Merge tag 'perf-core-for-mingo-5.5-20191011' 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:

perf trace:

  Arnaldo Carvalho de Melo:

  - Reuse the strace-like syscall_arg_fmt->scnprintf() beautification routines
    (convert integer arguments into strings, like open flags, etc) in tracepoint
    arguments.

    For now the type based scnprintf routines (pid_t, umode_t, etc) and the
    ones based in well known arg name based ("fd", etc) gets associated with
    tracepoint args of that type.

    A tracepoint only arg, "msr", for the msr:{write,read}_msr gets added as
    an initial step.

  - Introduce syscall_arg_fmt->strtoul() methods to be the reverse operation
    of ->scnprintf(), i.e. to go from a string to an integer.

  - Implement --filter, just like in 'perf record', that affects the tracepoint
    events specied thus far in the command line, use the ->strtoul() methods
    to allow strings in tables associated with beautifiers to the integers
    the in-kernel tracepoint (eBPF later) filters expect, e.g.:

     # perf trace --max-events 1 -e sched:*ipi --filter="cpu==1 || cpu==2"
      0.000 as/24630 sched:sched_wake_idle_without_ipi(cpu: 1)
     #

     # perf trace --max-events 1 --max-stack=32 -e msr:* --filter="msr==IA32_TSC_DEADLINE"
      207.000 cc1/19963 msr:write_msr(msr: IA32_TSC_DEADLINE, val: 5442316760822)
                                        do_trace_write_msr ([kernel.kallsyms])
                                        do_trace_write_msr ([kernel.kallsyms])
                                        lapic_next_deadline ([kernel.kallsyms])
                                        clockevents_program_event ([kernel.kallsyms])
                                        hrtimer_interrupt ([kernel.kallsyms])
                                        smp_apic_timer_interrupt ([kernel.kallsyms])
                                        apic_timer_interrupt ([kernel.kallsyms])
                                        [0x6ff66c] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x7047c3] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x707708] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_one_pass (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d37] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x4f3d49] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        execute_pass_list (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        cgraph_node::expand (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x2625b4] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        symbol_table::finalize_compilation_unit (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x5ae8b9] (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        toplev::main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        main (/usr/lib/gcc-cross/alpha-linux-gnu/8/cc1)
                                        [0x26b6a] (/usr/lib/x86_64-linux-gnu/libc-2.29.so)
     #
     # perf trace --max-events 8 -e msr:* --filter="msr==IA32_SPEC_CTRL"
         0.000 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.063 migration/3/25 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.217 kworker/u16:1-/4826 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.687 rcu_sched/11 msr:write_msr(msr: IA32_SPEC_CTRL)
         0.696 :13280/13280 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.305 :13281/13281 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         0.355 :13274/13274 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
         2.743 kworker/u16:0-/6711 msr:write_msr(msr: IA32_SPEC_CTRL)
     #
     # perf trace --max-events 8 --cpu 1 -e msr:* --filter="msr!=IA32_SPEC_CTRL && msr!=IA32_TSC_DEADLINE && msr != FS_BASE"
           0.000 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 68719479037)
           0.096 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
         238.925 mtr-packet/30819 msr:write_msr(msr: 0x830, val: 8589936893)
         511.010 :0/0 msr:write_msr(msr: 0x830, val: 68719479037)
        1005.052 :0/0 msr:read_msr(msr: IA32_TSC_ADJUST)
        1235.131 CPU 0/KVM/3750 msr:write_msr(msr: 0x830, val: 4294969595)
        1235.195 CPU 0/KVM/3750 msr:read_msr(msr: IA32_SYSENTER_ESP, val: -2199023037952)
        1235.201 CPU 0/KVM/3750 msr:read_msr(msr: IA32_APICBASE, val: 4276096000)
     #

  - Default to not using libtraceevent and its plugins for beautifying
    tracepoint arguments, since now we're reusing the strace-like beatufiers.
    Use --libtraceevent_print (using just --libtrace is unambiguous and can
    be used as a short hand) to go back to those beautifiers.

    This will help in the transition, as can be seen in some of the sched tracepoints
    that still need some work in the libbeauty based mode:

    # trace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.006 (         ): sched:sched_wakeup(comm: "trace", pid: 3319 (trace), prio: 120, success: 1)
         0.348 (         ): sched:sched_process_exec(filename: 140212596720100, pid: 3319 (sleep), old_pid: 3319 (sleep))
         0.490 (         ): msr:write_msr(msr: FS_BASE, val: 139631189321088)
         0.670 (         ): nanosleep(rqtp: 0x7ffc52c23bc0)                                    ...
         0.674 (         ): sched:sched_stat_runtime(comm: "sleep", pid: 3319 (sleep), runtime: 659259, vruntime: 78942418342)
         0.675 (         ): sched:sched_switch(prev_comm: "sleep", prev_pid: 3319 (sleep), prev_prio: 120, prev_state: 1, next_comm: "swapper/0", next_prio: 120)
      1001.059 (         ): sched:sched_waking(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
      1001.098 (         ): sched:sched_wakeup(comm: "sleep", pid: 3319 (sleep), prio: 120, success: 1)
         0.670 (1000.504 ms):  ... [continued]: nanosleep())                                        = 0
      1001.456 (         ): sched:sched_process_exit(comm: "sleep", pid: 3319 (sleep), prio: 120)
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
    # trace --libtrace --no-inherit -e msr:*,*sleep,sched:* sleep 1
         0.000 (         ): sched:sched_waking(comm=trace pid=3323 prio=120 target_cpu=000)
         0.007 (         ): sched:sched_wakeup(comm=trace pid=3323 prio=120 target_cpu=000)
         0.382 (         ): sched:sched_process_exec(filename=/usr/bin/sleep pid=3323 old_pid=3323)
         0.525 (         ): msr:write_msr(c0000100, value 7f5d508a0580)
         0.713 (         ): nanosleep(rqtp: 0x7fff487fb4a0)                                    ...
         0.717 (         ): sched:sched_stat_runtime(comm=sleep pid=3323 runtime=617722 [ns] vruntime=78957731636 [ns])
         0.719 (         ): sched:sched_switch(prev_comm=sleep prev_pid=3323 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120)
      1001.117 (         ): sched:sched_waking(comm=sleep pid=3323 prio=120 target_cpu=000)
      1001.157 (         ): sched:sched_wakeup(comm=sleep pid=3323 prio=120 target_cpu=000)
         0.713 (1000.522 ms):  ... [continued]: nanosleep())                                        = 0
      1001.538 (         ): sched:sched_process_exit(comm=sleep pid=3323 prio=120)
    #

  - Make -v (verbose) mode be honoured for .perfconfig based trace.add_events,
    to help in diagnosing problems with building eBPF events (-e source.c).

  - When using eBPF syscall payload augmentation do not show strace-like
    syscalls when all the user specified was some tracepoint event, bringing
    the behaviour in line with that of when not using eBPF augmentation.

Intel PT:

  exported-sql-viewer GUI:

  Adrian Hunter:

  - Add LookupModel, HBoxLayout, VBoxLayout, global time range calculations
    so as to add a time chart by CPU.

perf script:

  Andi Kleen:

  - Allow --time (to specify a time span of interest) with --reltime

perf diff:

  Jin Yao:

  - Report noise for cycles diff, i.e. a histogram + stddev.
    (timestamps relative to start).

perf annotate:

  Arnaldo Carvalho de Melo:

  - Initialize env->cpuid when running in live mode (perf top), as it
    is used in some of the per arch annotation init routines.

samples bpf:

  Björn Töpel:

  - Fixup fallout of using tools/perf/perf-sys. from outside tools/perf.

Core:

  Ian Rogers:

  - Avoid 'sample_reg_masks' being const + weak, as this breaks with some
    compilers that constant-propagate from the weak symbol.

libperf:

  - First part of moving the perf_mmap class from tools/perf to libperf.

  - Propagate CFLAGS to libperf from the tools/perf Makefile.

Vendor events:

  John Garry:

  - Add entry in MAINTAINERS with reviewers for the for perf tool arm64
    pmu-events files.

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

19 files changed, 248 insertions, 504 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8dcfca1a882f..39814b1806a6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -95,6 +95,7 @@ perf-y += cloexec.o
 perf-y += call-path.o
 perf-y += rwsem.o
 perf-y += thread-stack.o
+perf-y += spark.o
 perf-$(CONFIG_AUXTRACE) += auxtrace.o
 perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
 perf-$(CONFIG_AUXTRACE) += intel-pt.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4036c7f7b0fb..2b856b6b46f6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -853,6 +853,10 @@ static int __symbol__account_cycles(struct cyc_hist *ch,
 			   ch[offset].start < start)
 			return 0;
 	}
+
+	if (ch[offset].num < NUM_SPARKS)
+		ch[offset].cycles_spark[ch[offset].num] = cycles;
+
 	ch[offset].have_start = have_start;
 	ch[offset].start = start;
 	ch[offset].cycles += cycles;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d76fd0e81f46..3528bd4f8f21 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -11,6 +11,7 @@
 #include <pthread.h>
 #include <asm/bug.h>
 #include "symbol_conf.h"
+#include "spark.h"
 
 struct hist_browser_timer;
 struct hist_entry;
@@ -235,6 +236,7 @@ struct cyc_hist {
 	u64	cycles_aggr;
 	u64	cycles_max;
 	u64	cycles_min;
+	s64	cycles_spark[NUM_SPARKS];
 	u32	num;
 	u32	num_aggr;
 	u8	have_start;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 3baca06786fb..2a91a10ccfcc 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -2,6 +2,7 @@
 #include "cpumap.h"
 #include "debug.h"
 #include "env.h"
+#include "util/header.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 #include "bpf-event.h"
@@ -256,6 +257,21 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	return 0;
 }
 
+int perf_env__read_cpuid(struct perf_env *env)
+{
+	char cpuid[128];
+	int err = get_cpuid(cpuid, sizeof(cpuid));
+
+	if (err)
+		return err;
+
+	free(env->cpuid);
+	env->cpuid = strdup(cpuid);
+	if (env->cpuid == NULL)
+		return ENOMEM;
+	return 0;
+}
+
 static int perf_env__read_arch(struct perf_env *env)
 {
 	struct utsname uts;
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index db40906e2937..a3059dc1abe5 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -104,6 +104,7 @@ void perf_env__exit(struct perf_env *env);
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
+int perf_env__read_cpuid(struct perf_env *env);
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
 void cpu_cache_level__free(struct cpu_cache_level *cache);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d277a98e62df..21b77efa802c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -42,6 +42,7 @@
 #include <perf/evlist.h>
 #include <perf/evsel.h>
 #include <perf/cpumap.h>
+#include <perf/mmap.h>
 
 #include <internal/xyarray.h>
 
@@ -57,7 +58,6 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
 {
 	perf_evlist__init(&evlist->core);
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
-	fdarray__init(&evlist->core.pollfd, 64);
 	evlist->workload.pid = -1;
 	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
@@ -138,7 +138,7 @@ void evlist__exit(struct evlist *evlist)
 {
 	zfree(&evlist->mmap);
 	zfree(&evlist->overwrite_mmap);
-	fdarray__exit(&evlist->core.pollfd);
+	perf_evlist__exit(&evlist->core);
 }
 
 void evlist__delete(struct evlist *evlist)
@@ -148,10 +148,6 @@ void evlist__delete(struct evlist *evlist)
 
 	evlist__munmap(evlist);
 	evlist__close(evlist);
-	perf_cpu_map__put(evlist->core.cpus);
-	perf_thread_map__put(evlist->core.threads);
-	evlist->core.cpus = NULL;
-	evlist->core.threads = NULL;
 	evlist__purge(evlist);
 	evlist__exit(evlist);
 	free(evlist);
@@ -186,6 +182,30 @@ void perf_evlist__splice_list_tail(struct evlist *evlist,
 	}
 }
 
+int __evlist__set_tracepoints_handlers(struct evlist *evlist,
+				       const struct evsel_str_handler *assocs, size_t nr_assocs)
+{
+	struct evsel *evsel;
+	size_t i;
+	int err;
+
+	for (i = 0; i < nr_assocs; i++) {
+		// Adding a handler for an event not in this evlist, just ignore it.
+		evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name);
+		if (evsel == NULL)
+			continue;
+
+		err = -EEXIST;
+		if (evsel->handler != NULL)
+			goto out;
+		evsel->handler = assocs[i].handler;
+	}
+
+	err = 0;
+out:
+	return err;
+}
+
 void __perf_evlist__set_leader(struct list_head *list)
 {
 	struct evsel *evsel, *leader;
@@ -403,19 +423,9 @@ int evlist__add_pollfd(struct evlist *evlist, int fd)
 	return perf_evlist__add_pollfd(&evlist->core, fd, NULL, POLLIN);
 }
 
-static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
-					 void *arg __maybe_unused)
-{
-	struct mmap *map = fda->priv[fd].ptr;
-
-	if (map)
-		perf_mmap__put(map);
-}
-
 int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask)
 {
-	return fdarray__filter(&evlist->core.pollfd, revents_and_mask,
-			       perf_evlist__munmap_filtered, NULL);
+	return perf_evlist__filter_pollfd(&evlist->core, revents_and_mask);
 }
 
 int evlist__poll(struct evlist *evlist, int timeout)
@@ -423,22 +433,6 @@ int evlist__poll(struct evlist *evlist, int timeout)
 	return perf_evlist__poll(&evlist->core, timeout);
 }
 
-static void perf_evlist__set_sid_idx(struct evlist *evlist,
-				     struct evsel *evsel, int idx, int cpu,
-				     int thread)
-{
-	struct perf_sample_id *sid = SID(evsel, cpu, thread);
-	sid->idx = idx;
-	if (evlist->core.cpus && cpu >= 0)
-		sid->cpu = evlist->core.cpus->map[cpu];
-	else
-		sid->cpu = -1;
-	if (!evsel->core.system_wide && evlist->core.threads && thread >= 0)
-		sid->tid = perf_thread_map__pid(evlist->core.threads, thread);
-	else
-		sid->tid = -1;
-}
-
 struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
 {
 	struct hlist_head *head;
@@ -577,11 +571,11 @@ static void evlist__munmap_nofree(struct evlist *evlist)
 
 	if (evlist->mmap)
 		for (i = 0; i < evlist->core.nr_mmaps; i++)
-			perf_mmap__munmap(&evlist->mmap[i]);
+			perf_mmap__munmap(&evlist->mmap[i].core);
 
 	if (evlist->overwrite_mmap)
 		for (i = 0; i < evlist->core.nr_mmaps; i++)
-			perf_mmap__munmap(&evlist->overwrite_mmap[i]);
+			perf_mmap__munmap(&evlist->overwrite_mmap[i].core);
 }
 
 void evlist__munmap(struct evlist *evlist)
@@ -591,6 +585,13 @@ void evlist__munmap(struct evlist *evlist)
 	zfree(&evlist->overwrite_mmap);
 }
 
+static void perf_mmap__unmap_cb(struct perf_mmap *map)
+{
+	struct mmap *m = container_of(map, struct mmap, core);
+
+	mmap__munmap(m);
+}
+
 static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 				       bool overwrite)
 {
@@ -605,8 +606,6 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 		return NULL;
 
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
-		map[i].core.fd = -1;
-		map[i].core.overwrite = overwrite;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
 		 * one extra to let perf_mmap__consume() get the last
@@ -616,151 +615,54 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 		 * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
 		 * thus does perf_mmap__get() on it.
 		 */
-		refcount_set(&map[i].core.refcnt, 0);
+		perf_mmap__init(&map[i].core, overwrite, perf_mmap__unmap_cb);
 	}
-	return map;
-}
 
-static bool
-perf_evlist__should_poll(struct evlist *evlist __maybe_unused,
-			 struct evsel *evsel)
-{
-	if (evsel->core.attr.write_backward)
-		return false;
-	return true;
+	return map;
 }
 
-static int evlist__mmap_per_evsel(struct evlist *evlist, int idx,
-				       struct mmap_params *mp, int cpu_idx,
-				       int thread, int *_output, int *_output_overwrite)
+static void
+perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist,
+			 struct perf_mmap_param *_mp,
+			 int idx, bool per_cpu)
 {
-	struct evsel *evsel;
-	int revent;
-	int evlist_cpu = cpu_map__cpu(evlist->core.cpus, cpu_idx);
-
-	evlist__for_each_entry(evlist, evsel) {
-		struct mmap *maps = evlist->mmap;
-		int *output = _output;
-		int fd;
-		int cpu;
-
-		mp->prot = PROT_READ | PROT_WRITE;
-		if (evsel->core.attr.write_backward) {
-			output = _output_overwrite;
-			maps = evlist->overwrite_mmap;
-
-			if (!maps) {
-				maps = evlist__alloc_mmap(evlist, true);
-				if (!maps)
-					return -1;
-				evlist->overwrite_mmap = maps;
-				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
-					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
-			}
-			mp->prot &= ~PROT_WRITE;
-		}
-
-		if (evsel->core.system_wide && thread)
-			continue;
-
-		cpu = perf_cpu_map__idx(evsel->core.cpus, evlist_cpu);
-		if (cpu == -1)
-			continue;
-
-		fd = FD(evsel, cpu, thread);
-
-		if (*output == -1) {
-			*output = fd;
-
-			if (perf_mmap__mmap(&maps[idx], mp, *output, evlist_cpu) < 0)
-				return -1;
-		} else {
-			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
-				return -1;
-
-			perf_mmap__get(&maps[idx]);
-		}
-
-		revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0;
+	struct evlist *evlist = container_of(_evlist, struct evlist, core);
+	struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
 
-		/*
-		 * The system_wide flag causes a selected event to be opened
-		 * always without a pid.  Consequently it will never get a
-		 * POLLHUP, but it is used for tracking in combination with
-		 * other events, so it should not need to be polled anyway.
-		 * Therefore don't add it for polling.
-		 */
-		if (!evsel->core.system_wide &&
-		     perf_evlist__add_pollfd(&evlist->core, fd, &maps[idx], revent) < 0) {
-			perf_mmap__put(&maps[idx]);
-			return -1;
-		}
-
-		if (evsel->core.attr.read_format & PERF_FORMAT_ID) {
-			if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu, thread,
-						   fd) < 0)
-				return -1;
-			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
-						 thread);
-		}
-	}
-
-	return 0;
+	auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, idx, per_cpu);
 }
 
-static int evlist__mmap_per_cpu(struct evlist *evlist,
-				     struct mmap_params *mp)
+static struct perf_mmap*
+perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
 {
-	int cpu, thread;
-	int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
-	int nr_threads = perf_thread_map__nr(evlist->core.threads);
+	struct evlist *evlist = container_of(_evlist, struct evlist, core);
+	struct mmap *maps = evlist->mmap;
 
-	pr_debug2("perf event ring buffer mmapped per cpu\n");
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		int output = -1;
-		int output_overwrite = -1;
+	if (overwrite) {
+		maps = evlist->overwrite_mmap;
 
-		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
-					      true);
+		if (!maps) {
+			maps = evlist__alloc_mmap(evlist, true);
+			if (!maps)
+				return NULL;
 
-		for (thread = 0; thread < nr_threads; thread++) {
-			if (evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output, &output_overwrite))
-				goto out_unmap;
+			evlist->overwrite_mmap = maps;
+			if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
+				perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
 		}
 	}
 
-	return 0;
-
-out_unmap:
-	evlist__munmap_nofree(evlist);
-	return -1;
+	return &maps[idx].core;
 }
 
-static int evlist__mmap_per_thread(struct evlist *evlist,
-					struct mmap_params *mp)
+static int
+perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp,
+			  int output, int cpu)
 {
-	int thread;
-	int nr_threads = perf_thread_map__nr(evlist->core.threads);
-
-	pr_debug2("perf event ring buffer mmapped per thread\n");
-	for (thread = 0; thread < nr_threads; thread++) {
-		int output = -1;
-		int output_overwrite = -1;
-
-		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
-					      false);
+	struct mmap *map = container_of(_map, struct mmap, core);
+	struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
 
-		if (evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output, &output_overwrite))
-			goto out_unmap;
-	}
-
-	return 0;
-
-out_unmap:
-	evlist__munmap_nofree(evlist);
-	return -1;
+	return mmap__mmap(map, mp, output, cpu);
 }
 
 unsigned long perf_event_mlock_kb_in_pages(void)
@@ -890,43 +792,36 @@ int evlist__mmap_ex(struct evlist *evlist, unsigned int pages,
 			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush,
 			 int comp_level)
 {
-	struct evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->core.cpus;
-	const struct perf_thread_map *threads = evlist->core.threads;
 	/*
 	 * Delay setting mp.prot: set it before calling perf_mmap__mmap.
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush,
-				  .comp_level = comp_level };
+	struct mmap_params mp = {
+		.nr_cblocks	= nr_cblocks,
+		.affinity	= affinity,
+		.flush		= flush,
+		.comp_level	= comp_level
+	};
+	struct perf_evlist_mmap_ops ops = {
+		.idx  = perf_evlist__mmap_cb_idx,
+		.get  = perf_evlist__mmap_cb_get,
+		.mmap = perf_evlist__mmap_cb_mmap,
+	};
 
 	if (!evlist->mmap)
 		evlist->mmap = evlist__alloc_mmap(evlist, false);
 	if (!evlist->mmap)
 		return -ENOMEM;
 
-	if (evlist->core.pollfd.entries == NULL && perf_evlist__alloc_pollfd(&evlist->core) < 0)
-		return -ENOMEM;
-
 	evlist->core.mmap_len = evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->core.mmap_len);
-	mp.mask = evlist->core.mmap_len - page_size - 1;
+	mp.core.mask = evlist->core.mmap_len - page_size - 1;
 
 	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->core.mmap_len,
 				   auxtrace_pages, auxtrace_overwrite);
 
-	evlist__for_each_entry(evlist, evsel) {
-		if ((evsel->core.attr.read_format & PERF_FORMAT_ID) &&
-		    evsel->core.sample_id == NULL &&
-		    perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr) < 0)
-			return -ENOMEM;
-	}
-
-	if (perf_cpu_map__empty(cpus))
-		return evlist__mmap_per_thread(evlist, &mp);
-
-	return evlist__mmap_per_cpu(evlist, &mp);
+	return perf_evlist__mmap_ops(&evlist->core, &ops, &mp.core);
 }
 
 int evlist__mmap(struct evlist *evlist, unsigned int pages)
@@ -1029,6 +924,9 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 	struct evsel *evsel;
 	int err = 0;
 
+	if (filter == NULL)
+		return -1;
+
 	evlist__for_each_entry(evlist, evsel) {
 		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
@@ -1041,16 +939,35 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 	return err;
 }
 
-int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
+{
+	struct evsel *evsel;
+	int err = 0;
+
+	if (filter == NULL)
+		return -1;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
+		err = perf_evsel__append_tp_filter(evsel, filter);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static char *asprintf__tp_filter_pids(size_t npids, pid_t *pids)
 {
 	char *filter;
-	int ret = -1;
 	size_t i;
 
 	for (i = 0; i < npids; ++i) {
 		if (i == 0) {
 			if (asprintf(&filter, "common_pid != %d", pids[i]) < 0)
-				return -1;
+				return NULL;
 		} else {
 			char *tmp;
 
@@ -1062,9 +979,18 @@ int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *
 		}
 	}
 
-	ret = perf_evlist__set_tp_filter(evlist, filter);
+	return filter;
 out_free:
 	free(filter);
+	return NULL;
+}
+
+int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+{
+	char *filter = asprintf__tp_filter_pids(npids, pids);
+	int ret = perf_evlist__set_tp_filter(evlist, filter);
+
+	free(filter);
 	return ret;
 }
 
@@ -1073,6 +999,20 @@ int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
 	return perf_evlist__set_tp_filter_pids(evlist, 1, &pid);
 }
 
+int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+{
+	char *filter = asprintf__tp_filter_pids(npids, pids);
+	int ret = perf_evlist__append_tp_filter(evlist, filter);
+
+	free(filter);
+	return ret;
+}
+
+int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid)
+{
+	return perf_evlist__append_tp_filter_pids(evlist, 1, &pid);
+}
+
 bool perf_evlist__valid_sample_type(struct evlist *evlist)
 {
 	struct evsel *pos;
@@ -1729,9 +1669,9 @@ static void *perf_evlist__poll_thread(void *arg)
 			struct mmap *map = &evlist->mmap[i];
 			union perf_event *event;
 
-			if (perf_mmap__read_init(map))
+			if (perf_mmap__read_init(&map->core))
 				continue;
-			while ((event = perf_mmap__read_event(map)) != NULL) {
+			while ((event = perf_mmap__read_event(&map->core)) != NULL) {
 				struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
 
 				if (evsel && evsel->side_band.cb)
@@ -1739,10 +1679,10 @@ static void *perf_evlist__poll_thread(void *arg)
 				else
 					pr_warning("cannot locate proper evsel for the side band event\n");
 
-				perf_mmap__consume(map);
+				perf_mmap__consume(&map->core);
 				got_data = true;
 			}
-			perf_mmap__read_done(map);
+			perf_mmap__read_done(&map->core);
 		}
 
 		if (draining && !got_data)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7cfe75522ba5..13051409fd22 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -118,6 +118,13 @@ void perf_evlist__stop_sb_thread(struct evlist *evlist);
 int perf_evlist__add_newtp(struct evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
+int __evlist__set_tracepoints_handlers(struct evlist *evlist,
+				       const struct evsel_str_handler *assocs,
+				       size_t nr_assocs);
+
+#define evlist__set_tracepoints_handlers(evlist, array) \
+	__evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
+
 void __perf_evlist__set_sample_bit(struct evlist *evlist,
 				   enum perf_event_sample_format bit);
 void __perf_evlist__reset_sample_bit(struct evlist *evlist,
@@ -133,6 +140,11 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter);
 int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
 int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
+int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter);
+
+int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
+
 struct evsel *
 perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index a35dc57d5995..063d1b93c53d 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -13,6 +13,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h> // sysconf()
+#include <perf/mmap.h>
 #ifdef HAVE_LIBNUMA_SUPPORT
 #include <numaif.h>
 #endif
@@ -23,116 +24,9 @@
 #include "../perf.h"
 #include <internal/lib.h> /* page_size */
 
-size_t perf_mmap__mmap_len(struct mmap *map)
+size_t mmap__mmap_len(struct mmap *map)
 {
-	return map->core.mask + 1 + page_size;
-}
-
-/* When check_messup is true, 'end' must points to a good entry */
-static union perf_event *perf_mmap__read(struct mmap *map,
-					 u64 *startp, u64 end)
-{
-	unsigned char *data = map->core.base + page_size;
-	union perf_event *event = NULL;
-	int diff = end - *startp;
-
-	if (diff >= (int)sizeof(event->header)) {
-		size_t size;
-
-		event = (union perf_event *)&data[*startp & map->core.mask];
-		size = event->header.size;
-
-		if (size < sizeof(event->header) || diff < (int)size)
-			return NULL;
-
-		/*
-		 * Event straddles the mmap boundary -- header should always
-		 * be inside due to u64 alignment of output.
-		 */
-		if ((*startp & map->core.mask) + size != ((*startp + size) & map->core.mask)) {
-			unsigned int offset = *startp;
-			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = map->core.event_copy;
-
-			do {
-				cpy = min(map->core.mask + 1 - (offset & map->core.mask), len);
-				memcpy(dst, &data[offset & map->core.mask], cpy);
-				offset += cpy;
-				dst += cpy;
-				len -= cpy;
-			} while (len);
-
-			event = (union perf_event *)map->core.event_copy;
-		}
-
-		*startp += size;
-	}
-
-	return event;
-}
-
-/*
- * Read event from ring buffer one by one.
- * Return one event for each call.
- *
- * Usage:
- * perf_mmap__read_init()
- * while(event = perf_mmap__read_event()) {
- *	//process the event
- *	perf_mmap__consume()
- * }
- * perf_mmap__read_done()
- */
-union perf_event *perf_mmap__read_event(struct mmap *map)
-{
-	union perf_event *event;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->core.refcnt))
-		return NULL;
-
-	/* non-overwirte doesn't pause the ringbuffer */
-	if (!map->core.overwrite)
-		map->core.end = perf_mmap__read_head(map);
-
-	event = perf_mmap__read(map, &map->core.start, map->core.end);
-
-	if (!map->core.overwrite)
-		map->core.prev = map->core.start;
-
-	return event;
-}
-
-static bool perf_mmap__empty(struct mmap *map)
-{
-	return perf_mmap__read_head(map) == map->core.prev && !map->auxtrace_mmap.base;
-}
-
-void perf_mmap__get(struct mmap *map)
-{
-	refcount_inc(&map->core.refcnt);
-}
-
-void perf_mmap__put(struct mmap *map)
-{
-	BUG_ON(map->core.base && refcount_read(&map->core.refcnt) == 0);
-
-	if (refcount_dec_and_test(&map->core.refcnt))
-		perf_mmap__munmap(map);
-}
-
-void perf_mmap__consume(struct mmap *map)
-{
-	if (!map->core.overwrite) {
-		u64 old = map->core.prev;
-
-		perf_mmap__write_tail(map, old);
-	}
-
-	if (refcount_read(&map->core.refcnt) == 1 && perf_mmap__empty(map))
-		perf_mmap__put(map);
+	return perf_mmap__mmap_len(&map->core);
 }
 
 int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
@@ -170,7 +64,7 @@ static int perf_mmap__aio_enabled(struct mmap *map)
 #ifdef HAVE_LIBNUMA_SUPPORT
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)
 {
-	map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+	map->aio.data[idx] = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				  MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 	if (map->aio.data[idx] == MAP_FAILED) {
 		map->aio.data[idx] = NULL;
@@ -183,7 +77,7 @@ static int perf_mmap__aio_alloc(struct mmap *map, int idx)
 static void perf_mmap__aio_free(struct mmap *map, int idx)
 {
 	if (map->aio.data[idx]) {
-		munmap(map->aio.data[idx], perf_mmap__mmap_len(map));
+		munmap(map->aio.data[idx], mmap__mmap_len(map));
 		map->aio.data[idx] = NULL;
 	}
 }
@@ -196,7 +90,7 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
 		data = map->aio.data[idx];
-		mmap_len = perf_mmap__mmap_len(map);
+		mmap_len = mmap__mmap_len(map);
 		node_mask = 1UL << cpu__get_node(cpu);
 		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
 			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
@@ -210,7 +104,7 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 #else /* !HAVE_LIBNUMA_SUPPORT */
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)
 {
-	map->aio.data[idx] = malloc(perf_mmap__mmap_len(map));
+	map->aio.data[idx] = malloc(mmap__mmap_len(map));
 	if (map->aio.data[idx] == NULL)
 		return -1;
 
@@ -311,19 +205,13 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused)
 }
 #endif
 
-void perf_mmap__munmap(struct mmap *map)
+void mmap__munmap(struct mmap *map)
 {
 	perf_mmap__aio_munmap(map);
 	if (map->data != NULL) {
-		munmap(map->data, perf_mmap__mmap_len(map));
+		munmap(map->data, mmap__mmap_len(map));
 		map->data = NULL;
 	}
-	if (map->core.base != NULL) {
-		munmap(map->core.base, perf_mmap__mmap_len(map));
-		map->core.base = NULL;
-		map->core.fd = -1;
-		refcount_set(&map->core.refcnt, 0);
-	}
 	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
@@ -353,34 +241,13 @@ static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params
 		CPU_SET(map->core.cpu, &map->affinity_mask);
 }
 
-int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 {
-	/*
-	 * The last one will be done at perf_mmap__consume(), so that we
-	 * make sure we don't prevent tools from consuming every last event in
-	 * the ring buffer.
-	 *
-	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
-	 * anymore, but the last events for it are still in the ring buffer,
-	 * waiting to be consumed.
-	 *
-	 * Tools can chose to ignore this at their own discretion, but the
-	 * evlist layer can't just drop it when filtering events in
-	 * perf_evlist__filter_pollfd().
-	 */
-	refcount_set(&map->core.refcnt, 2);
-	map->core.prev = 0;
-	map->core.mask = mp->mask;
-	map->core.base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
-			 MAP_SHARED, fd, 0);
-	if (map->core.base == MAP_FAILED) {
+	if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
 			  errno);
-		map->core.base = NULL;
 		return -1;
 	}
-	map->core.fd = fd;
-	map->core.cpu = cpu;
 
 	perf_mmap__setup_affinity_mask(map, mp);
 
@@ -389,7 +256,7 @@ int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 	map->comp_level = mp->comp_level;
 
 	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
-		map->data = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
 			pr_debug2("failed to mmap data buffer, error %d\n",
@@ -406,96 +273,16 @@ int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 	return perf_mmap__aio_mmap(map, mp);
 }
 
-static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end)
-{
-	struct perf_event_header *pheader;
-	u64 evt_head = *start;
-	int size = mask + 1;
-
-	pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start);
-	pheader = (struct perf_event_header *)(buf + (*start & mask));
-	while (true) {
-		if (evt_head - *start >= (unsigned int)size) {
-			pr_debug("Finished reading overwrite ring buffer: rewind\n");
-			if (evt_head - *start > (unsigned int)size)
-				evt_head -= pheader->size;
-			*end = evt_head;
-			return 0;
-		}
-
-		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
-
-		if (pheader->size == 0) {
-			pr_debug("Finished reading overwrite ring buffer: get start\n");
-			*end = evt_head;
-			return 0;
-		}
-
-		evt_head += pheader->size;
-		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
-	}
-	WARN_ONCE(1, "Shouldn't get here\n");
-	return -1;
-}
-
-/*
- * Report the start and end of the available data in ringbuffer
- */
-static int __perf_mmap__read_init(struct mmap *md)
-{
-	u64 head = perf_mmap__read_head(md);
-	u64 old = md->core.prev;
-	unsigned char *data = md->core.base + page_size;
-	unsigned long size;
-
-	md->core.start = md->core.overwrite ? head : old;
-	md->core.end = md->core.overwrite ? old : head;
-
-	if ((md->core.end - md->core.start) < md->core.flush)
-		return -EAGAIN;
-
-	size = md->core.end - md->core.start;
-	if (size > (unsigned long)(md->core.mask) + 1) {
-		if (!md->core.overwrite) {
-			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
-
-			md->core.prev = head;
-			perf_mmap__consume(md);
-			return -EAGAIN;
-		}
-
-		/*
-		 * Backward ring buffer is full. We still have a chance to read
-		 * most of data from it.
-		 */
-		if (overwrite_rb_find_range(data, md->core.mask, &md->core.start, &md->core.end))
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-int perf_mmap__read_init(struct mmap *map)
-{
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->core.refcnt))
-		return -ENOENT;
-
-	return __perf_mmap__read_init(map);
-}
-
 int perf_mmap__push(struct mmap *md, void *to,
 		    int push(struct mmap *map, void *to, void *buf, size_t size))
 {
-	u64 head = perf_mmap__read_head(md);
+	u64 head = perf_mmap__read_head(&md->core);
 	unsigned char *data = md->core.base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md);
+	rc = perf_mmap__read_init(&md->core);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 1 : -1;
 
@@ -522,24 +309,7 @@ int perf_mmap__push(struct mmap *md, void *to,
 	}
 
 	md->core.prev = head;
-	perf_mmap__consume(md);
+	perf_mmap__consume(&md->core);
 out:
 	return rc;
 }
-
-/*
- * Mandatory for overwrite mode
- * The direction of overwrite mode is backward.
- * The last perf_mmap__read() will set tail to map->core.prev.
- * Need to correct the map->core.prev to head which is the end of next read.
- */
-void perf_mmap__read_done(struct mmap *map)
-{
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->core.refcnt))
-		return;
-
-	map->core.prev = perf_mmap__read_head(map);
-}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e567c1c875bd..bee4e83f7109 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -37,37 +37,19 @@ struct mmap {
 };
 
 struct mmap_params {
-	int prot, mask, nr_cblocks, affinity, flush, comp_level;
+	struct perf_mmap_param core;
+	int nr_cblocks, affinity, flush, comp_level;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int perf_mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
-void perf_mmap__munmap(struct mmap *map);
-
-void perf_mmap__get(struct mmap *map);
-void perf_mmap__put(struct mmap *map);
-
-void perf_mmap__consume(struct mmap *map);
-
-static inline u64 perf_mmap__read_head(struct mmap *mm)
-{
-	return ring_buffer_read_head(mm->core.base);
-}
-
-static inline void perf_mmap__write_tail(struct mmap *md, u64 tail)
-{
-	ring_buffer_write_tail(md->core.base, tail);
-}
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
+void mmap__munmap(struct mmap *map);
 
 union perf_event *perf_mmap__read_forward(struct mmap *map);
 
-union perf_event *perf_mmap__read_event(struct mmap *map);
-
 int perf_mmap__push(struct mmap *md, void *to,
 		    int push(struct mmap *map, void *to, void *buf, size_t size));
 
-size_t perf_mmap__mmap_len(struct mmap *map);
+size_t mmap__mmap_len(struct mmap *map);
 
-int perf_mmap__read_init(struct mmap *md);
-void perf_mmap__read_done(struct mmap *map);
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index ef46c2848808..e687497b3aac 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -13,7 +13,7 @@ static int
 __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
 {
 	uint64_t *mode = (uint64_t *)opt->value;
-	const struct sample_reg *r;
+	const struct sample_reg *r = NULL;
 	char *s, *os = NULL, *p;
 	int ret = -1;
 	uint64_t mask;
@@ -46,19 +46,23 @@ __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++) {
 					if (r->mask & mask)
 						fprintf(stderr, "%s ", r->name);
 				}
+#endif
 				fputc('\n', stderr);
 				/* just printing available regs */
 				return -1;
 			}
+#ifdef HAVE_PERF_REGS_SUPPORT
 			for (r = sample_reg_masks; r->name; r++) {
 				if ((r->mask & mask) && !strcasecmp(s, r->name))
 					break;
 			}
-			if (!r->name) {
+#endif
+			if (!r || !r->name) {
 				ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n",
 					    s, intr ? "-I" : "--user-regs=");
 				goto error;
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 2774cec1f15f..5ee47ae1509c 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -3,10 +3,6 @@
 #include "perf_regs.h"
 #include "event.h"
 
-const struct sample_reg __weak sample_reg_masks[] = {
-	SMPL_REG_END
-};
-
 int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
 				 char **new_op __maybe_unused)
 {
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 47fe34e5f7d5..e014c2c038f4 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -15,8 +15,6 @@ struct sample_reg {
 #define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
 #define SMPL_REG_END { .name = NULL }
 
-extern const struct sample_reg sample_reg_masks[];
-
 enum {
 	SDT_ARG_VALID = 0,
 	SDT_ARG_SKIP,
@@ -27,6 +25,8 @@ 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))
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 02460362256d..25118605f3f8 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -6,6 +6,7 @@
 #include <linux/err.h>
 #include <perf/cpumap.h>
 #include <traceevent/event-parse.h>
+#include <perf/mmap.h>
 #include "evlist.h"
 #include "callchain.h"
 #include "evsel.h"
@@ -1022,10 +1023,10 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	if (!md)
 		return NULL;
 
-	if (perf_mmap__read_init(md) < 0)
+	if (perf_mmap__read_init(&md->core) < 0)
 		goto end;
 
-	event = perf_mmap__read_event(md);
+	event = perf_mmap__read_event(&md->core);
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
@@ -1045,7 +1046,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
-		perf_mmap__consume(md);
+		perf_mmap__consume(&md->core);
 
 		if (err)
 			return PyErr_Format(PyExc_OSError,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 061bb4d6a3f5..6cc32f5ec043 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2355,35 +2355,6 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
 	fprintf(fp, "# ========\n#\n");
 }
 
-
-int __perf_session__set_tracepoints_handlers(struct perf_session *session,
-					     const struct evsel_str_handler *assocs,
-					     size_t nr_assocs)
-{
-	struct evsel *evsel;
-	size_t i;
-	int err;
-
-	for (i = 0; i < nr_assocs; i++) {
-		/*
-		 * Adding a handler for an event not in the session,
-		 * just ignore it.
-		 */
-		evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
-		if (evsel == NULL)
-			continue;
-
-		err = -EEXIST;
-		if (evsel->handler != NULL)
-			goto out;
-		evsel->handler = assocs[i].handler;
-	}
-
-	err = 0;
-out:
-	return err;
-}
-
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b4c9428c18f0..8456e1d868fd 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -120,12 +120,8 @@ void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
 struct evsel_str_handler;
 
-int __perf_session__set_tracepoints_handlers(struct perf_session *session,
-					     const struct evsel_str_handler *assocs,
-					     size_t nr_assocs);
-
 #define perf_session__set_tracepoints_handlers(session, array) \
-	__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
+	__evlist__set_tracepoints_handlers(session->evlist, array, ARRAY_SIZE(array))
 
 extern volatile int session_done;
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7b93f34ac1f4..5aff9542d9b7 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -10,6 +10,8 @@
 #include "callchain.h"
 #include "values.h"
 #include "hist.h"
+#include "stat.h"
+#include "spark.h"
 
 struct option;
 struct thread;
@@ -71,6 +73,8 @@ struct hist_entry_diff {
 		/* PERF_HPP_DIFF__CYCLES */
 		s64	cycles;
 	};
+	struct stats	stats;
+	unsigned long	svals[NUM_SPARKS];
 };
 
 struct hist_entry_ops {
diff --git a/tools/perf/util/spark.c b/tools/perf/util/spark.c
new file mode 100644
index 000000000000..70272a8b81a6
--- /dev/null
+++ b/tools/perf/util/spark.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <limits.h>
+#include <string.h>
+#include <stdlib.h>
+#include "spark.h"
+#include "stat.h"
+
+#define SPARK_SHIFT 8
+
+/* Print spark lines on outf for numval values in val. */
+int print_spark(char *bf, int size, unsigned long *val, int numval)
+{
+	static const char *ticks[NUM_SPARKS] = {
+		"▁",  "▂", "▃", "▄", "▅", "▆", "▇", "█"
+	};
+	int i, printed = 0;
+	unsigned long min = ULONG_MAX, max = 0, f;
+
+	for (i = 0; i < numval; i++) {
+		if (val[i] < min)
+			min = val[i];
+		if (val[i] > max)
+			max = val[i];
+	}
+	f = ((max - min) << SPARK_SHIFT) / (NUM_SPARKS - 1);
+	if (f < 1)
+		f = 1;
+	for (i = 0; i < numval; i++) {
+		printed += scnprintf(bf + printed, size - printed, "%s",
+				     ticks[((val[i] - min) << SPARK_SHIFT) / f]);
+	}
+
+	return printed;
+}
diff --git a/tools/perf/util/spark.h b/tools/perf/util/spark.h
new file mode 100644
index 000000000000..25402d7d7a64
--- /dev/null
+++ b/tools/perf/util/spark.h
@@ -0,0 +1,8 @@
+#ifndef SPARK_H
+#define SPARK_H 1
+
+#define NUM_SPARKS 8
+
+int print_spark(char *bf, int size, unsigned long *val, int numval);
+
+#endif
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 0b0c6b5b1899..cc2a89b99d3d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -11,6 +11,7 @@
 #include <stdio.h>
 #include "path.h"
 #include "symbol_conf.h"
+#include "spark.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -111,6 +112,7 @@ struct block_info {
 	u64			end;
 	u64			cycles;
 	u64			cycles_aggr;
+	s64			cycles_spark[NUM_SPARKS];
 	int			num;
 	int			num_aggr;
 	refcount_t		refcnt;