diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cbf39da..5cacc4f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 #include "perf.h"
+#include "perf-sys.h"
 
-#include "util/util.h"
+#include "util/cpumap.h"
 #include "util/evlist.h"
-#include "util/cache.h"
 #include "util/evsel.h"
+#include "util/evsel_fprintf.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
@@ -15,16 +16,20 @@
 #include "util/thread_map.h"
 #include "util/color.h"
 #include "util/stat.h"
+#include "util/string2.h"
 #include "util/callchain.h"
 #include "util/time-utils.h"
 
+#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
 
 #include "util/debug.h"
+#include "util/event.h"
 
 #include <linux/kernel.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <sys/prctl.h>
 #include <sys/resource.h>
 #include <inttypes.h>
@@ -34,9 +39,11 @@
 #include <pthread.h>
 #include <math.h>
 #include <api/fs/fs.h>
+#include <perf/cpumap.h>
 #include <linux/time64.h>
+#include <linux/err.h>
 
-#include "sane_ctype.h"
+#include <linux/ctype.h>
 
 #define PR_SET_NAME		15               /* Set process name */
 #define MAX_CPUS		4096
@@ -132,13 +139,13 @@
 struct perf_sched;
 
 struct trace_sched_handler {
-	int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+	int (*switch_event)(struct perf_sched *sched, struct evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine);
 
-	int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+	int (*runtime_event)(struct perf_sched *sched, struct evsel *evsel,
 			     struct perf_sample *sample, struct machine *machine);
 
-	int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
+	int (*wakeup_event)(struct perf_sched *sched, struct evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine);
 
 	/* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
@@ -146,7 +153,7 @@
 			  struct machine *machine);
 
 	int (*migrate_task_event)(struct perf_sched *sched,
-				  struct perf_evsel *evsel,
+				  struct evsel *evsel,
 				  struct perf_sample *sample,
 				  struct machine *machine);
 };
@@ -158,11 +165,11 @@
 	DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS);
 	int			*comp_cpus;
 	bool			 comp;
-	struct thread_map	*color_pids;
+	struct perf_thread_map *color_pids;
 	const char		*color_pids_str;
-	struct cpu_map		*color_cpus;
+	struct perf_cpu_map	*color_cpus;
 	const char		*color_cpus_str;
-	struct cpu_map		*cpus;
+	struct perf_cpu_map	*cpus;
 	const char		*cpus_str;
 };
 
@@ -213,7 +220,7 @@
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
+	struct rb_root_cached atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
 	bool skip_merge;
@@ -271,7 +278,7 @@
 struct idle_thread_runtime {
 	struct thread_runtime	tr;
 	struct thread		*last_thread;
-	struct rb_root		sorted_root;
+	struct rb_root_cached	sorted_root;
 	struct callchain_root	callchain;
 	struct callchain_cursor	cursor;
 };
@@ -798,7 +805,7 @@
 
 static int
 replay_wakeup_event(struct perf_sched *sched,
-		    struct perf_evsel *evsel, struct perf_sample *sample,
+		    struct evsel *evsel, struct perf_sample *sample,
 		    struct machine *machine __maybe_unused)
 {
 	const char *comm = perf_evsel__strval(evsel, sample, "comm");
@@ -819,7 +826,7 @@
 }
 
 static int replay_switch_event(struct perf_sched *sched,
-			       struct perf_evsel *evsel,
+			       struct evsel *evsel,
 			       struct perf_sample *sample,
 			       struct machine *machine __maybe_unused)
 {
@@ -950,10 +957,10 @@
 }
 
 static struct work_atoms *
-thread_atoms_search(struct rb_root *root, struct thread *thread,
+thread_atoms_search(struct rb_root_cached *root, struct thread *thread,
 			 struct list_head *sort_list)
 {
-	struct rb_node *node = root->rb_node;
+	struct rb_node *node = root->rb_root.rb_node;
 	struct work_atoms key = { .thread = thread };
 
 	while (node) {
@@ -976,10 +983,11 @@
 }
 
 static void
-__thread_latency_insert(struct rb_root *root, struct work_atoms *data,
+__thread_latency_insert(struct rb_root_cached *root, struct work_atoms *data,
 			 struct list_head *sort_list)
 {
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
+	bool leftmost = true;
 
 	while (*new) {
 		struct work_atoms *this;
@@ -992,12 +1000,14 @@
 
 		if (cmp > 0)
 			new = &((*new)->rb_left);
-		else
+		else {
 			new = &((*new)->rb_right);
+			leftmost = false;
+		}
 	}
 
 	rb_link_node(&data->node, parent, new);
-	rb_insert_color(&data->node, root);
+	rb_insert_color_cached(&data->node, root, leftmost);
 }
 
 static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
@@ -1089,7 +1099,7 @@
 }
 
 static int latency_switch_event(struct perf_sched *sched,
-				struct perf_evsel *evsel,
+				struct evsel *evsel,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
@@ -1159,7 +1169,7 @@
 }
 
 static int latency_runtime_event(struct perf_sched *sched,
-				 struct perf_evsel *evsel,
+				 struct evsel *evsel,
 				 struct perf_sample *sample,
 				 struct machine *machine)
 {
@@ -1194,7 +1204,7 @@
 }
 
 static int latency_wakeup_event(struct perf_sched *sched,
-				struct perf_evsel *evsel,
+				struct evsel *evsel,
 				struct perf_sample *sample,
 				struct machine *machine)
 {
@@ -1255,7 +1265,7 @@
 }
 
 static int latency_migrate_task_event(struct perf_sched *sched,
-				      struct perf_evsel *evsel,
+				      struct evsel *evsel,
 				      struct perf_sample *sample,
 				      struct machine *machine)
 {
@@ -1447,15 +1457,15 @@
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-	struct rb_root *root = &sched->atom_root;
+	struct rb_root_cached *root = &sched->atom_root;
 again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(root);
+		node = rb_first_cached(root);
 		if (!node)
 			break;
 
-		rb_erase(node, root);
+		rb_erase_cached(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
@@ -1466,7 +1476,7 @@
 }
 
 static int process_sched_wakeup_event(struct perf_tool *tool,
-				      struct perf_evsel *evsel,
+				      struct evsel *evsel,
 				      struct perf_sample *sample,
 				      struct machine *machine)
 {
@@ -1510,7 +1520,7 @@
 	return thread;
 }
 
-static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
+static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine)
 {
 	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
@@ -1651,7 +1661,7 @@
 }
 
 static int process_sched_switch_event(struct perf_tool *tool,
-				      struct perf_evsel *evsel,
+				      struct evsel *evsel,
 				      struct perf_sample *sample,
 				      struct machine *machine)
 {
@@ -1677,7 +1687,7 @@
 }
 
 static int process_sched_runtime_event(struct perf_tool *tool,
-				       struct perf_evsel *evsel,
+				       struct evsel *evsel,
 				       struct perf_sample *sample,
 				       struct machine *machine)
 {
@@ -1707,7 +1717,7 @@
 }
 
 static int process_sched_migrate_task_event(struct perf_tool *tool,
-					    struct perf_evsel *evsel,
+					    struct evsel *evsel,
 					    struct perf_sample *sample,
 					    struct machine *machine)
 {
@@ -1720,14 +1730,14 @@
 }
 
 typedef int (*tracepoint_handler)(struct perf_tool *tool,
-				  struct perf_evsel *evsel,
+				  struct evsel *evsel,
 				  struct perf_sample *sample,
 				  struct machine *machine);
 
 static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
 						 union perf_event *event __maybe_unused,
 						 struct perf_sample *sample,
-						 struct perf_evsel *evsel,
+						 struct evsel *evsel,
 						 struct machine *machine)
 {
 	int err = 0;
@@ -1773,7 +1783,7 @@
 
 static int perf_sched__read_events(struct perf_sched *sched)
 {
-	const struct perf_evsel_str_handler handlers[] = {
+	const struct evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",	      process_sched_switch_event, },
 		{ "sched:sched_stat_runtime", process_sched_runtime_event, },
 		{ "sched:sched_wakeup",	      process_sched_wakeup_event, },
@@ -1782,18 +1792,16 @@
 	};
 	struct perf_session *session;
 	struct perf_data data = {
-		.file      = {
-			.path = input_name,
-		},
-		.mode      = PERF_DATA_MODE_READ,
-		.force     = sched->force,
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = sched->force,
 	};
 	int rc = -1;
 
 	session = perf_session__new(&data, false, &sched->tool);
-	if (session == NULL) {
-		pr_debug("No Memory for session\n");
-		return -1;
+	if (IS_ERR(session)) {
+		pr_debug("Error creating perf session");
+		return PTR_ERR(session);
 	}
 
 	symbol__init(&session->header.env);
@@ -1837,7 +1845,7 @@
  * returns runtime data for event, allocating memory for it the
  * first time it is used.
  */
-static struct evsel_runtime *perf_evsel__get_runtime(struct perf_evsel *evsel)
+static struct evsel_runtime *perf_evsel__get_runtime(struct evsel *evsel)
 {
 	struct evsel_runtime *r = evsel->priv;
 
@@ -1852,7 +1860,7 @@
 /*
  * save last time event was seen per cpu
  */
-static void perf_evsel__save_time(struct perf_evsel *evsel,
+static void perf_evsel__save_time(struct evsel *evsel,
 				  u64 timestamp, u32 cpu)
 {
 	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
@@ -1879,7 +1887,7 @@
 }
 
 /* returns last time this event was seen on the given cpu */
-static u64 perf_evsel__get_time(struct perf_evsel *evsel, u32 cpu)
+static u64 perf_evsel__get_time(struct evsel *evsel, u32 cpu)
 {
 	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
 
@@ -1986,7 +1994,7 @@
 }
 
 static void timehist_print_sample(struct perf_sched *sched,
-				  struct perf_evsel *evsel,
+				  struct evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
@@ -2048,7 +2056,7 @@
 			    EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE |
 			    EVSEL__PRINT_CALLCHAIN_ARROW |
 			    EVSEL__PRINT_SKIP_IGNORED,
-			    &callchain_cursor, stdout);
+			    &callchain_cursor, symbol_conf.bt_stop_list,  stdout);
 
 out:
 	printf("\n");
@@ -2119,7 +2127,7 @@
 }
 
 static bool is_idle_sample(struct perf_sample *sample,
-			   struct perf_evsel *evsel)
+			   struct evsel *evsel)
 {
 	/* pid 0 == swapper == idle task */
 	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
@@ -2130,7 +2138,7 @@
 
 static void save_task_callchain(struct perf_sched *sched,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel,
+				struct evsel *evsel,
 				struct machine *machine)
 {
 	struct callchain_cursor *cursor = &callchain_cursor;
@@ -2284,7 +2292,7 @@
 static struct thread *timehist_get_thread(struct perf_sched *sched,
 					  struct perf_sample *sample,
 					  struct machine *machine,
-					  struct perf_evsel *evsel)
+					  struct evsel *evsel)
 {
 	struct thread *thread;
 
@@ -2330,7 +2338,7 @@
 
 static bool timehist_skip_sample(struct perf_sched *sched,
 				 struct thread *thread,
-				 struct perf_evsel *evsel,
+				 struct evsel *evsel,
 				 struct perf_sample *sample)
 {
 	bool rc = false;
@@ -2352,7 +2360,7 @@
 }
 
 static void timehist_print_wakeup_event(struct perf_sched *sched,
-					struct perf_evsel *evsel,
+					struct evsel *evsel,
 					struct perf_sample *sample,
 					struct machine *machine,
 					struct thread *awakened)
@@ -2387,7 +2395,7 @@
 
 static int timehist_sched_wakeup_event(struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
-				       struct perf_evsel *evsel,
+				       struct evsel *evsel,
 				       struct perf_sample *sample,
 				       struct machine *machine)
 {
@@ -2417,7 +2425,7 @@
 }
 
 static void timehist_print_migration_event(struct perf_sched *sched,
-					struct perf_evsel *evsel,
+					struct evsel *evsel,
 					struct perf_sample *sample,
 					struct machine *machine,
 					struct thread *migrated)
@@ -2471,7 +2479,7 @@
 
 static int timehist_migrate_task_event(struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
-				       struct perf_evsel *evsel,
+				       struct evsel *evsel,
 				       struct perf_sample *sample,
 				       struct machine *machine)
 {
@@ -2499,7 +2507,7 @@
 
 static int timehist_sched_change_event(struct perf_tool *tool,
 				       union perf_event *event,
-				       struct perf_evsel *evsel,
+				       struct evsel *evsel,
 				       struct perf_sample *sample,
 				       struct machine *machine)
 {
@@ -2625,7 +2633,7 @@
 
 static int timehist_sched_switch_event(struct perf_tool *tool,
 			     union perf_event *event,
-			     struct perf_evsel *evsel,
+			     struct evsel *evsel,
 			     struct perf_sample *sample,
 			     struct machine *machine __maybe_unused)
 {
@@ -2641,7 +2649,7 @@
 
 	timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
 	printf("%15s ", tstr);
-	printf("lost %" PRIu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
+	printf("lost %" PRI_lu64 " events on cpu %d\n", event->lost.lost, sample->cpu);
 
 	return 0;
 }
@@ -2762,12 +2770,12 @@
 	return ret;
 }
 
-static size_t timehist_print_idlehist_callchain(struct rb_root *root)
+static size_t timehist_print_idlehist_callchain(struct rb_root_cached *root)
 {
 	size_t ret = 0;
 	FILE *fp = stdout;
 	struct callchain_node *chain;
-	struct rb_node *rb_node = rb_first(root);
+	struct rb_node *rb_node = rb_first_cached(root);
 
 	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
 	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
@@ -2868,7 +2876,7 @@
 			if (itr == NULL)
 				continue;
 
-			callchain_param.sort(&itr->sorted_root, &itr->callchain,
+			callchain_param.sort(&itr->sorted_root.rb_root, &itr->callchain,
 					     0, &callchain_param);
 
 			printf("  CPU %2d:", i);
@@ -2895,14 +2903,14 @@
 
 typedef int (*sched_handler)(struct perf_tool *tool,
 			  union perf_event *event,
-			  struct perf_evsel *evsel,
+			  struct evsel *evsel,
 			  struct perf_sample *sample,
 			  struct machine *machine);
 
 static int perf_timehist__process_sample(struct perf_tool *tool,
 					 union perf_event *event,
 					 struct perf_sample *sample,
-					 struct perf_evsel *evsel,
+					 struct evsel *evsel,
 					 struct machine *machine)
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
@@ -2922,12 +2930,12 @@
 }
 
 static int timehist_check_attr(struct perf_sched *sched,
-			       struct perf_evlist *evlist)
+			       struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 	struct evsel_runtime *er;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	list_for_each_entry(evsel, &evlist->core.entries, core.node) {
 		er = perf_evsel__get_runtime(evsel);
 		if (er == NULL) {
 			pr_err("Failed to allocate memory for evsel runtime data\n");
@@ -2946,24 +2954,22 @@
 
 static int perf_sched__timehist(struct perf_sched *sched)
 {
-	const struct perf_evsel_str_handler handlers[] = {
+	const struct evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",       timehist_sched_switch_event, },
 		{ "sched:sched_wakeup",	      timehist_sched_wakeup_event, },
 		{ "sched:sched_wakeup_new",   timehist_sched_wakeup_event, },
 	};
-	const struct perf_evsel_str_handler migrate_handlers[] = {
+	const struct evsel_str_handler migrate_handlers[] = {
 		{ "sched:sched_migrate_task", timehist_migrate_task_event, },
 	};
 	struct perf_data data = {
-		.file      = {
-			.path = input_name,
-		},
-		.mode      = PERF_DATA_MODE_READ,
-		.force     = sched->force,
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+		.force = sched->force,
 	};
 
 	struct perf_session *session;
-	struct perf_evlist *evlist;
+	struct evlist *evlist;
 	int err = -1;
 
 	/*
@@ -2985,8 +2991,8 @@
 	symbol_conf.use_callchain = sched->show_callchain;
 
 	session = perf_session__new(&data, false, &sched->tool);
-	if (session == NULL)
-		return -ENOMEM;
+	if (IS_ERR(session))
+		return PTR_ERR(session);
 
 	evlist = session->evlist;
 
@@ -3074,11 +3080,12 @@
 	}
 }
 
-static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *data)
 {
-	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct rb_node **new = &(root->rb_root.rb_node), *parent = NULL;
 	struct work_atoms *this;
 	const char *comm = thread__comm_str(data->thread), *this_comm;
+	bool leftmost = true;
 
 	while (*new) {
 		int cmp;
@@ -3092,6 +3099,7 @@
 			new = &((*new)->rb_left);
 		} else if (cmp < 0) {
 			new = &((*new)->rb_right);
+			leftmost = false;
 		} else {
 			this->num_merged++;
 			this->total_runtime += data->total_runtime;
@@ -3109,7 +3117,7 @@
 
 	data->num_merged++;
 	rb_link_node(&data->node, parent, new);
-	rb_insert_color(&data->node, root);
+	rb_insert_color_cached(&data->node, root, leftmost);
 }
 
 static void perf_sched__merge_lat(struct perf_sched *sched)
@@ -3120,8 +3128,8 @@
 	if (sched->skip_merge)
 		return;
 
-	while ((node = rb_first(&sched->atom_root))) {
-		rb_erase(node, &sched->atom_root);
+	while ((node = rb_first_cached(&sched->atom_root))) {
+		rb_erase_cached(node, &sched->atom_root);
 		data = rb_entry(node, struct work_atoms, node);
 		__merge_work_atoms(&sched->merged_atom_root, data);
 	}
@@ -3143,7 +3151,7 @@
 	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
 	printf(" -----------------------------------------------------------------------------------------------------------------\n");
 
-	next = rb_first(&sched->sorted_atom_root);
+	next = rb_first_cached(&sched->sorted_atom_root);
 
 	while (next) {
 		struct work_atoms *work_list;
@@ -3168,7 +3176,7 @@
 
 static int setup_map_cpus(struct perf_sched *sched)
 {
-	struct cpu_map *map;
+	struct perf_cpu_map *map;
 
 	sched->max_cpu  = sysconf(_SC_NPROCESSORS_CONF);
 
@@ -3181,7 +3189,7 @@
 	if (!sched->map.cpus_str)
 		return 0;
 
-	map = cpu_map__new(sched->map.cpus_str);
+	map = perf_cpu_map__new(sched->map.cpus_str);
 	if (!map) {
 		pr_err("failed to get cpus map from %s\n", sched->map.cpus_str);
 		return -1;
@@ -3193,7 +3201,7 @@
 
 static int setup_color_pids(struct perf_sched *sched)
 {
-	struct thread_map *map;
+	struct perf_thread_map *map;
 
 	if (!sched->map.color_pids_str)
 		return 0;
@@ -3210,12 +3218,12 @@
 
 static int setup_color_cpus(struct perf_sched *sched)
 {
-	struct cpu_map *map;
+	struct perf_cpu_map *map;
 
 	if (!sched->map.color_cpus_str)
 		return 0;
 
-	map = cpu_map__new(sched->map.color_cpus_str);
+	map = perf_cpu_map__new(sched->map.color_cpus_str);
 	if (!map) {
 		pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str);
 		return -1;
@@ -3336,7 +3344,7 @@
 
 int cmd_sched(int argc, const char **argv)
 {
-	const char default_sort_order[] = "avg, max, switch, runtime";
+	static const char default_sort_order[] = "avg, max, switch, runtime";
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,