp_arm(void)
+{
+	return PERF_REG_ARM_SP;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_csky.c b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
new file mode 100644
index 000000000000..75b461ef2eba
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_csky.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../arch/csky/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_csky(int id)
+{
+	switch (id) {
+	case PERF_REG_CSKY_A0:
+		return "a0";
+	case PERF_REG_CSKY_A1:
+		return "a1";
+	case PERF_REG_CSKY_A2:
+		return "a2";
+	case PERF_REG_CSKY_A3:
+		return "a3";
+	case PERF_REG_CSKY_REGS0:
+		return "regs0";
+	case PERF_REG_CSKY_REGS1:
+		return "regs1";
+	case PERF_REG_CSKY_REGS2:
+		return "regs2";
+	case PERF_REG_CSKY_REGS3:
+		return "regs3";
+	case PERF_REG_CSKY_REGS4:
+		return "regs4";
+	case PERF_REG_CSKY_REGS5:
+		return "regs5";
+	case PERF_REG_CSKY_REGS6:
+		return "regs6";
+	case PERF_REG_CSKY_REGS7:
+		return "regs7";
+	case PERF_REG_CSKY_REGS8:
+		return "regs8";
+	case PERF_REG_CSKY_REGS9:
+		return "regs9";
+	case PERF_REG_CSKY_SP:
+		return "sp";
+	case PERF_REG_CSKY_LR:
+		return "lr";
+	case PERF_REG_CSKY_PC:
+		return "pc";
+#if defined(__CSKYABIV2__)
+	case PERF_REG_CSKY_EXREGS0:
+		return "exregs0";
+	case PERF_REG_CSKY_EXREGS1:
+		return "exregs1";
+	case PERF_REG_CSKY_EXREGS2:
+		return "exregs2";
+	case PERF_REG_CSKY_EXREGS3:
+		return "exregs3";
+	case PERF_REG_CSKY_EXREGS4:
+		return "exregs4";
+	case PERF_REG_CSKY_EXREGS5:
+		return "exregs5";
+	case PERF_REG_CSKY_EXREGS6:
+		return "exregs6";
+	case PERF_REG_CSKY_EXREGS7:
+		return "exregs7";
+	case PERF_REG_CSKY_EXREGS8:
+		return "exregs8";
+	case PERF_REG_CSKY_EXREGS9:
+		return "exregs9";
+	case PERF_REG_CSKY_EXREGS10:
+		return "exregs10";
+	case PERF_REG_CSKY_EXREGS11:
+		return "exregs11";
+	case PERF_REG_CSKY_EXREGS12:
+		return "exregs12";
+	case PERF_REG_CSKY_EXREGS13:
+		return "exregs13";
+	case PERF_REG_CSKY_EXREGS14:
+		return "exregs14";
+	case PERF_REG_CSKY_TLS:
+		return "tls";
+	case PERF_REG_CSKY_HI:
+		return "hi";
+	case PERF_REG_CSKY_LO:
+		return "lo";
+#endif
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_csky(void)
+{
+	return PERF_REG_CSKY_PC;
+}
+
+uint64_t __perf_reg_sp_csky(void)
+{
+	return PERF_REG_CSKY_SP;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
new file mode 100644
index 000000000000..043f97f4e3ac
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_loongarch.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/loongarch/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_loongarch(int id)
+{
+	switch (id) {
+	case PERF_REG_LOONGARCH_PC:
+		return "PC";
+	case PERF_REG_LOONGARCH_R1:
+		return "%r1";
+	case PERF_REG_LOONGARCH_R2:
+		return "%r2";
+	case PERF_REG_LOONGARCH_R3:
+		return "%r3";
+	case PERF_REG_LOONGARCH_R4:
+		return "%r4";
+	case PERF_REG_LOONGARCH_R5:
+		return "%r5";
+	case PERF_REG_LOONGARCH_R6:
+		return "%r6";
+	case PERF_REG_LOONGARCH_R7:
+		return "%r7";
+	case PERF_REG_LOONGARCH_R8:
+		return "%r8";
+	case PERF_REG_LOONGARCH_R9:
+		return "%r9";
+	case PERF_REG_LOONGARCH_R10:
+		return "%r10";
+	case PERF_REG_LOONGARCH_R11:
+		return "%r11";
+	case PERF_REG_LOONGARCH_R12:
+		return "%r12";
+	case PERF_REG_LOONGARCH_R13:
+		return "%r13";
+	case PERF_REG_LOONGARCH_R14:
+		return "%r14";
+	case PERF_REG_LOONGARCH_R15:
+		return "%r15";
+	case PERF_REG_LOONGARCH_R16:
+		return "%r16";
+	case PERF_REG_LOONGARCH_R17:
+		return "%r17";
+	case PERF_REG_LOONGARCH_R18:
+		return "%r18";
+	case PERF_REG_LOONGARCH_R19:
+		return "%r19";
+	case PERF_REG_LOONGARCH_R20:
+		return "%r20";
+	case PERF_REG_LOONGARCH_R21:
+		return "%r21";
+	case PERF_REG_LOONGARCH_R22:
+		return "%r22";
+	case PERF_REG_LOONGARCH_R23:
+		return "%r23";
+	case PERF_REG_LOONGARCH_R24:
+		return "%r24";
+	case PERF_REG_LOONGARCH_R25:
+		return "%r25";
+	case PERF_REG_LOONGARCH_R26:
+		return "%r26";
+	case PERF_REG_LOONGARCH_R27:
+		return "%r27";
+	case PERF_REG_LOONGARCH_R28:
+		return "%r28";
+	case PERF_REG_LOONGARCH_R29:
+		return "%r29";
+	case PERF_REG_LOONGARCH_R30:
+		return "%r30";
+	case PERF_REG_LOONGARCH_R31:
+		return "%r31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_loongarch(void)
+{
+	return PERF_REG_LOONGARCH_PC;
+}
+
+uint64_t __perf_reg_sp_loongarch(void)
+{
+	return PERF_REG_LOONGARCH_R3;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_mips.c b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
new file mode 100644
index 000000000000..793178fc3c78
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_mips.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/mips/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_mips(int id)
+{
+	switch (id) {
+	case PERF_REG_MIPS_PC:
+		return "PC";
+	case PERF_REG_MIPS_R1:
+		return "$1";
+	case PERF_REG_MIPS_R2:
+		return "$2";
+	case PERF_REG_MIPS_R3:
+		return "$3";
+	case PERF_REG_MIPS_R4:
+		return "$4";
+	case PERF_REG_MIPS_R5:
+		return "$5";
+	case PERF_REG_MIPS_R6:
+		return "$6";
+	case PERF_REG_MIPS_R7:
+		return "$7";
+	case PERF_REG_MIPS_R8:
+		return "$8";
+	case PERF_REG_MIPS_R9:
+		return "$9";
+	case PERF_REG_MIPS_R10:
+		return "$10";
+	case PERF_REG_MIPS_R11:
+		return "$11";
+	case PERF_REG_MIPS_R12:
+		return "$12";
+	case PERF_REG_MIPS_R13:
+		return "$13";
+	case PERF_REG_MIPS_R14:
+		return "$14";
+	case PERF_REG_MIPS_R15:
+		return "$15";
+	case PERF_REG_MIPS_R16:
+		return "$16";
+	case PERF_REG_MIPS_R17:
+		return "$17";
+	case PERF_REG_MIPS_R18:
+		return "$18";
+	case PERF_REG_MIPS_R19:
+		return "$19";
+	case PERF_REG_MIPS_R20:
+		return "$20";
+	case PERF_REG_MIPS_R21:
+		return "$21";
+	case PERF_REG_MIPS_R22:
+		return "$22";
+	case PERF_REG_MIPS_R23:
+		return "$23";
+	case PERF_REG_MIPS_R24:
+		return "$24";
+	case PERF_REG_MIPS_R25:
+		return "$25";
+	case PERF_REG_MIPS_R28:
+		return "$28";
+	case PERF_REG_MIPS_R29:
+		return "$29";
+	case PERF_REG_MIPS_R30:
+		return "$30";
+	case PERF_REG_MIPS_R31:
+		return "$31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_mips(void)
+{
+	return PERF_REG_MIPS_PC;
+}
+
+uint64_t __perf_reg_sp_mips(void)
+{
+	return PERF_REG_MIPS_R29;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
new file mode 100644
index 000000000000..08636bb09a3a
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_powerpc.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/powerpc/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_powerpc(int id)
+{
+	switch (id) {
+	case PERF_REG_POWERPC_R0:
+		return "r0";
+	case PERF_REG_POWERPC_R1:
+		return "r1";
+	case PERF_REG_POWERPC_R2:
+		return "r2";
+	case PERF_REG_POWERPC_R3:
+		return "r3";
+	case PERF_REG_POWERPC_R4:
+		return "r4";
+	case PERF_REG_POWERPC_R5:
+		return "r5";
+	case PERF_REG_POWERPC_R6:
+		return "r6";
+	case PERF_REG_POWERPC_R7:
+		return "r7";
+	case PERF_REG_POWERPC_R8:
+		return "r8";
+	case PERF_REG_POWERPC_R9:
+		return "r9";
+	case PERF_REG_POWERPC_R10:
+		return "r10";
+	case PERF_REG_POWERPC_R11:
+		return "r11";
+	case PERF_REG_POWERPC_R12:
+		return "r12";
+	case PERF_REG_POWERPC_R13:
+		return "r13";
+	case PERF_REG_POWERPC_R14:
+		return "r14";
+	case PERF_REG_POWERPC_R15:
+		return "r15";
+	case PERF_REG_POWERPC_R16:
+		return "r16";
+	case PERF_REG_POWERPC_R17:
+		return "r17";
+	case PERF_REG_POWERPC_R18:
+		return "r18";
+	case PERF_REG_POWERPC_R19:
+		return "r19";
+	case PERF_REG_POWERPC_R20:
+		return "r20";
+	case PERF_REG_POWERPC_R21:
+		return "r21";
+	case PERF_REG_POWERPC_R22:
+		return "r22";
+	case PERF_REG_POWERPC_R23:
+		return "r23";
+	case PERF_REG_POWERPC_R24:
+		return "r24";
+	case PERF_REG_POWERPC_R25:
+		return "r25";
+	case PERF_REG_POWERPC_R26:
+		return "r26";
+	case PERF_REG_POWERPC_R27:
+		return "r27";
+	case PERF_REG_POWERPC_R28:
+		return "r28";
+	case PERF_REG_POWERPC_R29:
+		return "r29";
+	case PERF_REG_POWERPC_R30:
+		return "r30";
+	case PERF_REG_POWERPC_R31:
+		return "r31";
+	case PERF_REG_POWERPC_NIP:
+		return "nip";
+	case PERF_REG_POWERPC_MSR:
+		return "msr";
+	case PERF_REG_POWERPC_ORIG_R3:
+		return "orig_r3";
+	case PERF_REG_POWERPC_CTR:
+		return "ctr";
+	case PERF_REG_POWERPC_LINK:
+		return "link";
+	case PERF_REG_POWERPC_XER:
+		return "xer";
+	case PERF_REG_POWERPC_CCR:
+		return "ccr";
+	case PERF_REG_POWERPC_SOFTE:
+		return "softe";
+	case PERF_REG_POWERPC_TRAP:
+		return "trap";
+	case PERF_REG_POWERPC_DAR:
+		return "dar";
+	case PERF_REG_POWERPC_DSISR:
+		return "dsisr";
+	case PERF_REG_POWERPC_SIER:
+		return "sier";
+	case PERF_REG_POWERPC_MMCRA:
+		return "mmcra";
+	case PERF_REG_POWERPC_MMCR0:
+		return "mmcr0";
+	case PERF_REG_POWERPC_MMCR1:
+		return "mmcr1";
+	case PERF_REG_POWERPC_MMCR2:
+		return "mmcr2";
+	case PERF_REG_POWERPC_MMCR3:
+		return "mmcr3";
+	case PERF_REG_POWERPC_SIER2:
+		return "sier2";
+	case PERF_REG_POWERPC_SIER3:
+		return "sier3";
+	case PERF_REG_POWERPC_PMC1:
+		return "pmc1";
+	case PERF_REG_POWERPC_PMC2:
+		return "pmc2";
+	case PERF_REG_POWERPC_PMC3:
+		return "pmc3";
+	case PERF_REG_POWERPC_PMC4:
+		return "pmc4";
+	case PERF_REG_POWERPC_PMC5:
+		return "pmc5";
+	case PERF_REG_POWERPC_PMC6:
+		return "pmc6";
+	case PERF_REG_POWERPC_SDAR:
+		return "sdar";
+	case PERF_REG_POWERPC_SIAR:
+		return "siar";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_powerpc(void)
+{
+	return PERF_REG_POWERPC_NIP;
+}
+
+uint64_t __perf_reg_sp_powerpc(void)
+{
+	return PERF_REG_POWERPC_R1;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_riscv.c b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
new file mode 100644
index 000000000000..337b687c655d
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_riscv.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/riscv/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_riscv(int id)
+{
+	switch (id) {
+	case PERF_REG_RISCV_PC:
+		return "pc";
+	case PERF_REG_RISCV_RA:
+		return "ra";
+	case PERF_REG_RISCV_SP:
+		return "sp";
+	case PERF_REG_RISCV_GP:
+		return "gp";
+	case PERF_REG_RISCV_TP:
+		return "tp";
+	case PERF_REG_RISCV_T0:
+		return "t0";
+	case PERF_REG_RISCV_T1:
+		return "t1";
+	case PERF_REG_RISCV_T2:
+		return "t2";
+	case PERF_REG_RISCV_S0:
+		return "s0";
+	case PERF_REG_RISCV_S1:
+		return "s1";
+	case PERF_REG_RISCV_A0:
+		return "a0";
+	case PERF_REG_RISCV_A1:
+		return "a1";
+	case PERF_REG_RISCV_A2:
+		return "a2";
+	case PERF_REG_RISCV_A3:
+		return "a3";
+	case PERF_REG_RISCV_A4:
+		return "a4";
+	case PERF_REG_RISCV_A5:
+		return "a5";
+	case PERF_REG_RISCV_A6:
+		return "a6";
+	case PERF_REG_RISCV_A7:
+		return "a7";
+	case PERF_REG_RISCV_S2:
+		return "s2";
+	case PERF_REG_RISCV_S3:
+		return "s3";
+	case PERF_REG_RISCV_S4:
+		return "s4";
+	case PERF_REG_RISCV_S5:
+		return "s5";
+	case PERF_REG_RISCV_S6:
+		return "s6";
+	case PERF_REG_RISCV_S7:
+		return "s7";
+	case PERF_REG_RISCV_S8:
+		return "s8";
+	case PERF_REG_RISCV_S9:
+		return "s9";
+	case PERF_REG_RISCV_S10:
+		return "s10";
+	case PERF_REG_RISCV_S11:
+		return "s11";
+	case PERF_REG_RISCV_T3:
+		return "t3";
+	case PERF_REG_RISCV_T4:
+		return "t4";
+	case PERF_REG_RISCV_T5:
+		return "t5";
+	case PERF_REG_RISCV_T6:
+		return "t6";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_riscv(void)
+{
+	return PERF_REG_RISCV_PC;
+}
+
+uint64_t __perf_reg_sp_riscv(void)
+{
+	return PERF_REG_RISCV_SP;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_s390.c b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
new file mode 100644
index 000000000000..d69bba881080
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_s390.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/s390/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_s390(int id)
+{
+	switch (id) {
+	case PERF_REG_S390_R0:
+		return "R0";
+	case PERF_REG_S390_R1:
+		return "R1";
+	case PERF_REG_S390_R2:
+		return "R2";
+	case PERF_REG_S390_R3:
+		return "R3";
+	case PERF_REG_S390_R4:
+		return "R4";
+	case PERF_REG_S390_R5:
+		return "R5";
+	case PERF_REG_S390_R6:
+		return "R6";
+	case PERF_REG_S390_R7:
+		return "R7";
+	case PERF_REG_S390_R8:
+		return "R8";
+	case PERF_REG_S390_R9:
+		return "R9";
+	case PERF_REG_S390_R10:
+		return "R10";
+	case PERF_REG_S390_R11:
+		return "R11";
+	case PERF_REG_S390_R12:
+		return "R12";
+	case PERF_REG_S390_R13:
+		return "R13";
+	case PERF_REG_S390_R14:
+		return "R14";
+	case PERF_REG_S390_R15:
+		return "R15";
+	case PERF_REG_S390_FP0:
+		return "FP0";
+	case PERF_REG_S390_FP1:
+		return "FP1";
+	case PERF_REG_S390_FP2:
+		return "FP2";
+	case PERF_REG_S390_FP3:
+		return "FP3";
+	case PERF_REG_S390_FP4:
+		return "FP4";
+	case PERF_REG_S390_FP5:
+		return "FP5";
+	case PERF_REG_S390_FP6:
+		return "FP6";
+	case PERF_REG_S390_FP7:
+		return "FP7";
+	case PERF_REG_S390_FP8:
+		return "FP8";
+	case PERF_REG_S390_FP9:
+		return "FP9";
+	case PERF_REG_S390_FP10:
+		return "FP10";
+	case PERF_REG_S390_FP11:
+		return "FP11";
+	case PERF_REG_S390_FP12:
+		return "FP12";
+	case PERF_REG_S390_FP13:
+		return "FP13";
+	case PERF_REG_S390_FP14:
+		return "FP14";
+	case PERF_REG_S390_FP15:
+		return "FP15";
+	case PERF_REG_S390_MASK:
+		return "MASK";
+	case PERF_REG_S390_PC:
+		return "PC";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_s390(void)
+{
+	return PERF_REG_S390_PC;
+}
+
+uint64_t __perf_reg_sp_s390(void)
+{
+	return PERF_REG_S390_R15;
+}
diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
new file mode 100644
index 000000000000..708954a9d35d
--- /dev/null
+++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../perf_regs.h"
+#include "../../../arch/x86/include/uapi/asm/perf_regs.h"
+
+const char *__perf_reg_name_x86(int id)
+{
+	switch (id) {
+	case PERF_REG_X86_AX:
+		return "AX";
+	case PERF_REG_X86_BX:
+		return "BX";
+	case PERF_REG_X86_CX:
+		return "CX";
+	case PERF_REG_X86_DX:
+		return "DX";
+	case PERF_REG_X86_SI:
+		return "SI";
+	case PERF_REG_X86_DI:
+		return "DI";
+	case PERF_REG_X86_BP:
+		return "BP";
+	case PERF_REG_X86_SP:
+		return "SP";
+	case PERF_REG_X86_IP:
+		return "IP";
+	case PERF_REG_X86_FLAGS:
+		return "FLAGS";
+	case PERF_REG_X86_CS:
+		return "CS";
+	case PERF_REG_X86_SS:
+		return "SS";
+	case PERF_REG_X86_DS:
+		return "DS";
+	case PERF_REG_X86_ES:
+		return "ES";
+	case PERF_REG_X86_FS:
+		return "FS";
+	case PERF_REG_X86_GS:
+		return "GS";
+	case PERF_REG_X86_R8:
+		return "R8";
+	case PERF_REG_X86_R9:
+		return "R9";
+	case PERF_REG_X86_R10:
+		return "R10";
+	case PERF_REG_X86_R11:
+		return "R11";
+	case PERF_REG_X86_R12:
+		return "R12";
+	case PERF_REG_X86_R13:
+		return "R13";
+	case PERF_REG_X86_R14:
+		return "R14";
+	case PERF_REG_X86_R15:
+		return "R15";
+
+#define XMM(x) \
+	case PERF_REG_X86_XMM ## x:	\
+	case PERF_REG_X86_XMM ## x + 1:	\
+		return "XMM" #x;
+	XMM(0)
+	XMM(1)
+	XMM(2)
+	XMM(3)
+	XMM(4)
+	XMM(5)
+	XMM(6)
+	XMM(7)
+	XMM(8)
+	XMM(9)
+	XMM(10)
+	XMM(11)
+	XMM(12)
+	XMM(13)
+	XMM(14)
+	XMM(15)
+#undef XMM
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+uint64_t __perf_reg_ip_x86(void)
+{
+	return PERF_REG_X86_IP;
+}
+
+uint64_t __perf_reg_sp_x86(void)
+{
+	return PERF_REG_X86_SP;
+}
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index e1e2d701599c..1de3b69cdf4a 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 	struct perf_cpu cpu;
 	int ret, i = 0;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 	cpu = perf_cpu_map__cpu(cpus, 0);
@@ -140,7 +140,7 @@ bool perf_can_record_cpu_wide(void)
 	struct perf_cpu cpu;
 	int fd;
 
-	cpus = perf_cpu_map__new(NULL);
+	cpus = perf_cpu_map__new_online_cpus();
 	if (!cpus)
 		return false;
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 2247991451f3..8f04d3b7f3ec 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -55,6 +55,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
 		bit_name(TYPE_SAVE), bit_name(HW_INDEX), bit_name(PRIV_SAVE),
+		bit_name(COUNTERS),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 9bdbaa37f813..44b90bbf2d07 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -3,6 +3,7 @@
 #include <string.h>
 #include "perf_regs.h"
 #include "util/sample.h"
+#include "debug.h"
 
 int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
 				 char **new_op __maybe_unused)
@@ -12,730 +13,21 @@ int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
 
 uint64_t __weak arch__intr_reg_mask(void)
 {
-	return PERF_REGS_MASK;
+	return 0;
 }
 
 uint64_t __weak arch__user_reg_mask(void)
 {
-	return PERF_REGS_MASK;
-}
-
-#ifdef HAVE_PERF_REGS_SUPPORT
-
-#define perf_event_arm_regs perf_event_arm64_regs
-#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
-#undef perf_event_arm_regs
-
-#include "../../arch/arm/include/uapi/asm/perf_regs.h"
-#include "../../arch/csky/include/uapi/asm/perf_regs.h"
-#include "../../arch/loongarch/include/uapi/asm/perf_regs.h"
-#include "../../arch/mips/include/uapi/asm/perf_regs.h"
-#include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
-#include "../../arch/riscv/include/uapi/asm/perf_regs.h"
-#include "../../arch/s390/include/uapi/asm/perf_regs.h"
-#include "../../arch/x86/include/uapi/asm/perf_regs.h"
-
-static const char *__perf_reg_name_arm64(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM64_X0:
-		return "x0";
-	case PERF_REG_ARM64_X1:
-		return "x1";
-	case PERF_REG_ARM64_X2:
-		return "x2";
-	case PERF_REG_ARM64_X3:
-		return "x3";
-	case PERF_REG_ARM64_X4:
-		return "x4";
-	case PERF_REG_ARM64_X5:
-		return "x5";
-	case PERF_REG_ARM64_X6:
-		return "x6";
-	case PERF_REG_ARM64_X7:
-		return "x7";
-	case PERF_REG_ARM64_X8:
-		return "x8";
-	case PERF_REG_ARM64_X9:
-		return "x9";
-	case PERF_REG_ARM64_X10:
-		return "x10";
-	case PERF_REG_ARM64_X11:
-		return "x11";
-	case PERF_REG_ARM64_X12:
-		return "x12";
-	case PERF_REG_ARM64_X13:
-		return "x13";
-	case PERF_REG_ARM64_X14:
-		return "x14";
-	case PERF_REG_ARM64_X15:
-		return "x15";
-	case PERF_REG_ARM64_X16:
-		return "x16";
-	case PERF_REG_ARM64_X17:
-		return "x17";
-	case PERF_REG_ARM64_X18:
-		return "x18";
-	case PERF_REG_ARM64_X19:
-		return "x19";
-	case PERF_REG_ARM64_X20:
-		return "x20";
-	case PERF_REG_ARM64_X21:
-		return "x21";
-	case PERF_REG_ARM64_X22:
-		return "x22";
-	case PERF_REG_ARM64_X23:
-		return "x23";
-	case PERF_REG_ARM64_X24:
-		return "x24";
-	case PERF_REG_ARM64_X25:
-		return "x25";
-	case PERF_REG_ARM64_X26:
-		return "x26";
-	case PERF_REG_ARM64_X27:
-		return "x27";
-	case PERF_REG_ARM64_X28:
-		return "x28";
-	case PERF_REG_ARM64_X29:
-		return "x29";
-	case PERF_REG_ARM64_SP:
-		return "sp";
-	case PERF_REG_ARM64_LR:
-		return "lr";
-	case PERF_REG_ARM64_PC:
-		return "pc";
-	case PERF_REG_ARM64_VG:
-		return "vg";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_arm(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM_R0:
-		return "r0";
-	case PERF_REG_ARM_R1:
-		return "r1";
-	case PERF_REG_ARM_R2:
-		return "r2";
-	case PERF_REG_ARM_R3:
-		return "r3";
-	case PERF_REG_ARM_R4:
-		return "r4";
-	case PERF_REG_ARM_R5:
-		return "r5";
-	case PERF_REG_ARM_R6:
-		return "r6";
-	case PERF_REG_ARM_R7:
-		return "r7";
-	case PERF_REG_ARM_R8:
-		return "r8";
-	case PERF_REG_ARM_R9:
-		return "r9";
-	case PERF_REG_ARM_R10:
-		return "r10";
-	case PERF_REG_ARM_FP:
-		return "fp";
-	case PERF_REG_ARM_IP:
-		return "ip";
-	case PERF_REG_ARM_SP:
-		return "sp";
-	case PERF_REG_ARM_LR:
-		return "lr";
-	case PERF_REG_ARM_PC:
-		return "pc";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static const char *__perf_reg_name_csky(int id)
-{
-	switch (id) {
-	case PERF_REG_CSKY_A0:
-		return "a0";
-	case PERF_REG_CSKY_A1:
-		return "a1";
-	case PERF_REG_CSKY_A2:
-		return "a2";
-	case PERF_REG_CSKY_A3:
-		return "a3";
-	case PERF_REG_CSKY_REGS0:
-		return "regs0";
-	case PERF_REG_CSKY_REGS1:
-		return "regs1";
-	case PERF_REG_CSKY_REGS2:
-		return "regs2";
-	case PERF_REG_CSKY_REGS3:
-		return "regs3";
-	case PERF_REG_CSKY_REGS4:
-		return "regs4";
-	case PERF_REG_CSKY_REGS5:
-		return "regs5";
-	case PERF_REG_CSKY_REGS6:
-		return "regs6";
-	case PERF_REG_CSKY_REGS7:
-		return "regs7";
-	case PERF_REG_CSKY_REGS8:
-		return "regs8";
-	case PERF_REG_CSKY_REGS9:
-		return "regs9";
-	case PERF_REG_CSKY_SP:
-		return "sp";
-	case PERF_REG_CSKY_LR:
-		return "lr";
-	case PERF_REG_CSKY_PC:
-		return "pc";
-#if defined(__CSKYABIV2__)
-	case PERF_REG_CSKY_EXREGS0:
-		return "exregs0";
-	case PERF_REG_CSKY_EXREGS1:
-		return "exregs1";
-	case PERF_REG_CSKY_EXREGS2:
-		return "exregs2";
-	case PERF_REG_CSKY_EXREGS3:
-		return "exregs3";
-	case PERF_REG_CSKY_EXREGS4:
-		return "exregs4";
-	case PERF_REG_CSKY_EXREGS5:
-		return "exregs5";
-	case PERF_REG_CSKY_EXREGS6:
-		return "exregs6";
-	case PERF_REG_CSKY_EXREGS7:
-		return "exregs7";
-	case PERF_REG_CSKY_EXREGS8:
-		return "exregs8";
-	case PERF_REG_CSKY_EXREGS9:
-		return "exregs9";
-	case PERF_REG_CSKY_EXREGS10:
-		return "exregs10";
-	case PERF_REG_CSKY_EXREGS11:
-		return "exregs11";
-	case PERF_REG_CSKY_EXREGS12:
-		return "exregs12";
-	case PERF_REG_CSKY_EXREGS13:
-		return "exregs13";
-	case PERF_REG_CSKY_EXREGS14:
-		return "exregs14";
-	case PERF_REG_CSKY_TLS:
-		return "tls";
-	case PERF_REG_CSKY_HI:
-		return "hi";
-	case PERF_REG_CSKY_LO:
-		return "lo";
-#endif
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
-static inline const char *__perf_reg_name_loongarch(int id)
-{
-	switch (id) {
-	case PERF_REG_LOONGARCH_PC:
-		return "PC";
-	case PERF_REG_LOONGARCH_R1:
-		return "%r1";
-	case PERF_REG_LOONGARCH_R2:
-		return "%r2";
-	case PERF_REG_LOONGARCH_R3:
-		return "%r3";
-	case PERF_REG_LOONGARCH_R4:
-		return "%r4";
-	case PERF_REG_LOONGARCH_R5:
-		return "%r5";
-	case PERF_REG_LOONGARCH_R6:
-		return "%r6";
-	case PERF_REG_LOONGARCH_R7:
-		return "%r7";
-	case PERF_REG_LOONGARCH_R8:
-		return "%r8";
-	case PERF_REG_LOONGARCH_R9:
-		return "%r9";
-	case PERF_REG_LOONGARCH_R10:
-		return "%r10";
-	case PERF_REG_LOONGARCH_R11:
-		return "%r11";
-	case PERF_REG_LOONGARCH_R12:
-		return "%r12";
-	case PERF_REG_LOONGARCH_R13:
-		return "%r13";
-	case PERF_REG_LOONGARCH_R14:
-		return "%r14";
-	case PERF_REG_LOONGARCH_R15:
-		return "%r15";
-	case PERF_REG_LOONGARCH_R16:
-		return "%r16";
-	case PERF_REG_LOONGARCH_R17:
-		return "%r17";
-	case PERF_REG_LOONGARCH_R18:
-		return "%r18";
-	case PERF_REG_LOONGARCH_R19:
-		return "%r19";
-	case PERF_REG_LOONGARCH_R20:
-		return "%r20";
-	case PERF_REG_LOONGARCH_R21:
-		return "%r21";
-	case PERF_REG_LOONGARCH_R22:
-		return "%r22";
-	case PERF_REG_LOONGARCH_R23:
-		return "%r23";
-	case PERF_REG_LOONGARCH_R24:
-		return "%r24";
-	case PERF_REG_LOONGARCH_R25:
-		return "%r25";
-	case PERF_REG_LOONGARCH_R26:
-		return "%r26";
-	case PERF_REG_LOONGARCH_R27:
-		return "%r27";
-	case PERF_REG_LOONGARCH_R28:
-		return "%r28";
-	case PERF_REG_LOONGARCH_R29:
-		return "%r29";
-	case PERF_REG_LOONGARCH_R30:
-		return "%r30";
-	case PERF_REG_LOONGARCH_R31:
-		return "%r31";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_mips(int id)
-{
-	switch (id) {
-	case PERF_REG_MIPS_PC:
-		return "PC";
-	case PERF_REG_MIPS_R1:
-		return "$1";
-	case PERF_REG_MIPS_R2:
-		return "$2";
-	case PERF_REG_MIPS_R3:
-		return "$3";
-	case PERF_REG_MIPS_R4:
-		return "$4";
-	case PERF_REG_MIPS_R5:
-		return "$5";
-	case PERF_REG_MIPS_R6:
-		return "$6";
-	case PERF_REG_MIPS_R7:
-		return "$7";
-	case PERF_REG_MIPS_R8:
-		return "$8";
-	case PERF_REG_MIPS_R9:
-		return "$9";
-	case PERF_REG_MIPS_R10:
-		return "$10";
-	case PERF_REG_MIPS_R11:
-		return "$11";
-	case PERF_REG_MIPS_R12:
-		return "$12";
-	case PERF_REG_MIPS_R13:
-		return "$13";
-	case PERF_REG_MIPS_R14:
-		return "$14";
-	case PERF_REG_MIPS_R15:
-		return "$15";
-	case PERF_REG_MIPS_R16:
-		return "$16";
-	case PERF_REG_MIPS_R17:
-		return "$17";
-	case PERF_REG_MIPS_R18:
-		return "$18";
-	case PERF_REG_MIPS_R19:
-		return "$19";
-	case PERF_REG_MIPS_R20:
-		return "$20";
-	case PERF_REG_MIPS_R21:
-		return "$21";
-	case PERF_REG_MIPS_R22:
-		return "$22";
-	case PERF_REG_MIPS_R23:
-		return "$23";
-	case PERF_REG_MIPS_R24:
-		return "$24";
-	case PERF_REG_MIPS_R25:
-		return "$25";
-	case PERF_REG_MIPS_R28:
-		return "$28";
-	case PERF_REG_MIPS_R29:
-		return "$29";
-	case PERF_REG_MIPS_R30:
-		return "$30";
-	case PERF_REG_MIPS_R31:
-		return "$31";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_powerpc(int id)
-{
-	switch (id) {
-	case PERF_REG_POWERPC_R0:
-		return "r0";
-	case PERF_REG_POWERPC_R1:
-		return "r1";
-	case PERF_REG_POWERPC_R2:
-		return "r2";
-	case PERF_REG_POWERPC_R3:
-		return "r3";
-	case PERF_REG_POWERPC_R4:
-		return "r4";
-	case PERF_REG_POWERPC_R5:
-		return "r5";
-	case PERF_REG_POWERPC_R6:
-		return "r6";
-	case PERF_REG_POWERPC_R7:
-		return "r7";
-	case PERF_REG_POWERPC_R8:
-		return "r8";
-	case PERF_REG_POWERPC_R9:
-		return "r9";
-	case PERF_REG_POWERPC_R10:
-		return "r10";
-	case PERF_REG_POWERPC_R11:
-		return "r11";
-	case PERF_REG_POWERPC_R12:
-		return "r12";
-	case PERF_REG_POWERPC_R13:
-		return "r13";
-	case PERF_REG_POWERPC_R14:
-		return "r14";
-	case PERF_REG_POWERPC_R15:
-		return "r15";
-	case PERF_REG_POWERPC_R16:
-		return "r16";
-	case PERF_REG_POWERPC_R17:
-		return "r17";
-	case PERF_REG_POWERPC_R18:
-		return "r18";
-	case PERF_REG_POWERPC_R19:
-		return "r19";
-	case PERF_REG_POWERPC_R20:
-		return "r20";
-	case PERF_REG_POWERPC_R21:
-		return "r21";
-	case PERF_REG_POWERPC_R22:
-		return "r22";
-	case PERF_REG_POWERPC_R23:
-		return "r23";
-	case PERF_REG_POWERPC_R24:
-		return "r24";
-	case PERF_REG_POWERPC_R25:
-		return "r25";
-	case PERF_REG_POWERPC_R26:
-		return "r26";
-	case PERF_REG_POWERPC_R27:
-		return "r27";
-	case PERF_REG_POWERPC_R28:
-		return "r28";
-	case PERF_REG_POWERPC_R29:
-		return "r29";
-	case PERF_REG_POWERPC_R30:
-		return "r30";
-	case PERF_REG_POWERPC_R31:
-		return "r31";
-	case PERF_REG_POWERPC_NIP:
-		return "nip";
-	case PERF_REG_POWERPC_MSR:
-		return "msr";
-	case PERF_REG_POWERPC_ORIG_R3:
-		return "orig_r3";
-	case PERF_REG_POWERPC_CTR:
-		return "ctr";
-	case PERF_REG_POWERPC_LINK:
-		return "link";
-	case PERF_REG_POWERPC_XER:
-		return "xer";
-	case PERF_REG_POWERPC_CCR:
-		return "ccr";
-	case PERF_REG_POWERPC_SOFTE:
-		return "softe";
-	case PERF_REG_POWERPC_TRAP:
-		return "trap";
-	case PERF_REG_POWERPC_DAR:
-		return "dar";
-	case PERF_REG_POWERPC_DSISR:
-		return "dsisr";
-	case PERF_REG_POWERPC_SIER:
-		return "sier";
-	case PERF_REG_POWERPC_MMCRA:
-		return "mmcra";
-	case PERF_REG_POWERPC_MMCR0:
-		return "mmcr0";
-	case PERF_REG_POWERPC_MMCR1:
-		return "mmcr1";
-	case PERF_REG_POWERPC_MMCR2:
-		return "mmcr2";
-	case PERF_REG_POWERPC_MMCR3:
-		return "mmcr3";
-	case PERF_REG_POWERPC_SIER2:
-		return "sier2";
-	case PERF_REG_POWERPC_SIER3:
-		return "sier3";
-	case PERF_REG_POWERPC_PMC1:
-		return "pmc1";
-	case PERF_REG_POWERPC_PMC2:
-		return "pmc2";
-	case PERF_REG_POWERPC_PMC3:
-		return "pmc3";
-	case PERF_REG_POWERPC_PMC4:
-		return "pmc4";
-	case PERF_REG_POWERPC_PMC5:
-		return "pmc5";
-	case PERF_REG_POWERPC_PMC6:
-		return "pmc6";
-	case PERF_REG_POWERPC_SDAR:
-		return "sdar";
-	case PERF_REG_POWERPC_SIAR:
-		return "siar";
-	default:
-		break;
-	}
-	return NULL;
-}
-
-static const char *__perf_reg_name_riscv(int id)
-{
-	switch (id) {
-	case PERF_REG_RISCV_PC:
-		return "pc";
-	case PERF_REG_RISCV_RA:
-		return "ra";
-	case PERF_REG_RISCV_SP:
-		return "sp";
-	case PERF_REG_RISCV_GP:
-		return "gp";
-	case PERF_REG_RISCV_TP:
-		return "tp";
-	case PERF_REG_RISCV_T0:
-		return "t0";
-	case PERF_REG_RISCV_T1:
-		return "t1";
-	case PERF_REG_RISCV_T2:
-		return "t2";
-	case PERF_REG_RISCV_S0:
-		return "s0";
-	case PERF_REG_RISCV_S1:
-		return "s1";
-	case PERF_REG_RISCV_A0:
-		return "a0";
-	case PERF_REG_RISCV_A1:
-		return "a1";
-	case PERF_REG_RISCV_A2:
-		return "a2";
-	case PERF_REG_RISCV_A3:
-		return "a3";
-	case PERF_REG_RISCV_A4:
-		return "a4";
-	case PERF_REG_RISCV_A5:
-		return "a5";
-	case PERF_REG_RISCV_A6:
-		return "a6";
-	case PERF_REG_RISCV_A7:
-		return "a7";
-	case PERF_REG_RISCV_S2:
-		return "s2";
-	case PERF_REG_RISCV_S3:
-		return "s3";
-	case PERF_REG_RISCV_S4:
-		return "s4";
-	case PERF_REG_RISCV_S5:
-		return "s5";
-	case PERF_REG_RISCV_S6:
-		return "s6";
-	case PERF_REG_RISCV_S7:
-		return "s7";
-	case PERF_REG_RISCV_S8:
-		return "s8";
-	case PERF_REG_RISCV_S9:
-		return "s9";
-	case PERF_REG_RISCV_S10:
-		return "s10";
-	case PERF_REG_RISCV_S11:
-		return "s11";
-	case PERF_REG_RISCV_T3:
-		return "t3";
-	case PERF_REG_RISCV_T4:
-		return "t4";
-	case PERF_REG_RISCV_T5:
-		return "t5";
-	case PERF_REG_RISCV_T6:
-		return "t6";
-	default:
-		return NULL;
-	}
-
-	return NULL;
+	return 0;
 }
 
-static const char *__perf_reg_name_s390(int id)
-{
-	switch (id) {
-	case PERF_REG_S390_R0:
-		return "R0";
-	case PERF_REG_S390_R1:
-		return "R1";
-	case PERF_REG_S390_R2:
-		return "R2";
-	case PERF_REG_S390_R3:
-		return "R3";
-	case PERF_REG_S390_R4:
-		return "R4";
-	case PERF_REG_S390_R5:
-		return "R5";
-	case PERF_REG_S390_R6:
-		return "R6";
-	case PERF_REG_S390_R7:
-		return "R7";
-	case PERF_REG_S390_R8:
-		return "R8";
-	case PERF_REG_S390_R9:
-		return "R9";
-	case PERF_REG_S390_R10:
-		return "R10";
-	case PERF_REG_S390_R11:
-		return "R11";
-	case PERF_REG_S390_R12:
-		return "R12";
-	case PERF_REG_S390_R13:
-		return "R13";
-	case PERF_REG_S390_R14:
-		return "R14";
-	case PERF_REG_S390_R15:
-		return "R15";
-	case PERF_REG_S390_FP0:
-		return "FP0";
-	case PERF_REG_S390_FP1:
-		return "FP1";
-	case PERF_REG_S390_FP2:
-		return "FP2";
-	case PERF_REG_S390_FP3:
-		return "FP3";
-	case PERF_REG_S390_FP4:
-		return "FP4";
-	case PERF_REG_S390_FP5:
-		return "FP5";
-	case PERF_REG_S390_FP6:
-		return "FP6";
-	case PERF_REG_S390_FP7:
-		return "FP7";
-	case PERF_REG_S390_FP8:
-		return "FP8";
-	case PERF_REG_S390_FP9:
-		return "FP9";
-	case PERF_REG_S390_FP10:
-		return "FP10";
-	case PERF_REG_S390_FP11:
-		return "FP11";
-	case PERF_REG_S390_FP12:
-		return "FP12";
-	case PERF_REG_S390_FP13:
-		return "FP13";
-	case PERF_REG_S390_FP14:
-		return "FP14";
-	case PERF_REG_S390_FP15:
-		return "FP15";
-	case PERF_REG_S390_MASK:
-		return "MASK";
-	case PERF_REG_S390_PC:
-		return "PC";
-	default:
-		return NULL;
-	}
+static const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG_END
+};
 
-	return NULL;
-}
-
-static const char *__perf_reg_name_x86(int id)
+const struct sample_reg * __weak arch__sample_reg_masks(void)
 {
-	switch (id) {
-	case PERF_REG_X86_AX:
-		return "AX";
-	case PERF_REG_X86_BX:
-		return "BX";
-	case PERF_REG_X86_CX:
-		return "CX";
-	case PERF_REG_X86_DX:
-		return "DX";
-	case PERF_REG_X86_SI:
-		return "SI";
-	case PERF_REG_X86_DI:
-		return "DI";
-	case PERF_REG_X86_BP:
-		return "BP";
-	case PERF_REG_X86_SP:
-		return "SP";
-	case PERF_REG_X86_IP:
-		return "IP";
-	case PERF_REG_X86_FLAGS:
-		return "FLAGS";
-	case PERF_REG_X86_CS:
-		return "CS";
-	case PERF_REG_X86_SS:
-		return "SS";
-	case PERF_REG_X86_DS:
-		return "DS";
-	case PERF_REG_X86_ES:
-		return "ES";
-	case PERF_REG_X86_FS:
-		return "FS";
-	case PERF_REG_X86_GS:
-		return "GS";
-	case PERF_REG_X86_R8:
-		return "R8";
-	case PERF_REG_X86_R9:
-		return "R9";
-	case PERF_REG_X86_R10:
-		return "R10";
-	case PERF_REG_X86_R11:
-		return "R11";
-	case PERF_REG_X86_R12:
-		return "R12";
-	case PERF_REG_X86_R13:
-		return "R13";
-	case PERF_REG_X86_R14:
-		return "R14";
-	case PERF_REG_X86_R15:
-		return "R15";
-
-#define XMM(x) \
-	case PERF_REG_X86_XMM ## x:	\
-	case PERF_REG_X86_XMM ## x + 1:	\
-		return "XMM" #x;
-	XMM(0)
-	XMM(1)
-	XMM(2)
-	XMM(3)
-	XMM(4)
-	XMM(5)
-	XMM(6)
-	XMM(7)
-	XMM(8)
-	XMM(9)
-	XMM(10)
-	XMM(11)
-	XMM(12)
-	XMM(13)
-	XMM(14)
-	XMM(15)
-#undef XMM
-	default:
-		return NULL;
-	}
-
-	return NULL;
+	return sample_reg_masks;
 }
 
 const char *perf_reg_name(int id, const char *arch)
@@ -790,4 +82,53 @@ out:
 	*valp = regs->cache_regs[id];
 	return 0;
 }
-#endif
+
+uint64_t perf_arch_reg_ip(const char *arch)
+{
+	if (!strcmp(arch, "arm"))
+		return __perf_reg_ip_arm();
+	else if (!strcmp(arch, "arm64"))
+		return __perf_reg_ip_arm64();
+	else if (!strcmp(arch, "csky"))
+		return __perf_reg_ip_csky();
+	else if (!strcmp(arch, "loongarch"))
+		return __perf_reg_ip_loongarch();
+	else if (!strcmp(arch, "mips"))
+		return __perf_reg_ip_mips();
+	else if (!strcmp(arch, "powerpc"))
+		return __perf_reg_ip_powerpc();
+	else if (!strcmp(arch, "riscv"))
+		return __perf_reg_ip_riscv();
+	else if (!strcmp(arch, "s390"))
+		return __perf_reg_ip_s390();
+	else if (!strcmp(arch, "x86"))
+		return __perf_reg_ip_x86();
+
+	pr_err("Fail to find IP register for arch %s, returns 0\n", arch);
+	return 0;
+}
+
+uint64_t perf_arch_reg_sp(const char *arch)
+{
+	if (!strcmp(arch, "arm"))
+		return __perf_reg_sp_arm();
+	else if (!strcmp(arch, "arm64"))
+		return __perf_reg_sp_arm64();
+	else if (!strcmp(arch, "csky"))
+		return __perf_reg_sp_csky();
+	else if (!strcmp(arch, "loongarch"))
+		return __perf_reg_sp_loongarch();
+	else if (!strcmp(arch, "mips"))
+		return __perf_reg_sp_mips();
+	else if (!strcmp(arch, "powerpc"))
+		return __perf_reg_sp_powerpc();
+	else if (!strcmp(arch, "riscv"))
+		return __perf_reg_sp_riscv();
+	else if (!strcmp(arch, "s390"))
+		return __perf_reg_sp_s390();
+	else if (!strcmp(arch, "x86"))
+		return __perf_reg_sp_x86();
+
+	pr_err("Fail to find SP register for arch %s, returns 0\n", arch);
+	return 0;
+}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index ce1127af05e4..f2d0736d65cc 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -26,33 +26,43 @@ enum {
 int arch_sdt_arg_parse_op(char *old_op, char **new_op);
 uint64_t arch__intr_reg_mask(void);
 uint64_t arch__user_reg_mask(void);
-
-#ifdef HAVE_PERF_REGS_SUPPORT
-extern const struct sample_reg sample_reg_masks[];
-
-#include <perf_regs.h>
-
-#define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
+const struct sample_reg *arch__sample_reg_masks(void);
 
 const char *perf_reg_name(int id, const char *arch);
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+uint64_t perf_arch_reg_ip(const char *arch);
+uint64_t perf_arch_reg_sp(const char *arch);
+const char *__perf_reg_name_arm64(int id);
+uint64_t __perf_reg_ip_arm64(void);
+uint64_t __perf_reg_sp_arm64(void);
+const char *__perf_reg_name_arm(int id);
+uint64_t __perf_reg_ip_arm(void);
+uint64_t __perf_reg_sp_arm(void);
+const char *__perf_reg_name_csky(int id);
+uint64_t __perf_reg_ip_csky(void);
+uint64_t __perf_reg_sp_csky(void);
+const char *__perf_reg_name_loongarch(int id);
+uint64_t __perf_reg_ip_loongarch(void);
+uint64_t __perf_reg_sp_loongarch(void);
+const char *__perf_reg_name_mips(int id);
+uint64_t __perf_reg_ip_mips(void);
+uint64_t __perf_reg_sp_mips(void);
+const char *__perf_reg_name_powerpc(int id);
+uint64_t __perf_reg_ip_powerpc(void);
+uint64_t __perf_reg_sp_powerpc(void);
+const char *__perf_reg_name_riscv(int id);
+uint64_t __perf_reg_ip_riscv(void);
+uint64_t __perf_reg_sp_riscv(void);
+const char *__perf_reg_name_s390(int id);
+uint64_t __perf_reg_ip_s390(void);
+uint64_t __perf_reg_sp_s390(void);
+const char *__perf_reg_name_x86(int id);
+uint64_t __perf_reg_ip_x86(void);
+uint64_t __perf_reg_sp_x86(void);
 
-#else
-#define PERF_REGS_MASK	0
-#define PERF_REGS_MAX	0
-
-#define DWARF_MINIMAL_REGS PERF_REGS_MASK
-
-static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)
+static inline uint64_t DWARF_MINIMAL_REGS(const char *arch)
 {
-	return "unknown";
+	return (1ULL << perf_arch_reg_ip(arch)) | (1ULL << perf_arch_reg_sp(arch));
 }
 
-static inline int perf_reg_value(u64 *valp __maybe_unused,
-				 struct regs_dump *regs __maybe_unused,
-				 int id __maybe_unused)
-{
-	return 0;
-}
-#endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c
index 862e4a689868..5ccfe4b64cdf 100644
--- a/tools/perf/util/pfm.c
+++ b/tools/perf/util/pfm.c
@@ -145,7 +145,20 @@ static bool is_libpfm_event_supported(const char *name, struct perf_cpu_map *cpu
 
 	evsel->is_libpfm_event = true;
 
-	if (evsel__open(evsel, cpus, threads) < 0)
+	ret = evsel__open(evsel, cpus, threads);
+	if (ret == -EACCES) {
+		/*
+		 * This happens if the paranoid value
+		 * /proc/sys/kernel/perf_event_paranoid is set to 2
+		 * Re-run with exclude_kernel set; we don't do that
+		 * by default as some ARM machines do not support it.
+		 *
+		 */
+		evsel->core.attr.exclude_kernel = 1;
+		ret = evsel__open(evsel, cpus, threads);
+
+	}
+	if (ret < 0)
 		result = false;
 
 	evsel__close(evsel);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 28380e7aa8d0..f39cbbc1a7ec 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -19,8 +19,8 @@
 #include "evsel.h"
 #include "pmu.h"
 #include "pmus.h"
-#include "pmu-bison.h"
-#include "pmu-flex.h"
+#include <util/pmu-bison.h>
+#include <util/pmu-flex.h>
 #include "parse-events.h"
 #include "print-events.h"
 #include "header.h"
@@ -28,8 +28,65 @@
 #include "strbuf.h"
 #include "fncache.h"
 #include "util/evsel_config.h"
+#include <regex.h>
 
-struct perf_pmu perf_pmu__fake;
+struct perf_pmu perf_pmu__fake = {
+	.name = "fake",
+};
+
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
+/**
+ * struct perf_pmu_alias - An event either read from sysfs or builtin in
+ * pmu-events.c, created by parsing the pmu-events json files.
+ */
+struct perf_pmu_alias {
+	/** @name: Name of the event like "mem-loads". */
+	char *name;
+	/** @desc: Optional short description of the event. */
+	char *desc;
+	/** @long_desc: Optional long description. */
+	char *long_desc;
+	/**
+	 * @topic: Optional topic such as cache or pipeline, particularly for
+	 * json events.
+	 */
+	char *topic;
+	/** @terms: Owned list of the original parsed parameters. */
+	struct parse_events_terms terms;
+	/** @list: List element of struct perf_pmu aliases. */
+	struct list_head list;
+	/**
+	 * @pmu_name: The name copied from the json struct pmu_event. This can
+	 * differ from the PMU name as it won't have suffixes.
+	 */
+	char *pmu_name;
+	/** @unit: Units for the event, such as bytes or cache lines. */
+	char unit[UNIT_MAX_LEN+1];
+	/** @scale: Value to scale read counter values by. */
+	double scale;
+	/**
+	 * @per_pkg: Does the file
+	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or
+	 * equivalent json value exist and have the value 1.
+	 */
+	bool per_pkg;
+	/**
+	 * @snapshot: Does the file
+	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot
+	 * exist and have the value 1.
+	 */
+	bool snapshot;
+	/**
+	 * @deprecated: Is the event hidden and so not shown in perf list by
+	 * default.
+	 */
+	bool deprecated;
+	/** @from_sysfs: Was the alias from sysfs or a json event? */
+	bool from_sysfs;
+	/** @info_loaded: Have the scale, unit and other values been read from disk? */
+	bool info_loaded;
+};
 
 /**
  * struct perf_pmu_format - Values from a format file read from
@@ -40,6 +97,10 @@ struct perf_pmu perf_pmu__fake;
  * value=PERF_PMU_FORMAT_VALUE_CONFIG and bits 0 to 7 will be set.
  */
 struct perf_pmu_format {
+	/** @list: Element on list within struct perf_pmu. */
+	struct list_head list;
+	/** @bits: Which config bits are set by this format value. */
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
 	/** @name: The modifier/file name. */
 	char *name;
 	/**
@@ -47,18 +108,81 @@ struct perf_pmu_format {
 	 * are from PERF_PMU_FORMAT_VALUE_CONFIG to
 	 * PERF_PMU_FORMAT_VALUE_CONFIG_END.
 	 */
-	int value;
-	/** @bits: Which config bits are set by this format value. */
-	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
-	/** @list: Element on list within struct perf_pmu. */
-	struct list_head list;
+	u16 value;
+	/** @loaded: Has the contents been loaded/parsed. */
+	bool loaded;
 };
 
+static int pmu_aliases_parse(struct perf_pmu *pmu);
+
+static struct perf_pmu_format *perf_pmu__new_format(struct list_head *list, char *name)
+{
+	struct perf_pmu_format *format;
+
+	format = zalloc(sizeof(*format));
+	if (!format)
+		return NULL;
+
+	format->name = strdup(name);
+	if (!format->name) {
+		free(format);
+		return NULL;
+	}
+	list_add_tail(&format->list, list);
+	return format;
+}
+
+/* Called at the end of parsing a format. */
+void perf_pmu_format__set_value(void *vformat, int config, unsigned long *bits)
+{
+	struct perf_pmu_format *format = vformat;
+
+	format->value = config;
+	memcpy(format->bits, bits, sizeof(format->bits));
+}
+
+static void __perf_pmu_format__load(struct perf_pmu_format *format, FILE *file)
+{
+	void *scanner;
+	int ret;
+
+	ret = perf_pmu_lex_init(&scanner);
+	if (ret)
+		return;
+
+	perf_pmu_set_in(file, scanner);
+	ret = perf_pmu_parse(format, scanner);
+	perf_pmu_lex_destroy(scanner);
+	format->loaded = true;
+}
+
+static void perf_pmu_format__load(const struct perf_pmu *pmu, struct perf_pmu_format *format)
+{
+	char path[PATH_MAX];
+	FILE *file = NULL;
+
+	if (format->loaded)
+		return;
+
+	if (!perf_pmu__pathname_scnprintf(path, sizeof(path), pmu->name, "format"))
+		return;
+
+	assert(strlen(path) + strlen(format->name) + 2 < sizeof(path));
+	strcat(path, "/");
+	strcat(path, format->name);
+
+	file = fopen(path, "r");
+	if (!file)
+		return;
+	__perf_pmu_format__load(format, file);
+	fclose(file);
+}
+
 /*
  * Parse & process all the sysfs attributes located under
  * the directory specified in 'dir' parameter.
  */
-int perf_pmu__format_parse(int dirfd, struct list_head *head)
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load)
 {
 	struct dirent *evt_ent;
 	DIR *format_dir;
@@ -68,37 +192,35 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head)
 	if (!format_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(format_dir))) {
+	while ((evt_ent = readdir(format_dir)) != NULL) {
+		struct perf_pmu_format *format;
 		char *name = evt_ent->d_name;
-		int fd;
-		void *scanner;
-		FILE *file;
 
 		if (!strcmp(name, ".") || !strcmp(name, ".."))
 			continue;
 
-
-		ret = -EINVAL;
-		fd = openat(dirfd, name, O_RDONLY);
-		if (fd < 0)
-			break;
-
-		file = fdopen(fd, "r");
-		if (!file) {
-			close(fd);
+		format = perf_pmu__new_format(&pmu->format, name);
+		if (!format) {
+			ret = -ENOMEM;
 			break;
 		}
 
-		ret = perf_pmu_lex_init(&scanner);
-		if (ret) {
+		if (eager_load) {
+			FILE *file;
+			int fd = openat(dirfd, name, O_RDONLY);
+
+			if (fd < 0) {
+				ret = -errno;
+				break;
+			}
+			file = fdopen(fd, "r");
+			if (!file) {
+				close(fd);
+				break;
+			}
+			__perf_pmu_format__load(format, file);
 			fclose(file);
-			break;
 		}
-
-		perf_pmu_set_in(file, scanner);
-		ret = perf_pmu_parse(head, name, scanner);
-		perf_pmu_lex_destroy(scanner);
-		fclose(file);
 	}
 
 	closedir(format_dir);
@@ -110,7 +232,7 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(int dirfd, const char *name, struct list_head *format)
+static int pmu_format(struct perf_pmu *pmu, int dirfd, const char *name)
 {
 	int fd;
 
@@ -119,7 +241,7 @@ static int pmu_format(int dirfd, const char *name, struct list_head *format)
 		return 0;
 
 	/* it'll close the fd */
-	if (perf_pmu__format_parse(fd, format))
+	if (perf_pmu__format_parse(pmu, fd, /*eager_load=*/false))
 		return -1;
 
 	return 0;
@@ -162,17 +284,21 @@ out:
 	return ret;
 }
 
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, char *name)
+static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	struct stat st;
 	ssize_t sret;
+	size_t len;
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
 
-	scnprintf(path, PATH_MAX, "%s.scale", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events/%s.scale", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -194,15 +320,20 @@ error:
 	return ret;
 }
 
-static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, char *name)
+static int perf_pmu__parse_unit(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	ssize_t sret;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.unit", name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events/%s.unit", pmu->name, alias->name);
+
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -225,14 +356,18 @@ error:
 }
 
 static int
-perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name)
+perf_pmu__parse_per_pkg(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.per-pkg", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events/%s.per-pkg", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -242,15 +377,18 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name)
 	return 0;
 }
 
-static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
-				    int dirfd, char *name)
+static int perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
 {
 	char path[PATH_MAX];
+	size_t len;
 	int fd;
 
-	scnprintf(path, PATH_MAX, "%s.snapshot", name);
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events/%s.snapshot", pmu->name, alias->name);
 
-	fd = openat(dirfd, path, O_RDONLY);
+	fd = open(path, O_RDONLY);
 	if (fd == -1)
 		return -1;
 
@@ -259,48 +397,15 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 	return 0;
 }
 
-static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
-				char **new_str)
-{
-	if (!*old_str)
-		goto set_new;
-
-	if (*new_str) {	/* Have new string, check with old */
-		if (strcasecmp(*old_str, *new_str))
-			pr_debug("alias %s differs in field '%s'\n",
-				 name, field);
-		zfree(old_str);
-	} else		/* Nothing new --> keep old string */
-		return;
-set_new:
-	*old_str = *new_str;
-	*new_str = NULL;
-}
-
-static void perf_pmu_update_alias(struct perf_pmu_alias *old,
-				  struct perf_pmu_alias *newalias)
-{
-	perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
-	perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
-			    &newalias->long_desc);
-	perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
-	perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
-	old->scale = newalias->scale;
-	old->per_pkg = newalias->per_pkg;
-	old->snapshot = newalias->snapshot;
-	memcpy(old->unit, newalias->unit, sizeof(old->unit));
-}
-
 /* Delete an alias entry. */
-void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
 	zfree(&newalias->name);
 	zfree(&newalias->desc);
 	zfree(&newalias->long_desc);
 	zfree(&newalias->topic);
-	zfree(&newalias->str);
 	zfree(&newalias->pmu_name);
-	parse_events_terms__purge(&newalias->terms);
+	parse_events_terms__exit(&newalias->terms);
 	free(newalias);
 }
 
@@ -314,38 +419,99 @@ static void perf_pmu__del_aliases(struct perf_pmu *pmu)
 	}
 }
 
-/* Merge an alias, search in alias list. If this name is already
- * present merge both of them to combine all information.
- */
-static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
-				 struct list_head *alist)
+static struct perf_pmu_alias *perf_pmu__find_alias(struct perf_pmu *pmu,
+						   const char *name,
+						   bool load)
 {
-	struct perf_pmu_alias *a;
+	struct perf_pmu_alias *alias;
 
-	list_for_each_entry(a, alist, list) {
-		if (!strcasecmp(newalias->name, a->name)) {
-			if (newalias->pmu_name && a->pmu_name &&
-			    !strcasecmp(newalias->pmu_name, a->pmu_name)) {
-				continue;
-			}
-			perf_pmu_update_alias(a, newalias);
-			perf_pmu_free_alias(newalias);
-			return true;
-		}
+	if (load && !pmu->sysfs_aliases_loaded)
+		pmu_aliases_parse(pmu);
+
+	list_for_each_entry(alias, &pmu->aliases, list) {
+		if (!strcasecmp(alias->name, name))
+			return alias;
 	}
-	return false;
+	return NULL;
 }
 
-static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name,
-				 char *desc, char *val, const struct pmu_event *pe)
+static bool assign_str(const char *name, const char *field, char **old_str,
+				const char *new_str)
+{
+	if (!*old_str && new_str) {
+		*old_str = strdup(new_str);
+		return true;
+	}
+
+	if (!new_str || !strcasecmp(*old_str, new_str))
+		return false; /* Nothing to update. */
+
+	pr_debug("alias %s differs in field '%s' ('%s' != '%s')\n",
+		name, field, *old_str, new_str);
+	zfree(old_str);
+	*old_str = strdup(new_str);
+	return true;
+}
+
+static void read_alias_info(struct perf_pmu *pmu, struct perf_pmu_alias *alias)
+{
+	if (!alias->from_sysfs || alias->info_loaded)
+		return;
+
+	/*
+	 * load unit name and scale if available
+	 */
+	perf_pmu__parse_unit(pmu, alias);
+	perf_pmu__parse_scale(pmu, alias);
+	perf_pmu__parse_per_pkg(pmu, alias);
+	perf_pmu__parse_snapshot(pmu, alias);
+}
+
+struct update_alias_data {
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+};
+
+static int update_alias(const struct pmu_event *pe,
+			const struct pmu_events_table *table __maybe_unused,
+			void *vdata)
+{
+	struct update_alias_data *data = vdata;
+	int ret = 0;
+
+	read_alias_info(data->pmu, data->alias);
+	assign_str(pe->name, "desc", &data->alias->desc, pe->desc);
+	assign_str(pe->name, "long_desc", &data->alias->long_desc, pe->long_desc);
+	assign_str(pe->name, "topic", &data->alias->topic, pe->topic);
+	data->alias->per_pkg = pe->perpkg;
+	if (pe->event) {
+		parse_events_terms__exit(&data->alias->terms);
+		ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL);
+	}
+	if (!ret && pe->unit) {
+		char *unit;
+
+		ret = perf_pmu__convert_scale(pe->unit, &unit, &data->alias->scale);
+		if (!ret)
+			snprintf(data->alias->unit, sizeof(data->alias->unit), "%s", unit);
+	}
+	return ret;
+}
+
+static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
+				const char *desc, const char *val, FILE *val_fd,
+				const struct pmu_event *pe)
 {
-	struct parse_events_term *term;
 	struct perf_pmu_alias *alias;
 	int ret;
-	char newval[256];
 	const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL;
 	bool deprecated = false, perpkg = false;
 
+	if (perf_pmu__find_alias(pmu, name, /*load=*/ false)) {
+		/* Alias was already created/loaded. */
+		return 0;
+	}
+
 	if (pe) {
 		long_desc = pe->long_desc;
 		topic = pe->topic;
@@ -355,92 +521,61 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name,
 		pmu_name = pe->pmu;
 	}
 
-	alias = malloc(sizeof(*alias));
+	alias = zalloc(sizeof(*alias));
 	if (!alias)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&alias->terms);
+	parse_events_terms__init(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
 	alias->per_pkg = perpkg;
 	alias->snapshot = false;
 	alias->deprecated = deprecated;
 
-	ret = parse_events_terms(&alias->terms, val);
+	ret = parse_events_terms(&alias->terms, val, val_fd);
 	if (ret) {
 		pr_err("Cannot parse alias %s: %d\n", val, ret);
 		free(alias);
 		return ret;
 	}
 
-	/* Scan event and remove leading zeroes, spaces, newlines, some
-	 * platforms have terms specified as
-	 * event=0x0091 (read from files ../<PMU>/events/<FILE>
-	 * and terms specified as event=0x91 (read from JSON files).
-	 *
-	 * Rebuild string to make alias->str member comparable.
-	 */
-	memset(newval, 0, sizeof(newval));
-	ret = 0;
-	list_for_each_entry(term, &alias->terms, list) {
-		if (ret)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 ",");
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%#x", term->config, term->val.num);
-		else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			ret += scnprintf(newval + ret, sizeof(newval) - ret,
-					 "%s=%s", term->config, term->val.str);
-	}
-
 	alias->name = strdup(name);
-	if (dirfd >= 0) {
-		/*
-		 * load unit name and scale if available
-		 */
-		perf_pmu__parse_unit(alias, dirfd, name);
-		perf_pmu__parse_scale(alias, dirfd, name);
-		perf_pmu__parse_per_pkg(alias, dirfd, name);
-		perf_pmu__parse_snapshot(alias, dirfd, name);
-	}
-
 	alias->desc = desc ? strdup(desc) : NULL;
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
 	alias->topic = topic ? strdup(topic) : NULL;
+	alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL;
 	if (unit) {
-		if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0)
+		if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0) {
+			perf_pmu_free_alias(alias);
 			return -1;
+		}
 		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
 	}
-	alias->str = strdup(newval);
-	alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL;
-
-	if (!perf_pmu_merge_alias(alias, list))
-		list_add_tail(&alias->list, list);
+	if (!pe) {
+		/* Update an event from sysfs with json data. */
+		struct update_alias_data data = {
+			.pmu = pmu,
+			.alias = alias,
+		};
+
+		alias->from_sysfs = true;
+		if (pmu->events_table) {
+			if (pmu_events_table__find_event(pmu->events_table, pmu, name,
+							 update_alias, &data) == 0)
+				pmu->loaded_json_aliases++;
+		}
+	}
 
+	if (!pe)
+		pmu->sysfs_aliases++;
+	else
+		pmu->loaded_json_aliases++;
+	list_add_tail(&alias->list, &pmu->aliases);
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, FILE *file)
-{
-	char buf[256];
-	int ret;
-
-	ret = fread(buf, 1, sizeof(buf), file);
-	if (ret == 0)
-		return -EINVAL;
-
-	buf[ret] = 0;
-
-	/* Remove trailing newline from sysfs file */
-	strim(buf);
-
-	return __perf_pmu__new_alias(list, dirfd, name, NULL, buf, NULL);
-}
-
-static inline bool pmu_alias_info_file(char *name)
+static inline bool pmu_alias_info_file(const char *name)
 {
 	size_t len;
 
@@ -458,18 +593,33 @@ static inline bool pmu_alias_info_file(char *name)
 }
 
 /*
- * Process all the sysfs attributes located under the directory
- * specified in 'dir' parameter.
+ * Reading the pmu event aliases definition, which should be located at:
+ * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases_parse(int dirfd, struct list_head *head)
+static int pmu_aliases_parse(struct perf_pmu *pmu)
 {
+	char path[PATH_MAX];
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int fd;
+	size_t len;
+	int fd, dir_fd;
 
-	event_dir = fdopendir(dirfd);
-	if (!event_dir)
+	len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path));
+	if (!len)
+		return 0;
+	scnprintf(path + len, sizeof(path) - len, "%s/events", pmu->name);
+
+	dir_fd = open(path, O_DIRECTORY);
+	if (dir_fd == -1) {
+		pmu->sysfs_aliases_loaded = true;
+		return 0;
+	}
+
+	event_dir = fdopendir(dir_fd);
+	if (!event_dir){
+		close (dir_fd);
 		return -EINVAL;
+	}
 
 	while ((evt_ent = readdir(event_dir))) {
 		char *name = evt_ent->d_name;
@@ -484,7 +634,7 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head)
 		if (pmu_alias_info_file(name))
 			continue;
 
-		fd = openat(dirfd, name, O_RDONLY);
+		fd = openat(dir_fd, name, O_RDONLY);
 		if (fd == -1) {
 			pr_debug("Cannot open %s\n", name);
 			continue;
@@ -495,45 +645,29 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head)
 			continue;
 		}
 
-		if (perf_pmu__new_alias(head, dirfd, name, file) < 0)
+		if (perf_pmu__new_alias(pmu, name, /*desc=*/ NULL,
+					/*val=*/ NULL, file, /*pe=*/ NULL) < 0)
 			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
 
 	closedir(event_dir);
+	close (dir_fd);
+	pmu->sysfs_aliases_loaded = true;
 	return 0;
 }
 
-/*
- * Reading the pmu event aliases definition, which should be located at:
- * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
- */
-static int pmu_aliases(int dirfd, const char *name, struct list_head *head)
-{
-	int fd;
-
-	fd = perf_pmu__pathname_fd(dirfd, name, "events", O_DIRECTORY);
-	if (fd < 0)
-		return 0;
-
-	/* it'll close the fd */
-	if (pmu_aliases_parse(fd, head))
-		return -1;
-
-	return 0;
-}
-
-static int pmu_alias_terms(struct perf_pmu_alias *alias,
-			   struct list_head *terms)
+static int pmu_alias_terms(struct perf_pmu_alias *alias, int err_loc, struct list_head *terms)
 {
 	struct parse_events_term *term, *cloned;
-	LIST_HEAD(list);
-	int ret;
+	struct parse_events_terms clone_terms;
+
+	parse_events_terms__init(&clone_terms);
+	list_for_each_entry(term, &alias->terms.terms, list) {
+		int ret = parse_events_term__clone(&cloned, term);
 
-	list_for_each_entry(term, &alias->terms, list) {
-		ret = parse_events_term__clone(&cloned, term);
 		if (ret) {
-			parse_events_terms__purge(&list);
+			parse_events_terms__exit(&clone_terms);
 			return ret;
 		}
 		/*
@@ -541,9 +675,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 		 * which we don't want for implicit terms in aliases.
 		 */
 		cloned->weak = true;
-		list_add_tail(&cloned->list, &list);
+		cloned->err_term = cloned->err_val = err_loc;
+		list_add_tail(&cloned->list, &clone_terms.terms);
 	}
-	list_splice(&list, terms);
+	list_splice_init(&clone_terms.terms, terms);
+	parse_events_terms__exit(&clone_terms);
 	return 0;
 }
 
@@ -642,11 +778,6 @@ char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 	return cpuid;
 }
 
-__weak const struct pmu_events_table *pmu_events_table__find(void)
-{
-	return perf_pmu__find_events_table(NULL);
-}
-
 __weak const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
 	return perf_pmu__find_metrics_table(NULL);
@@ -741,28 +872,35 @@ out:
 	return res;
 }
 
-struct pmu_add_cpu_aliases_map_data {
-	/* List being added to. */
-	struct list_head *head;
-	/* If a pmu_event lacks a given PMU the default used. */
-	char *default_pmu_name;
-	/* The PMU that we're searching for events for. */
-	struct perf_pmu *pmu;
-};
+bool pmu_uncore_identifier_match(const char *compat, const char *id)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+
+	if (regcomp(&re, compat, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", compat);
+		return false;
+	}
+
+	match = !regexec(&re, id, 1, pmatch, 0);
+	if (match) {
+		/* Ensure a full match. */
+		match = pmatch[0].rm_so == 0 && (size_t)pmatch[0].rm_eo == strlen(id);
+	}
+	regfree(&re);
+
+	return match;
+}
 
 static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
 					const struct pmu_events_table *table __maybe_unused,
 					void *vdata)
 {
-	struct pmu_add_cpu_aliases_map_data *data = vdata;
-	const char *pname = pe->pmu ?: data->default_pmu_name;
+	struct perf_pmu *pmu = vdata;
 
-	if (!strcmp(pname, data->pmu->name) ||
-	    (data->pmu->is_uncore && pmu_uncore_alias_match(pname, data->pmu->name))) {
-		/* need type casts to override 'const' */
-		__perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc,
-				      (char *)pe->event, pe);
-	}
+	perf_pmu__new_alias(pmu, pe->name, pe->desc, pe->event, /*val_fd=*/ NULL, pe);
 	return 0;
 }
 
@@ -770,86 +908,74 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe,
  * From the pmu_events_table, find the events that correspond to the given
  * PMU and add them to the list 'head'.
  */
-void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
-			const struct pmu_events_table *table)
+void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table)
 {
-	struct pmu_add_cpu_aliases_map_data data = {
-		.head = head,
-		.default_pmu_name = perf_pmus__default_pmu_name(),
-		.pmu = pmu,
-	};
-
-	pmu_events_table_for_each_event(table, pmu_add_cpu_aliases_map_callback, &data);
-	free(data.default_pmu_name);
+	pmu_events_table__for_each_event(table, pmu, pmu_add_cpu_aliases_map_callback, pmu);
 }
 
-static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
+static void pmu_add_cpu_aliases(struct perf_pmu *pmu)
 {
-	const struct pmu_events_table *table;
+	if (!pmu->events_table)
+		return;
 
-	table = perf_pmu__find_events_table(pmu);
-	if (!table)
+	if (pmu->cpu_aliases_added)
 		return;
 
-	pmu_add_cpu_aliases_table(head, pmu, table);
+	pmu_add_cpu_aliases_table(pmu, pmu->events_table);
+	pmu->cpu_aliases_added = true;
 }
 
-struct pmu_sys_event_iter_data {
-	struct list_head *head;
-	struct perf_pmu *pmu;
-};
-
 static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe,
 				       const struct pmu_events_table *table __maybe_unused,
-				       void *data)
+				       void *vdata)
 {
-	struct pmu_sys_event_iter_data *idata = data;
-	struct perf_pmu *pmu = idata->pmu;
+	struct perf_pmu *pmu = vdata;
 
 	if (!pe->compat || !pe->pmu)
 		return 0;
 
-	if (!strcmp(pmu->id, pe->compat) &&
-	    pmu_uncore_alias_match(pe->pmu, pmu->name)) {
-		__perf_pmu__new_alias(idata->head, -1,
-				      (char *)pe->name,
-				      (char *)pe->desc,
-				      (char *)pe->event,
-				      pe);
+	if (pmu_uncore_alias_match(pe->pmu, pmu->name) &&
+			pmu_uncore_identifier_match(pe->compat, pmu->id)) {
+		perf_pmu__new_alias(pmu,
+				pe->name,
+				pe->desc,
+				pe->event,
+				/*val_fd=*/ NULL,
+				pe);
 	}
 
 	return 0;
 }
 
-void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu)
+void pmu_add_sys_aliases(struct perf_pmu *pmu)
 {
-	struct pmu_sys_event_iter_data idata = {
-		.head = head,
-		.pmu = pmu,
-	};
-
 	if (!pmu->id)
 		return;
 
-	pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata);
+	pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, pmu);
 }
 
-struct perf_event_attr * __weak
-perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+static char *pmu_find_alias_name(struct perf_pmu *pmu, int dirfd)
 {
-	return NULL;
-}
+	FILE *file = perf_pmu__open_file_at(pmu, dirfd, "alias");
+	char *line = NULL;
+	size_t line_len = 0;
+	ssize_t ret;
 
-char * __weak
-pmu_find_real_name(const char *name)
-{
-	return (char *)name;
-}
+	if (!file)
+		return NULL;
 
-char * __weak
-pmu_find_alias_name(const char *name __maybe_unused)
-{
-	return NULL;
+	ret = getline(&line, &line_len, file);
+	if (ret < 0) {
+		fclose(file);
+		return NULL;
+	}
+	/* Remove trailing newline. */
+	if (ret > 0 && line[ret - 1] == '\n')
+		line[--ret] = '\0';
+
+	fclose(file);
+	return line;
 }
 
 static int pmu_max_precise(int dirfd, struct perf_pmu *pmu)
@@ -860,66 +986,59 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu)
 	return max_precise;
 }
 
-struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name)
+void __weak
+perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	if (pmu->is_core)
+		pmu->mem_events = perf_mem_events;
+}
+
+struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name)
 {
 	struct perf_pmu *pmu;
-	LIST_HEAD(format);
-	LIST_HEAD(aliases);
 	__u32 type;
-	char *name = pmu_find_real_name(lookup_name);
-	char *alias_name;
-
-	/*
-	 * The pmu data we store & need consists of the pmu
-	 * type value and format definitions. Load both right
-	 * now.
-	 */
-	if (pmu_format(dirfd, name, &format))
-		return NULL;
-
-	/*
-	 * Check the aliases first to avoid unnecessary work.
-	 */
-	if (pmu_aliases(dirfd, name, &aliases))
-		return NULL;
 
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
 
-	pmu->is_core = is_pmu_core(name);
-	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 	pmu->name = strdup(name);
 	if (!pmu->name)
 		goto err;
 
-	/* Read type, and ensure that type value is successfully assigned (return 1) */
+	/*
+	 * Read type early to fail fast if a lookup name isn't a PMU. Ensure
+	 * that type value is successfully assigned (return 1).
+	 */
 	if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1)
 		goto err;
 
-	alias_name = pmu_find_alias_name(name);
-	if (alias_name) {
-		pmu->alias_name = strdup(alias_name);
-		if (!pmu->alias_name)
-			goto err;
-	}
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+
+	/*
+	 * The pmu data we store & need consists of the pmu
+	 * type value and format definitions. Load both right
+	 * now.
+	 */
+	if (pmu_format(pmu, dirfd, name))
+		goto err;
+
+	pmu->is_core = is_pmu_core(name);
+	pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core);
 
 	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(dirfd, name);
 	if (pmu->is_uncore)
 		pmu->id = pmu_id(name);
 	pmu->max_precise = pmu_max_precise(dirfd, pmu);
-	pmu_add_cpu_aliases(&aliases, pmu);
-	pmu_add_sys_aliases(&aliases, pmu);
-
-	INIT_LIST_HEAD(&pmu->format);
-	INIT_LIST_HEAD(&pmu->aliases);
-	INIT_LIST_HEAD(&pmu->caps);
-	list_splice(&format, &pmu->format);
-	list_splice(&aliases, &pmu->aliases);
+	pmu->alias_name = pmu_find_alias_name(pmu, dirfd);
+	pmu->events_table = perf_pmu__find_events_table(pmu);
+	pmu_add_sys_aliases(pmu);
 	list_add_tail(&pmu->list, pmus);
 
-	pmu->default_config = perf_pmu__get_default_config(pmu);
+	perf_pmu__arch_init(pmu);
 
 	return pmu;
 err:
@@ -966,13 +1085,15 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
 	if (pmu == &perf_pmu__fake)
 		return;
 
-	list_for_each_entry(format, &pmu->format, list)
+	list_for_each_entry(format, &pmu->format, list) {
+		perf_pmu_format__load(pmu, format);
 		if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) {
 			pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'"
 				   "which is not supported by this version of perf!\n",
 				   pmu->name, format->name, format->value);
 			return;
 		}
+	}
 }
 
 bool evsel__is_aux_event(const struct evsel *evsel)
@@ -1000,7 +1121,7 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel,
 	if (term)
 		user_bits = term->val.cfg_chg;
 
-	bits = perf_pmu__format_bits(&pmu->format, config_name);
+	bits = perf_pmu__format_bits(pmu, config_name);
 
 	/* Do nothing if the user changed the value */
 	if (bits & user_bits)
@@ -1012,7 +1133,7 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel,
 }
 
 static struct perf_pmu_format *
-pmu_find_format(struct list_head *formats, const char *name)
+pmu_find_format(const struct list_head *formats, const char *name)
 {
 	struct perf_pmu_format *format;
 
@@ -1023,9 +1144,9 @@ pmu_find_format(struct list_head *formats, const char *name)
 	return NULL;
 }
 
-__u64 perf_pmu__format_bits(struct list_head *formats, const char *name)
+__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_format *format = pmu_find_format(formats, name);
+	struct perf_pmu_format *format = pmu_find_format(&pmu->format, name);
 	__u64 bits = 0;
 	int fbit;
 
@@ -1038,13 +1159,14 @@ __u64 perf_pmu__format_bits(struct list_head *formats, const char *name)
 	return bits;
 }
 
-int perf_pmu__format_type(struct list_head *formats, const char *name)
+int perf_pmu__format_type(struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_format *format = pmu_find_format(formats, name);
+	struct perf_pmu_format *format = pmu_find_format(&pmu->format, name);
 
 	if (!format)
 		return -1;
 
+	perf_pmu_format__load(pmu, format);
 	return format->value;
 }
 
@@ -1089,12 +1211,12 @@ static __u64 pmu_format_max_value(const unsigned long *format)
  *   in a config string) later on in the term list.
  */
 static int pmu_resolve_param_term(struct parse_events_term *term,
-				  struct list_head *head_terms,
+				  struct parse_events_terms *head_terms,
 				  __u64 *value)
 {
 	struct parse_events_term *t;
 
-	list_for_each_entry(t, head_terms, list) {
+	list_for_each_entry(t, &head_terms->terms, list) {
 		if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM &&
 		    t->config && !strcmp(t->config, term->config)) {
 			t->used = true;
@@ -1109,7 +1231,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
-static char *pmu_formats_string(struct list_head *formats)
+static char *pmu_formats_string(const struct list_head *formats)
 {
 	struct perf_pmu_format *format;
 	char *str = NULL;
@@ -1135,11 +1257,10 @@ error:
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
  */
-static int pmu_config_term(const char *pmu_name,
-			   struct list_head *formats,
+static int pmu_config_term(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
-			   struct list_head *head_terms,
+			   struct parse_events_terms *head_terms,
 			   bool zero, struct parse_events_error *err)
 {
 	struct perf_pmu_format *format;
@@ -1160,15 +1281,15 @@ static int pmu_config_term(const char *pmu_name,
 	if (parse_events__is_hardcoded_term(term))
 		return 0;
 
-	format = pmu_find_format(formats, term->config);
+	format = pmu_find_format(&pmu->format, term->config);
 	if (!format) {
-		char *pmu_term = pmu_formats_string(formats);
+		char *pmu_term = pmu_formats_string(&pmu->format);
 		char *unknown_term;
 		char *help_msg;
 
 		if (asprintf(&unknown_term,
 				"unknown term '%s' for pmu '%s'",
-				term->config, pmu_name) < 0)
+				term->config, pmu->name) < 0)
 			unknown_term = NULL;
 		help_msg = parse_events_formats_error_string(pmu_term);
 		if (err) {
@@ -1182,7 +1303,7 @@ static int pmu_config_term(const char *pmu_name,
 		free(pmu_term);
 		return -EINVAL;
 	}
-
+	perf_pmu_format__load(pmu, format);
 	switch (format->value) {
 	case PERF_PMU_FORMAT_VALUE_CONFIG:
 		vp = &attr->config;
@@ -1242,8 +1363,8 @@ static int pmu_config_term(const char *pmu_name,
 
 			parse_events_error__handle(err, term->err_val,
 				asprintf(&err_str,
-				    "value too big for format, maximum is %llu",
-				    (unsigned long long)max_val) < 0
+				    "value too big for format (%s), maximum is %llu",
+				    format->name, (unsigned long long)max_val) < 0
 				    ? strdup("value too big for format")
 				    : err_str,
 				    NULL);
@@ -1259,16 +1380,15 @@ static int pmu_config_term(const char *pmu_name,
 	return 0;
 }
 
-int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
+int perf_pmu__config_terms(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms,
+			   struct parse_events_terms *terms,
 			   bool zero, struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
-	list_for_each_entry(term, head_terms, list) {
-		if (pmu_config_term(pmu_name, formats, attr, term, head_terms,
-				    zero, err))
+	list_for_each_entry(term, &terms->terms, list) {
+		if (pmu_config_term(pmu, attr, term, terms, zero, err))
 			return -EINVAL;
 	}
 
@@ -1281,30 +1401,30 @@ int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
  * 2) pmu format definitions - specified by pmu parameter
  */
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms,
+		     struct parse_events_terms *head_terms,
 		     struct parse_events_error *err)
 {
-	bool zero = !!pmu->default_config;
+	bool zero = !!pmu->perf_event_attr_init_default;
 
-	return perf_pmu__config_terms(pmu->name, &pmu->format, attr,
-				      head_terms, zero, err);
+	return perf_pmu__config_terms(pmu, attr, head_terms, zero, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 					     struct parse_events_term *term)
 {
 	struct perf_pmu_alias *alias;
-	char *name;
+	const char *name;
 
 	if (parse_events__is_hardcoded_term(term))
 		return NULL;
 
 	if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
-		if (term->val.num != 1)
+		if (!term->no_value)
 			return NULL;
 		if (pmu_find_format(&pmu->format, term->config))
 			return NULL;
 		name = term->config;
+
 	} else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcasecmp(term->config, "event"))
 			return NULL;
@@ -1313,26 +1433,51 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 		return NULL;
 	}
 
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcasecmp(alias->name, name))
-			return alias;
+	alias = perf_pmu__find_alias(pmu, name, /*load=*/ true);
+	if (alias || pmu->cpu_aliases_added)
+		return alias;
+
+	/* Alias doesn't exist, try to get it from the json events. */
+	if (pmu->events_table &&
+	    pmu_events_table__find_event(pmu->events_table, pmu, name,
+				         pmu_add_cpu_aliases_map_callback,
+				         pmu) == 0) {
+		alias = perf_pmu__find_alias(pmu, name, /*load=*/ false);
 	}
-	return NULL;
+	return alias;
 }
 
 
-static int check_info_data(struct perf_pmu_alias *alias,
-			   struct perf_pmu_info *info)
+static int check_info_data(struct perf_pmu *pmu,
+			   struct perf_pmu_alias *alias,
+			   struct perf_pmu_info *info,
+			   struct parse_events_error *err,
+			   int column)
 {
+	read_alias_info(pmu, alias);
 	/*
 	 * Only one term in event definition can
 	 * define unit, scale and snapshot, fail
 	 * if there's more than one.
 	 */
-	if ((info->unit && alias->unit[0]) ||
-	    (info->scale && alias->scale) ||
-	    (info->snapshot && alias->snapshot))
+	if (info->unit && alias->unit[0]) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event's unit twice"),
+					NULL);
+		return -EINVAL;
+	}
+	if (info->scale && alias->scale) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event's scale twice"),
+					NULL);
+		return -EINVAL;
+	}
+	if (info->snapshot && alias->snapshot) {
+		parse_events_error__handle(err, column,
+					strdup("Attempt to set event snapshot twice"),
+					NULL);
 		return -EINVAL;
+	}
 
 	if (alias->unit[0])
 		info->unit = alias->unit;
@@ -1350,13 +1495,15 @@ static int check_info_data(struct perf_pmu_alias *alias,
  * Find alias in the terms list and replace it with the terms
  * defined for the alias
  */
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  struct perf_pmu_info *info)
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*rewrote_terms = false;
 	info->per_pkg = false;
 
 	/*
@@ -1367,15 +1514,19 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	info->scale    = 0.0;
 	info->snapshot = false;
 
-	list_for_each_entry_safe(term, h, head_terms, list) {
+	list_for_each_entry_safe(term, h, &head_terms->terms, list) {
 		alias = pmu_find_alias(pmu, term);
 		if (!alias)
 			continue;
-		ret = pmu_alias_terms(alias, &term->list);
-		if (ret)
+		ret = pmu_alias_terms(alias, term->err_term, &term->list);
+		if (ret) {
+			parse_events_error__handle(err, term->err_term,
+						strdup("Failure to duplicate terms"),
+						NULL);
 			return ret;
-
-		ret = check_info_data(alias, info);
+		}
+		*rewrote_terms = true;
+		ret = check_info_data(pmu, alias, info, err, term->err_term);
 		if (ret)
 			return ret;
 
@@ -1400,36 +1551,36 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	return 0;
 }
 
-int perf_pmu__new_format(struct list_head *list, char *name,
-			 int config, unsigned long *bits)
-{
-	struct perf_pmu_format *format;
+struct find_event_args {
+	const char *event;
+	void *state;
+	pmu_event_callback cb;
+};
 
-	format = zalloc(sizeof(*format));
-	if (!format)
-		return -ENOMEM;
+static int find_event_callback(void *state, struct pmu_event_info *info)
+{
+	struct find_event_args *args = state;
 
-	format->name = strdup(name);
-	format->value = config;
-	memcpy(format->bits, bits, sizeof(format->bits));
+	if (!strcmp(args->event, info->name))
+		return args->cb(args->state, info);
 
-	list_add_tail(&format->list, list);
 	return 0;
 }
 
-void perf_pmu__set_format(unsigned long *bits, long from, long to)
+int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb)
 {
-	long b;
-
-	if (!to)
-		to = from;
+	struct find_event_args args = {
+		.event = event,
+		.state = state,
+		.cb = cb,
+	};
 
-	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
-	for (b = from; b <= to; b++)
-		__set_bit(b, bits);
+	/* Sub-optimal, but function is only used by tests. */
+	return perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ false,
+					&args, find_event_callback);
 }
 
-void perf_pmu__del_formats(struct list_head *formats)
+static void perf_pmu__del_formats(struct list_head *formats)
 {
 	struct perf_pmu_format *fmt, *tmp;
 
@@ -1466,19 +1617,157 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 	return !pmu->is_core || perf_pmus__num_core_pmus() == 1;
 }
 
-bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)
+bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
 {
-	struct perf_pmu_alias *alias;
+	if (!name)
+		return false;
+	if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
+		return true;
+	if (pmu->cpu_aliases_added || !pmu->events_table)
+		return false;
+	return pmu_events_table__find_event(pmu->events_table, pmu, name, NULL, NULL) == 0;
+}
 
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (!strcmp(alias->name, name))
-			return true;
+size_t perf_pmu__num_events(struct perf_pmu *pmu)
+{
+	size_t nr;
+
+	if (!pmu->sysfs_aliases_loaded)
+		pmu_aliases_parse(pmu);
+
+	nr = pmu->sysfs_aliases;
+
+	if (pmu->cpu_aliases_added)
+		 nr += pmu->loaded_json_aliases;
+	else if (pmu->events_table)
+		nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->loaded_json_aliases;
+
+	return pmu->selectable ? nr + 1 : nr;
+}
+
+static int sub_non_neg(int a, int b)
+{
+	if (b > a)
+		return 0;
+	return a - b;
+}
+
+static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
+			  const struct perf_pmu_alias *alias, bool skip_duplicate_pmus)
+{
+	struct parse_events_term *term;
+	int pmu_name_len = skip_duplicate_pmus
+		? pmu_name_len_no_suffix(pmu->name, /*num=*/NULL)
+		: (int)strlen(pmu->name);
+	int used = snprintf(buf, len, "%.*s/%s", pmu_name_len, pmu->name, alias->name);
+
+	list_for_each_entry(term, &alias->terms.terms, list) {
+		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+			used += snprintf(buf + used, sub_non_neg(len, used),
+					",%s=%s", term->config,
+					term->val.str);
 	}
-	return false;
+
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '/';
+		used++;
+	}
+	if (sub_non_neg(len, used) > 0) {
+		buf[used] = '\0';
+		used++;
+	} else
+		buf[len - 1] = '\0';
+
+	return buf;
+}
+
+int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
+			     void *state, pmu_event_callback cb)
+{
+	char buf[1024];
+	struct perf_pmu_alias *event;
+	struct pmu_event_info info = {
+		.pmu = pmu,
+	};
+	int ret = 0;
+	struct strbuf sb;
+
+	strbuf_init(&sb, /*hint=*/ 0);
+	pmu_add_cpu_aliases(pmu);
+	list_for_each_entry(event, &pmu->aliases, list) {
+		size_t buf_used;
+
+		info.pmu_name = event->pmu_name ?: pmu->name;
+		info.alias = NULL;
+		if (event->desc) {
+			info.name = event->name;
+			buf_used = 0;
+		} else {
+			info.name = format_alias(buf, sizeof(buf), pmu, event,
+						 skip_duplicate_pmus);
+			if (pmu->is_core) {
+				info.alias = info.name;
+				info.name = event->name;
+			}
+			buf_used = strlen(buf) + 1;
+		}
+		info.scale_unit = NULL;
+		if (strlen(event->unit) || event->scale != 1.0) {
+			info.scale_unit = buf + buf_used;
+			buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
+					"%G%s", event->scale, event->unit) + 1;
+		}
+		info.desc = event->desc;
+		info.long_desc = event->long_desc;
+		info.encoding_desc = buf + buf_used;
+		parse_events_terms__to_strbuf(&event->terms, &sb);
+		buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
+				"%s/%s/", info.pmu_name, sb.buf) + 1;
+		info.topic = event->topic;
+		info.str = sb.buf;
+		info.deprecated = event->deprecated;
+		ret = cb(state, &info);
+		if (ret)
+			goto out;
+		strbuf_setlen(&sb, /*len=*/ 0);
+	}
+	if (pmu->selectable) {
+		info.name = buf;
+		snprintf(buf, sizeof(buf), "%s//", pmu->name);
+		info.alias = NULL;
+		info.scale_unit = NULL;
+		info.desc = NULL;
+		info.long_desc = NULL;
+		info.encoding_desc = NULL;
+		info.topic = NULL;
+		info.pmu_name = pmu->name;
+		info.deprecated = false;
+		ret = cb(state, &info);
+	}
+out:
+	strbuf_release(&sb);
+	return ret;
+}
+
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name)
+{
+	return !strcmp(pmu->name, pmu_name) ||
+		(pmu->is_uncore && pmu_uncore_alias_match(pmu_name, pmu->name)) ||
+		/*
+		 * jevents and tests use default_core as a marker for any core
+		 * PMU as the PMU name varies across architectures.
+		 */
+	        (pmu->is_core && !strcmp(pmu_name, "default_core"));
 }
 
 bool perf_pmu__is_software(const struct perf_pmu *pmu)
 {
+	const char *known_sw_pmus[] = {
+		"kprobe",
+		"msr",
+		"uprobe",
+	};
+
 	if (pmu->is_core || pmu->is_uncore || pmu->auxtrace)
 		return false;
 	switch (pmu->type) {
@@ -1490,10 +1779,14 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu)
 	case PERF_TYPE_BREAKPOINT:	return true;
 	default: break;
 	}
-	return !strcmp(pmu->name, "kprobe") || !strcmp(pmu->name, "uprobe");
+	for (size_t i = 0; i < ARRAY_SIZE(known_sw_pmus); i++) {
+		if (!strcmp(pmu->name, known_sw_pmus[i]))
+			return true;
+	}
+	return false;
 }
 
-FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name)
 {
 	char path[PATH_MAX];
 
@@ -1504,7 +1797,7 @@ FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
 	return fopen(path, "r");
 }
 
-FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name)
+FILE *perf_pmu__open_file_at(const struct perf_pmu *pmu, int dirfd, const char *name)
 {
 	int fd;
 
@@ -1515,7 +1808,7 @@ FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name)
 	return fdopen(fd, "r");
 }
 
-int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt,
 			...)
 {
 	va_list args;
@@ -1532,7 +1825,7 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
 	return ret;
 }
 
-int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name,
+int perf_pmu__scan_file_at(const struct perf_pmu *pmu, int dirfd, const char *name,
 			   const char *fmt, ...)
 {
 	va_list args;
@@ -1549,7 +1842,7 @@ int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name,
 	return ret;
 }
 
-bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name)
+bool perf_pmu__file_exists(const struct perf_pmu *pmu, const char *name)
 {
 	char path[PATH_MAX];
 
@@ -1710,7 +2003,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 		   name ?: "N/A", buf, config_name, config);
 }
 
-int perf_pmu__match(char *pattern, char *name, char *tok)
+int perf_pmu__match(const char *pattern, const char *name, const char *tok)
 {
 	if (!name)
 		return -1;
@@ -1756,17 +2049,19 @@ int perf_pmu__event_source_devices_fd(void)
  * then pathname will be filled with
  * "/sys/bus/event_source/devices/cs_etm/format"
  *
- * Return 0 if the sysfs mountpoint couldn't be found or if no
- * characters were written.
+ * Return 0 if the sysfs mountpoint couldn't be found, if no characters were
+ * written or if the buffer size is exceeded.
  */
 int perf_pmu__pathname_scnprintf(char *buf, size_t size,
 				 const char *pmu_name, const char *filename)
 {
-	char base_path[PATH_MAX];
+	size_t len;
 
-	if (!perf_pmu__event_source_devices_scnprintf(base_path, sizeof(base_path)))
+	len = perf_pmu__event_source_devices_scnprintf(buf, size);
+	if (!len || (len + strlen(pmu_name) + strlen(filename) + 1)  >= size)
 		return 0;
-	return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename);
+
+	return scnprintf(buf + len, size - len, "%s/%s", pmu_name, filename);
 }
 
 int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags)
@@ -1785,8 +2080,8 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 
 	perf_cpu_map__put(pmu->cpus);
 
-	zfree(&pmu->default_config);
 	zfree(&pmu->name);
 	zfree(&pmu->alias_name);
+	zfree(&pmu->id);
 	free(pmu);
 }
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b414cecbad2..e35d985206db 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -10,6 +10,8 @@
 #include <stdio.h>
 #include "parse-events.h"
 #include "pmu-events/pmu-events.h"
+#include "map_symbol.h"
+#include "mem-events.h"
 
 struct evsel_config_term;
 struct perf_cpu_map;
@@ -39,7 +41,7 @@ struct perf_pmu_caps {
  */
 struct perf_pmu {
 	/** @name: The name of the PMU such as "cpu". */
-	char *name;
+	const char *name;
 	/**
 	 * @alias_name: Optional alternate name for the PMU determined in
 	 * architecture specific code.
@@ -49,7 +51,7 @@ struct perf_pmu {
 	 * @id: Optional PMU identifier read from
 	 * <sysfs>/bus/event_source/devices/<name>/identifier.
 	 */
-	char *id;
+	const char *id;
 	/**
 	 * @type: Perf event attributed type value, read from
 	 * <sysfs>/bus/event_source/devices/<name>/type.
@@ -92,10 +94,11 @@ struct perf_pmu {
 	 */
 	int max_precise;
 	/**
-	 * @default_config: Optional default perf_event_attr determined in
-	 * architecture specific code.
+	 * @perf_event_attr_init_default: Optional function to default
+	 * initialize PMU specific parts of the perf_event_attr.
 	 */
-	struct perf_event_attr *default_config;
+	void (*perf_event_attr_init_default)(const struct perf_pmu *pmu,
+					     struct perf_event_attr *attr);
 	/**
 	 * @cpus: Empty or the contents of either of:
 	 * <sysfs>/bus/event_source/devices/<name>/cpumask.
@@ -114,6 +117,21 @@ struct perf_pmu {
 	 * from json events in pmu-events.c.
 	 */
 	struct list_head aliases;
+	/**
+	 * @events_table: The events table for json events in pmu-events.c.
+	 */
+	const struct pmu_events_table *events_table;
+	/** @sysfs_aliases: Number of sysfs aliases loaded. */
+	uint32_t sysfs_aliases;
+	/** @sysfs_aliases: Number of json event aliases loaded. */
+	uint32_t loaded_json_aliases;
+	/** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */
+	bool sysfs_aliases_loaded;
+	/**
+	 * @cpu_aliases_added: Have all json events table entries for the PMU
+	 * been added?
+	 */
+	bool cpu_aliases_added;
 	/** @caps_initialized: Has the list caps been initialized? */
 	bool caps_initialized;
 	/** @nr_caps: The length of the list caps. */
@@ -146,6 +164,11 @@ struct perf_pmu {
 		 */
 		bool exclude_guest;
 	} missing_features;
+
+	/**
+	 * @mem_events: List of the supported mem events
+	 */
+	struct perf_mem_event *mem_events;
 };
 
 /** @perf_pmu__fake: A special global PMU used for testing. */
@@ -158,113 +181,75 @@ struct perf_pmu_info {
 	bool snapshot;
 };
 
-#define UNIT_MAX_LEN	31 /* max length for event unit name */
-
-/**
- * struct perf_pmu_alias - An event either read from sysfs or builtin in
- * pmu-events.c, created by parsing the pmu-events json files.
- */
-struct perf_pmu_alias {
-	/** @name: Name of the event like "mem-loads". */
-	char *name;
-	/** @desc: Optional short description of the event. */
-	char *desc;
-	/** @long_desc: Optional long description. */
-	char *long_desc;
-	/**
-	 * @topic: Optional topic such as cache or pipeline, particularly for
-	 * json events.
-	 */
-	char *topic;
-	/**
-	 * @str: Comma separated parameter list like
-	 * "event=0xcd,umask=0x1,ldlat=0x3".
-	 */
-	char *str;
-	/** @terms: Owned list of the original parsed parameters. */
-	struct list_head terms;
-	/** @list: List element of struct perf_pmu aliases. */
-	struct list_head list;
-	/** @unit: Units for the event, such as bytes or cache lines. */
-	char unit[UNIT_MAX_LEN+1];
-	/** @scale: Value to scale read counter values by. */
-	double scale;
-	/**
-	 * @per_pkg: Does the file
-	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.per-pkg or
-	 * equivalent json value exist and have the value 1.
-	 */
-	bool per_pkg;
-	/**
-	 * @snapshot: Does the file
-	 * <sysfs>/bus/event_source/devices/<pmu_name>/events/<name>.snapshot
-	 * exist and have the value 1.
-	 */
-	bool snapshot;
-	/**
-	 * @deprecated: Is the event hidden and so not shown in perf list by
-	 * default.
-	 */
+struct pmu_event_info {
+	const struct perf_pmu *pmu;
+	const char *name;
+	const char* alias;
+	const char *scale_unit;
+	const char *desc;
+	const char *long_desc;
+	const char *encoding_desc;
+	const char *topic;
+	const char *pmu_name;
+	const char *str;
 	bool deprecated;
-	/**
-	 * @pmu_name: The name copied from the json struct pmu_event. This can
-	 * differ from the PMU name as it won't have suffixes.
-	 */
-	char *pmu_name;
 };
 
-void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu);
+typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info);
+
+void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms,
+		     struct parse_events_terms *head_terms,
 		     struct parse_events_error *error);
-int perf_pmu__config_terms(const char *pmu_name, struct list_head *formats,
+int perf_pmu__config_terms(const struct perf_pmu *pmu,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms,
+			   struct parse_events_terms *terms,
 			   bool zero, struct parse_events_error *error);
-__u64 perf_pmu__format_bits(struct list_head *formats, const char *name);
-int perf_pmu__format_type(struct list_head *formats, const char *name);
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  struct perf_pmu_info *info);
-struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
-				  struct list_head *head_terms);
-void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg);
+__u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name);
+int perf_pmu__format_type(struct perf_pmu *pmu, const char *name);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms,
+			  struct perf_pmu_info *info, bool *rewrote_terms,
+			  struct parse_events_error *err);
+int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb);
 
-int perf_pmu__new_format(struct list_head *list, char *name,
-			 int config, unsigned long *bits);
-void perf_pmu__set_format(unsigned long *bits, long from, long to);
-int perf_pmu__format_parse(int dirfd, struct list_head *head);
-void perf_pmu__del_formats(struct list_head *formats);
+int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
+void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
 
 bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
 bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu);
-bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name);
+bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name);
+size_t perf_pmu__num_events(struct perf_pmu *pmu);
+int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
+			     void *state, pmu_event_callback cb);
+bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name);
+
 /**
  * perf_pmu_is_software - is the PMU a software PMU as in it uses the
  *                        perf_sw_context in the kernel?
  */
 bool perf_pmu__is_software(const struct perf_pmu *pmu);
 
-FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name);
-FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name);
+FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name);
+FILE *perf_pmu__open_file_at(const struct perf_pmu *pmu, int dirfd, const char *name);
 
-int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4);
-int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name,
+int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...)
+	__scanf(3, 4);
+int perf_pmu__scan_file_at(const struct perf_pmu *pmu, int dirfd, const char *name,
 			   const char *fmt, ...) __scanf(4, 5);
 
-bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name);
+bool perf_pmu__file_exists(const struct perf_pmu *pmu, const char *name);
 
 int perf_pmu__test(void);
 
-struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
-void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu,
+void perf_pmu__arch_init(struct perf_pmu *pmu);
+void pmu_add_cpu_aliases_table(struct perf_pmu *pmu,
 			       const struct pmu_events_table *table);
 
 char *perf_pmu__getcpuid(struct perf_pmu *pmu);
-const struct pmu_events_table *pmu_events_table__find(void);
 const struct pmu_metrics_table *pmu_metrics_table__find(void);
-void perf_pmu_free_alias(struct perf_pmu_alias *alias);
+bool pmu_uncore_identifier_match(const char *compat, const char *id);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
@@ -275,10 +260,8 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *config_name);
 void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
-int perf_pmu__match(char *pattern, char *name, char *tok);
+int perf_pmu__match(const char *pattern, const char *name, const char *tok);
 
-char *pmu_find_real_name(const char *name);
-char *pmu_find_alias_name(const char *name);
 double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size);
 int perf_pmu__pathname_scnprintf(char *buf, size_t size,
@@ -289,5 +272,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
+struct perf_pmu *perf_pmus__find_core_pmu(void);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index dff4e892ac4d..198907a8a48a 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -1,16 +1,22 @@
 %define api.pure full
-%parse-param {struct list_head *format}
-%parse-param {char *name}
+%parse-param {void *format}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
 
 %{
 
+#ifndef NDEBUG
+#define YYDEBUG 1
+#endif
+
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/bitmap.h>
 #include <string.h>
 #include "pmu.h"
+#include "pmu-bison.h"
+
+int perf_pmu_lex(YYSTYPE * yylval_param , void *yyscanner);
 
 #define ABORT_ON(val) \
 do { \
@@ -18,6 +24,20 @@ do { \
                 YYABORT; \
 } while (0)
 
+static void perf_pmu_error(void *format, void *scanner, const char *msg);
+
+static void perf_pmu__set_format(unsigned long *bits, long from, long to)
+{
+	long b;
+
+	if (!to)
+		to = from;
+
+	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
+	for (b = from; b <= to; b++)
+		__set_bit(b, bits);
+}
+
 %}
 
 %token PP_CONFIG
@@ -42,16 +62,12 @@ format_term
 format_term:
 PP_CONFIG ':' bits
 {
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      PERF_PMU_FORMAT_VALUE_CONFIG,
-				      $3));
+	perf_pmu_format__set_value(format, PERF_PMU_FORMAT_VALUE_CONFIG, $3);
 }
 |
 PP_CONFIG PP_VALUE ':' bits
 {
-	ABORT_ON(perf_pmu__new_format(format, name,
-				      $2,
-				      $4));
+	perf_pmu_format__set_value(format, $2, $4);
 }
 
 bits:
@@ -78,9 +94,8 @@ PP_VALUE
 
 %%
 
-void perf_pmu_error(struct list_head *list __maybe_unused,
-		    char *name __maybe_unused,
-		    void *scanner __maybe_unused,
-		    char const *msg __maybe_unused)
+static void perf_pmu_error(void *format __maybe_unused,
+			   void *scanner __maybe_unused,
+			   const char *msg __maybe_unused)
 {
 }
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index c58ba9fb6a36..16505071d362 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -1,12 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/list.h>
+#include <linux/list_sort.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
 #include <sys/types.h>
+#include <ctype.h>
 #include <dirent.h>
 #include <pthread.h>
 #include <string.h>
 #include <unistd.h>
+#include "cpumap.h"
 #include "debug.h"
 #include "evsel.h"
 #include "pmus.h"
@@ -33,6 +37,33 @@ static LIST_HEAD(other_pmus);
 static bool read_sysfs_core_pmus;
 static bool read_sysfs_all_pmus;
 
+static void pmu_read_sysfs(bool core_only);
+
+int pmu_name_len_no_suffix(const char *str, unsigned long *num)
+{
+	int orig_len, len;
+
+	orig_len = len = strlen(str);
+
+	/* Non-uncore PMUs have their full length, for example, i915. */
+	if (!strstarts(str, "uncore_"))
+		return len;
+
+	/*
+	 * Count trailing digits and '_', if '_{num}' suffix isn't present use
+	 * the full length.
+	 */
+	while (len > 0 && isdigit(str[len - 1]))
+		len--;
+
+	if (len > 0 && len != orig_len && str[len - 1] == '_') {
+		if (num)
+			*num = strtoul(&str[len], NULL, 10);
+		return len - 1;
+	}
+	return orig_len;
+}
+
 void perf_pmus__destroy(void)
 {
 	struct perf_pmu *pmu, *tmp;
@@ -95,6 +126,14 @@ struct perf_pmu *perf_pmus__find(const char *name)
 	pmu = perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
 	close(dirfd);
 
+	if (!pmu) {
+		/*
+		 * Looking up an inidividual PMU failed. This may mean name is
+		 * an alias, so read the PMUs from sysfs and try to find again.
+		 */
+		pmu_read_sysfs(core_pmu);
+		pmu = pmu_find(name);
+	}
 	return pmu;
 }
 
@@ -122,6 +161,25 @@ static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name)
 	return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name);
 }
 
+static int pmus_cmp(void *priv __maybe_unused,
+		    const struct list_head *lhs, const struct list_head *rhs)
+{
+	unsigned long lhs_num = 0, rhs_num = 0;
+	struct perf_pmu *lhs_pmu = container_of(lhs, struct perf_pmu, list);
+	struct perf_pmu *rhs_pmu = container_of(rhs, struct perf_pmu, list);
+	const char *lhs_pmu_name = lhs_pmu->name ?: "";
+	const char *rhs_pmu_name = rhs_pmu->name ?: "";
+	int lhs_pmu_name_len = pmu_name_len_no_suffix(lhs_pmu_name, &lhs_num);
+	int rhs_pmu_name_len = pmu_name_len_no_suffix(rhs_pmu_name, &rhs_num);
+	int ret = strncmp(lhs_pmu_name, rhs_pmu_name,
+			lhs_pmu_name_len < rhs_pmu_name_len ? lhs_pmu_name_len : rhs_pmu_name_len);
+
+	if (lhs_pmu_name_len != rhs_pmu_name_len || ret != 0 || lhs_pmu_name_len == 0)
+		return ret;
+
+	return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0);
+}
+
 /* Add all pmus in sysfs to pmu list: */
 static void pmu_read_sysfs(bool core_only)
 {
@@ -156,6 +214,8 @@ static void pmu_read_sysfs(bool core_only)
 		if (!perf_pmu__create_placeholder_core_pmu(&core_pmus))
 			pr_err("Failure to set up any core PMUs\n");
 	}
+	list_sort(NULL, &core_pmus, pmus_cmp);
+	list_sort(NULL, &other_pmus, pmus_cmp);
 	if (!list_empty(&core_pmus)) {
 		read_sysfs_core_pmus = true;
 		if (!core_only)
@@ -219,7 +279,7 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu)
 {
 	if (!pmu) {
 		pmu_read_sysfs(/*core_only=*/true);
-		pmu = list_prepare_entry(pmu, &core_pmus, list);
+		return list_first_entry_or_null(&core_pmus, typeof(*pmu), list);
 	}
 	list_for_each_entry_continue(pmu, &core_pmus, list)
 		return pmu;
@@ -227,6 +287,43 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu)
 	return NULL;
 }
 
+static struct perf_pmu *perf_pmus__scan_skip_duplicates(struct perf_pmu *pmu)
+{
+	bool use_core_pmus = !pmu || pmu->is_core;
+	int last_pmu_name_len = 0;
+	const char *last_pmu_name = (pmu && pmu->name) ? pmu->name : "";
+
+	if (!pmu) {
+		pmu_read_sysfs(/*core_only=*/false);
+		pmu = list_prepare_entry(pmu, &core_pmus, list);
+	} else
+		last_pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", NULL);
+
+	if (use_core_pmus) {
+		list_for_each_entry_continue(pmu, &core_pmus, list) {
+			int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL);
+
+			if (last_pmu_name_len == pmu_name_len &&
+			    !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len))
+				continue;
+
+			return pmu;
+		}
+		pmu = NULL;
+		pmu = list_prepare_entry(pmu, &other_pmus, list);
+	}
+	list_for_each_entry_continue(pmu, &other_pmus, list) {
+		int pmu_name_len = pmu_name_len_no_suffix(pmu->name ?: "", /*num=*/NULL);
+
+		if (last_pmu_name_len == pmu_name_len &&
+		    !strncmp(last_pmu_name, pmu->name ?: "", pmu_name_len))
+			continue;
+
+		return pmu;
+	}
+	return NULL;
+}
+
 const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str)
 {
 	struct perf_pmu *pmu = NULL;
@@ -248,229 +345,157 @@ const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str)
 	return NULL;
 }
 
-int __weak perf_pmus__num_mem_pmus(void)
-{
-	/* All core PMUs are for mem events. */
-	return perf_pmus__num_core_pmus();
-}
-
 /** Struct for ordering events as output in perf list. */
 struct sevent {
 	/** PMU for event. */
 	const struct perf_pmu *pmu;
-	/**
-	 * Optional event for name, desc, etc. If not present then this is a
-	 * selectable PMU and the event name is shown as "//".
-	 */
-	const struct perf_pmu_alias *event;
-	/** Is the PMU for the CPU? */
-	bool is_cpu;
+	const char *name;
+	const char* alias;
+	const char *scale_unit;
+	const char *desc;
+	const char *long_desc;
+	const char *encoding_desc;
+	const char *topic;
+	const char *pmu_name;
+	bool deprecated;
 };
 
 static int cmp_sevent(const void *a, const void *b)
 {
 	const struct sevent *as = a;
 	const struct sevent *bs = b;
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *a_desc = NULL, *a_topic = "";
-	const char *b_name = "//", *b_desc = NULL, *b_topic = "";
+	bool a_iscpu, b_iscpu;
 	int ret;
 
-	if (as->event) {
-		a_name = as->event->name;
-		a_desc = as->event->desc;
-		a_topic = as->event->topic ?: "";
-		a_pmu_name = as->event->pmu_name;
-	}
-	if (bs->event) {
-		b_name = bs->event->name;
-		b_desc = bs->event->desc;
-		b_topic = bs->event->topic ?: "";
-		b_pmu_name = bs->event->pmu_name;
-	}
 	/* Put extra events last. */
-	if (!!a_desc != !!b_desc)
-		return !!a_desc - !!b_desc;
+	if (!!as->desc != !!bs->desc)
+		return !!as->desc - !!bs->desc;
 
 	/* Order by topics. */
-	ret = strcmp(a_topic, b_topic);
+	ret = strcmp(as->topic ?: "", bs->topic ?: "");
 	if (ret)
 		return ret;
 
 	/* Order CPU core events to be first */
-	if (as->is_cpu != bs->is_cpu)
-		return as->is_cpu ? -1 : 1;
+	a_iscpu = as->pmu ? as->pmu->is_core : true;
+	b_iscpu = bs->pmu ? bs->pmu->is_core : true;
+	if (a_iscpu != b_iscpu)
+		return a_iscpu ? -1 : 1;
 
 	/* Order by PMU name. */
 	if (as->pmu != bs->pmu) {
-		a_pmu_name = a_pmu_name ?: (as->pmu->name ?: "");
-		b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: "");
-		ret = strcmp(a_pmu_name, b_pmu_name);
+		ret = strcmp(as->pmu_name ?: "", bs->pmu_name ?: "");
 		if (ret)
 			return ret;
 	}
 
 	/* Order by event name. */
-	return strcmp(a_name, b_name);
+	return strcmp(as->name, bs->name);
 }
 
-static bool pmu_alias_is_duplicate(struct sevent *alias_a,
-				   struct sevent *alias_b)
+static bool pmu_alias_is_duplicate(struct sevent *a, struct sevent *b)
 {
-	const char *a_pmu_name = NULL, *b_pmu_name = NULL;
-	const char *a_name = "//", *b_name = "//";
-
-
-	if (alias_a->event) {
-		a_name = alias_a->event->name;
-		a_pmu_name = alias_a->event->pmu_name;
-	}
-	if (alias_b->event) {
-		b_name = alias_b->event->name;
-		b_pmu_name = alias_b->event->pmu_name;
-	}
-
 	/* Different names -> never duplicates */
-	if (strcmp(a_name, b_name))
+	if (strcmp(a->name ?: "//", b->name ?: "//"))
 		return false;
 
 	/* Don't remove duplicates for different PMUs */
-	a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: "");
-	b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: "");
-	return strcmp(a_pmu_name, b_pmu_name) == 0;
+	return strcmp(a->pmu_name, b->pmu_name) == 0;
 }
 
-static int sub_non_neg(int a, int b)
-{
-	if (b > a)
-		return 0;
-	return a - b;
-}
+struct events_callback_state {
+	struct sevent *aliases;
+	size_t aliases_len;
+	size_t index;
+};
 
-static char *format_alias(char *buf, int len, const struct perf_pmu *pmu,
-			  const struct perf_pmu_alias *alias)
+static int perf_pmus__print_pmu_events__callback(void *vstate,
+						struct pmu_event_info *info)
 {
-	struct parse_events_term *term;
-	int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name);
-
-	list_for_each_entry(term, &alias->terms, list) {
-		if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
-			used += snprintf(buf + used, sub_non_neg(len, used),
-					",%s=%s", term->config,
-					term->val.str);
-	}
+	struct events_callback_state *state = vstate;
+	struct sevent *s;
 
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '/';
-		used++;
+	if (state->index >= state->aliases_len) {
+		pr_err("Unexpected event %s/%s/\n", info->pmu->name, info->name);
+		return 1;
 	}
-	if (sub_non_neg(len, used) > 0) {
-		buf[used] = '\0';
-		used++;
-	} else
-		buf[len - 1] = '\0';
-
-	return buf;
+	s = &state->aliases[state->index];
+	s->pmu = info->pmu;
+#define COPY_STR(str) s->str = info->str ? strdup(info->str) : NULL
+	COPY_STR(name);
+	COPY_STR(alias);
+	COPY_STR(scale_unit);
+	COPY_STR(desc);
+	COPY_STR(long_desc);
+	COPY_STR(encoding_desc);
+	COPY_STR(topic);
+	COPY_STR(pmu_name);
+#undef COPY_STR
+	s->deprecated = info->deprecated;
+	state->index++;
+	return 0;
 }
 
 void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state)
 {
 	struct perf_pmu *pmu;
-	struct perf_pmu_alias *event;
-	char buf[1024];
 	int printed = 0;
-	int len, j;
+	int len;
 	struct sevent *aliases;
+	struct events_callback_state state;
+	bool skip_duplicate_pmus = print_cb->skip_duplicate_pmus(print_state);
+	struct perf_pmu *(*scan_fn)(struct perf_pmu *);
+
+	if (skip_duplicate_pmus)
+		scan_fn = perf_pmus__scan_skip_duplicates;
+	else
+		scan_fn = perf_pmus__scan;
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		list_for_each_entry(event, &pmu->aliases, list)
-			len++;
-		if (pmu->selectable)
-			len++;
-	}
+	while ((pmu = scan_fn(pmu)) != NULL)
+		len += perf_pmu__num_events(pmu);
+
 	aliases = zalloc(sizeof(struct sevent) * len);
 	if (!aliases) {
 		pr_err("FATAL: not enough memory to print PMU events\n");
 		return;
 	}
 	pmu = NULL;
-	j = 0;
-	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		bool is_cpu = pmu->is_core;
-
-		list_for_each_entry(event, &pmu->aliases, list) {
-			aliases[j].event = event;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
-		if (pmu->selectable) {
-			aliases[j].event = NULL;
-			aliases[j].pmu = pmu;
-			aliases[j].is_cpu = is_cpu;
-			j++;
-		}
+	state = (struct events_callback_state) {
+		.aliases = aliases,
+		.aliases_len = len,
+		.index = 0,
+	};
+	while ((pmu = scan_fn(pmu)) != NULL) {
+		perf_pmu__for_each_event(pmu, skip_duplicate_pmus, &state,
+					 perf_pmus__print_pmu_events__callback);
 	}
-	len = j;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
-	for (j = 0; j < len; j++) {
-		const char *name, *alias = NULL, *scale_unit = NULL,
-			*desc = NULL, *long_desc = NULL,
-			*encoding_desc = NULL, *topic = NULL,
-			*pmu_name = NULL;
-		bool deprecated = false;
-		size_t buf_used;
-
+	for (int j = 0; j < len; j++) {
 		/* Skip duplicates */
 		if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
 			continue;
 
-		if (!aliases[j].event) {
-			/* A selectable event. */
-			pmu_name = aliases[j].pmu->name;
-			buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1;
-			name = buf;
-		} else {
-			if (aliases[j].event->desc) {
-				name = aliases[j].event->name;
-				buf_used = 0;
-			} else {
-				name = format_alias(buf, sizeof(buf), aliases[j].pmu,
-						    aliases[j].event);
-				if (aliases[j].is_cpu) {
-					alias = name;
-					name = aliases[j].event->name;
-				}
-				buf_used = strlen(buf) + 1;
-			}
-			pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: "");
-			if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) {
-				scale_unit = buf + buf_used;
-				buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-						"%G%s", aliases[j].event->scale,
-						aliases[j].event->unit) + 1;
-			}
-			desc = aliases[j].event->desc;
-			long_desc = aliases[j].event->long_desc;
-			topic = aliases[j].event->topic;
-			encoding_desc = buf + buf_used;
-			buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-					"%s/%s/", pmu_name, aliases[j].event->str) + 1;
-			deprecated = aliases[j].event->deprecated;
-		}
 		print_cb->print_event(print_state,
-				pmu_name,
-				topic,
-				name,
-				alias,
-				scale_unit,
-				deprecated,
+				aliases[j].pmu_name,
+				aliases[j].topic,
+				aliases[j].name,
+				aliases[j].alias,
+				aliases[j].scale_unit,
+				aliases[j].deprecated,
 				"Kernel PMU event",
-				desc,
-				long_desc,
-				encoding_desc);
+				aliases[j].desc,
+				aliases[j].long_desc,
+				aliases[j].encoding_desc);
+		zfree(&aliases[j].name);
+		zfree(&aliases[j].alias);
+		zfree(&aliases[j].scale_unit);
+		zfree(&aliases[j].desc);
+		zfree(&aliases[j].long_desc);
+		zfree(&aliases[j].encoding_desc);
+		zfree(&aliases[j].topic);
+		zfree(&aliases[j].pmu_name);
 	}
 	if (printed && pager_in_use())
 		printf("\n");
@@ -572,3 +597,8 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
 	}
 	return pmu;
 }
+
+struct perf_pmu *perf_pmus__find_core_pmu(void)
+{
+	return perf_pmus__scan_core(NULL);
+}
diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h
index a21464432d0f..94d2a08d894b 100644
--- a/tools/perf/util/pmus.h
+++ b/tools/perf/util/pmus.h
@@ -5,6 +5,8 @@
 struct perf_pmu;
 struct print_callbacks;
 
+int pmu_name_len_no_suffix(const char *str, unsigned long *num);
+
 void perf_pmus__destroy(void);
 
 struct perf_pmu *perf_pmus__find(const char *name);
@@ -15,7 +17,6 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu);
 
 const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str);
 
-int perf_pmus__num_mem_pmus(void);
 void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state);
 bool perf_pmus__have_event(const char *pname, const char *name);
 int perf_pmus__num_core_pmus(void);
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index a7566edc86a3..7b54e9385442 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -28,6 +28,7 @@
 #include "tracepoint.h"
 #include "pfm.h"
 #include "thread_map.h"
+#include "util.h"
 
 #define MAX_NAME_LEN 100
 
@@ -63,17 +64,16 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 {
 	char *events_path = get_tracing_file("events");
 	int events_fd = open(events_path, O_PATH);
+	struct dirent **sys_namelist = NULL;
+	int sys_items;
 
 	put_tracing_file(events_path);
 	if (events_fd < 0) {
-		printf("Error: failed to open tracing events directory\n");
+		pr_err("Error: failed to open tracing events directory\n");
 		return;
 	}
 
-#ifdef HAVE_SCANDIRAT_SUPPORT
-{
-	struct dirent **sys_namelist = NULL;
-	int sys_items = tracing_events__scandir_alphasort(&sys_namelist);
+	sys_items = tracing_events__scandir_alphasort(&sys_namelist);
 
 	for (int i = 0; i < sys_items; i++) {
 		struct dirent *sys_dirent = sys_namelist[i];
@@ -130,11 +130,6 @@ next_sys:
 	}
 
 	free(sys_namelist);
-}
-#else
-	printf("\nWARNING: Your libc doesn't have the scandirat function, please ask its maintainers to implement it.\n"
-	       "         As a rough fallback, please do 'ls %s' to see the available tracepoint events.\n", events_path);
-#endif
 	close(events_fd);
 }
 
@@ -232,7 +227,6 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state)
 bool is_event_supported(u8 type, u64 config)
 {
 	bool ret = true;
-	int open_return;
 	struct evsel *evsel;
 	struct perf_event_attr attr = {
 		.type = type,
@@ -246,20 +240,32 @@ bool is_event_supported(u8 type, u64 config)
 
 	evsel = evsel__new(&attr);
 	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
+		ret = evsel__open(evsel, NULL, tmap) >= 0;
 
-		if (open_return == -EACCES) {
+		if (!ret) {
 			/*
-			 * This happens if the paranoid value
+			 * The event may fail to open if the paranoid value
 			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
+			 * Re-run with exclude_kernel set; we don't do that by
+			 * default as some ARM machines do not support it.
 			 */
 			evsel->core.attr.exclude_kernel = 1;
 			ret = evsel__open(evsel, NULL, tmap) >= 0;
 		}
+
+		if (!ret) {
+			/*
+			 * The event may fail to open if the PMU requires
+			 * exclude_guest to be set (e.g. as the Apple M1 PMU
+			 * requires).
+			 * Re-run with exclude_guest set; we don't do that by
+			 * default as it's equally legitimate for another PMU
+			 * driver to require that exclude_guest is clear.
+			 */
+			evsel->core.attr.exclude_guest = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+
 		evsel__delete(evsel);
 	}
 
@@ -395,6 +401,8 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta
  */
 void print_events(const struct print_callbacks *print_cb, void *print_state)
 {
+	char *tmp;
+
 	print_symbol_events(print_cb, print_state, PERF_TYPE_HARDWARE,
 			event_symbols_hw, PERF_COUNT_HW_MAX);
 	print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE,
@@ -418,17 +426,21 @@ void print_events(const struct print_callbacks *print_cb, void *print_state)
 			/*long_desc=*/NULL,
 			/*encoding_desc=*/NULL);
 
-	print_cb->print_event(print_state,
-			/*topic=*/NULL,
-			/*pmu_name=*/NULL,
-			"cpu/t1=v1[,t2=v2,t3 ...]/modifier",
-			/*event_alias=*/NULL,
-			/*scale_unit=*/NULL,
-			/*deprecated=*/false,
-			event_type_descriptors[PERF_TYPE_RAW],
-			"(see 'man perf-list' on how to encode it)",
-			/*long_desc=*/NULL,
-			/*encoding_desc=*/NULL);
+	if (asprintf(&tmp, "%s/t1=v1[,t2=v2,t3 ...]/modifier",
+		     perf_pmus__scan_core(/*pmu=*/NULL)->name) > 0) {
+		print_cb->print_event(print_state,
+				/*topic=*/NULL,
+				/*pmu_name=*/NULL,
+				tmp,
+				/*event_alias=*/NULL,
+				/*scale_unit=*/NULL,
+				/*deprecated=*/false,
+				event_type_descriptors[PERF_TYPE_RAW],
+				"(see 'man perf-list' on how to encode it)",
+				/*long_desc=*/NULL,
+				/*encoding_desc=*/NULL);
+		free(tmp);
+	}
 
 	print_cb->print_event(print_state,
 			/*topic=*/NULL,
diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h
index d7fab411e75c..bf4290bef0cd 100644
--- a/tools/perf/util/print-events.h
+++ b/tools/perf/util/print-events.h
@@ -26,6 +26,7 @@ struct print_callbacks {
 			const char *expr,
 			const char *threshold,
 			const char *unit);
+	bool (*skip_duplicate_pmus)(void *print_state);
 };
 
 /** Print all events, the default when no options are specified. */
diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
new file mode 100644
index 000000000000..459e0e93d7b1
--- /dev/null
+++ b/tools/perf/util/print_insn.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Instruction binary disassembler based on capstone.
+ *
+ * Author(s): Changbin Du <changbin.du@huawei.com>
+ */
+#include <string.h>
+#include <stdbool.h>
+#include "debug.h"
+#include "sample.h"
+#include "symbol.h"
+#include "machine.h"
+#include "thread.h"
+#include "print_insn.h"
+
+size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
+{
+	int printed = 0;
+
+	for (int i = 0; i < sample->insn_len; i++) {
+		printed += fprintf(fp, "%02x", (unsigned char)sample->insn[i]);
+		if (sample->insn_len - i > 1)
+			printed += fprintf(fp, " ");
+	}
+	return printed;
+}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+#include <capstone/capstone.h>
+
+static int capstone_init(struct machine *machine, csh *cs_handle)
+{
+	cs_arch arch;
+	cs_mode mode;
+
+	if (machine__is(machine, "x86_64")) {
+		arch = CS_ARCH_X86;
+		mode = CS_MODE_64;
+	} else if (machine__normalized_is(machine, "x86")) {
+		arch = CS_ARCH_X86;
+		mode = CS_MODE_32;
+	} else if (machine__normalized_is(machine, "arm64")) {
+		arch = CS_ARCH_ARM64;
+		mode = CS_MODE_ARM;
+	} else if (machine__normalized_is(machine, "arm")) {
+		arch = CS_ARCH_ARM;
+		mode = CS_MODE_ARM + CS_MODE_V8;
+	} else if (machine__normalized_is(machine, "s390")) {
+		arch = CS_ARCH_SYSZ;
+		mode = CS_MODE_BIG_ENDIAN;
+	} else {
+		return -1;
+	}
+
+	if (cs_open(arch, mode, cs_handle) != CS_ERR_OK) {
+		pr_warning_once("cs_open failed\n");
+		return -1;
+	}
+
+	if (machine__normalized_is(machine, "x86")) {
+		cs_option(*cs_handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
+		/*
+		 * Resolving address operands to symbols is implemented
+		 * on x86 by investigating instruction details.
+		 */
+		cs_option(*cs_handle, CS_OPT_DETAIL, CS_OPT_ON);
+	}
+
+	return 0;
+}
+
+static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
+			     cs_insn *insn, FILE *fp)
+{
+	struct addr_location al;
+	size_t printed = 0;
+
+	if (insn->detail && insn->detail->x86.op_count == 1) {
+		cs_x86_op *op = &insn->detail->x86.operands[0];
+
+		addr_location__init(&al);
+		if (op->type == X86_OP_IMM &&
+		    thread__find_symbol(thread, sample->cpumode, op->imm, &al)) {
+			printed += fprintf(fp, "%s ", insn[0].mnemonic);
+			printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
+			addr_location__exit(&al);
+			return printed;
+		}
+		addr_location__exit(&al);
+	}
+
+	printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+	return printed;
+}
+
+size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
+				struct machine *machine, FILE *fp)
+{
+	csh cs_handle;
+	cs_insn *insn;
+	size_t count;
+	size_t printed = 0;
+	int ret;
+
+	/* TODO: Try to initiate capstone only once but need a proper place. */
+	ret = capstone_init(machine, &cs_handle);
+	if (ret < 0) {
+		/* fallback */
+		return sample__fprintf_insn_raw(sample, fp);
+	}
+
+	count = cs_disasm(cs_handle, (uint8_t *)sample->insn, sample->insn_len,
+			  sample->ip, 1, &insn);
+	if (count > 0) {
+		if (machine__normalized_is(machine, "x86"))
+			printed += print_insn_x86(sample, thread, &insn[0], fp);
+		else
+			printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+		cs_free(insn, count);
+	} else {
+		printed += fprintf(fp, "illegal instruction");
+	}
+
+	cs_close(&cs_handle);
+	return printed;
+}
+#else
+size_t sample__fprintf_insn_asm(struct perf_sample *sample __maybe_unused,
+				struct thread *thread __maybe_unused,
+				struct machine *machine __maybe_unused,
+				FILE *fp __maybe_unused)
+{
+	return 0;
+}
+#endif
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
new file mode 100644
index 000000000000..465bdcfcc2fd
--- /dev/null
+++ b/tools/perf/util/print_insn.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_PRINT_INSN_H
+#define PERF_PRINT_INSN_H
+
+#include <stddef.h>
+#include <stdio.h>
+
+struct perf_sample;
+struct thread;
+struct machine;
+
+size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
+				struct machine *machine, FILE *fp);
+size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
+
+#endif /* PERF_PRINT_INSN_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 16822a8a540f..2a0ad9ecf0a2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -53,6 +53,8 @@
 bool probe_event_dry_run;	/* Dry run flag */
 struct probe_conf probe_conf = { .magic_num = DEFAULT_PROBE_MAGIC_NUM };
 
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
 #define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
 int e_snprintf(char *str, size_t size, const char *format, ...)
@@ -147,10 +149,32 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	return 0;
 }
 
+struct kernel_get_module_map_cb_args {
+	const char *module;
+	struct map *result;
+};
+
+static int kernel_get_module_map_cb(struct map *map, void *data)
+{
+	struct kernel_get_module_map_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+	const char *short_name = dso->short_name; /* short_name is "[module]" */
+	u16 short_name_len =  dso->short_name_len;
+
+	if (strncmp(short_name + 1, args->module, short_name_len - 2) == 0 &&
+	    args->module[short_name_len - 2] == '\0') {
+		args->result = map__get(map);
+		return 1;
+	}
+	return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct maps *maps = machine__kernel_maps(host_machine);
-	struct map_rb_node *pos;
+	struct kernel_get_module_map_cb_args args = {
+		.module = module,
+		.result = NULL,
+	};
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
@@ -162,19 +186,9 @@ static struct map *kernel_get_module_map(const char *module)
 		return map__get(map);
 	}
 
-	maps__for_each_entry(maps, pos) {
-		/* short_name is "[module]" */
-		struct dso *dso = map__dso(pos->map);
-		const char *short_name = dso->short_name;
-		u16 short_name_len =  dso->short_name_len;
+	maps__for_each_map(machine__kernel_maps(host_machine), kernel_get_module_map_cb, &args);
 
-		if (strncmp(short_name + 1, module,
-			    short_name_len - 2) == 0 &&
-		    module[short_name_len - 2] == '\0') {
-			return map__get(pos->map);
-		}
-	}
-	return NULL;
+	return args.result;
 }
 
 struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
@@ -344,6 +358,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 		map = maps__find_by_name(machine__kernel_maps(host_machine), module_name);
 		if (map) {
 			dso = map__dso(map);
+			map__put(map);
 			goto found;
 		}
 		pr_debug("Failed to find module %s.\n", module);
@@ -961,8 +976,9 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	debuginfo__delete(dinfo);
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found.\n",
-			   synthesize_perf_probe_point(&pev->point));
+		char *probe_point = synthesize_perf_probe_point(&pev->point);
+		pr_warning("Probe point '%s' not found.\n", probe_point);
+		free(probe_point);
 		return -ENODEV;
 	} else if (ntevs < 0) {
 		/* Error path : ntevs < 0 */
@@ -2009,7 +2025,7 @@ out:
 }
 
 /* Compose only probe point (not argument) */
-char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
 	struct strbuf buf;
 	char *tmp, *ret = NULL;
@@ -2062,14 +2078,18 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 			goto out;
 
 	tmp = synthesize_perf_probe_point(&pev->point);
-	if (!tmp || strbuf_addstr(&buf, tmp) < 0)
+	if (!tmp || strbuf_addstr(&buf, tmp) < 0) {
+		free(tmp);
 		goto out;
+	}
 	free(tmp);
 
 	for (i = 0; i < pev->nargs; i++) {
 		tmp = synthesize_perf_probe_arg(pev->args + i);
-		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0)
+		if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0) {
+			free(tmp);
 			goto out;
+		}
 		free(tmp);
 	}
 
@@ -2254,9 +2274,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 	ret = pp->function ? 0 : -ENOMEM;
 
 out:
-	if (map && !is_kprobe) {
-		map__put(map);
-	}
+	map__put(map);
 
 	return ret;
 }
@@ -2800,13 +2818,18 @@ static void warn_uprobe_event_compat(struct probe_trace_event *tev)
 	if (!tev->uprobes || tev->nargs == 0 || !buf)
 		goto out;
 
-	for (i = 0; i < tev->nargs; i++)
-		if (strglobmatch(tev->args[i].value, "[$@+-]*")) {
-			pr_warning("Please upgrade your kernel to at least "
-				   "3.14 to have access to feature %s\n",
+	for (i = 0; i < tev->nargs; i++) {
+		if (strchr(tev->args[i].value, '@')) {
+			pr_warning("%s accesses a variable by symbol name, but that is not supported for user application probe.\n",
+				   tev->args[i].value);
+			break;
+		}
+		if (strglobmatch(tev->args[i].value, "[$+-]*")) {
+			pr_warning("Please upgrade your kernel to at least 3.14 to have access to feature %s\n",
 				   tev->args[i].value);
 			break;
 		}
+	}
 out:
 	free(buf);
 }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 8ad5b1579f1d..7e3b6c3d1f74 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -137,7 +137,6 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
-char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 
 int perf_probe_event__copy(struct perf_probe_event *dst,
 			   struct perf_probe_event *src);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f171360b0ef4..c8923375e30d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -23,6 +23,7 @@
 #include "event.h"
 #include "dso.h"
 #include "debug.h"
+#include "debuginfo.h"
 #include "intlist.h"
 #include "strbuf.h"
 #include "strlist.h"
@@ -31,128 +32,9 @@
 #include "probe-file.h"
 #include "string2.h"
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-#include <elfutils/debuginfod.h>
-#endif
-
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/* Dwarf FL wrappers */
-static char *debuginfo_path;	/* Currently dummy */
-
-static const Dwfl_Callbacks offline_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.section_address = dwfl_offline_section_address,
-
-	/* We use this table for core files too.  */
-	.find_elf = dwfl_build_id_find_elf,
-};
-
-/* Get a Dwarf from offline image */
-static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
-					 const char *path)
-{
-	GElf_Addr dummy;
-	int fd;
-
-	fd = open(path, O_RDONLY);
-	if (fd < 0)
-		return fd;
-
-	dbg->dwfl = dwfl_begin(&offline_callbacks);
-	if (!dbg->dwfl)
-		goto error;
-
-	dwfl_report_begin(dbg->dwfl);
-	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
-	if (!dbg->mod)
-		goto error;
-
-	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
-	if (!dbg->dbg)
-		goto error;
-
-	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
-
-	dwfl_report_end(dbg->dwfl, NULL, NULL);
-
-	return 0;
-error:
-	if (dbg->dwfl)
-		dwfl_end(dbg->dwfl);
-	else
-		close(fd);
-	memset(dbg, 0, sizeof(*dbg));
-
-	return -ENOENT;
-}
-
-static struct debuginfo *__debuginfo__new(const char *path)
-{
-	struct debuginfo *dbg = zalloc(sizeof(*dbg));
-	if (!dbg)
-		return NULL;
-
-	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
-		zfree(&dbg);
-	if (dbg)
-		pr_debug("Open Debuginfo file: %s\n", path);
-	return dbg;
-}
-
-enum dso_binary_type distro_dwarf_types[] = {
-	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
-	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
-	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
-	DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
-	DSO_BINARY_TYPE__NOT_FOUND,
-};
-
-struct debuginfo *debuginfo__new(const char *path)
-{
-	enum dso_binary_type *type;
-	char buf[PATH_MAX], nil = '\0';
-	struct dso *dso;
-	struct debuginfo *dinfo = NULL;
-	struct build_id bid;
-
-	/* Try to open distro debuginfo files */
-	dso = dso__new(path);
-	if (!dso)
-		goto out;
-
-	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
-	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
-		dso__set_build_id(dso, &bid);
-
-	for (type = distro_dwarf_types;
-	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
-	     type++) {
-		if (dso__read_binary_type_filename(dso, *type, &nil,
-						   buf, PATH_MAX) < 0)
-			continue;
-		dinfo = __debuginfo__new(buf);
-	}
-	dso__put(dso);
-
-out:
-	/* if failed to open all distro debuginfo, open given binary */
-	return dinfo ? : __debuginfo__new(path);
-}
-
-void debuginfo__delete(struct debuginfo *dbg)
-{
-	if (dbg) {
-		if (dbg->dwfl)
-			dwfl_end(dbg->dwfl);
-		free(dbg);
-	}
-}
-
 /*
  * Probe finder related functions
  */
@@ -722,7 +604,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1);
 	if (ret <= 0 || nops == 0) {
 		pf->fb_ops = NULL;
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
 		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
@@ -733,7 +615,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 			free(frame);
 			return -ENOENT;
 		}
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 	}
 
 	/* Call finder's callback handler */
@@ -1258,7 +1140,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 	pf->machine = ehdr.e_machine;
 
-#if _ELFUTILS_PREREQ(0, 142)
+#ifdef HAVE_DWARF_CFI_SUPPORT
 	do {
 		GElf_Shdr shdr;
 
@@ -1268,7 +1150,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 		pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
 	} while (0);
-#endif
+#endif /* HAVE_DWARF_CFI_SUPPORT */
 
 	ret = debuginfo__find_probe_location(dbg, pf);
 	return ret;
@@ -1677,44 +1559,6 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	return (ret < 0) ? ret : af.nvls;
 }
 
-/* For the kernel module, we need a special code to get a DIE */
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-				bool adjust_offset)
-{
-	int n, i;
-	Elf32_Word shndx;
-	Elf_Scn *scn;
-	Elf *elf;
-	GElf_Shdr mem, *shdr;
-	const char *p;
-
-	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
-	if (!elf)
-		return -EINVAL;
-
-	/* Get the number of relocations */
-	n = dwfl_module_relocations(dbg->mod);
-	if (n < 0)
-		return -ENOENT;
-	/* Search the relocation related .text section */
-	for (i = 0; i < n; i++) {
-		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
-		if (strcmp(p, ".text") == 0) {
-			/* OK, get the section header */
-			scn = elf_getscn(elf, shndx);
-			if (!scn)
-				return -ENOENT;
-			shdr = gelf_getshdr(scn, &mem);
-			if (!shdr)
-				return -ENOENT;
-			*offs = shdr->sh_addr;
-			if (adjust_offset)
-				*offs -= shdr->sh_offset;
-		}
-	}
-	return 0;
-}
-
 /* Reverse search */
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt)
@@ -2009,41 +1853,6 @@ found:
 	return (ret < 0) ? ret : lf.found;
 }
 
-#ifdef HAVE_DEBUGINFOD_SUPPORT
-/* debuginfod doesn't require the comp_dir but buildid is required */
-static int get_source_from_debuginfod(const char *raw_path,
-				const char *sbuild_id, char **new_path)
-{
-	debuginfod_client *c = debuginfod_begin();
-	const char *p = raw_path;
-	int fd;
-
-	if (!c)
-		return -ENOMEM;
-
-	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
-				0, p, new_path);
-	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
-	if (fd >= 0)
-		close(fd);
-	debuginfod_end(c);
-	if (fd < 0) {
-		pr_debug("Failed to find %s in debuginfod (%s)\n",
-			raw_path, sbuild_id);
-		return -ENOENT;
-	}
-	pr_debug("Got a source %s\n", *new_path);
-
-	return 0;
-}
-#else
-static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
-				const char *sbuild_id __maybe_unused,
-				char **new_path __maybe_unused)
-{
-	return -ENOTSUP;
-}
-#endif
 /*
  * Find a src file from a DWARF tag path. Prepend optional source path prefix
  * and chop off leading directories that do not exist. Result is passed back as
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 8bc1c80d3c1c..3add5ff516e1 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -24,21 +24,7 @@ static inline int is_c_varname(const char *name)
 #ifdef HAVE_DWARF_SUPPORT
 
 #include "dwarf-aux.h"
-
-/* TODO: export debuginfo data structure even if no dwarf support */
-
-/* debug information structure */
-struct debuginfo {
-	Dwarf		*dbg;
-	Dwfl_Module	*mod;
-	Dwfl		*dwfl;
-	Dwarf_Addr	bias;
-	const unsigned char	*build_id;
-};
-
-/* This also tries to open distro debuginfo */
-struct debuginfo *debuginfo__new(const char *path);
-void debuginfo__delete(struct debuginfo *dbg);
+#include "debuginfo.h"
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
@@ -49,9 +35,6 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
 				struct perf_probe_point *ppt);
 
-int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
-			       bool adjust_offset);
-
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index d4c9b4cd35ef..1bec945f4838 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -31,6 +31,7 @@ util/counts.c
 util/print_binary.c
 util/strlist.c
 util/trace-event.c
+util/trace-event-parse.c
 ../lib/rbtree.c
 util/string.c
 util/symbol_fprintf.c
@@ -40,3 +41,13 @@ util/rwsem.c
 util/hashmap.c
 util/perf_regs.c
 util/fncache.c
+util/rlimit.c
+util/perf-regs-arch/perf_regs_aarch64.c
+util/perf-regs-arch/perf_regs_arm.c
+util/perf-regs-arch/perf_regs_csky.c
+util/perf-regs-arch/perf_regs_loongarch.c
+util/perf-regs-arch/perf_regs_mips.c
+util/perf-regs-arch/perf_regs_powerpc.c
+util/perf-regs-arch/perf_regs_riscv.c
+util/perf-regs-arch/perf_regs_s390.c
+util/perf-regs-arch/perf_regs_x86.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4eed8ec23994..075c0f79b1b9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -98,7 +98,7 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused)
 	return NULL;
 }
 
-int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...)
+int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...)
 {
 	return EOF;
 }
@@ -113,6 +113,11 @@ bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused)
 	return false;
 }
 
+bool perf_pmus__supports_extended_type(void)
+{
+	return false;
+}
+
 /*
  * Add this one here not to drag util/metricgroup.c
  */
@@ -176,6 +181,7 @@ int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused)
  * implementing 'verbose' and 'eprintf'.
  */
 int verbose;
+int debug_kmaps;
 int debug_peo_args;
 
 int eprintf(int level, int var, const char *fmt, ...);
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index 376e86cb4c3c..d927a0d25052 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -143,9 +143,4 @@ struct __name##_sorted *__name = __name##_sorted__new
 	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.rb_root, \
-			   __machine->threads[hash_bucket].nr)
-
 #endif /* _PERF_RESORT_RB_H_ */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 9eb5c6a08999..87e817b3cf7e 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -237,8 +237,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) {
-		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
+	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
+		struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 
 		if (cpus)
 			cpu =  perf_cpu_map__cpu(cpus, 0);
diff --git a/tools/perf/util/rlimit.c b/tools/perf/util/rlimit.c
index 13521d392a22..f857405fe1aa 100644
--- a/tools/perf/util/rlimit.c
+++ b/tools/perf/util/rlimit.c
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: LGPL-2.1 */
 
+#include <errno.h>
 #include "util/debug.h"
 #include "util/rlimit.h"
 #include <sys/time.h>
@@ -27,3 +28,30 @@ void rlimit__bump_memlock(void)
 		}
 	}
 }
+
+bool rlimit__increase_nofile(enum rlimit_action *set_rlimit)
+{
+	int old_errno;
+	struct rlimit l;
+
+	if (*set_rlimit < INCREASED_MAX) {
+		old_errno = errno;
+
+		if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+			if (*set_rlimit == NO_CHANGE) {
+				l.rlim_cur = l.rlim_max;
+			} else {
+				l.rlim_cur = l.rlim_max + 1000;
+				l.rlim_max = l.rlim_cur;
+			}
+			if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
+				(*set_rlimit) += 1;
+				errno = old_errno;
+				return true;
+			}
+		}
+		errno = old_errno;
+	}
+
+	return false;
+}
diff --git a/tools/perf/util/rlimit.h b/tools/perf/util/rlimit.h
index 9f59d8e710a3..19050d7fb9d7 100644
--- a/tools/perf/util/rlimit.h
+++ b/tools/perf/util/rlimit.h
@@ -1,6 +1,15 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
 #ifndef __PERF_RLIMIT_H_
 #define __PERF_RLIMIT_H_
-/* SPDX-License-Identifier: LGPL-2.1 */
+
+enum rlimit_action {
+	NO_CHANGE,
+	SET_TO_MAX,
+	INCREASED_MAX
+};
 
 void rlimit__bump_memlock(void);
+
+bool rlimit__increase_nofile(enum rlimit_action *set_rlimit);
+
 #endif // __PERF_RLIMIT_H_
diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c
index f3d29d8ddc99..5109167f27f7 100644
--- a/tools/perf/util/rwsem.c
+++ b/tools/perf/util/rwsem.c
@@ -2,32 +2,66 @@
 #include "util.h"
 #include "rwsem.h"
 
+#if RWS_ERRORCHECK
+#include "mutex.h"
+#endif
+
 int init_rwsem(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_init(&sem->mtx);
+	return 0;
+#else
 	return pthread_rwlock_init(&sem->lock, NULL);
+#endif
 }
 
 int exit_rwsem(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_destroy(&sem->mtx);
+	return 0;
+#else
 	return pthread_rwlock_destroy(&sem->lock);
+#endif
 }
 
 int down_read(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_lock(&sem->mtx);
+	return 0;
+#else
 	return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock);
+#endif
 }
 
 int up_read(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_unlock(&sem->mtx);
+	return 0;
+#else
 	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+#endif
 }
 
 int down_write(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_lock(&sem->mtx);
+	return 0;
+#else
 	return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock);
+#endif
 }
 
 int up_write(struct rw_semaphore *sem)
 {
+#if RWS_ERRORCHECK
+	mutex_unlock(&sem->mtx);
+	return 0;
+#else
 	return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock);
+#endif
 }
diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h
index 94565ad4d494..ef5cbc31d967 100644
--- a/tools/perf/util/rwsem.h
+++ b/tools/perf/util/rwsem.h
@@ -2,9 +2,20 @@
 #define _PERF_RWSEM_H
 
 #include <pthread.h>
+#include "mutex.h"
+
+/*
+ * Mutexes have additional error checking. Enable to use a mutex rather than a
+ * rwlock for debugging.
+ */
+#define RWS_ERRORCHECK 0
 
 struct rw_semaphore {
+#if RWS_ERRORCHECK
+	struct mutex mtx;
+#else
 	pthread_rwlock_t lock;
+#endif
 };
 
 int init_rwsem(struct rw_semaphore *sem);
diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
index f55ca07f3ca1..74b36644e384 100644
--- a/tools/perf/util/s390-cpumcf-kernel.h
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -12,6 +12,8 @@
 #define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
 #define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
 #define PERF_EVENT_CPUM_SF_DIAG	0xBD000 /* Event: Combined-sampling */
+#define PERF_EVENT_PAI_CRYPTO_ALL	0x1000 /* Event: CRYPTO_ALL */
+#define PERF_EVENT_PAI_NNPA_ALL	0x1800 /* Event: NNPA_ALL */
 
 struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
 	unsigned int def:16;	/* 0-15  Data Entry Format */
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index c10b891dbad6..53383e97ec9d 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -27,7 +27,7 @@
 #include "color.h"
 #include "sample-raw.h"
 #include "s390-cpumcf-kernel.h"
-#include "pmu-events/pmu-events.h"
+#include "util/pmu.h"
 #include "util/sample.h"
 
 static size_t ctrset_size(struct cf_ctrset_entry *set)
@@ -51,8 +51,6 @@ static bool s390_cpumcfdg_testctr(struct perf_sample *sample)
 	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);
@@ -125,6 +123,9 @@ static int get_counterset_start(int setnr)
 		return 128;
 	case CPUMF_CTR_SET_MT_DIAG:		/* Diagnostic counter set */
 		return 448;
+	case PERF_EVENT_PAI_NNPA_ALL:		/* PAI NNPA counter set */
+	case PERF_EVENT_PAI_CRYPTO_ALL:		/* PAI CRYPTO counter set */
+		return setnr;
 	default:
 		return -1;
 	}
@@ -132,56 +133,58 @@ static int get_counterset_start(int setnr)
 
 struct get_counter_name_data {
 	int wanted;
-	const char *result;
+	char *result;
 };
 
-static int get_counter_name_callback(const struct pmu_event *evp,
-				     const struct pmu_events_table *table __maybe_unused,
-				     void *vdata)
+static int get_counter_name_callback(void *vdata, struct pmu_event_info *info)
 {
 	struct get_counter_name_data *data = vdata;
 	int rc, event_nr;
+	const char *event_str;
+
+	if (info->str == NULL)
+		return 0;
 
-	if (evp->name == NULL || evp->event == NULL)
+	event_str = strstr(info->str, "event=");
+	if (!event_str)
 		return 0;
-	rc = sscanf(evp->event, "event=%x", &event_nr);
+
+	rc = sscanf(event_str, "event=%x", &event_nr);
 	if (rc == 1 && event_nr == data->wanted) {
-		data->result = evp->name;
+		data->result = strdup(info->name);
 		return 1; /* Terminate the search. */
 	}
 	return 0;
 }
 
-/* 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.
+/* Scan the PMU and extract the logical name of a counter from the event. 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, const struct pmu_events_table *table)
+static char *get_counter_name(int set, int nr, struct perf_pmu *pmu)
 {
 	struct get_counter_name_data data = {
 		.wanted = get_counterset_start(set) + nr,
 		.result = NULL,
 	};
 
-	if (!table)
+	if (!pmu)
 		return NULL;
 
-	pmu_events_table_for_each_event(table, get_counter_name_callback, &data);
+	perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/ true,
+				 &data, get_counter_name_callback);
 	return data.result;
 }
 
-static void s390_cpumcfdg_dump(struct perf_sample *sample)
+static void s390_cpumcfdg_dump(struct perf_pmu *pmu, 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;
-	const struct pmu_events_table *table;
 	u64 *p;
 
-	table = pmu_events_table__find();
 	while (offset < len) {
 		cep = (struct cf_ctrset_entry *)(buf + offset);
 
@@ -199,37 +202,131 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample)
 		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, table);
+			char *ev_name = get_counter_name(ce.set, i, pmu);
 
 			color_fprintf(stdout, color,
 				      "\tCounter:%03d %s Value:%#018lx\n", i,
 				      ev_name ?: "<unknown>", be64_to_cpu(*p));
+			free(ev_name);
 		}
 		offset += ctrset_size(&ce);
 	}
 }
 
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wpacked"
+#pragma GCC diagnostic ignored "-Wattributes"
+/*
+ * Check for consistency of PAI_CRYPTO/PAI_NNPA raw data.
+ */
+struct pai_data {		/* Event number and value */
+	u16 event_nr;
+	u64 event_val;
+} __packed;
+
+#pragma GCC diagnostic pop
+
+/*
+ * Test for valid raw data. At least one PAI event should be in the raw
+ * data section.
+ */
+static bool s390_pai_all_test(struct perf_sample *sample)
+{
+	size_t len = sample->raw_size;
+
+	if (len < 0xa)
+		return false;
+	return true;
+}
+
+static void s390_pai_all_dump(struct evsel *evsel, struct perf_sample *sample)
+{
+	size_t len = sample->raw_size, offset = 0;
+	unsigned char *p = sample->raw_data;
+	const char *color = PERF_COLOR_BLUE;
+	struct pai_data pai_data;
+	char *ev_name;
+
+	while (offset < len) {
+		memcpy(&pai_data.event_nr, p, sizeof(pai_data.event_nr));
+		pai_data.event_nr = be16_to_cpu(pai_data.event_nr);
+		p += sizeof(pai_data.event_nr);
+		offset += sizeof(pai_data.event_nr);
+
+		memcpy(&pai_data.event_val, p, sizeof(pai_data.event_val));
+		pai_data.event_val = be64_to_cpu(pai_data.event_val);
+		p += sizeof(pai_data.event_val);
+		offset += sizeof(pai_data.event_val);
+
+		ev_name = get_counter_name(evsel->core.attr.config,
+					   pai_data.event_nr, evsel->pmu);
+		color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n",
+			      pai_data.event_nr, ev_name ?: "<unknown>",
+			      pai_data.event_val);
+		free(ev_name);
+
+		if (offset + 0xa > len)
+			break;
+	}
+	color_fprintf(stdout, color, "\n");
+}
+
 /* 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.
+ * and if the event was triggered by a
+ * - counter set diagnostic event
+ * - processor activity assist (PAI) crypto counter event
+ * - processor activity assist (PAI) neural network processor assist (NNPA)
+ *   counter event
+ * display its raw data.
  * The function is only invoked when the dump flag -D is set.
+ *
+ * Function evlist__s390_sample_raw() is defined as call back after it has
+ * been verified that the perf.data file was created on s390 platform.
  */
-void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
+			     struct perf_sample *sample)
 {
-	struct evsel *ev_bc000;
+	const char *pai_name;
+	struct evsel *evsel;
 
 	if (event->header.type != PERF_RECORD_SAMPLE)
 		return;
 
-	ev_bc000 = evlist__event2evsel(evlist, event);
-	if (ev_bc000 == NULL ||
-	    ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
+	evsel = evlist__event2evsel(evlist, event);
+	if (!evsel)
+		return;
+
+	/* Check for raw data in sample */
+	if (!sample->raw_size || !sample->raw_data)
 		return;
 
 	/* Display raw data on screen */
-	if (!s390_cpumcfdg_testctr(sample)) {
-		pr_err("Invalid counter set data encountered\n");
+	if (evsel->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find("cpum_cf");
+		if (!s390_cpumcfdg_testctr(sample))
+			pr_err("Invalid counter set data encountered\n");
+		else
+			s390_cpumcfdg_dump(evsel->pmu, sample);
 		return;
 	}
-	s390_cpumcfdg_dump(sample);
+
+	switch (evsel->core.attr.config) {
+	case PERF_EVENT_PAI_NNPA_ALL:
+		pai_name = "NNPA_ALL";
+		break;
+	case PERF_EVENT_PAI_CRYPTO_ALL:
+		pai_name = "CRYPTO_ALL";
+		break;
+	default:
+		return;
+	}
+
+	if (!s390_pai_all_test(sample)) {
+		pr_err("Invalid %s raw data encountered\n", pai_name);
+	} else {
+		if (!evsel->pmu)
+			evsel->pmu = perf_pmus__find_by_type(evsel->core.attr.type);
+		s390_pai_all_dump(evsel, sample);
+	}
 }
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index c92ad0f51ecd..70b2c3135555 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -113,6 +113,7 @@ struct perf_sample {
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
+	u64 *branch_stack_cntr;
 	struct regs_dump  user_regs;
 	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index c220fec97032..586b94e90f4e 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -5,4 +5,5 @@ 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 -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
 
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum
+# -Wno-declaration-after-statement: The python headers have mixed code with declarations (decls after asserts, for instance)
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-deprecated-declarations -Wno-switch-enum -Wno-declaration-after-statement
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 603091317bed..b072ac5d3bc2 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -490,6 +490,9 @@ static int perl_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 
 	command_line = malloc((argc + 2) * sizeof(const char *));
+	if (!command_line)
+		return -ENOMEM;
+
 	command_line[0] = "";
 	command_line[1] = script;
 	for (i = 2; i < argc + 2; i++)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 94312741443a..b4f0f60e60a6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -353,6 +353,8 @@ static PyObject *get_field_numeric_entry(struct tep_event *event,
 
 	if (is_array) {
 		list = PyList_New(field->arraylen);
+		if (!list)
+			Py_FatalError("couldn't create Python list");
 		item_size = field->size / field->arraylen;
 		n_items = field->arraylen;
 	} else {
@@ -754,7 +756,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch
 	}
 }
 
-static void set_regs_in_dict(PyObject *dict,
+static int set_regs_in_dict(PyObject *dict,
 			     struct perf_sample *sample,
 			     struct evsel *evsel)
 {
@@ -770,6 +772,8 @@ static void set_regs_in_dict(PyObject *dict,
 	 */
 	int size = __sw_hweight64(attr->sample_regs_intr) * 28;
 	char *bf = malloc(size);
+	if (!bf)
+		return -1;
 
 	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size);
 
@@ -781,6 +785,8 @@ static void set_regs_in_dict(PyObject *dict,
 	pydict_set_item_string_decref(dict, "uregs",
 			_PyUnicode_FromString(bf));
 	free(bf);
+
+	return 0;
 }
 
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
@@ -852,6 +858,10 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(evsel__name(evsel)));
 	pydict_set_item_string_decref(dict, "attr", _PyBytes_FromStringAndSize((const char *)&evsel->core.attr, sizeof(evsel->core.attr)));
 
+	pydict_set_item_string_decref(dict_sample, "id",
+			PyLong_FromUnsignedLongLong(sample->id));
+	pydict_set_item_string_decref(dict_sample, "stream_id",
+			PyLong_FromUnsignedLongLong(sample->stream_id));
 	pydict_set_item_string_decref(dict_sample, "pid",
 			_PyLong_FromLong(sample->pid));
 	pydict_set_item_string_decref(dict_sample, "tid",
@@ -920,7 +930,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->cyc_cnt));
 	}
 
-	set_regs_in_dict(dict, sample, evsel);
+	if (set_regs_in_dict(dict, sample, evsel))
+		Py_FatalError("Failed to setting regs in dict");
 
 	return dict;
 }
@@ -1299,7 +1310,7 @@ static void python_export_sample_table(struct db_export *dbe,
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(25);
+	t = tuple_new(27);
 
 	tuple_set_d64(t, 0, es->db_id);
 	tuple_set_d64(t, 1, es->evsel->db_id);
@@ -1326,6 +1337,8 @@ static void python_export_sample_table(struct db_export *dbe,
 	tuple_set_d64(t, 22, es->sample->insn_cnt);
 	tuple_set_d64(t, 23, es->sample->cyc_cnt);
 	tuple_set_s32(t, 24, es->sample->flags);
+	tuple_set_d64(t, 25, es->sample->id);
+	tuple_set_d64(t, 26, es->sample->stream_id);
 
 	call_object(tables->sample_handler, t, "sample_table");
 
@@ -1918,12 +1931,18 @@ static int python_start_script(const char *script, int argc, const char **argv,
 	scripting_context->session = session;
 #if PY_MAJOR_VERSION < 3
 	command_line = malloc((argc + 1) * sizeof(const char *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
 	PyImport_AppendInittab(name, initperf_trace_context);
 #else
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
+	if (!command_line)
+		return -1;
+
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 00d18c74c090..06d0bd7fb459 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -115,6 +115,11 @@ static int perf_session__open(struct perf_session *session, int repipe_fd)
 		return -1;
 	}
 
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) {
+		/* Auxiliary events may reference exited threads, hold onto dead ones. */
+		symbol_conf.keep_exited_threads = true;
+	}
+
 	if (perf_data__is_pipe(data))
 		return 0;
 
@@ -833,8 +838,8 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 	perf_event__attr_swap(&event->attr.attr);
 
 	size = event->header.size;
-	size -= (void *)&event->attr.id - (void *)event;
-	mem_bswap_64(event->attr.id, size);
+	size -= perf_record_header_attr_id(event) - (void *)event;
+	mem_bswap_64(perf_record_header_attr_id(event), size);
 }
 
 static void perf_event__event_update_swap(union perf_event *event,
@@ -1150,9 +1155,13 @@ static void callchain__printf(struct evsel *evsel,
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample, bool callstack)
+static void branch_stack__printf(struct perf_sample *sample,
+				 struct evsel *evsel)
 {
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
+	bool callstack = evsel__has_branch_callstack(evsel);
+	u64 *branch_stack_cntr = sample->branch_stack_cntr;
+	struct perf_env *env = evsel__env(evsel);
 	uint64_t i;
 
 	if (!callstack) {
@@ -1194,6 +1203,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 			}
 		}
 	}
+
+	if (branch_stack_cntr) {
+		printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n",
+			sample->branch_stack->nr, env->br_cntr_width, env->br_cntr_nr);
+		for (i = 0; i < sample->branch_stack->nr; i++)
+			printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]);
+	}
 }
 
 static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
@@ -1355,7 +1371,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		callchain__printf(evsel, sample);
 
 	if (evsel__has_br_stack(evsel))
-		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
+		branch_stack__printf(sample, evsel);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample, arch);
@@ -2704,6 +2720,17 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
 	return machine__fprintf(&session->machines.host, fp);
 }
 
+void perf_session__dump_kmaps(struct perf_session *session)
+{
+	int save_verbose = verbose;
+
+	fflush(stdout);
+	fprintf(stderr, "Kernel and module maps:\n");
+	verbose = 0; /* Suppress verbose to print a summary only */
+	maps__fprintf(machine__kernel_maps(&session->machines.host), stderr);
+	verbose = save_verbose;
+}
+
 struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index ee3715e8563b..5064c6ec11e7 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -133,6 +133,8 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp,
 				       bool skip_empty);
 
+void perf_session__dump_kmaps(struct perf_session *session);
+
 struct evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 869738fc06c3..3107f5aa8c9a 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -66,6 +66,9 @@ if cc_is_clang:
 else:
     cflags += ['-Wno-cast-function-type' ]
 
+# The python headers have mixed code with declarations (decls after asserts, for instance)
+cflags += [ "-Wno-declaration-after-statement" ]
+
 src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
@@ -82,6 +85,7 @@ if '-DHAVE_LIBTRACEEVENT' in cflags:
     extra_libraries += [ 'traceevent' ]
 else:
     ext_sources.remove('util/trace-event.c')
+    ext_sources.remove('util/trace-event-parse.c')
 
 # use full paths with source files
 ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 6aa1c7f2b444..92a1bd695e8a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -24,6 +24,7 @@
 #include "strbuf.h"
 #include "mem-events.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "event.h"
 #include "time-utils.h"
 #include "cgroup.h"
@@ -128,7 +129,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void
 	if (type != HIST_FILTER__THREAD)
 		return -1;
 
-	return th && RC_CHK_ACCESS(he->thread) != RC_CHK_ACCESS(th);
+	return th && !RC_CHK_EQUAL(he->thread, th);
 }
 
 struct sort_entry sort_thread = {
@@ -418,6 +419,52 @@ struct sort_entry sort_sym = {
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
+/* --sort symoff */
+
+static int64_t
+sort__symoff_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_cmp(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int64_t
+sort__symoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	int64_t ret;
+
+	ret = sort__sym_sort(left, right);
+	if (ret)
+		return ret;
+
+	return left->ip - right->ip;
+}
+
+static int
+hist_entry__symoff_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width)
+{
+	struct symbol *sym = he->ms.sym;
+
+	if (sym == NULL)
+		return repsep_snprintf(bf, size, "[%c] %-#.*llx", he->level, width - 4, he->ip);
+
+	return repsep_snprintf(bf, size, "[%c] %s+0x%llx", he->level, sym->name, he->ip - sym->start);
+}
+
+struct sort_entry sort_sym_offset = {
+	.se_header	= "Symbol Offset",
+	.se_cmp		= sort__symoff_cmp,
+	.se_sort	= sort__symoff_sort,
+	.se_snprintf	= hist_entry__symoff_snprintf,
+	.se_filter	= hist_entry__sym_filter,
+	.se_width_idx	= HISTC_SYMBOL_OFFSET,
+};
+
 /* --sort srcline */
 
 char *hist_entry__srcline(struct hist_entry *he)
@@ -583,21 +630,21 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf,
 {
 
 	struct symbol *sym = he->ms.sym;
-	struct annotation *notes;
+	struct annotated_branch *branch;
 	double ipc = 0.0, coverage = 0.0;
 	char tmp[64];
 
 	if (!sym)
 		return repsep_snprintf(bf, size, "%-*s", width, "-");
 
-	notes = symbol__annotation(sym);
+	branch = symbol__annotation(sym)->branch;
 
-	if (notes->hit_cycles)
-		ipc = notes->hit_insn / ((double)notes->hit_cycles);
+	if (branch && branch->hit_cycles)
+		ipc = branch->hit_insn / ((double)branch->hit_cycles);
 
-	if (notes->total_insn) {
-		coverage = notes->cover_insn * 100.0 /
-			((double)notes->total_insn);
+	if (branch && branch->total_insn) {
+		coverage = branch->cover_insn * 100.0 /
+			((double)branch->total_insn);
 	}
 
 	snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage);
@@ -2094,7 +2141,7 @@ struct sort_entry sort_dso_size = {
 	.se_width_idx	= HISTC_DSO_SIZE,
 };
 
-/* --sort dso_size */
+/* --sort addr */
 
 static int64_t
 sort__addr_cmp(struct hist_entry *left, struct hist_entry *right)
@@ -2131,6 +2178,152 @@ struct sort_entry sort_addr = {
 	.se_width_idx	= HISTC_ADDR,
 };
 
+/* --sort type */
+
+struct annotated_data_type unknown_type = {
+	.self = {
+		.type_name = (char *)"(unknown)",
+		.children = LIST_HEAD_INIT(unknown_type.self.children),
+	},
+};
+
+static int64_t
+sort__type_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__addr_cmp(left, right);
+}
+
+static void sort__type_init(struct hist_entry *he)
+{
+	if (he->mem_type)
+		return;
+
+	he->mem_type = hist_entry__get_data_type(he);
+	if (he->mem_type == NULL) {
+		he->mem_type = &unknown_type;
+		he->mem_type_off = 0;
+	}
+}
+
+static int64_t
+sort__type_collapse(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	return strcmp(left_type->self.type_name, right_type->self.type_name);
+}
+
+static int64_t
+sort__type_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	return sort__type_collapse(left, right);
+}
+
+static int hist_entry__type_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*s", width, he->mem_type->self.type_name);
+}
+
+struct sort_entry sort_type = {
+	.se_header	= "Data Type",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__type_collapse,
+	.se_sort	= sort__type_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__type_snprintf,
+	.se_width_idx	= HISTC_TYPE,
+};
+
+/* --sort typeoff */
+
+static int64_t
+sort__typeoff_sort(struct hist_entry *left, struct hist_entry *right)
+{
+	struct annotated_data_type *left_type = left->mem_type;
+	struct annotated_data_type *right_type = right->mem_type;
+	int64_t ret;
+
+	if (!left_type) {
+		sort__type_init(left);
+		left_type = left->mem_type;
+	}
+
+	if (!right_type) {
+		sort__type_init(right);
+		right_type = right->mem_type;
+	}
+
+	ret = strcmp(left_type->self.type_name, right_type->self.type_name);
+	if (ret)
+		return ret;
+	return left->mem_type_off - right->mem_type_off;
+}
+
+static void fill_member_name(char *buf, size_t sz, struct annotated_member *m,
+			     int offset, bool first)
+{
+	struct annotated_member *child;
+
+	if (list_empty(&m->children))
+		return;
+
+	list_for_each_entry(child, &m->children, node) {
+		if (child->offset <= offset && offset < child->offset + child->size) {
+			int len = 0;
+
+			/* It can have anonymous struct/union members */
+			if (child->var_name) {
+				len = scnprintf(buf, sz, "%s%s",
+						first ? "" : ".", child->var_name);
+				first = false;
+			}
+
+			fill_member_name(buf + len, sz - len, child, offset, first);
+			return;
+		}
+	}
+}
+
+static int hist_entry__typeoff_snprintf(struct hist_entry *he, char *bf,
+				     size_t size, unsigned int width __maybe_unused)
+{
+	struct annotated_data_type *he_type = he->mem_type;
+	char buf[4096];
+
+	buf[0] = '\0';
+	if (list_empty(&he_type->self.children))
+		snprintf(buf, sizeof(buf), "no field");
+	else
+		fill_member_name(buf, sizeof(buf), &he_type->self,
+				 he->mem_type_off, true);
+	buf[4095] = '\0';
+
+	return repsep_snprintf(bf, size, "%s %+d (%s)", he_type->self.type_name,
+			       he->mem_type_off, buf);
+}
+
+struct sort_entry sort_type_offset = {
+	.se_header	= "Data Type Offset",
+	.se_cmp		= sort__type_cmp,
+	.se_collapse	= sort__typeoff_sort,
+	.se_sort	= sort__typeoff_sort,
+	.se_init	= sort__type_init,
+	.se_snprintf	= hist_entry__typeoff_snprintf,
+	.se_width_idx	= HISTC_TYPE_OFFSET,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -2185,7 +2378,10 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_ADDR, "addr", sort_addr),
 	DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
-	DIM(SORT_SIMD, "simd", sort_simd)
+	DIM(SORT_SIMD, "simd", sort_simd),
+	DIM(SORT_ANNOTATE_DATA_TYPE, "type", sort_type),
+	DIM(SORT_ANNOTATE_DATA_TYPE_OFFSET, "typeoff", sort_type_offset),
+	DIM(SORT_SYM_OFFSET, "symoff", sort_sym_offset),
 };
 
 #undef DIM
@@ -3176,7 +3372,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 				sort_dimension_add_dynamic_header(sd);
 		}
 
-		if (sd->entry == &sort_parent) {
+		if (sd->entry == &sort_parent && parent_pattern) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
 				char err[BUFSIZ];
@@ -3205,6 +3401,8 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			list->thread = 1;
 		} else if (sd->entry == &sort_comm) {
 			list->comm = 1;
+		} else if (sd->entry == &sort_type_offset) {
+			symbol_conf.annotate_data_member = true;
 		}
 
 		return __sort_dimension__add(sd, list, level);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ecfb7f1359d5..6f6b4189a389 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -15,6 +15,7 @@
 
 struct option;
 struct thread;
+struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -34,6 +35,7 @@ extern struct sort_entry sort_dso_to;
 extern struct sort_entry sort_sym_from;
 extern struct sort_entry sort_sym_to;
 extern struct sort_entry sort_srcline;
+extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
@@ -111,6 +113,7 @@ struct hist_entry {
 	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
+	int			mem_type_off;
 	struct simd_flags	simd_flags;
 
 	/* We are added by hists__add_dummy_entry. */
@@ -154,6 +157,7 @@ struct hist_entry {
 	struct perf_hpp_list	*hpp_list;
 	struct hist_entry	*parent_he;
 	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
 	union {
 		/* this is for hierarchical entry structure */
 		struct {
@@ -243,6 +247,9 @@ enum sort_type {
 	SORT_LOCAL_RETIRE_LAT,
 	SORT_GLOBAL_RETIRE_LAT,
 	SORT_SIMD,
+	SORT_ANNOTATE_DATA_TYPE,
+	SORT_ANNOTATE_DATA_TYPE_OFFSET,
+	SORT_SYM_OFFSET,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 034b496df297..7addc34afcf5 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -399,6 +399,8 @@ static void addr2line_subprocess_cleanup(struct child_process *a2l)
 		kill(a2l->pid, SIGKILL);
 		finish_command(a2l); /* ignore result, we don't care */
 		a2l->pid = -1;
+		close(a2l->in);
+		close(a2l->out);
 	}
 
 	free(a2l);
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index d45d5dcb0e2b..bfc1d705f437 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -201,6 +201,9 @@ static void print_aggr_id_std(struct perf_stat_config *config,
 		snprintf(buf, sizeof(buf), "S%d-D%d-L%d-ID%d",
 			 id.socket, id.die, id.cache_lvl, id.cache);
 		break;
+	case AGGR_CLUSTER:
+		snprintf(buf, sizeof(buf), "S%d-D%d-CLS%d", id.socket, id.die, id.cluster);
+		break;
 	case AGGR_DIE:
 		snprintf(buf, sizeof(buf), "S%d-D%d", id.socket, id.die);
 		break;
@@ -251,6 +254,10 @@ static void print_aggr_id_csv(struct perf_stat_config *config,
 		fprintf(config->output, "S%d-D%d-L%d-ID%d%s%d%s",
 			id.socket, id.die, id.cache_lvl, id.cache, sep, aggr_nr, sep);
 		break;
+	case AGGR_CLUSTER:
+		fprintf(config->output, "S%d-D%d-CLS%d%s%d%s",
+			id.socket, id.die, id.cluster, sep, aggr_nr, sep);
+		break;
 	case AGGR_DIE:
 		fprintf(output, "S%d-D%d%s%d%s",
 			id.socket, id.die, sep, aggr_nr, sep);
@@ -300,6 +307,10 @@ static void print_aggr_id_json(struct perf_stat_config *config,
 		fprintf(output, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d, ",
 			id.socket, id.die, id.cache_lvl, id.cache, aggr_nr);
 		break;
+	case AGGR_CLUSTER:
+		fprintf(output, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d, ",
+			id.socket, id.die, id.cluster, aggr_nr);
+		break;
 	case AGGR_DIE:
 		fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ",
 			id.socket, id.die, aggr_nr);
@@ -560,7 +571,7 @@ static void print_metric_only(struct perf_stat_config *config,
 	if (color)
 		mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
 
-	color_snprintf(str, sizeof(str), color ?: "", fmt, val);
+	color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val);
 	fprintf(out, "%*s ", mlen, str);
 	os->first = false;
 }
@@ -578,7 +589,7 @@ static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof buf, fmt, val);
+	snprintf(buf, sizeof(buf), fmt ?: "", val);
 	ends = vals = skip_spaces(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
@@ -600,7 +611,7 @@ static void print_metric_only_json(struct perf_stat_config *config __maybe_unuse
 	if (!valid_only_metric(unit))
 		return;
 	unit = fixunit(tbuf, os->evsel, unit);
-	snprintf(buf, sizeof(buf), fmt, val);
+	snprintf(buf, sizeof(buf), fmt ?: "", val);
 	ends = vals = skip_spaces(buf);
 	while (isdigit(*ends) || *ends == '.')
 		ends++;
@@ -898,7 +909,7 @@ static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config
 
 static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter)
 {
-	if (config->no_merge || hybrid_uniquify(counter, config))
+	if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config))
 		uniquify_event_name(counter);
 }
 
@@ -1126,11 +1137,16 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 			u64 ena, run, val;
 			double uval;
 			struct perf_stat_evsel *ps = counter->stats;
-			int aggr_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
+			int aggr_idx = 0;
 
-			if (aggr_idx < 0)
+			if (!perf_cpu_map__has(evsel__cpus(counter), cpu))
 				continue;
 
+			cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
+				if (config->aggr_map->map[aggr_idx].cpu.cpu == cpu.cpu)
+					break;
+			}
+
 			os->evsel = counter;
 			os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
 			if (first) {
@@ -1248,6 +1264,7 @@ static void print_header_interval_std(struct perf_stat_config *config,
 	case AGGR_NODE:
 	case AGGR_SOCKET:
 	case AGGR_DIE:
+	case AGGR_CLUSTER:
 	case AGGR_CACHE:
 	case AGGR_CORE:
 		fprintf(output, "#%*s %-*s cpus",
@@ -1550,6 +1567,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_CACHE:
+	case AGGR_CLUSTER:
 	case AGGR_DIE:
 	case AGGR_SOCKET:
 	case AGGR_NODE:
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 1c5c3eeba4cf..3466aa952442 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -264,7 +264,7 @@ static void print_ll_miss(struct perf_stat_config *config,
 	static const double color_ratios[3] = {20.0, 10.0, 5.0};
 
 	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
-		    "of all L1-icache accesses");
+		    "of all LL-cache accesses");
 }
 
 static void print_dtlb_miss(struct perf_stat_config *config,
@@ -355,11 +355,13 @@ static void print_nsecs(struct perf_stat_config *config,
 		print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 }
 
-static int prepare_metric(struct evsel **metric_events,
-			  struct metric_ref *metric_refs,
+static int prepare_metric(const struct metric_expr *mexp,
+			  const struct evsel *evsel,
 			  struct expr_parse_ctx *pctx,
 			  int aggr_idx)
 {
+	struct evsel * const *metric_events = mexp->metric_events;
+	struct metric_ref *metric_refs = mexp->metric_refs;
 	int i;
 
 	for (i = 0; metric_events[i]; i++) {
@@ -398,12 +400,33 @@ static int prepare_metric(struct evsel **metric_events,
 			source_count = 1;
 		} else {
 			struct perf_stat_evsel *ps = metric_events[i]->stats;
-			struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx];
+			struct perf_stat_aggr *aggr;
 
+			/*
+			 * If there are multiple uncore PMUs and we're not
+			 * reading the leader's stats, determine the stats for
+			 * the appropriate uncore PMU.
+			 */
+			if (evsel && evsel->metric_leader &&
+			    evsel->pmu != evsel->metric_leader->pmu &&
+			    mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) {
+				struct evsel *pos;
+
+				evlist__for_each_entry(evsel->evlist, pos) {
+					if (pos->pmu != evsel->pmu)
+						continue;
+					if (pos->metric_leader != mexp->metric_events[i])
+						continue;
+					ps = pos->stats;
+					source_count = 1;
+					break;
+				}
+			}
+			aggr = &ps->aggr[aggr_idx];
 			if (!aggr)
 				break;
 
-                        if (!metric_events[i]->supported) {
+			if (!metric_events[i]->supported) {
 				/*
 				 * Not supported events will have a count of 0,
 				 * which can be confusing in a
@@ -414,13 +437,9 @@ static int prepare_metric(struct evsel **metric_events,
 				val = NAN;
 				source_count = 0;
 			} else {
-				/*
-				 * If an event was scaled during stat gathering,
-				 * reverse the scale before computing the
-				 * metric.
-				 */
-				val = aggr->counts.val * (1.0 / metric_events[i]->scale);
-				source_count = evsel__source_count(metric_events[i]);
+				val = aggr->counts.val;
+				if (!source_count)
+					source_count = evsel__source_count(metric_events[i]);
 			}
 		}
 		n = strdup(evsel__metric_id(metric_events[i]));
@@ -441,18 +460,18 @@ static int prepare_metric(struct evsel **metric_events,
 }
 
 static void generic_metric(struct perf_stat_config *config,
-			   const char *metric_expr,
-			   const char *metric_threshold,
-			   struct evsel **metric_events,
-			   struct metric_ref *metric_refs,
-			   char *name,
-			   const char *metric_name,
-			   const char *metric_unit,
-			   int runtime,
+			   struct metric_expr *mexp,
+			   struct evsel *evsel,
 			   int aggr_idx,
 			   struct perf_stat_output_ctx *out)
 {
 	print_metric_t print_metric = out->print_metric;
+	const char *metric_name = mexp->metric_name;
+	const char *metric_expr = mexp->metric_expr;
+	const char *metric_threshold = mexp->metric_threshold;
+	const char *metric_unit = mexp->metric_unit;
+	struct evsel * const *metric_events = mexp->metric_events;
+	int runtime = mexp->runtime;
 	struct expr_parse_ctx *pctx;
 	double ratio, scale, threshold;
 	int i;
@@ -467,7 +486,7 @@ static void generic_metric(struct perf_stat_config *config,
 		pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list);
 	pctx->sctx.runtime = runtime;
 	pctx->sctx.system_wide = config->system_wide;
-	i = prepare_metric(metric_events, metric_refs, pctx, aggr_idx);
+	i = prepare_metric(mexp, evsel, pctx, aggr_idx);
 	if (i < 0) {
 		expr__ctx_free(pctx);
 		return;
@@ -502,18 +521,18 @@ static void generic_metric(struct perf_stat_config *config,
 				print_metric(config, ctxp, color, "%8.2f",
 					metric_name ?
 					metric_name :
-					out->force_header ?  name : "",
+					out->force_header ?  evsel->name : "",
 					ratio);
 			}
 		} else {
 			print_metric(config, ctxp, color, /*unit=*/NULL,
 				     out->force_header ?
-				     (metric_name ? metric_name : name) : "", 0);
+				     (metric_name ?: evsel->name) : "", 0);
 		}
 	} else {
 		print_metric(config, ctxp, color, /*unit=*/NULL,
 			     out->force_header ?
-			     (metric_name ? metric_name : name) : "", 0);
+			     (metric_name ?: evsel->name) : "", 0);
 	}
 
 	expr__ctx_free(pctx);
@@ -528,7 +547,7 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
 	if (!pctx)
 		return NAN;
 
-	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, aggr_idx) < 0)
+	if (prepare_metric(mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0)
 		goto out;
 
 	if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -630,10 +649,7 @@ void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
 
 		if ((*num)++ > 0)
 			out->new_line(config, ctxp);
-		generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
-			       mexp->metric_events, mexp->metric_refs, evsel->name,
-			       mexp->metric_name, mexp->metric_unit, mexp->runtime,
-			       aggr_idx, out);
+		generic_metric(config, mexp, evsel, aggr_idx, out);
 	}
 
 	return NULL;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 967e583392c7..b0bcf92f0f9c 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	if (!counter->per_pkg)
 		return 0;
 
-	if (perf_cpu_map__empty(cpus))
+	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
 		return 0;
 
 	if (!mask) {
@@ -592,7 +592,7 @@ void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *ev
 {
 	struct evsel *evsel;
 
-	if (config->no_merge)
+	if (config->aggr_mode == AGGR_NONE)
 		return;
 
 	evlist__for_each_entry(evlist, evsel)
@@ -729,7 +729,7 @@ size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
 
 size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 {
-	struct perf_stat_config sc;
+	struct perf_stat_config sc = {};
 	size_t ret;
 
 	perf_event__read_stat_config(&sc, &event->stat_config);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 325d0fad1842..d6e5c8787ba2 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -48,6 +48,7 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_DIE,
+	AGGR_CLUSTER,
 	AGGR_CACHE,
 	AGGR_CORE,
 	AGGR_THREAD,
@@ -76,7 +77,6 @@ struct perf_stat_config {
 	bool			 null_run;
 	bool			 ru_display;
 	bool			 big_num;
-	bool			 no_merge;
 	bool			 hybrid_merge;
 	bool			 walltime_run_table;
 	bool			 all_kernel;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index cf05b0b56c57..116a642ad99d 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -301,3 +301,51 @@ unsigned int hex(char c)
 		return c - 'a' + 10;
 	return c - 'A' + 10;
 }
+
+/*
+ * Replace all occurrences of character 'needle' in string 'haystack' with
+ * string 'replace'
+ *
+ * The new string could be longer so a new string is returned which must be
+ * freed.
+ */
+char *strreplace_chars(char needle, const char *haystack, const char *replace)
+{
+	int replace_len = strlen(replace);
+	char *new_s, *to;
+	const char *loc = strchr(haystack, needle);
+	const char *from = haystack;
+	int num = 0;
+
+	/* Count occurrences */
+	while (loc) {
+		loc = strchr(loc + 1, needle);
+		num++;
+	}
+
+	/* Allocate enough space for replacements and reset first location */
+	new_s = malloc(strlen(haystack) + (num * (replace_len - 1) + 1));
+	if (!new_s)
+		return NULL;
+	loc = strchr(haystack, needle);
+	to = new_s;
+
+	while (loc) {
+		/* Copy original string up to found char and update positions */
+		memcpy(to, from, 1 + loc - from);
+		to += loc - from;
+		from = loc + 1;
+
+		/* Copy replacement string and update positions */
+		memcpy(to, replace, replace_len);
+		to += replace_len;
+
+		/* needle next occurrence or end of string */
+		loc = strchr(from, needle);
+	}
+
+	/* Copy any remaining chars + null */
+	strcpy(to, from);
+
+	return new_s;
+}
diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h
index 56c30fef9682..52cb8ba057c7 100644
--- a/tools/perf/util/string2.h
+++ b/tools/perf/util/string2.h
@@ -39,5 +39,6 @@ char *strpbrk_esc(char *str, const char *stopset);
 char *strdup_esc(const char *str);
 
 unsigned int hex(char c);
+char *strreplace_chars(char needle, const char *haystack, const char *replace);
 
 #endif /* PERF_STRING_H */
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 5c62d3118c41..1892e9b6aa7f 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -331,7 +331,7 @@ static char *cpu_model(void)
 	file = fopen("/proc/cpuinfo", "r");
 	if (file) {
 		while (fgets(buf, 255, file)) {
-			if (strstr(buf, "model name")) {
+			if (strcasestr(buf, "model name")) {
 				strlcpy(cpu_m, &buf[13], 255);
 				break;
 			}
@@ -754,6 +754,7 @@ int svg_build_topology_map(struct perf_env *env)
 	int i, nr_cpus;
 	struct topology t;
 	char *sib_core, *sib_thr;
+	int ret = -1;
 
 	nr_cpus = min(env->nr_cpus_online, MAX_NR_CPUS);
 
@@ -799,11 +800,11 @@ int svg_build_topology_map(struct perf_env *env)
 
 	scan_core_topology(topology_map, &t, nr_cpus);
 
-	return 0;
+	ret = 0;
 
 exit:
 	zfree(&t.sib_core);
 	zfree(&t.sib_thr);
 
-	return -1;
+	return ret;
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 8bd466d1c2bd..0b91f813c4fa 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -23,6 +23,7 @@
 #include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
+#include <linux/string.h>
 #include <symbol/kallsyms.h>
 #include <internal/lib.h>
 
@@ -1329,6 +1330,58 @@ out_close:
 	return -1;
 }
 
+static bool is_exe_text(int flags)
+{
+	return (flags & (SHF_ALLOC | SHF_EXECINSTR)) == (SHF_ALLOC | SHF_EXECINSTR);
+}
+
+/*
+ * Some executable module sections like .noinstr.text might be laid out with
+ * .text so they can use the same mapping (memory address to file offset).
+ * Check if that is the case. Refer to kernel layout_sections(). Return the
+ * maximum offset.
+ */
+static u64 max_text_section(Elf *elf, GElf_Ehdr *ehdr)
+{
+	Elf_Scn *sec = NULL;
+	GElf_Shdr shdr;
+	u64 offs = 0;
+
+	/* Doesn't work for some arch */
+	if (ehdr->e_machine == EM_PARISC ||
+	    ehdr->e_machine == EM_ALPHA)
+		return 0;
+
+	/* ELF is corrupted/truncated, avoid calling elf_strptr. */
+	if (!elf_rawdata(elf_getscn(elf, ehdr->e_shstrndx), NULL))
+		return 0;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		char *sec_name;
+
+		if (!gelf_getshdr(sec, &shdr))
+			break;
+
+		if (!is_exe_text(shdr.sh_flags))
+			continue;
+
+		/* .init and .exit sections are not placed with .text */
+		sec_name = elf_strptr(elf, ehdr->e_shstrndx, shdr.sh_name);
+		if (!sec_name ||
+		    strstarts(sec_name, ".init") ||
+		    strstarts(sec_name, ".exit"))
+			break;
+
+		/* Must be next to previous, assumes .text is first */
+		if (offs && PERF_ALIGN(offs, shdr.sh_addralign ?: 1) != shdr.sh_offset)
+			break;
+
+		offs = shdr.sh_offset + shdr.sh_size;
+	}
+
+	return offs;
+}
+
 /**
  * ref_reloc_sym_not_found - has kernel relocation symbol been found.
  * @kmap: kernel maps and relocation reference symbol
@@ -1368,7 +1421,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 				      struct maps *kmaps, struct kmap *kmap,
 				      struct dso **curr_dsop, struct map **curr_mapp,
 				      const char *section_name,
-				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel)
+				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel,
+				      u64 max_text_sh_offset)
 {
 	struct dso *curr_dso = *curr_dsop;
 	struct map *curr_map;
@@ -1392,8 +1446,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
 			map__set_end(map, map__start(map) + shdr->sh_size);
 			map__set_pgoff(map, shdr->sh_offset);
-			map__set_map_ip(map, map__dso_map_ip);
-			map__set_unmap_ip(map, map__dso_unmap_ip);
+			map__set_mapping_type(map, MAPPING_TYPE__DSO);
 			/* Ensure maps are correctly ordered */
 			if (kmaps) {
 				int err;
@@ -1425,6 +1478,17 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 	if (!kmap)
 		return 0;
 
+	/*
+	 * perf does not record module section addresses except for .text, but
+	 * some sections can use the same mapping as .text.
+	 */
+	if (kmodule && adjust_kernel_syms && is_exe_text(shdr->sh_flags) &&
+	    shdr->sh_offset <= max_text_sh_offset) {
+		*curr_mapp = map;
+		*curr_dsop = dso;
+		return 0;
+	}
+
 	snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
 
 	curr_map = maps__find_by_name(kmaps, dso_name);
@@ -1440,6 +1504,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		curr_dso->kernel = dso->kernel;
 		curr_dso->long_name = dso->long_name;
 		curr_dso->long_name_len = dso->long_name_len;
+		curr_dso->binary_type = dso->binary_type;
+		curr_dso->adjust_symbols = dso->adjust_symbols;
 		curr_map = map__new2(start, curr_dso);
 		dso__put(curr_dso);
 		if (curr_map == NULL)
@@ -1453,8 +1519,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 			map__set_end(curr_map, map__start(curr_map) + shdr->sh_size);
 			map__set_pgoff(curr_map, shdr->sh_offset);
 		} else {
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 		}
 		curr_dso->symtab_type = dso->symtab_type;
 		if (maps__insert(kmaps, curr_map))
@@ -1470,8 +1535,10 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
 		dso__set_loaded(curr_dso);
 		*curr_mapp = curr_map;
 		*curr_dsop = curr_dso;
-	} else
+	} else {
 		*curr_dsop = map__dso(curr_map);
+		map__put(curr_map);
+	}
 
 	return 0;
 }
@@ -1497,6 +1564,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	Elf *elf;
 	int nr = 0;
 	bool remap_kernel = false, adjust_kernel_syms = false;
+	u64 max_text_sh_offset = 0;
 
 	if (kmap && !kmaps)
 		return -1;
@@ -1512,8 +1580,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	}
 
 	if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
-				".text", NULL))
+				".text", NULL)) {
 		dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
+		dso->text_end = tshdr.sh_offset + tshdr.sh_size;
+	}
 
 	if (runtime_ss->opdsec)
 		opddata = elf_rawdata(runtime_ss->opdsec, NULL);
@@ -1582,6 +1652,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		remap_kernel = true;
 		adjust_kernel_syms = dso->adjust_symbols;
 	}
+
+	if (kmodule && adjust_kernel_syms)
+		max_text_sh_offset = max_text_section(runtime_ss->elf, &runtime_ss->ehdr);
+
 	elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
 		struct symbol *f;
 		const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1671,7 +1745,8 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		if (dso->kernel) {
 			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
-						       section_name, adjust_kernel_syms, kmodule, &remap_kernel))
+						       section_name, adjust_kernel_syms, kmodule,
+						       &remap_kernel, max_text_sh_offset))
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index a81a14769bd1..1da8b713509c 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -159,9 +159,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	} else {
 		Elf64_Ehdr ehdr;
@@ -210,9 +211,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 
 			ret = read_build_id(buf, buf_size, bid, need_swap);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = bid->size;
-			break;
+				break;
+			}
 		}
 	}
 out_free:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f849f9ef68e6..9ebdb8e13c0b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -48,11 +48,6 @@ static bool symbol__is_idle(const char *name);
 int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
-struct map_list_node {
-	struct list_head node;
-	struct map *map;
-};
-
 struct symbol_conf symbol_conf = {
 	.nanosecs		= false,
 	.use_modules		= true,
@@ -68,6 +63,16 @@ struct symbol_conf symbol_conf = {
 	.res_sample		= 0,
 };
 
+struct map_list_node {
+	struct list_head node;
+	struct map *map;
+};
+
+static struct map_list_node *map_list_node__new(void)
+{
+	return malloc(sizeof(struct map_list_node));
+}
+
 static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__KALLSYMS,
 	DSO_BINARY_TYPE__GUEST_KALLSYMS,
@@ -90,11 +95,6 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-static struct map_list_node *map_list_node__new(void)
-{
-	return malloc(sizeof(struct map_list_node));
-}
-
 static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
@@ -202,11 +202,10 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 again:
 		nd = rb_next(&curr->rb_node);
-		next = rb_entry(nd, struct symbol, rb_node);
-
 		if (!nd)
 			break;
 
+		next = rb_entry(nd, struct symbol, rb_node);
 		if (curr->start != next->start)
 			continue;
 
@@ -249,14 +248,31 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 		 * segment is very big.  Therefore do not fill this gap and do
 		 * not assign it to the kernel dso map (kallsyms).
 		 *
+		 * Also BPF code can be allocated separately from text segments
+		 * and modules.  So the last entry in a module should not fill
+		 * the gap too.
+		 *
 		 * In kallsyms, it determines module symbols using '[' character
 		 * like in:
 		 *   ffffffffc1937000 T hdmi_driver_init  [snd_hda_codec_hdmi]
 		 */
 		if (prev->end == prev->start) {
+			const char *prev_mod;
+			const char *curr_mod;
+
+			if (!is_kallsyms) {
+				prev->end = curr->start;
+				continue;
+			}
+
+			prev_mod = strchr(prev->name, '[');
+			curr_mod = strchr(curr->name, '[');
+
 			/* Last kernel/module symbol mapped to end of page */
-			if (is_kallsyms && (!strchr(prev->name, '[') !=
-					    !strchr(curr->name, '[')))
+			if (!prev_mod != !curr_mod)
+				prev->end = roundup(prev->end + 4096, 4096);
+			/* Last symbol in the previous module */
+			else if (prev_mod && strcmp(prev_mod, curr_mod))
 				prev->end = roundup(prev->end + 4096, 4096);
 			else
 				prev->end = curr->start;
@@ -271,29 +287,6 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
-void maps__fixup_end(struct maps *maps)
-{
-	struct map_rb_node *prev = NULL, *curr;
-
-	down_write(maps__lock(maps));
-
-	maps__for_each_entry(maps, curr) {
-		if (prev != NULL && !map__end(prev->map))
-			map__set_end(prev->map, map__start(curr->map));
-
-		prev = curr;
-	}
-
-	/*
-	 * We still haven't the actual symbols, so guess the
-	 * last map final address.
-	 */
-	if (curr && !map__end(curr->map))
-		map__set_end(curr->map, ~0ULL);
-
-	up_write(maps__lock(maps));
-}
-
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
@@ -719,6 +712,7 @@ static bool symbol__is_idle(const char *name)
 		"cpu_startup_entry",
 		"idle_cpu",
 		"intel_idle",
+		"intel_idle_ibrs",
 		"default_idle",
 		"native_safe_halt",
 		"enter_idle",
@@ -790,7 +784,6 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename)
 
 static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso)
 {
-	struct map *curr_map;
 	struct symbol *pos;
 	int count = 0;
 	struct rb_root_cached old_root = dso->symbols;
@@ -803,6 +796,7 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso)
 	*root = RB_ROOT_CACHED;
 
 	while (next) {
+		struct map *curr_map;
 		struct dso *curr_map_dso;
 		char *module;
 
@@ -829,6 +823,7 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso)
 			pos->end -= map__start(curr_map) - map__pgoff(curr_map);
 		symbols__insert(&curr_map_dso->symbols, pos);
 		++count;
+		map__put(curr_map);
 	}
 
 	/* Symbols have been adjusted */
@@ -846,7 +841,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 				struct map *initial_map)
 {
 	struct machine *machine;
-	struct map *curr_map = initial_map;
+	struct map *curr_map = map__get(initial_map);
 	struct symbol *pos;
 	int count = 0, moved = 0;
 	struct rb_root_cached *root = &dso->symbols;
@@ -877,7 +872,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 			*module++ = '\0';
 			curr_map_dso = map__dso(curr_map);
 			if (strcmp(curr_map_dso->short_name, module)) {
-				if (RC_CHK_ACCESS(curr_map) != RC_CHK_ACCESS(initial_map) &&
+				if (!RC_CHK_EQUAL(curr_map, initial_map) &&
 				    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
 				    machine__is_default_guest(machine)) {
 					/*
@@ -890,13 +885,14 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 					dso__set_loaded(curr_map_dso);
 				}
 
+				map__zput(curr_map);
 				curr_map = maps__find_by_name(kmaps, module);
 				if (curr_map == NULL) {
 					pr_debug("%s/proc/{kallsyms,modules} "
 					         "inconsistency while looking "
 						 "for \"%s\" module!\n",
 						 machine->root_dir, module);
-					curr_map = initial_map;
+					curr_map = map__get(initial_map);
 					goto discard_symbol;
 				}
 				curr_map_dso = map__dso(curr_map);
@@ -920,7 +916,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 			 * symbols at this point.
 			 */
 			goto discard_symbol;
-		} else if (curr_map != initial_map) {
+		} else if (!RC_CHK_EQUAL(curr_map, initial_map)) {
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
@@ -931,7 +927,8 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 			}
 
 			if (count == 0) {
-				curr_map = initial_map;
+				map__zput(curr_map);
+				curr_map = map__get(initial_map);
 				goto add_symbol;
 			}
 
@@ -945,6 +942,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 					kernel_range++);
 
 			ndso = dso__new(dso_name);
+			map__zput(curr_map);
 			if (ndso == NULL)
 				return -1;
 
@@ -956,9 +954,9 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 				return -1;
 			}
 
-			map__set_map_ip(curr_map, identity__map_ip);
-			map__set_unmap_ip(curr_map, identity__map_ip);
+			map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
 			if (maps__insert(kmaps, curr_map)) {
+				map__zput(curr_map);
 				dso__put(ndso);
 				return -1;
 			}
@@ -969,7 +967,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
 			pos->end -= delta;
 		}
 add_symbol:
-		if (curr_map != initial_map) {
+		if (!RC_CHK_EQUAL(curr_map, initial_map)) {
 			struct dso *curr_map_dso = map__dso(curr_map);
 
 			rb_erase_cached(&pos->rb_node, root);
@@ -984,12 +982,12 @@ discard_symbol:
 		symbol__delete(pos);
 	}
 
-	if (curr_map != initial_map &&
+	if (!RC_CHK_EQUAL(curr_map, initial_map) &&
 	    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
 	    machine__is_default_guest(maps__machine(kmaps))) {
 		dso__set_loaded(map__dso(curr_map));
 	}
-
+	map__put(curr_map);
 	return count + moved;
 }
 
@@ -1148,33 +1146,35 @@ out_delete_from:
 	return ret;
 }
 
+static int do_validate_kcore_modules_cb(struct map *old_map, void *data)
+{
+	struct rb_root *modules = data;
+	struct module_info *mi;
+	struct dso *dso;
+
+	if (!__map__is_kmodule(old_map))
+		return 0;
+
+	dso = map__dso(old_map);
+	/* Module must be in memory at the same address */
+	mi = find_module(dso->short_name, modules);
+	if (!mi || mi->start != map__start(old_map))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int do_validate_kcore_modules(const char *filename, struct maps *kmaps)
 {
 	struct rb_root modules = RB_ROOT;
-	struct map_rb_node *old_node;
 	int err;
 
 	err = read_proc_modules(filename, &modules);
 	if (err)
 		return err;
 
-	maps__for_each_entry(kmaps, old_node) {
-		struct map *old_map = old_node->map;
-		struct module_info *mi;
-		struct dso *dso;
+	err = maps__for_each_map(kmaps, do_validate_kcore_modules_cb, &modules);
 
-		if (!__map__is_kmodule(old_map)) {
-			continue;
-		}
-		dso = map__dso(old_map);
-		/* Module must be in memory at the same address */
-		mi = find_module(dso->short_name, &modules);
-		if (!mi || mi->start != map__start(old_map)) {
-			err = -EINVAL;
-			goto out;
-		}
-	}
-out:
 	delete_modules(&modules);
 	return err;
 }
@@ -1271,101 +1271,15 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	return 0;
 }
 
-/*
- * Merges map into maps by splitting the new map within the existing map
- * regions.
- */
-int maps__merge_in(struct maps *kmaps, struct map *new_map)
+static bool remove_old_maps(struct map *map, void *data)
 {
-	struct map_rb_node *rb_node;
-	LIST_HEAD(merged);
-	int err = 0;
-
-	maps__for_each_entry(kmaps, rb_node) {
-		struct map *old_map = rb_node->map;
-
-		/* no overload with this one */
-		if (map__end(new_map) < map__start(old_map) ||
-		    map__start(new_map) >= map__end(old_map))
-			continue;
+	const struct map *map_to_save = data;
 
-		if (map__start(new_map) < map__start(old_map)) {
-			/*
-			 * |new......
-			 *       |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 * |new......|     -> |new..|
-				 *       |old....| ->       |old....|
-				 */
-				map__set_end(new_map, map__start(old_map));
-			} else {
-				/*
-				 * |new.............| -> |new..|       |new..|
-				 *       |old....|    ->       |old....|
-				 */
-				struct map_list_node *m = map_list_node__new();
-
-				if (!m) {
-					err = -ENOMEM;
-					goto out;
-				}
-
-				m->map = map__clone(new_map);
-				if (!m->map) {
-					free(m);
-					err = -ENOMEM;
-					goto out;
-				}
-
-				map__set_end(m->map, map__start(old_map));
-				list_add_tail(&m->node, &merged);
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		} else {
-			/*
-			 *      |new......
-			 * |old....
-			 */
-			if (map__end(new_map) < map__end(old_map)) {
-				/*
-				 *      |new..|   -> x
-				 * |old.........| -> |old.........|
-				 */
-				map__put(new_map);
-				new_map = NULL;
-				break;
-			} else {
-				/*
-				 *      |new......| ->         |new...|
-				 * |old....|        -> |old....|
-				 */
-				map__add_pgoff(new_map, map__end(old_map) - map__start(new_map));
-				map__set_start(new_map, map__end(old_map));
-			}
-		}
-	}
-
-out:
-	while (!list_empty(&merged)) {
-		struct map_list_node *old_node;
-
-		old_node = list_entry(merged.next, struct map_list_node, node);
-		list_del_init(&old_node->node);
-		if (!err)
-			err = maps__insert(kmaps, old_node->map);
-		map__put(old_node->map);
-		free(old_node);
-	}
-
-	if (new_map) {
-		if (!err)
-			err = maps__insert(kmaps, new_map);
-		map__put(new_map);
-	}
-	return err;
+	/*
+	 * We need to preserve eBPF maps even if they are covered by kcore,
+	 * because we need to access eBPF dso for source data.
+	 */
+	return !RC_CHK_EQUAL(map, map_to_save) && !__map__is_bpf_prog(map);
 }
 
 static int dso__load_kcore(struct dso *dso, struct map *map,
@@ -1374,7 +1288,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	struct maps *kmaps = map__kmaps(map);
 	struct kcore_mapfn_data md;
 	struct map *replacement_map = NULL;
-	struct map_rb_node *old_node, *next;
 	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
@@ -1421,17 +1334,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Remove old maps */
-	maps__for_each_entry_safe(kmaps, old_node, next) {
-		struct map *old_map = old_node->map;
-
-		/*
-		 * We need to preserve eBPF maps even if they are
-		 * covered by kcore, because we need to access
-		 * eBPF dso for source data.
-		 */
-		if (old_map != map && !__map__is_bpf_prog(old_map))
-			maps__remove(kmaps, old_map);
-	}
+	maps__remove_maps(kmaps, remove_old_maps, map);
 	machine->trampolines_mapped = false;
 
 	/* Find the kernel map using the '_stext' symbol */
@@ -1469,14 +1372,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 		list_del_init(&new_node->node);
 
-		if (RC_CHK_ACCESS(new_map) == RC_CHK_ACCESS(replacement_map)) {
+		if (RC_CHK_EQUAL(new_map, replacement_map)) {
 			struct map *map_ref;
 
 			map__set_start(map, map__start(new_map));
 			map__set_end(map, map__end(new_map));
 			map__set_pgoff(map, map__pgoff(new_map));
-			map__set_map_ip(map, map__map_ip_ptr(new_map));
-			map__set_unmap_ip(map, map__unmap_ip_ptr(new_map));
+			map__set_mapping_type(map, map__mapping_type(new_map));
 			/* Ensure maps are correctly ordered */
 			map_ref = map__get(map);
 			maps__remove(kmaps, map_ref);
@@ -1733,8 +1635,10 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 			/* PE symbols can only have 4 bytes, so use .text high bits */
 			dso->text_offset = section->vma - (u32)section->vma;
 			dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
+			dso->text_end = (section->vma - dso->text_offset) + section->size;
 		} else {
 			dso->text_offset = section->vma - section->filepos;
+			dso->text_end = section->filepos + section->size;
 		}
 	}
 
@@ -2065,124 +1969,6 @@ out:
 	return ret;
 }
 
-static int map__strcmp(const void *a, const void *b)
-{
-	const struct map *map_a = *(const struct map **)a;
-	const struct map *map_b = *(const struct map **)b;
-	const struct dso *dso_a = map__dso(map_a);
-	const struct dso *dso_b = map__dso(map_b);
-	int ret = strcmp(dso_a->short_name, dso_b->short_name);
-
-	if (ret == 0 && map_a != map_b) {
-		/*
-		 * Ensure distinct but name equal maps have an order in part to
-		 * aid reference counting.
-		 */
-		ret = (int)map__start(map_a) - (int)map__start(map_b);
-		if (ret == 0)
-			ret = (int)((intptr_t)map_a - (intptr_t)map_b);
-	}
-
-	return ret;
-}
-
-static int map__strcmp_name(const void *name, const void *b)
-{
-	const struct dso *dso = map__dso(*(const struct map **)b);
-
-	return strcmp(name, dso->short_name);
-}
-
-void __maps__sort_by_name(struct maps *maps)
-{
-	qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp);
-}
-
-static int map__groups__sort_by_name_from_rbtree(struct maps *maps)
-{
-	struct map_rb_node *rb_node;
-	struct map **maps_by_name = realloc(maps__maps_by_name(maps),
-					    maps__nr_maps(maps) * sizeof(struct map *));
-	int i = 0;
-
-	if (maps_by_name == NULL)
-		return -1;
-
-	up_read(maps__lock(maps));
-	down_write(maps__lock(maps));
-
-	RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name;
-	RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps);
-
-	maps__for_each_entry(maps, rb_node)
-		maps_by_name[i++] = map__get(rb_node->map);
-
-	__maps__sort_by_name(maps);
-
-	up_write(maps__lock(maps));
-	down_read(maps__lock(maps));
-
-	return 0;
-}
-
-static struct map *__maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map **mapp;
-
-	if (maps__maps_by_name(maps) == NULL &&
-	    map__groups__sort_by_name_from_rbtree(maps))
-		return NULL;
-
-	mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps),
-		       sizeof(*mapp), map__strcmp_name);
-	if (mapp)
-		return *mapp;
-	return NULL;
-}
-
-struct map *maps__find_by_name(struct maps *maps, const char *name)
-{
-	struct map_rb_node *rb_node;
-	struct map *map;
-
-	down_read(maps__lock(maps));
-
-
-	if (RC_CHK_ACCESS(maps)->last_search_by_name) {
-		const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name);
-
-		if (strcmp(dso->short_name, name) == 0) {
-			map = RC_CHK_ACCESS(maps)->last_search_by_name;
-			goto out_unlock;
-		}
-	}
-	/*
-	 * If we have maps->maps_by_name, then the name isn't in the rbtree,
-	 * as maps->maps_by_name mirrors the rbtree when lookups by name are
-	 * made.
-	 */
-	map = __maps__find_by_name(maps, name);
-	if (map || maps__maps_by_name(maps) != NULL)
-		goto out_unlock;
-
-	/* Fallback to traversing the rbtree... */
-	maps__for_each_entry(maps, rb_node) {
-		struct dso *dso;
-
-		map = rb_node->map;
-		dso = map__dso(map);
-		if (strcmp(dso->short_name, name) == 0) {
-			RC_CHK_ACCESS(maps)->last_search_by_name = map;
-			goto out_unlock;
-		}
-	}
-	map = NULL;
-
-out_unlock:
-	up_read(maps__lock(maps));
-	return map;
-}
-
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, bool vmlinux_allocated)
 {
@@ -2204,15 +1990,20 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
 		return -1;
 
+	/*
+	 * dso__load_sym() may copy 'dso' which will result in the copies having
+	 * an incorrect long name unless we set it here first.
+	 */
+	dso__set_long_name(dso, vmlinux, vmlinux_allocated);
+	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+	else
+		dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
+
 	err = dso__load_sym(dso, map, &ss, &ss, 0);
 	symsrc__destroy(&ss);
 
 	if (err > 0) {
-		if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
-			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
-		else
-			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
-		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
@@ -2784,8 +2575,11 @@ struct mem_info *mem_info__get(struct mem_info *mi)
 
 void mem_info__put(struct mem_info *mi)
 {
-	if (mi && refcount_dec_and_test(&mi->refcnt))
+	if (mi && refcount_dec_and_test(&mi->refcnt)) {
+		addr_map_symbol__exit(&mi->iaddr);
+		addr_map_symbol__exit(&mi->daddr);
 		free(mi);
+	}
 }
 
 struct mem_info *mem_info__new(void)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index af87c46b3f89..071837ddce2a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -189,7 +189,6 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
 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, bool is_kallsyms);
-void maps__fixup_end(struct maps *maps);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index 0b589570d1d0..c114bbceef40 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -42,7 +42,11 @@ struct symbol_conf {
 			inline_name,
 			disable_add2line_warn,
 			buildid_mmap2,
-			guest_code;
+			guest_code,
+			lazy_load_kernel_maps,
+			keep_exited_threads,
+			annotate_data_member,
+			annotate_data_sample;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 45714a2785fd..2a0289c14959 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -665,18 +665,74 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused,
 }
 #endif
 
+struct perf_event__synthesize_modules_maps_cb_args {
+	struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
+{
+	struct perf_event__synthesize_modules_maps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct dso *dso;
+	size_t size;
+
+	if (!__map__is_kmodule(map))
+		return 0;
+
+	dso = map__dso(map);
+	if (symbol_conf.buildid_mmap2) {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap2.header.type = PERF_RECORD_MMAP2;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap2.header.size += args->machine->id_hdr_size;
+		event->mmap2.start = map__start(map);
+		event->mmap2.len   = map__size(map);
+		event->mmap2.pid   = args->machine->pid;
+
+		memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
+
+		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
+	} else {
+		size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
+		event->mmap.header.type = PERF_RECORD_MMAP;
+		event->mmap.header.size = (sizeof(event->mmap) -
+					(sizeof(event->mmap.filename) - size));
+		memset(event->mmap.filename + size, 0, args->machine->id_hdr_size);
+		event->mmap.header.size += args->machine->id_hdr_size;
+		event->mmap.start = map__start(map);
+		event->mmap.len   = map__size(map);
+		event->mmap.pid   = args->machine->pid;
+
+		memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
+	}
+
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
+
+	return 0;
+}
+
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
 				   struct machine *machine)
 {
-	int rc = 0;
-	struct map_rb_node *pos;
+	int rc;
 	struct maps *maps = machine__kernel_maps(machine);
-	union perf_event *event;
-	size_t size = symbol_conf.buildid_mmap2 ?
-			sizeof(event->mmap2) : sizeof(event->mmap);
+	struct perf_event__synthesize_modules_maps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+	};
+	size_t size = symbol_conf.buildid_mmap2
+		? sizeof(args.event->mmap2)
+		: sizeof(args.event->mmap);
 
-	event = zalloc(size + machine->id_hdr_size);
-	if (event == NULL) {
+	args.event = zalloc(size + machine->id_hdr_size);
+	if (args.event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
 		return -1;
@@ -687,53 +743,13 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t
 	 * __perf_event_mmap
 	 */
 	if (machine__is_host(machine))
-		event->header.misc = PERF_RECORD_MISC_KERNEL;
+		args.event->header.misc = PERF_RECORD_MISC_KERNEL;
 	else
-		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-
-	maps__for_each_entry(maps, pos) {
-		struct map *map = pos->map;
-		struct dso *dso;
+		args.event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-		if (!__map__is_kmodule(map))
-			continue;
+	rc = maps__for_each_map(maps, perf_event__synthesize_modules_maps_cb, &args);
 
-		dso = map__dso(map);
-		if (symbol_conf.buildid_mmap2) {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap2.header.type = PERF_RECORD_MMAP2;
-			event->mmap2.header.size = (sizeof(event->mmap2) -
-						(sizeof(event->mmap2.filename) - size));
-			memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-			event->mmap2.header.size += machine->id_hdr_size;
-			event->mmap2.start = map__start(map);
-			event->mmap2.len   = map__size(map);
-			event->mmap2.pid   = machine->pid;
-
-			memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1);
-
-			perf_record_mmap2__read_build_id(&event->mmap2, machine, false);
-		} else {
-			size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64));
-			event->mmap.header.type = PERF_RECORD_MMAP;
-			event->mmap.header.size = (sizeof(event->mmap) -
-						(sizeof(event->mmap.filename) - size));
-			memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-			event->mmap.header.size += machine->id_hdr_size;
-			event->mmap.start = map__start(map);
-			event->mmap.len   = map__size(map);
-			event->mmap.pid   = machine->pid;
-
-			memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1);
-		}
-
-		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
-			rc = -1;
-			break;
-		}
-	}
-
-	free(event);
+	free(args.event);
 	return rc;
 }
 
@@ -1039,11 +1055,11 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (thread_nr > n)
 		thread_nr = n;
 
-	synthesize_threads = calloc(sizeof(pthread_t), thread_nr);
+	synthesize_threads = calloc(thread_nr, sizeof(pthread_t));
 	if (synthesize_threads == NULL)
 		goto free_dirent;
 
-	args = calloc(sizeof(*args), thread_nr);
+	args = calloc(thread_nr, sizeof(*args));
 	if (args == NULL)
 		goto free_threads;
 
@@ -2145,7 +2161,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *
 		return -ENOMEM;
 
 	ev->attr.attr = *attr;
-	memcpy(ev->attr.id, id, ids * sizeof(u64));
+	memcpy(perf_record_header_attr_id(ev), id, ids * sizeof(u64));
 
 	ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
 	ev->attr.header.size = (u16)size;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0b166404c5c3..1aa8962dcf52 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -26,7 +26,7 @@ int thread__init_maps(struct thread *thread, struct machine *machine)
 	if (pid == thread__tid(thread) || pid == -1) {
 		thread__set_maps(thread, maps__new(machine));
 	} else {
-		struct thread *leader = __machine__findnew_thread(machine, pid, pid);
+		struct thread *leader = machine__findnew_thread(machine, pid, pid);
 
 		if (leader) {
 			thread__set_maps(thread, maps__get(thread__maps(leader)));
@@ -80,6 +80,15 @@ err_thread:
 	return NULL;
 }
 
+static void (*thread__priv_destructor)(void *priv);
+
+void thread__set_priv_destructor(void (*destructor)(void *priv))
+{
+	assert(thread__priv_destructor == NULL);
+
+	thread__priv_destructor = destructor;
+}
+
 void thread__delete(struct thread *thread)
 {
 	struct namespaces *namespaces, *tmp_namespaces;
@@ -112,6 +121,10 @@ void thread__delete(struct thread *thread)
 	exit_rwsem(thread__namespaces_lock(thread));
 	exit_rwsem(thread__comm_lock(thread));
 	thread__free_stitch_list(thread);
+
+	if (thread__priv_destructor)
+		thread__priv_destructor(thread__priv(thread));
+
 	RC_CHK_FREE(thread);
 }
 
@@ -332,38 +345,36 @@ int thread__insert_map(struct thread *thread, struct map *map)
 	if (ret)
 		return ret;
 
-	maps__fixup_overlappings(thread__maps(thread), map, stderr);
-	return maps__insert(thread__maps(thread), map);
+	return maps__fixup_overlap_and_insert(thread__maps(thread), map);
 }
 
-static int __thread__prepare_access(struct thread *thread)
+struct thread__prepare_access_maps_cb_args {
+	int err;
+	struct maps *maps;
+};
+
+static int thread__prepare_access_maps_cb(struct map *map, void *data)
 {
 	bool initialized = false;
-	int err = 0;
-	struct maps *maps = thread__maps(thread);
-	struct map_rb_node *rb_node;
+	struct thread__prepare_access_maps_cb_args *args = data;
 
-	down_read(maps__lock(maps));
+	args->err = unwind__prepare_access(args->maps, map, &initialized);
 
-	maps__for_each_entry(maps, rb_node) {
-		err = unwind__prepare_access(thread__maps(thread), rb_node->map, &initialized);
-		if (err || initialized)
-			break;
-	}
-
-	up_read(maps__lock(maps));
-
-	return err;
+	return (args->err || initialized) ? 1 : 0;
 }
 
 static int thread__prepare_access(struct thread *thread)
 {
-	int err = 0;
+	struct thread__prepare_access_maps_cb_args args = {
+		.err = 0,
+	};
 
-	if (dwarf_callchain_users)
-		err = __thread__prepare_access(thread);
+	if (dwarf_callchain_users) {
+		args.maps = thread__maps(thread);
+		maps__for_each_map(thread__maps(thread), thread__prepare_access_maps_cb, &args);
+	}
 
-	return err;
+	return args.err;
 }
 
 static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone)
@@ -372,14 +383,14 @@ static int thread__clone_maps(struct thread *thread, struct thread *parent, bool
 	if (thread__pid(thread) == thread__pid(parent))
 		return thread__prepare_access(thread);
 
-	if (thread__maps(thread) == thread__maps(parent)) {
+	if (maps__equal(thread__maps(thread), thread__maps(parent))) {
 		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
 			 thread__pid(thread), thread__tid(thread),
 			 thread__pid(parent), thread__tid(parent));
 		return 0;
 	}
 	/* But this one is new process, copy maps. */
-	return do_maps_clone ? maps__clone(thread, thread__maps(parent)) : 0;
+	return do_maps_clone ? maps__copy_from(thread__maps(thread), thread__maps(parent)) : 0;
 }
 
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9068a21ce0fa..8b4a3c69bad1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -3,7 +3,6 @@
 #define __PERF_THREAD_H
 
 #include <linux/refcount.h>
-#include <linux/rbtree.h>
 #include <linux/list.h>
 #include <stdio.h>
 #include <unistd.h>
@@ -13,7 +12,6 @@
 #include <strlist.h>
 #include <intlist.h>
 #include "rwsem.h"
-#include "event.h"
 #include "callchain.h"
 #include <internal/rc_check.h>
 
@@ -30,19 +28,23 @@ struct lbr_stitch {
 	struct callchain_cursor_node	*prev_lbr_cursor;
 };
 
-struct thread_rb_node {
-	struct rb_node rb_node;
-	struct thread *thread;
-};
-
 DECLARE_RC_STRUCT(thread) {
+	/** @maps: mmaps associated with this thread. */
 	struct maps		*maps;
 	pid_t			pid_; /* Not all tools update this */
+	/** @tid: thread ID number unique to a machine. */
 	pid_t			tid;
+	/** @ppid: parent process of the process this thread belongs to. */
 	pid_t			ppid;
 	int			cpu;
 	int			guest_cpu; /* For QEMU thread */
 	refcount_t		refcnt;
+	/**
+	 * @exited: Has the thread had an exit event. Such threads are usually
+	 * removed from the machine's threads but some events/tools require
+	 * access to dead threads.
+	 */
+	bool			exited;
 	bool			comm_set;
 	int			comm_len;
 	struct list_head	namespaces_list;
@@ -71,6 +73,8 @@ struct thread *thread__new(pid_t pid, pid_t tid);
 int thread__init_maps(struct thread *thread, struct machine *machine);
 void thread__delete(struct thread *thread);
 
+void thread__set_priv_destructor(void (*destructor)(void *priv));
+
 struct thread *thread__get(struct thread *thread);
 void thread__put(struct thread *thread);
 
@@ -187,6 +191,11 @@ static inline refcount_t *thread__refcnt(struct thread *thread)
 	return &RC_CHK_ACCESS(thread)->refcnt;
 }
 
+static inline void thread__set_exited(struct thread *thread, bool exited)
+{
+	RC_CHK_ACCESS(thread)->exited = exited;
+}
+
 static inline bool thread__comm_set(const struct thread *thread)
 {
 	return RC_CHK_ACCESS(thread)->comm_set;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index e848579e61a8..b5f12390c355 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -109,9 +109,10 @@ static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid)
 
 		snprintf(path, sizeof(path), "/proc/%d/task", pid);
 		items = scandir(path, &namelist, filter, NULL);
-		if (items <= 0)
-			goto out_free_closedir;
-
+		if (items <= 0) {
+			pr_debug("scandir for %d returned empty, skipping\n", pid);
+			continue;
+		}
 		while (threads->nr + items >= max_threads) {
 			max_threads *= 2;
 			grow = true;
@@ -152,8 +153,6 @@ out_free_namelist:
 	for (i = 0; i < items; i++)
 		zfree(&namelist[i]);
 	free(namelist);
-
-out_free_closedir:
 	zfree(&threads);
 	goto out_closedir;
 }
@@ -280,13 +279,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		threads->nr = ntasks;
 	}
 out:
+	strlist__delete(slist);
 	if (threads)
 		refcount_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
 	zfree(&threads);
-	strlist__delete(slist);
 	goto out;
 }
 
diff --git a/tools/perf/util/threads.c b/tools/perf/util/threads.c
new file mode 100644
index 000000000000..ff2b169e0085
--- /dev/null
+++ b/tools/perf/util/threads.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "threads.h"
+#include "machine.h"
+#include "thread.h"
+
+static struct threads_table_entry *threads__table(struct threads *threads, pid_t tid)
+{
+	/* Cast it to handle tid == -1 */
+	return &threads->table[(unsigned int)tid % THREADS__TABLE_SIZE];
+}
+
+static size_t key_hash(long key, void *ctx __maybe_unused)
+{
+	/* The table lookup removes low bit entropy, but this is just ignored here. */
+	return key;
+}
+
+static bool key_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
+void threads__init(struct threads *threads)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		hashmap__init(&table->shard, key_hash, key_equal, NULL);
+		init_rwsem(&table->lock);
+		table->last_match = NULL;
+	}
+}
+
+void threads__exit(struct threads *threads)
+{
+	threads__remove_all_threads(threads);
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		hashmap__clear(&table->shard);
+		exit_rwsem(&table->lock);
+	}
+}
+
+size_t threads__nr(struct threads *threads)
+{
+	size_t nr = 0;
+
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+
+		down_read(&table->lock);
+		nr += hashmap__size(&table->shard);
+		up_read(&table->lock);
+	}
+	return nr;
+}
+
+/*
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
+ */
+static struct thread *__threads_table_entry__get_last_match(struct threads_table_entry *table,
+							    pid_t tid)
+{
+	struct thread *th, *res = NULL;
+
+	th = table->last_match;
+	if (th != NULL) {
+		if (thread__tid(th) == tid)
+			res = thread__get(th);
+	}
+	return res;
+}
+
+static void __threads_table_entry__set_last_match(struct threads_table_entry *table,
+						  struct thread *th)
+{
+	thread__put(table->last_match);
+	table->last_match = thread__get(th);
+}
+
+static void threads_table_entry__set_last_match(struct threads_table_entry *table,
+						struct thread *th)
+{
+	down_write(&table->lock);
+	__threads_table_entry__set_last_match(table, th);
+	up_write(&table->lock);
+}
+
+struct thread *threads__find(struct threads *threads, pid_t tid)
+{
+	struct threads_table_entry *table  = threads__table(threads, tid);
+	struct thread *res;
+
+	down_read(&table->lock);
+	res = __threads_table_entry__get_last_match(table, tid);
+	if (!res) {
+		if (hashmap__find(&table->shard, tid, &res))
+			res = thread__get(res);
+	}
+	up_read(&table->lock);
+	if (res)
+		threads_table_entry__set_last_match(table, res);
+	return res;
+}
+
+struct thread *threads__findnew(struct threads *threads, pid_t pid, pid_t tid, bool *created)
+{
+	struct threads_table_entry *table  = threads__table(threads, tid);
+	struct thread *res = NULL;
+
+	*created = false;
+	down_write(&table->lock);
+	res = thread__new(pid, tid);
+	if (res) {
+		if (hashmap__add(&table->shard, tid, res)) {
+			/* Add failed. Assume a race so find other entry. */
+			thread__put(res);
+			res = NULL;
+			if (hashmap__find(&table->shard, tid, &res))
+				res = thread__get(res);
+		} else {
+			res = thread__get(res);
+			*created = true;
+		}
+		if (res)
+			__threads_table_entry__set_last_match(table, res);
+	}
+	up_write(&table->lock);
+	return res;
+}
+
+void threads__remove_all_threads(struct threads *threads)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+		struct hashmap_entry *cur, *tmp;
+		size_t bkt;
+
+		down_write(&table->lock);
+		__threads_table_entry__set_last_match(table, NULL);
+		hashmap__for_each_entry_safe((&table->shard), cur, tmp, bkt) {
+			struct thread *old_value;
+
+			hashmap__delete(&table->shard, cur->key, /*old_key=*/NULL, &old_value);
+			thread__put(old_value);
+		}
+		up_write(&table->lock);
+	}
+}
+
+void threads__remove(struct threads *threads, struct thread *thread)
+{
+	struct threads_table_entry *table  = threads__table(threads, thread__tid(thread));
+	struct thread *old_value;
+
+	down_write(&table->lock);
+	if (table->last_match && RC_CHK_EQUAL(table->last_match, thread))
+		__threads_table_entry__set_last_match(table, NULL);
+
+	hashmap__delete(&table->shard, thread__tid(thread), /*old_key=*/NULL, &old_value);
+	thread__put(old_value);
+	up_write(&table->lock);
+}
+
+int threads__for_each_thread(struct threads *threads,
+			     int (*fn)(struct thread *thread, void *data),
+			     void *data)
+{
+	for (int i = 0; i < THREADS__TABLE_SIZE; i++) {
+		struct threads_table_entry *table = &threads->table[i];
+		struct hashmap_entry *cur;
+		size_t bkt;
+
+		down_read(&table->lock);
+		hashmap__for_each_entry((&table->shard), cur, bkt) {
+			int rc = fn((struct thread *)cur->pvalue, data);
+
+			if (rc != 0) {
+				up_read(&table->lock);
+				return rc;
+			}
+		}
+		up_read(&table->lock);
+	}
+	return 0;
+
+}
diff --git a/tools/perf/util/threads.h b/tools/perf/util/threads.h
new file mode 100644
index 000000000000..da68d2223f18
--- /dev/null
+++ b/tools/perf/util/threads.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_THREADS_H
+#define __PERF_THREADS_H
+
+#include "hashmap.h"
+#include "rwsem.h"
+
+struct thread;
+
+#define THREADS__TABLE_BITS	3
+#define THREADS__TABLE_SIZE	(1 << THREADS__TABLE_BITS)
+
+struct threads_table_entry {
+	/* Key is tid, value is struct thread. */
+	struct hashmap	       shard;
+	struct rw_semaphore    lock;
+	struct thread	       *last_match;
+};
+
+struct threads {
+	struct threads_table_entry table[THREADS__TABLE_SIZE];
+};
+
+void threads__init(struct threads *threads);
+void threads__exit(struct threads *threads);
+size_t threads__nr(struct threads *threads);
+struct thread *threads__find(struct threads *threads, pid_t tid);
+struct thread *threads__findnew(struct threads *threads, pid_t pid, pid_t tid, bool *created);
+void threads__remove_all_threads(struct threads *threads);
+void threads__remove(struct threads *threads, struct thread *thread);
+int threads__for_each_thread(struct threads *threads,
+			     int (*fn)(struct thread *thread, void *data),
+			     void *data);
+
+#endif	/* __PERF_THREADS_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index be7157de0451..4db3d1bd686c 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -28,6 +28,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	struct record_opts *opts = &top->record_opts;
 	struct target *target = &opts->target;
 	size_t ret = 0;
+	int nr_cpus;
 
 	if (top->samples) {
 		samples_per_sec = top->samples / top->delay_secs;
@@ -93,19 +94,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
+	nr_cpus = perf_cpu_map__nr(top->evlist->core.user_requested_cpus);
 	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
-				perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-				? "s" : "",
+				nr_cpus > 1 ? "s" : "",
 				target->cpu_list);
 	else {
 		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus),
-					perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1
-					? "s" : "");
+					nr_cpus, nr_cpus > 1 ? "s" : "");
 	}
 
 	perf_top__reset_sample_counters(top);
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index a8b0d79bd96c..4c5588dbb131 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -21,7 +21,6 @@ struct perf_top {
 	struct perf_tool   tool;
 	struct evlist *evlist, *sb_evlist;
 	struct record_opts record_opts;
-	struct annotation_options annotation_opts;
 	struct evswitch	   evswitch;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 319ccf09a435..c8755679281e 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -313,7 +313,8 @@ static int record_event_files(struct tracepoint_path *tps)
 	}
 	err = 0;
 out:
-	closedir(dir);
+	if (dir)
+		closedir(dir);
 	put_tracing_file(path);
 
 	return err;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 2d3c2576bab7..f0332bd3a501 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -122,6 +122,119 @@ void event_format__print(struct tep_event *event,
 	return event_format__fprintf(event, cpu, data, size, stdout);
 }
 
+/*
+ * prev_state is of size long, which is 32 bits on 32 bit architectures.
+ * As it needs to have the same bits for both 32 bit and 64 bit architectures
+ * we can just assume that the flags we care about will all be within
+ * the 32 bits.
+ */
+#define MAX_STATE_BITS 32
+
+static const char *convert_sym(struct tep_print_flag_sym *sym)
+{
+	static char save_states[MAX_STATE_BITS + 1];
+
+	memset(save_states, 0, sizeof(save_states));
+
+	/* This is the flags for the prev_state_field, now make them into a string */
+	for (; sym; sym = sym->next) {
+		long bitmask = strtoul(sym->value, NULL, 0);
+		int i;
+
+		for (i = 0; !(bitmask & 1); i++)
+			bitmask >>= 1;
+
+		if (i >= MAX_STATE_BITS)
+			continue;
+
+		save_states[i] = sym->str[0];
+	}
+
+	return save_states;
+}
+
+static struct tep_print_arg_field *
+find_arg_field(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_arg_field *field;
+
+	if (!arg)
+		return NULL;
+
+	if (arg->type == TEP_PRINT_FIELD)
+		return &arg->field;
+
+	if (arg->type == TEP_PRINT_OP) {
+		field = find_arg_field(prev_state_field, arg->op.left);
+		if (field && field->field == prev_state_field)
+			return field;
+		field = find_arg_field(prev_state_field, arg->op.right);
+		if (field && field->field == prev_state_field)
+			return field;
+	}
+	return NULL;
+}
+
+static struct tep_print_flag_sym *
+test_flags(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_arg_field *field;
+
+	field = find_arg_field(prev_state_field, arg->flags.field);
+	if (!field)
+		return NULL;
+
+	return arg->flags.flags;
+}
+
+static struct tep_print_flag_sym *
+search_op(struct tep_format_field *prev_state_field, struct tep_print_arg *arg)
+{
+	struct tep_print_flag_sym *sym = NULL;
+
+	if (!arg)
+		return NULL;
+
+	if (arg->type == TEP_PRINT_OP) {
+		sym = search_op(prev_state_field, arg->op.left);
+		if (sym)
+			return sym;
+
+		sym = search_op(prev_state_field, arg->op.right);
+		if (sym)
+			return sym;
+	} else if (arg->type == TEP_PRINT_FLAGS) {
+		sym = test_flags(prev_state_field, arg);
+	}
+
+	return sym;
+}
+
+const char *parse_task_states(struct tep_format_field *state_field)
+{
+	struct tep_print_flag_sym *sym;
+	struct tep_print_arg *arg;
+	struct tep_event *event;
+
+	event = state_field->event;
+
+	/*
+	 * Look at the event format fields, and search for where
+	 * the prev_state is parsed via the format flags.
+	 */
+	for (arg = event->print_fmt.args; arg; arg = arg->next) {
+		/*
+		 * Currently, the __print_flags() for the prev_state
+		 * is embedded in operations, so they too must be
+		 * searched.
+		 */
+		sym = search_op(state_field, arg);
+		if (sym)
+			return convert_sym(sym);
+	}
+	return NULL;
+}
+
 void parse_ftrace_printk(struct tep_handle *pevent,
 			 char *file, unsigned int size __maybe_unused)
 {
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a69ee29419f3..bbf8b26bc8da 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -15,6 +15,7 @@ struct perf_tool;
 struct thread;
 struct tep_plugin_list;
 struct evsel;
+struct tep_format_field;
 
 struct trace_event {
 	struct tep_handle	*pevent;
@@ -51,6 +52,8 @@ int parse_event_file(struct tep_handle *pevent,
 unsigned long long
 raw_field_value(struct tep_event *event, const char *name, void *data);
 
+const char *parse_task_states(struct tep_format_field *state_field);
+
 void parse_proc_kallsyms(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct tep_handle *pevent, char *file, unsigned int size);
 void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2a96df4c8d42..b38d322734b4 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -17,6 +17,7 @@
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
+#include "util/env.h"
 
 static char *debuginfo_path;
 
@@ -45,6 +46,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
+	Dwarf_Addr base;
 	/*
 	 * Some callers will use al->sym, so we can't just use the
 	 * cheaper thread__find_map() here.
@@ -57,13 +59,25 @@ static int __report_module(struct addr_location *al, u64 ip,
 	if (!dso)
 		return 0;
 
+	/*
+	 * The generated JIT DSO files only map the code segment without
+	 * ELF headers.  Since JIT codes used to be packed in a memory
+	 * segment, calculating the base address using pgoff falls into
+	 * a different code in another DSO.  So just use the map->start
+	 * directly to pick the correct one.
+	 */
+	if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
+		base = map__start(al->map);
+	else
+		base = map__start(al->map) - map__pgoff(al->map);
+
 	mod = dwfl_addrmodule(ui->dwfl, ip);
 	if (mod) {
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != map__start(al->map) - map__pgoff(al->map))
-			mod = 0;
+		if (s != base)
+			mod = NULL;
 	}
 
 	if (!mod) {
@@ -71,14 +85,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 
 		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-				      map__start(al->map) - map__pgoff(al->map), false);
+				      base, false);
 	}
 	if (!mod) {
 		char filename[PATH_MAX];
 
 		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
 			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-					      map__start(al->map) - map__pgoff(al->map), false);
+					      base, false);
 	}
 
 	if (mod) {
@@ -170,12 +184,14 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *
 			void *arg)
 {
 	struct unwind_info *ui = arg;
+	const char *arch = perf_env__arch(ui->machine->env);
 	struct stack_dump *stack = &ui->sample->user_stack;
 	u64 start, end;
 	int offset;
 	int ret;
 
-	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	ret = perf_reg_value(&start, &ui->sample->user_regs,
+			     perf_arch_reg_sp(arch));
 	if (ret)
 		return false;
 
@@ -247,12 +263,13 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
 		.thread		= thread,
-		.machine	= RC_CHK_ACCESS(thread__maps(thread))->machine,
+		.machine	= maps__machine((thread__maps(thread))),
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,
 		.best_effort    = best_effort
 	};
+	const char *arch = perf_env__arch(ui_buf.machine->env);
 	Dwarf_Word ip;
 	int err = -EINVAL, i;
 
@@ -269,7 +286,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (!ui->dwfl)
 		goto out;
 
-	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	err = perf_reg_value(&ip, &data->user_regs, perf_arch_reg_ip(arch));
 	if (err)
 		goto out;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index ebfde537b99b..6a5ac0faa6f4 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -302,12 +302,31 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
 	return 0;
 }
 
+struct read_unwind_spec_eh_frame_maps_cb_args {
+	struct dso *dso;
+	u64 base_addr;
+};
+
+static int read_unwind_spec_eh_frame_maps_cb(struct map *map, void *data)
+{
+
+	struct read_unwind_spec_eh_frame_maps_cb_args *args = data;
+
+	if (map__dso(map) == args->dso && map__start(map) - map__pgoff(map) < args->base_addr)
+		args->base_addr = map__start(map) - map__pgoff(map);
+
+	return 0;
+}
+
+
 static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 				     u64 *table_data, u64 *segbase,
 				     u64 *fde_count)
 {
-	struct map_rb_node *map_node;
-	u64 base_addr = UINT64_MAX;
+	struct read_unwind_spec_eh_frame_maps_cb_args args = {
+		.dso = dso,
+		.base_addr = UINT64_MAX,
+	};
 	int ret, fd;
 
 	if (dso->data.eh_frame_hdr_offset == 0) {
@@ -325,16 +344,11 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 			return -EINVAL;
 	}
 
-	maps__for_each_entry(thread__maps(ui->thread), map_node) {
-		struct map *map = map_node->map;
-		u64 start = map__start(map);
+	maps__for_each_map(thread__maps(ui->thread), read_unwind_spec_eh_frame_maps_cb, &args);
 
-		if (map__dso(map) == dso && start < base_addr)
-			base_addr = start;
-	}
-	base_addr -= dso->data.elf_base_addr;
+	args.base_addr -= dso->data.elf_base_addr;
 	/* Address of .eh_frame_hdr */
-	*segbase = base_addr + dso->data.eh_frame_hdr_addr;
+	*segbase = args.base_addr + dso->data.eh_frame_hdr_addr;
 	ret = unwind_spec_ehframe(dso, ui->machine, dso->data.eh_frame_hdr_offset,
 				   table_data, fde_count);
 	if (ret)
@@ -553,6 +567,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 		      int __write, void *arg)
 {
 	struct unwind_info *ui = arg;
+	const char *arch = perf_env__arch(ui->machine->env);
 	struct stack_dump *stack = &ui->sample->user_stack;
 	u64 start, end;
 	int offset;
@@ -565,7 +580,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 	}
 
 	ret = perf_reg_value(&start, &ui->sample->user_regs,
-			     LIBUNWIND__ARCH_REG_SP);
+			     perf_arch_reg_sp(arch));
 	if (ret)
 		return ret;
 
@@ -691,7 +706,7 @@ static int _unwind__prepare_access(struct maps *maps)
 {
 	void *addr_space = unw_create_addr_space(&accessors, 0);
 
-	RC_CHK_ACCESS(maps)->addr_space = addr_space;
+	maps__set_addr_space(maps, addr_space);
 	if (!addr_space) {
 		pr_err("unwind: Can't create unwind address space.\n");
 		return -ENOMEM;
@@ -714,6 +729,7 @@ static void _unwind__finish_access(struct maps *maps)
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		       void *arg, int max_stack)
 {
+	const char *arch = perf_env__arch(ui->machine->env);
 	u64 val;
 	unw_word_t ips[max_stack];
 	unw_addr_space_t addr_space;
@@ -721,7 +737,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 	int ret, i = 0;
 
 	ret = perf_reg_value(&val, &ui->sample->user_regs,
-			     LIBUNWIND__ARCH_REG_IP);
+			     perf_arch_reg_ip(arch));
 	if (ret)
 		return ret;
 
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 76cd63de80a8..2728eb4f13ea 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -12,11 +12,6 @@ struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
 struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops;
 
-static void unwind__register_ops(struct maps *maps, struct unwind_libunwind_ops *ops)
-{
-	RC_CHK_ACCESS(maps)->unwind_libunwind_ops = ops;
-}
-
 int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized)
 {
 	const char *arch;
@@ -60,7 +55,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized
 		return 0;
 	}
 out_register:
-	unwind__register_ops(maps, ops);
+	maps__set_unwind_libunwind_ops(maps, ops);
 
 	err = maps__unwind_libunwind_ops(maps)->prepare_access(maps);
 	if (initialized)
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index b2a03fa5289b..9f7164c6d9aa 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -42,14 +42,6 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
 #endif
 
-#ifndef LIBUNWIND__ARCH_REG_SP
-#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP
-#endif
-
-#ifndef LIBUNWIND__ARCH_REG_IP
-#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP
-#endif
-
 int LIBUNWIND__ARCH_REG_ID(int regnum);
 int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized);
 void unwind__flush_access(struct maps *maps);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index c1fd9ba6d697..4f561e5e4162 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -552,3 +552,22 @@ int sched_getcpu(void)
 	return -1;
 }
 #endif
+
+#ifndef HAVE_SCANDIRAT_SUPPORT
+int scandirat(int dirfd, const char *dirp,
+	      struct dirent ***namelist,
+	      int (*filter)(const struct dirent *),
+	      int (*compar)(const struct dirent **, const struct dirent **))
+{
+	char path[PATH_MAX];
+	int err, fd = openat(dirfd, dirp, O_PATH);
+
+	if (fd < 0)
+		return fd;
+
+	snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd);
+	err = scandir(path, namelist, filter, compar);
+	close(fd);
+	return err;
+}
+#endif
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7c8915d92dca..9966c21aaf04 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -6,6 +6,7 @@
 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
 #define _DEFAULT_SOURCE 1
 
+#include <dirent.h>
 #include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
@@ -56,6 +57,13 @@ int perf_tip(char **strp, const char *dirpath);
 int sched_getcpu(void);
 #endif
 
+#ifndef HAVE_SCANDIRAT_SUPPORT
+int scandirat(int dirfd, const char *dirp,
+	      struct dirent ***namelist,
+	      int (*filter)(const struct dirent *),
+	      int (*compar)(const struct dirent **, const struct dirent **));
+#endif
+
 extern bool perf_singlethreaded;
 
 void perf_set_singlethreaded(void);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index ae3eee69b659..df8963796187 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -140,23 +140,34 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	return dso;
 }
 
+struct machine__thread_dso_type_maps_cb_args {
+	struct machine *machine;
+	enum dso_type dso_type;
+};
+
+static int machine__thread_dso_type_maps_cb(struct map *map, void *data)
+{
+	struct machine__thread_dso_type_maps_cb_args *args = data;
+	struct dso *dso = map__dso(map);
+
+	if (!dso || dso->long_name[0] != '/')
+		return 0;
+
+	args->dso_type = dso__type(dso, args->machine);
+	return (args->dso_type != DSO__TYPE_UNKNOWN) ? 1 : 0;
+}
+
 static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
-	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
-	struct map_rb_node *rb_node;
-
-	maps__for_each_entry(thread__maps(thread), rb_node) {
-		struct dso *dso = map__dso(rb_node->map);
+	struct machine__thread_dso_type_maps_cb_args args = {
+		.machine = machine,
+		.dso_type = DSO__TYPE_UNKNOWN,
+	};
 
-		if (!dso || dso->long_name[0] != '/')
-			continue;
-		dso_type = dso__type(dso, machine);
-		if (dso_type != DSO__TYPE_UNKNOWN)
-			break;
-	}
+	maps__for_each_map(thread__maps(thread), machine__thread_dso_type_maps_cb, &args);
 
-	return dso_type;
+	return args.dso_type;
 }
 
 #if BITS_PER_LONG == 64
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 48dd2b018c47..57027e0ac7b6 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -7,35 +7,9 @@
 
 int zstd_init(struct zstd_data *data, int level)
 {
-	size_t ret;
-
-	data->dstream = ZSTD_createDStream();
-	if (data->dstream == NULL) {
-		pr_err("Couldn't create decompression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initDStream(data->dstream);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
-	if (!level)
-		return 0;
-
-	data->cstream = ZSTD_createCStream();
-	if (data->cstream == NULL) {
-		pr_err("Couldn't create compression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initCStream(data->cstream, level);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
 	return 0;
 }
 
@@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data)
 	return 0;
 }
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment))
 {
@@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t
 	ZSTD_outBuffer output;
 	void *record;
 
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
 	while (input.pos < input.size) {
 		record = dst;
 		size = process_header(record, 0);
@@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	ZSTD_inBuffer input = { src, src_size, 0 };
 	ZSTD_outBuffer output = { dst, dst_size, 0 };
 
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {