Merge tag 'perf-core-for-mingo-20161201' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New features:

 - Support AArch64 in the 'annotate' code, native/local and
   cross-arch/remote (Kim Phillips)

 - Allow considering just events in a given time interval, via the
   '--time start.s.ms,end.s.ms' command line, added to 'perf kmem',
   'perf report', 'perf sched timehist' and 'perf script' (David Ahern)

 - Add option to stop printing a callchain at one of a given group of
   symbol names (David Ahern)

 - Handle CPU migration events in 'perf sched timehist' (David Ahern)

 - Track memory freed in 'perf kmem stat' (David Ahern)

Infrastructure:

 - Add initial support (and perf test entry) for tooling hooks, starting with
   'record_start' and 'record_end', that will have as its initial user the
   eBPF infrastructure, where perf_ prefixed functions will be JITed and
   run when such hooks are called (Wang Nan)

 - Remove redundant "test" and similar strings from 'perf test' descriptions
   (Arnaldo Carvalho de Melo)

 - Implement assorted libbpf improvements (Wang Nan)

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

37 files changed, 842 insertions, 149 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 4212ed62235b..8143536b462a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -110,3 +110,59 @@ int bpf_map_update_elem(int fd, void *key, void *value,
 
 	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
 }
+
+int bpf_map_lookup_elem(int fd, void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_delete_elem(int fd, void *key)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+
+	return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_map_get_next_key(int fd, void *key, void *next_key)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.next_key = ptr_to_u64(next_key);
+
+	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+}
+
+int bpf_obj_pin(int fd, const char *pathname)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.pathname = ptr_to_u64((void *)pathname);
+	attr.bpf_fd = fd;
+
+	return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+}
+
+int bpf_obj_get(const char *pathname)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.pathname = ptr_to_u64((void *)pathname);
+
+	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index e8ba54087497..253c3dbb06b4 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -35,4 +35,11 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 
 int bpf_map_update_elem(int fd, void *key, void *value,
 			u64 flags);
+
+int bpf_map_lookup_elem(int fd, void *key, void *value);
+int bpf_map_delete_elem(int fd, void *key);
+int bpf_map_get_next_key(int fd, void *key, void *next_key);
+int bpf_obj_pin(int fd, const char *pathname);
+int bpf_obj_get(const char *pathname);
+
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 96a2b2ff1212..2e974593f3e8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -229,6 +229,10 @@ struct bpf_object {
 	 * all objects.
 	 */
 	struct list_head list;
+
+	void *priv;
+	bpf_object_clear_priv_t clear_priv;
+
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
@@ -1229,6 +1233,9 @@ void bpf_object__close(struct bpf_object *obj)
 	if (!obj)
 		return;
 
+	if (obj->clear_priv)
+		obj->clear_priv(obj, obj->priv);
+
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 
@@ -1282,6 +1289,22 @@ unsigned int bpf_object__kversion(struct bpf_object *obj)
 	return obj ? obj->kern_version : 0;
 }
 
+int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+			 bpf_object_clear_priv_t clear_priv)
+{
+	if (obj->priv && obj->clear_priv)
+		obj->clear_priv(obj, obj->priv);
+
+	obj->priv = priv;
+	obj->clear_priv = clear_priv;
+	return 0;
+}
+
+void *bpf_object__priv(struct bpf_object *obj)
+{
+	return obj ? obj->priv : ERR_PTR(-EINVAL);
+}
+
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
@@ -1501,3 +1524,15 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 	}
 	return NULL;
 }
+
+struct bpf_map *
+bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
+{
+	int i;
+
+	for (i = 0; i < obj->nr_maps; i++) {
+		if (obj->maps[i].offset == offset)
+			return &obj->maps[i];
+	}
+	return ERR_PTR(-ENOENT);
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index dd7a513efb10..a5a8b86a06fe 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -24,6 +24,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/err.h>
+#include <sys/types.h>  // for size_t
 
 enum libbpf_errno {
 	__LIBBPF_ERRNO__START = 4000,
@@ -79,6 +80,11 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev);
 	     (pos) != NULL;				\
 	     (pos) = (tmp), (tmp) = bpf_object__next(tmp))
 
+typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *);
+int bpf_object__set_priv(struct bpf_object *obj, void *priv,
+			 bpf_object_clear_priv_t clear_priv);
+void *bpf_object__priv(struct bpf_object *prog);
+
 /* Accessors of bpf_program. */
 struct bpf_program;
 struct bpf_program *bpf_program__next(struct bpf_program *prog,
@@ -195,6 +201,13 @@ struct bpf_map;
 struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name);
 
+/*
+ * Get bpf_map through the offset of corresponding struct bpf_map_def
+ * in the bpf object file.
+ */
+struct bpf_map *
+bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
+
 struct bpf_map *
 bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 #define bpf_map__for_each(pos, obj)		\
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index ff0f433b3fce..479fc3261a50 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -61,6 +61,13 @@ OPTIONS
 	default, but this option shows live (currently allocated) pages
 	instead.  (This option works with --page option only)
 
+--time::
+	Only analyze samples within given time window: <start>,<stop>. Times
+	have the format seconds.microseconds. If start is not given (i.e., time
+	string is ',x.y') then analysis starts at the beginning of the file. If
+	stop time is not given (i.e, time string is 'x.y,') then analysis goes
+	to end of file.
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d1746295abf..3a166ae4a4d3 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -382,6 +382,13 @@ OPTIONS
 --header-only::
 	Show only perf.data header (forces --stdio).
 
+--time::
+	Only analyze samples within given time window: <start>,<stop>. Times
+	have the format seconds.microseconds. If start is not given (i.e., time
+	string is ',x.y') then analysis starts at the beginning of the file. If
+	stop time is not given (i.e, time string is 'x.y,') then analysis goes
+	to end of file.
+
 --itrace::
 	Options for decoding instruction tracing data. The options are:
 
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index fb9e52d65fca..7775b1eb2bee 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -128,6 +128,18 @@ OPTIONS for 'perf sched timehist'
 --wakeups::
 	Show wakeup events.
 
+-M::
+--migrations::
+	Show migration events.
+
+--time::
+	Only analyze samples within given time window: <start>,<stop>. Times
+	have the format seconds.microseconds. If start is not given (i.e., time
+	string is ',x.y') then analysis starts at the beginning of the file. If
+	stop time is not given (i.e, time string is 'x.y,') then analysis goes
+	to end of file.
+
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index c01904f388ce..5dc5c6a09ac4 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -212,6 +212,9 @@ OPTIONS
 --hide-call-graph::
         When printing symbols do not display call chain.
 
+--stop-bt::
+        Stop display of callgraph at these symbols
+
 -C::
 --cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
 	be provided as a comma-separated list with no space: 0,1. Ranges of
@@ -289,6 +292,13 @@ include::itrace.txt[]
 --force::
 	Don't do ownership validation.
 
+--time::
+	Only analyze samples within given time window: <start>,<stop>. Times
+	have the format seconds.microseconds. If start is not given (i.e., time
+	string is ',x.y') then analysis starts at the beginning of the file. If
+	stop time is not given (i.e, time string is 'x.y,') then analysis goes
+	to end of file.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
new file mode 100644
index 000000000000..44eafd6f2d50
--- /dev/null
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -0,0 +1,62 @@
+#include <sys/types.h>
+#include <regex.h>
+
+struct arm64_annotate {
+	regex_t call_insn,
+		jump_insn;
+};
+
+static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct arm64_annotate *arm = arch->priv;
+	struct ins_ops *ops;
+	regmatch_t match[2];
+
+	if (!regexec(&arm->jump_insn, name, 2, match, 0))
+		ops = &jump_ops;
+	else if (!regexec(&arm->call_insn, name, 2, match, 0))
+		ops = &call_ops;
+	else if (!strcmp(name, "ret"))
+		ops = &ret_ops;
+	else
+		return NULL;
+
+	arch__associate_ins_ops(arch, name, ops);
+	return ops;
+}
+
+static int arm64__annotate_init(struct arch *arch)
+{
+	struct arm64_annotate *arm;
+	int err;
+
+	if (arch->initialized)
+		return 0;
+
+	arm = zalloc(sizeof(*arm));
+	if (!arm)
+		return -1;
+
+	/* bl, blr */
+	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
+	if (err)
+		goto out_free_arm;
+	/* b, b.cond, br, cbz/cbnz, tbz/tbnz */
+	err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$",
+		      REG_EXTENDED);
+	if (err)
+		goto out_free_call;
+
+	arch->initialized = true;
+	arch->priv	  = arm;
+	arch->associate_instruction_ops   = arm64__associate_instruction_ops;
+	arch->objdump.comment_char	  = ';';
+	arch->objdump.skip_functions_char = '+';
+	return 0;
+
+out_free_call:
+	regfree(&arm->call_insn);
+out_free_arm:
+	free(arm);
+	return -1;
+}
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 2218cb64f840..99d66191e56c 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -4,27 +4,27 @@
 
 struct test arch_tests[] = {
 	{
-		.desc = "x86 rdpmc test",
+		.desc = "x86 rdpmc",
 		.func = test__rdpmc,
 	},
 	{
-		.desc = "Test converting perf time to TSC",
+		.desc = "Convert perf time to TSC",
 		.func = test__perf_time_to_tsc,
 	},
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
-		.desc = "Test dwarf unwind",
+		.desc = "DWARF unwind",
 		.func = test__dwarf_unwind,
 	},
 #endif
 #ifdef HAVE_AUXTRACE_SUPPORT
 	{
-		.desc = "Test x86 instruction decoder - new instructions",
+		.desc = "x86 instruction decoder - new instructions",
 		.func = test__insn_x86,
 	},
 #endif
 	{
-		.desc = "Test intel cqm nmi context read",
+		.desc = "Intel cqm nmi context read",
 		.func = test__intel_cqm_count_nmi_context,
 	},
 	{
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index d426dcb18ce9..35a02f8e5a4a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -11,6 +11,7 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/callchain.h"
+#include "util/time-utils.h"
 
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
@@ -49,6 +50,7 @@ struct alloc_stat {
 	u64	ptr;
 	u64	bytes_req;
 	u64	bytes_alloc;
+	u64	last_alloc;
 	u32	hit;
 	u32	pingpong;
 
@@ -62,9 +64,13 @@ static struct rb_root root_alloc_sorted;
 static struct rb_root root_caller_stat;
 static struct rb_root root_caller_sorted;
 
-static unsigned long total_requested, total_allocated;
+static unsigned long total_requested, total_allocated, total_freed;
 static unsigned long nr_allocs, nr_cross_allocs;
 
+/* filters for controlling start and stop of time of analysis */
+static struct perf_time_interval ptime;
+const char *time_str;
+
 static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 			     int bytes_req, int bytes_alloc, int cpu)
 {
@@ -105,6 +111,8 @@ static int insert_alloc_stat(unsigned long call_site, unsigned long ptr,
 	}
 	data->call_site = call_site;
 	data->alloc_cpu = cpu;
+	data->last_alloc = bytes_alloc;
+
 	return 0;
 }
 
@@ -223,6 +231,8 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 	if (!s_alloc)
 		return 0;
 
+	total_freed += s_alloc->last_alloc;
+
 	if ((short)sample->cpu != s_alloc->alloc_cpu) {
 		s_alloc->pingpong++;
 
@@ -907,6 +917,15 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	return 0;
 }
 
+static bool perf_kmem__skip_sample(struct perf_sample *sample)
+{
+	/* skip sample based on time? */
+	if (perf_time__skip_sample(&ptime, sample->time))
+		return true;
+
+	return false;
+}
+
 typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
 				  struct perf_sample *sample);
 
@@ -926,6 +945,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
+	if (perf_kmem__skip_sample(sample))
+		return 0;
+
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 
 	if (evsel->handler != NULL) {
@@ -1128,6 +1150,11 @@ static void print_slab_summary(void)
 	printf("\n========================\n");
 	printf("Total bytes requested: %'lu\n", total_requested);
 	printf("Total bytes allocated: %'lu\n", total_allocated);
+	printf("Total bytes freed:     %'lu\n", total_freed);
+	if (total_allocated > total_freed) {
+		printf("Net total bytes allocated: %'lu\n",
+		total_allocated - total_freed);
+	}
 	printf("Total bytes wasted on internal fragmentation: %'lu\n",
 	       total_allocated - total_requested);
 	printf("Internal fragmentation: %f%%\n",
@@ -1884,6 +1911,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
 			   parse_page_opt),
 	OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
+	OPT_STRING(0, "time", &time_str, "str",
+		   "Time span of interest (start,stop)"),
 	OPT_END()
 	};
 	const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -1944,6 +1973,11 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	symbol__init(&session->header.env);
 
+	if (perf_time__parse_str(&ptime, time_str) != 0) {
+		pr_err("Invalid time string\n");
+		return -EINVAL;
+	}
+
 	if (!strcmp(argv[0], "stat")) {
 		setlocale(LC_ALL, "");
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 67d2a9003294..fa26865364b6 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -37,6 +37,7 @@
 #include "util/llvm-utils.h"
 #include "util/bpf-loader.h"
 #include "util/trigger.h"
+#include "util/perf-hooks.h"
 #include "asm/bug.h"
 
 #include <unistd.h>
@@ -206,6 +207,12 @@ static void sig_handler(int sig)
 	done = 1;
 }
 
+static void sigsegv_handler(int sig)
+{
+	perf_hooks__recover();
+	sighandler_dump_stack(sig);
+}
+
 static void record__sig_exit(void)
 {
 	if (signr == -1)
@@ -833,6 +840,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
+	signal(SIGSEGV, sigsegv_handler);
 
 	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
 		signal(SIGUSR2, snapshot_sig_handler);
@@ -970,6 +978,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	trigger_ready(&auxtrace_snapshot_trigger);
 	trigger_ready(&switch_output_trigger);
+	perf_hooks__invoke_record_start();
 	for (;;) {
 		unsigned long long hits = rec->samples;
 
@@ -1114,6 +1123,8 @@ out_child:
 		}
 	}
 
+	perf_hooks__invoke_record_end();
+
 	if (!err && !quiet) {
 		char samples[128];
 		const char *postfix = rec->timestamp_filename ?
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3dfbfffe2ecd..d2afbe4a240d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,7 +36,7 @@
 #include "util/hist.h"
 #include "util/data.h"
 #include "arch/common.h"
-
+#include "util/time-utils.h"
 #include "util/auxtrace.h"
 
 #include <dlfcn.h>
@@ -59,6 +59,8 @@ struct report {
 	const char		*pretty_printing_style;
 	const char		*cpu_list;
 	const char		*symbol_filter_str;
+	const char		*time_str;
+	struct perf_time_interval ptime;
 	float			min_percent;
 	u64			nr_entries;
 	u64			queue_size;
@@ -158,6 +160,9 @@ static int process_sample_event(struct perf_tool *tool,
 	};
 	int ret = 0;
 
+	if (perf_time__skip_sample(&rep->ptime, sample->time))
+		return 0;
+
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
 			 event->header.type);
@@ -830,6 +835,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
 			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
 			     stdio__config_color, "always"),
+	OPT_STRING(0, "time", &report.time_str, "str",
+		   "Time span of interest (start,stop)"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -1015,6 +1022,11 @@ repeat:
 	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
+	if (perf_time__parse_str(&report.ptime, report.time_str) != 0) {
+		pr_err("Invalid time string\n");
+		return -EINVAL;
+	}
+
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index a49a032f5b15..870d94cd20ba 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -15,6 +15,7 @@
 #include "util/color.h"
 #include "util/stat.h"
 #include "util/callchain.h"
+#include "util/time-utils.h"
 
 #include <subcmd/parse-options.h>
 #include "util/trace-event.h"
@@ -203,7 +204,10 @@ struct perf_sched {
 	unsigned int	max_stack;
 	bool		show_cpu_visual;
 	bool		show_wakeups;
+	bool		show_migrations;
 	u64		skipped_samples;
+	const char	*time_str;
+	struct perf_time_interval ptime;
 };
 
 /* per thread run time data */
@@ -216,6 +220,8 @@ struct thread_runtime {
 
 	struct stats run_stats;
 	u64 total_run_time;
+
+	u64 migrations;
 };
 
 /* per event run time data */
@@ -1834,13 +1840,14 @@ static void timehist_header(struct perf_sched *sched)
 static void timehist_print_sample(struct perf_sched *sched,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
-				  struct thread *thread)
+				  struct thread *thread,
+				  u64 t)
 {
 	struct thread_runtime *tr = thread__priv(thread);
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
 
-	timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
+	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
 
 	if (sched->show_cpu_visual) {
@@ -2191,12 +2198,94 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool,
 		tr->ready_to_run = sample->time;
 
 	/* show wakeups if requested */
-	if (sched->show_wakeups)
+	if (sched->show_wakeups &&
+	    !perf_time__skip_sample(&sched->ptime, sample->time))
 		timehist_print_wakeup_event(sched, sample, machine, thread);
 
 	return 0;
 }
 
+static void timehist_print_migration_event(struct perf_sched *sched,
+					struct perf_evsel *evsel,
+					struct perf_sample *sample,
+					struct machine *machine,
+					struct thread *migrated)
+{
+	struct thread *thread;
+	char tstr[64];
+	u32 max_cpus = sched->max_cpu + 1;
+	u32 ocpu, dcpu;
+
+	if (sched->summary_only)
+		return;
+
+	max_cpus = sched->max_cpu + 1;
+	ocpu = perf_evsel__intval(evsel, sample, "orig_cpu");
+	dcpu = perf_evsel__intval(evsel, sample, "dest_cpu");
+
+	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	if (thread == NULL)
+		return;
+
+	if (timehist_skip_sample(sched, thread) &&
+	    timehist_skip_sample(sched, migrated)) {
+		return;
+	}
+
+	timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
+	printf("%15s [%04d] ", tstr, sample->cpu);
+
+	if (sched->show_cpu_visual) {
+		u32 i;
+		char c;
+
+		printf("  ");
+		for (i = 0; i < max_cpus; ++i) {
+			c = (i == sample->cpu) ? 'm' : ' ';
+			printf("%c", c);
+		}
+		printf("  ");
+	}
+
+	printf(" %-*s ", comm_width, timehist_get_commstr(thread));
+
+	/* dt spacer */
+	printf("  %9s  %9s  %9s ", "", "", "");
+
+	printf("migrated: %s", timehist_get_commstr(migrated));
+	printf(" cpu %d => %d", ocpu, dcpu);
+
+	printf("\n");
+}
+
+static int timehist_migrate_task_event(struct perf_tool *tool,
+				       union perf_event *event __maybe_unused,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       struct machine *machine)
+{
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	struct thread *thread;
+	struct thread_runtime *tr = NULL;
+	/* want pid of migrated task not pid in sample */
+	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+
+	thread = machine__findnew_thread(machine, 0, pid);
+	if (thread == NULL)
+		return -1;
+
+	tr = thread__get_runtime(thread);
+	if (tr == NULL)
+		return -1;
+
+	tr->migrations++;
+
+	/* show migrations if requested */
+	timehist_print_migration_event(sched, evsel, sample, machine, thread);
+
+	return 0;
+}
+
 static int timehist_sched_change_event(struct perf_tool *tool,
 				       union perf_event *event,
 				       struct perf_evsel *evsel,
@@ -2204,10 +2293,11 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
+	struct perf_time_interval *ptime = &sched->ptime;
 	struct addr_location al;
 	struct thread *thread;
 	struct thread_runtime *tr = NULL;
-	u64 tprev;
+	u64 tprev, t = sample->time;
 	int rc = 0;
 
 	if (machine__resolve(machine, &al, sample) < 0) {
@@ -2234,9 +2324,35 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 
 	tprev = perf_evsel__get_time(evsel, sample->cpu);
 
-	timehist_update_runtime_stats(tr, sample->time, tprev);
+	/*
+	 * If start time given:
+	 * - sample time is under window user cares about - skip sample
+	 * - tprev is under window user cares about  - reset to start of window
+	 */
+	if (ptime->start && ptime->start > t)
+		goto out;
+
+	if (ptime->start > tprev)
+		tprev = ptime->start;
+
+	/*
+	 * If end time given:
+	 * - previous sched event is out