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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Intel Knights Landing support.  (Harish Chegondi)

   - Intel Broadwell-EP uncore PMU support.  (Kan Liang)

   - Core code improvements.  (Peter Zijlstra.)

   - Event filter, LBR and PEBS fixes.  (Stephane Eranian)

   - Enable cycles:pp on Intel Atom.  (Stephane Eranian)

   - Add cycles:ppp support for Skylake.  (Andi Kleen)

   - Various x86 NMI overhead optimizations.  (Andi Kleen)

   - Intel PT enhancements.  (Takao Indoh)

   - AMD cache events fix.  (Vince Weaver)

  Tons of tooling changes:

   - Show random perf tool tips in the 'perf report' bottom line
     (Namhyung Kim)

   - perf report now defaults to --group if the perf.data file has
     grouped events, try it with:

      # perf record -e '{cycles,instructions}' -a sleep 1
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
      # perf report
      # Samples: 1K of event 'anon group { cycles, instructions }'
      # Event count (approx.): 1955219195
      #
      #       Overhead  Command     Shared Object      Symbol

         2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
         1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
         1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
         0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
         0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
         0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
         0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
         0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
         0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

   - Introduce the 'perf stat record/report' workflow:

     Generate perf.data files from 'perf stat', to tap into the
     scripting capabilities perf has instead of defining a 'perf stat'
     specific scripting support to calculate event ratios, etc.

     Simple example:

        $ perf stat record -e cycles usleep 1

         Performance counter stats for 'usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $ perf stat report

         Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $

     It generates PERF_RECORD_ userspace records to store the details:

        $ perf report -D | grep PERF_RECORD
        0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
        0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
        0x12a [0x40]: PERF_RECORD_STAT_CONFIG
        0x16a [0x30]: PERF_RECORD_STAT
        -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
        0x1da [0x18]: PERF_RECORD_STAT_ROUND
        [acme@ssdandy linux]$

     An effort was made to make perf.data files generated like this to
     not generate cryptic messages when processed by older tools.

     The 'perf script' bits need rebasing, will go up later.

   - Make command line options always available, even when they depend
     on some feature being enabled, warning the user about use of such
     options (Wang Nan)

   - Support hw breakpoint events (mem:0xAddress) in the default output
     mode in 'perf script' (Wang Nan)

   - Fixes and improvements for supporting annotating ARM binaries,
     support ARM call and jump instructions, more work needed to have
     arch specific stuff separated into tools/perf/arch/*/annotate/
     (Russell King)

   - Add initial 'perf config' command, for now just with a --list
     command to the contents of the configuration file in use and a
     basic man page describing its format, commands for doing edits and
     detailed documentation are being reviewed and proof-read.  (Taeung
     Song)

   - Allows BPF scriptlets specify arguments to be fetched using DWARF
     info, using a prologue generated at compile/build time (He Kuang,
     Wang Nan)

   - Allow attaching BPF scriptlets to module symbols (Wang Nan)

   - Allow attaching BPF scriptlets to userspace code using uprobe (Wang
     Nan)

   - BPF programs now can specify 'perf probe' tunables via its section
     name, separating key=val values using semicolons (Wang Nan)

     Testing some of these new BPF features:

        Use case: get callchains when receiving SSL packets, filter then in the
                  kernel, at arbitrary place.

        # cat ssl.bpf.c
        #define SEC(NAME) __attribute__((section(NAME), used))

        struct pt_regs;

        SEC("func=__inet_lookup_established hnum")
        int func(struct pt_regs *ctx, int err, unsigned short port)
        {
                return err == 0 && port == 443;
        }

        char _license[] SEC("license") = "GPL";
        int  _version   SEC("version") = LINUX_VERSION_CODE;
        #
        # perf record -a -g -e ssl.bpf.c
        ^C[ perf record: Woken up 1 times to write data ]
        [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
        # perf script | head -30
        swapper     0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
           856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
           2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
           2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
           96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
           969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
           2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
           95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
          1163ffa start_kernel ([kernel.vmlinux].init.text)
          11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
          1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)

        qemu-system-x86  9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
           8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
             430a br_handle_frame_finish ([bridge])
             48bc br_handle_frame ([bridge])
           855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
        #

   - Use 'perf probe' various options to list functions, see what
     variables can be collected at any given point, experiment first
     collecting without a filter, then filter, use it together with
     'perf trace', 'perf top', with or without callchains, if it
     explodes, please tell us!

   - Introduce a new callchain mode: "folded", that will list per line
     representations of all callchains for a give histogram entry,
     facilitating 'perf report' output processing by other tools, such
     as Brendan Gregg's flamegraph tools (Namhyung Kim)

     E.g:

        # perf report | grep -v ^# | head
           18.37%     0.00%  swapper  [kernel.kallsyms]   [k] cpu_startup_entry
                           |
                           ---cpu_startup_entry
                              |
                              |--12.07%--start_secondary
                              |
                               --6.30%--rest_init
                                         start_kernel
                                         x86_64_start_reservations
                                         x86_64_start_kernel
         #

     Becomes, in "folded" mode:

        # perf report -g folded | grep -v ^# | head -5
            18.37%     0.00%  swapper [kernel.kallsyms]   [k] cpu_startup_entry
          12.07% cpu_startup_entry;start_secondary
           6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] call_cpuidle
          11.23% call_cpuidle;cpu_startup_entry;start_secondary
           5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter
          11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
           5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            15.12%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter_state
         #

     The user can also select one of "count", "period" or "percent" as
     the first column.

  ... and lots of infrastructure enhancements, plus fixes and other
  changes, features I failed to list - see the shortlog and the git log
  for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
  perf evlist: Add --trace-fields option to show trace fields
  perf record: Store data mmaps for dwarf unwind
  perf libdw: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Use find_map function in access_dso_mem
  perf evlist: Remove perf_evlist__(enable|disable)_event functions
  perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
  perf report: Show random usage tip on the help line
  perf hists: Export a couple of hist functions
  perf diff: Use perf_hpp__register_sort_field interface
  perf tools: Add overhead/overhead_children keys defaults via string
  perf tools: Remove list entry from struct sort_entry
  perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
  perf script: Align event name properly
  perf tools: Add missing headers in perf's MANIFEST
  perf tools: Do not show trace command if it's not compiled in
  perf report: Change default to use event group view
  perf top: Decay periods in callchains
  tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
  tools lib: Sync tools/lib/find_bit.c with the kernel
  ...

80 files changed, 3560 insertions, 2541 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 591b3fe3ed49..5eec53a3f4ac 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -6,24 +6,20 @@ libperf-y += config.o
 libperf-y += ctype.o
 libperf-y += db-export.o
 libperf-y += env.o
-libperf-y += environment.o
 libperf-y += event.o
 libperf-y += evlist.o
 libperf-y += evsel.o
-libperf-y += exec_cmd.o
-libperf-y += find_next_bit.o
-libperf-y += help.o
+libperf-y += find_bit.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
-libperf-y += parse-options.o
 libperf-y += parse-events.o
 libperf-y += perf_regs.o
 libperf-y += path.o
 libperf-y += rbtree.o
+libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
-libperf-y += run-command.o
 libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
@@ -32,11 +28,9 @@ libperf-y += strfilter.o
 libperf-y += top.o
 libperf-y += usage.o
 libperf-y += wrapper.o
-libperf-y += sigchain.o
 libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += color.o
-libperf-y += pager.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
@@ -86,8 +80,11 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-$(CONFIG_AUXTRACE) += intel-bts.o
 libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
+libperf-y += term.o
+libperf-y += help-unknown-cmd.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
+libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-file.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -110,7 +107,6 @@ libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
-CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))"
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
@@ -136,8 +132,10 @@ CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
-CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(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
 
@@ -145,7 +143,11 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE
+$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
@@ -153,6 +155,10 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
+$(OUTPUT)util/libstring.o: ../lib/string.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
+
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1dd1949b0e79..b795b6994144 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -65,6 +65,11 @@ static int call__parse(struct ins_operands *ops)
 
 	name++;
 
+#ifdef __arm__
+	if (strchr(name, '+'))
+		return -1;
+#endif
+
 	tok = strchr(name, '>');
 	if (tok == NULL)
 		return -1;
@@ -246,7 +251,11 @@ static int mov__parse(struct ins_operands *ops)
 		return -1;
 
 	target = ++s;
+#ifdef __arm__
+	comment = strchr(s, ';');
+#else
 	comment = strchr(s, '#');
+#endif
 
 	if (comment != NULL)
 		s = comment - 1;
@@ -354,6 +363,20 @@ static struct ins instructions[] = {
 	{ .name = "addq",  .ops  = &mov_ops, },
 	{ .name = "addw",  .ops  = &mov_ops, },
 	{ .name = "and",   .ops  = &mov_ops, },
+#ifdef __arm__
+	{ .name = "b",     .ops  = &jump_ops, }, // might also be a call
+	{ .name = "bcc",   .ops  = &jump_ops, },
+	{ .name = "bcs",   .ops  = &jump_ops, },
+	{ .name = "beq",   .ops  = &jump_ops, },
+	{ .name = "bge",   .ops  = &jump_ops, },
+	{ .name = "bgt",   .ops  = &jump_ops, },
+	{ .name = "bhi",   .ops  = &jump_ops, },
+	{ .name = "bl",    .ops  = &call_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
+	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blx",   .ops  = &call_ops, },
+	{ .name = "bne",   .ops  = &jump_ops, },
+#endif
 	{ .name = "bts",   .ops  = &mov_ops, },
 	{ .name = "call",  .ops  = &call_ops, },
 	{ .name = "callq", .ops  = &call_ops, },
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7f10430af39c..360fda01f3b0 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -45,7 +45,7 @@
 #include "event.h"
 #include "session.h"
 #include "debug.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include "intel-pt.h"
 #include "intel-bts.h"
diff --git a/tools/perf/util/bitmap.c b/tools/perf/util/bitmap.c
deleted file mode 100644
index 0a1adc1111fd..000000000000
--- a/tools/perf/util/bitmap.c
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * From lib/bitmap.c
- * Helper functions for bitmap.h.
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.  See the file COPYING for more details.
- */
-#include <linux/bitmap.h>
-
-int __bitmap_weight(const unsigned long *bitmap, int bits)
-{
-	int k, w = 0, lim = bits/BITS_PER_LONG;
-
-	for (k = 0; k < lim; k++)
-		w += hweight_long(bitmap[k]);
-
-	if (bits % BITS_PER_LONG)
-		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
-
-	return w;
-}
-
-void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-		 const unsigned long *bitmap2, int bits)
-{
-	int k;
-	int nr = BITS_TO_LONGS(bits);
-
-	for (k = 0; k < nr; k++)
-		dst[k] = bitmap1[k] | bitmap2[k];
-}
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4c50411371db..540a7efa657e 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -5,11 +5,15 @@
  * Copyright (C) 2015 Huawei Inc.
  */
 
+#include <linux/bpf.h>
 #include <bpf/libbpf.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include "perf.h"
 #include "debug.h"
 #include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
 #include "llvm-utils.h"
@@ -32,6 +36,10 @@ DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
 	struct perf_probe_event pev;
+	bool need_prologue;
+	struct bpf_insn *insns_buf;
+	int nr_types;
+	int *type_mapping;
 };
 
 static bool libbpf_initialized;
@@ -106,10 +114,178 @@ bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
 	struct bpf_prog_priv *priv = _priv;
 
 	cleanup_perf_probe_events(&priv->pev, 1);
+	zfree(&priv->insns_buf);
+	zfree(&priv->type_mapping);
 	free(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("No 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, 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);
+
+	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;
@@ -117,6 +293,10 @@ config_bpf_program(struct bpf_program *prog)
 	const char *config_str;
 	int err;
 
+	/* Initialize per-program probing setting */
+	probe_conf.no_inlines = false;
+	probe_conf.force_add = false;
+
 	config_str = bpf_program__title(prog, false);
 	if (IS_ERR(config_str)) {
 		pr_debug("bpf: unable to get title for program\n");
@@ -131,13 +311,9 @@ config_bpf_program(struct bpf_program *prog)
 	pev = &priv->pev;
 
 	pr_debug("bpf: config program '%s'\n", config_str);
-	err = parse_perf_probe_command(config_str, pev);
-	if (err < 0) {
-		pr_debug("bpf: '%s' is not a valid config string\n",
-			 config_str);
-		err = -BPF_LOADER_ERRNO__CONFIG;
+	err = parse_prog_config(config_str, pev);
+	if (err)
 		goto errout;
-	}
 
 	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
 		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
@@ -197,6 +373,220 @@ static int bpf__prepare_probe(void)
 	return err;
 }
 
+static int
+preproc_gen_prologue(struct bpf_program *prog, int n,
+		     struct bpf_insn *orig_insns, int orig_insns_cnt,
+		     struct bpf_prog_prep_result *res)
+{
+	struct probe_trace_event *tev;
+	struct perf_probe_event *pev;
+	struct bpf_prog_priv *priv;
+	struct bpf_insn *buf;
+	size_t prologue_cnt = 0;
+	int i, err;
+
+	err = bpf_program__get_private(prog, (void **)&priv);
+	if (err || !priv)
+		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__title(prog, false);
+		if (!title)
+			title = "[unknown]";
+
+		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;
+	res->pfd = NULL;
+	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("No ehough 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 perf_probe_event *pev;
+	struct bpf_prog_priv *priv;
+	bool need_prologue = false;
+	int err, i;
+
+	err = bpf_program__get_private(prog, (void **)&priv);
+	if (err || !priv) {
+		pr_debug("Internal error when hook preprocessor\n");
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	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("No enough memory: alloc insns_buf failed\n");
+		return -ENOMEM;
+	}
+
+	priv->type_mapping = malloc(sizeof(int) * pev->ntevs);
+	if (!priv->type_mapping) {
+		pr_debug("No enough memory: alloc type_mapping failed\n");
+		return -ENOMEM;
+	}
+	memset(priv->type_mapping, -1,
+	       sizeof(int) * pev->ntevs);
+
+	err = map_prologue(pev, priv->type_mapping, &priv->nr_types);
+	if (err)
+		return err;
+
+	err = bpf_program__set_prep(prog, priv->nr_types,
+				    preproc_gen_prologue);
+	return err;
+}
+
 int bpf__probe(struct bpf_object *obj)
 {
 	int err = 0;
@@ -231,6 +621,18 @@ int bpf__probe(struct bpf_object *obj)
 			pr_debug("bpf_probe: failed to apply perf probe events");
 			goto out;
 		}
+
+		/*
+		 * After probing, let's consider prologue, which
+		 * adds program fetcher to BPF programs.
+		 *
+		 * hook_load_preprocessorr() 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;
@@ -314,7 +716,14 @@ int bpf__foreach_tev(struct bpf_object *obj,
 		for (i = 0; i < pev->ntevs; i++) {
 			tev = &pev->tevs[i];
 
-			fd = bpf_program__fd(prog);
+			if (priv->need_prologue) {
+				int type = priv->type_mapping[i];
+
+				fd = bpf_program__nth_fd(prog, type);
+			} else {
+				fd = bpf_program__fd(prog);
+			}
+
 			if (fd < 0) {
 				pr_debug("bpf: failed to get file descriptor\n");
 				return fd;
@@ -340,6 +749,10 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[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",
 };
 
 static int
@@ -420,7 +833,11 @@ int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
 			int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
+	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");
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 9caf3ae4acf3..6fdc0457e2b6 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -20,6 +20,10 @@ enum bpf_loader_errno {
 	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__END,
 };
 
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
new file mode 100644
index 000000000000..6cdbee119ceb
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.c
@@ -0,0 +1,455 @@
+/*
+ * 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 "perf.h"
+#include "debug.h"
+#include "bpf-loader.h"
+#include "bpf-prologue.h"
+#include "probe-finder.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;
+}
+
+/* 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)
+{
+	/* 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(BPF_FUNC_probe_read), 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;
+
+	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;
+		while (ref) {
+			pr_debug("prologue: arg %d: offset %ld\n",
+				 i, ref->offset);
+			err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
+					   ref->offset);
+			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++)
+		ins(BPF_LDX_MEM(BPF_DW, 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-prologue.h b/tools/perf/util/bpf-prologue.h
new file mode 100644
index 000000000000..d94cbea12899
--- /dev/null
+++ b/tools/perf/util/bpf-prologue.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2015, He Kuang <hekuang@huawei.com>
+ * Copyright (C) 2015, Huawei Inc.
+ */
+#ifndef __BPF_PROLOGUE_H
+#define __BPF_PROLOGUE_H
+
+#include <linux/compiler.h>
+#include <linux/filter.h>
+#include "probe-event.h"
+
+#define BPF_PROLOGUE_MAX_ARGS 3
+#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3
+#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2
+
+#ifdef HAVE_BPF_PROLOGUE
+int bpf__gen_prologue(struct probe_trace_arg *args, int nargs,
+		      struct bpf_insn *new_prog, size_t *new_cnt,
+		      size_t cnt_space);
+#else
+static inline int
+bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
+		  int nargs __maybe_unused,
+		  struct bpf_insn *new_prog __maybe_unused,
+		  size_t *new_cnt,
+		  size_t cnt_space __maybe_unused)
+{
+	if (!new_cnt)
+		return -EINVAL;
+	*new_cnt = 0;
+	return -ENOTSUP;
+}
+#endif
+#endif /* __BPF_PROLOGUE_H */
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index c861373aaed3..07b5d63947b1 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -4,9 +4,12 @@
 #include <stdbool.h>
 #include "util.h"
 #include "strbuf.h"
+#include <subcmd/pager.h>
 #include "../perf.h"
 #include "../ui/ui.h"
 
+#include <linux/string.h>
+
 #define CMD_EXEC_PATH "--exec-path"
 #define CMD_PERF_DIR "--perf-dir="
 #define CMD_WORK_TREE "--work-tree="
@@ -18,6 +21,7 @@
 #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
+#define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
@@ -28,11 +32,6 @@ extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
 
-/* pager.c */
-extern void setup_pager(void);
-extern int pager_in_use(void);
-extern int pager_use_color;
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -71,9 +70,4 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
-#ifndef __UCLIBC__
-/* Matches the libc/libbsd function attribute so we declare this unconditionally: */
-extern size_t strlcpy(char *dest, const char *src, size_t size);
-#endif
-
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 735ad48e1858..53c43eb9489e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -44,6 +44,10 @@ static int parse_callchain_mode(const char *value)
 		callchain_param.mode = CHAIN_GRAPH_REL;
 		return 0;
 	}
+	if (!strncmp(value, "folded", strlen(value))) {
+		callchain_param.mode = CHAIN_FOLDED;
+		return 0;
+	}
 	return -1;
 }
 
@@ -79,6 +83,23 @@ static int parse_callchain_sort_key(const char *value)
 	return -1;
 }
 
+static int parse_callchain_value(const char *value)
+{
+	if (!strncmp(value, "percent", strlen(value))) {
+		callchain_param.value = CCVAL_PERCENT;
+		return 0;
+	}
+	if (!strncmp(value, "period", strlen(value))) {
+		callchain_param.value = CCVAL_PERIOD;
+		return 0;
+	}
+	if (!strncmp(value, "count", strlen(value))) {
+		callchain_param.value = CCVAL_COUNT;
+		return 0;
+	}
+	return -1;
+}
+
 static int
 __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 {
@@ -102,7 +123,8 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt)
 
 		if (!parse_callchain_mode(tok) ||
 		    !parse_callchain_order(tok) ||
-		    !parse_callchain_sort_key(tok)) {
+		    !parse_callchain_sort_key(tok) ||
+		    !parse_callchain_value(tok)) {
 			/* parsing ok - move on to the next */
 			try_stack_size = false;
 			goto next;
@@ -218,6 +240,7 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 
 		switch (mode) {
 		case CHAIN_FLAT:
+		case CHAIN_FOLDED:
 			if (rnode->hit < chain->hit)
 				p = &(*p)->rb_left;
 			else
@@ -267,6 +290,7 @@ static void
 sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
 		u64 min_hit, struct callchain_param *param __maybe_unused)
 {
+	*rb_root = RB_ROOT;
 	__sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
@@ -338,6 +362,7 @@ int callchain_register_param(struct callchain_param *param)
 		param->sort = sort_chain_graph_rel;
 		break;
 	case CHAIN_FLAT:
+	case CHAIN_FOLDED:
 		param->sort = sort_chain_flat;
 		break;
 	case CHAIN_NONE:
@@ -363,6 +388,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 	}
 	new->parent = parent;
 	INIT_LIST_HEAD(&new->val);
+	INIT_LIST_HEAD(&new->parent_val);
 
 	if (inherit_children) {
 		struct rb_node *n;
@@ -431,6 +457,8 @@ add_child(struct callchain_node *parent,
 
 	new->children_hit = 0;
 	new->hit = period;
+	new->children_count = 0;
+	new->count = 1;
 	return new;
 }
 
@@ -478,6 +506,9 @@ split_add_child(struct callchain_node *parent,
 	parent->children_hit = callchain_cumul_hits(new);
 	new->val_nr = parent->val_nr - idx_local;
 	parent->val_nr = idx_local;
+	new->count = parent->count;
+	new->children_count = parent->children_count;
+	parent->children_count = callchain_cumul_counts(new);
 
 	/* create a new child for the new branch if any */
 	if (idx_total < cursor->nr) {
@@ -488,6 +519,8 @@ split_add_child(struct callchain_node *parent,
 
 		parent->hit = 0;
 		parent->children_hit += period;
+		parent->count = 0;
+		parent->children_count += 1;
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
@@ -510,6 +543,7 @@ split_add_child(struct callchain_node *parent,
 		rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
 	} else {
 		parent->hit = period;
+		parent->count = 1;
 	}
 }
 
@@ -556,6 +590,7 @@ append_chain_children(struct callchain_node *root,
 
 inc_children_hit:
 	root->children_hit += period;
+	root->children_count++;
 }
 
 static int
@@ -608,6 +643,7 @@ append_chain(struct callchain_node *root,
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
+		root->count++;
 		return 0;
 	}
 
@@ -799,12 +835,72 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 	return bf;
 }
 
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+				      char *bf, size_t bfsize, u64 total)
+{
+	double percent = 0.0;
+	u64 period = callchain_cumul_hits(node);
+	unsigned count = callchain_cumul_counts(node);
+
+	if (callchain_param.mode == CHAIN_FOLDED) {
+		period = node->hit;
+		count = node->count;
+	}
+
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		scnprintf(bf, bfsize, "%"PRIu64, period);
+		break;
+	case CCVAL_COUNT:
+		scnprintf(bf, bfsize, "%u", count);
+		break;
+	case CCVAL_PERCENT:
+	default:
+		if (total)
+			percent = period * 100.0 / total;
+		scnprintf(bf, bfsize, "%.2f%%", percent);
+		break;
+	}
+	return bf;
+}
+
+int callchain_node__fprintf_value(struct callchain_node *node,
+				 FILE *fp, u64 total)
+{
+	double percent = 0.0;
+	u64 period = callchain_cumul_hits(node);
+	unsigned count = callchain_cumul_counts(node);
+
+	if (callchain_param.mode == CHAIN_FOLDED) {
+		period = node->hit;
+		count = node->count;
+	}
+
+	switch (callchain_param.value) {
+	case CCVAL_PERIOD:
+		return fprintf(fp, "%"PRIu64, period);
+	case CCVAL_COUNT:
+		return fprintf(fp, "%u", count);
+	case CCVAL_PERCENT:
+	default:
+		if (total)
+			percent = period * 100.0 / total;
+		return percent_color_fprintf(fp, "%.2f%%", percent);
+	}
+	return 0;
+}
+
 static void free_callchain_node(struct callchain_node *node)
 {
 	struct callchain_list *list, *tmp;
 	struct callchain_node *child;
 	struct rb_node *n;
 
+	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
+		list_del(&list->list);
+		free(list);
+	}
+
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
 		free(list);
@@ -828,3 +924,69 @@ void free_callchain(struct callchain_root *root)
 
 	free_callchain_node(&root->node);
 }
+
+static u64 decay_callchain_node(struct callchain_node *node)
+{
+	struct callchain_node *child;
+	struct rb_node *n;
+	u64 child_hits = 0;
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+
+		child_hits += decay_callchain_node(child);
+		n = rb_next(n);
+	}
+
+	node->hit = (node->hit * 7) / 8;
+	node->children_hit = child_hits;
+
+	return node->hit;
+}
+
+void decay_callchain(struct callchain_root *root)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	decay_callchain_node(&root->node);
+}
+
+int callchain_node__make_parent_list(struct callchain_node *node)
+{
+	struct callchain_node *parent = node->parent;
+	struct callchain_list *chain, *new;
+	LIST_HEAD(head);
+
+	while (parent) {
+		list_for_each_entry_reverse(chain, &parent->val, list) {
+			new = malloc(sizeof(*new));
+			if (new == NULL)
+				goto out;
+			*new = *chain;
+			new->has_children = false;
+			list_add_tail(&new->list, &head);
+		}
+		parent = parent->parent;
+	}
+
+	list_for_each_entry_safe_reverse(chain, new, &head, list)
+		list_move_tail(&chain->list, &node->parent_val);
+
+	if (!list_empty(&node->parent_val)) {
+		chain = list_first_entry(&node->parent_val, struct callchain_list, list);
+		chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node);
+
+		chain = list_first_entry(&node->val, struct callchain_list, list);
+		chain->has_children = false;
+	}
+	return 0;
+
+out:
+	list_for_each_entry_safe(chain, new, &head, list) {
+		list_del(&chain->list);
+		free(chain);
+	}
+	return -ENOMEM;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index fce8161e54db..18dd22269764 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -24,12 +24,13 @@
 #define CALLCHAIN_RECORD_HELP  CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP
 
 #define CALLCHAIN_REPORT_HELP						\
-	HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \
+	HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \
 	HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \
 	HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \
 	HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \
 	HELP_PAD "sort_key:\tcall graph sort key (function|address)\n"	\
-	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n"
+	HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \
+	HELP_PAD "value:\t\tcall graph value (percent|period|count)\n"
 
 enum perf_call_graph_mode {
 	CALLCHAIN_NONE,
@@ -43,7 +44,8 @@ enum chain_mode {
 	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
-	CHAIN_GRAPH_REL
+	CHAIN_GRAPH_REL,
+	CHAIN_FOLDED,
 };
 
 enum chain_order {
@@ -54,11 +56,14 @@ enum chain_order {
 struct callchain_node {
 	struct callchain_node	*parent;
 	struct list_head	val;
+	struct list_head	parent_val;
 	struct rb_node		rb_node_in; /* to insert nodes in an rbtree */
 	struct rb_node		rb_node;    /* to sort nodes in an output tree */
 	struct rb_root		rb_root_in; /* input tree of children */
 	struct rb_root		rb_root;    /* sorted output tree of children */
 	unsigned int		val_nr;
+	unsigned int		count;
+	unsigned int		children_count;
 	u64			hit;
 	u64			children_hit;
 };
@@ -78,6 +83,12 @@ enum chain_key {
 	CCKEY_ADDRESS
 };
 
+enum chain_value {
+	CCVAL_PERCENT,
+	CCVAL_PERIOD,
+	CCVAL_COUNT,
+};
+
 struct callchain_param {
 	bool			enabled;
 	enum perf_call_graph_mode record_mode;
@@ -90,6 +101,7 @@ struct callchain_param {
 	bool			order_set;
 	enum chain_key		key;
 	bool			branch_callstack;
+	enum chain_value	value;
 };
 
 extern struct callchain_param callchain_param;
@@ -131,6 +143,7 @@ extern __thread struct callchain_cursor callchain_cursor;
 static inline void callchain_init(struct callchain_root *root)
 {
 	INIT_LIST_HEAD(&root->node.val);
+	INIT_LIST_HEAD(&root->node.parent_val);
 
 	root->node.parent = NULL;
 	root->node.hit = 0;
@@ -144,6 +157,11 @@ static inline u64 callchain_cumul_hits(struct callchain_node *node)
 	return node->hit + node->children_hit;
 }
 
+static inline unsigned callchain_cumul_counts(struct callchain_node *node)
+{
+	return node->count + node->children_count;
+}
+
 int callchain_register_param(struct callchain_param *param);
 int callchain_append(struct callchain_root *root,
 		     struct callchain_cursor *cursor,
@@ -229,7 +247,13 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
+char *callchain_node__scnprintf_value(struct callchain_node *node,
+				      char *bf, size_t bfsize, u64 total);
+int callchain_node__fprintf_value(struct callchain_node *node,
+				  FILE *fp, u64 total);
 
 void free_callchain(struct callchain_root *root);
+void decay_callchain(struct callchain_root *root);
+int callchain_node__make_parent_list(struct callchain_node *node);
 
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 32e12ecfe9c5..90aa1b46b2e5 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,6 +1,6 @@
 #include "util.h"
 #include "../perf.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 9b9565416f90..e5fb88bab9e1 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -24,7 +24,7 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
  auto_color:
 	if (stdout_is_tty < 0)
 		stdout_is_tty = isatty(1);
-	if (stdout_is_tty || (pager_in_use() && pager_use_color)) {
+	if (stdout_is_tty || pager_in_use()) {
 		char *term = getenv("TERM");
 		if (term && strcmp(term, "dumb"))
 			return 1;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 2e452ac1353d..d3e12e30e1d5 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -10,7 +10,7 @@
  */
 #include "util.h"
 #include "cache.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 10af1e7524fb..fa935093a599 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -5,6 +5,7 @@
 #include <assert.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/bitmap.h>
 #include "asm/bug.h"
 
 static struct cpu_map *cpu_map__default_new(void)
@@ -179,6 +180,56 @@ out:
 	return cpus;
 }
 
+static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
+{
+	struct cpu_map *map;
+
+	map = cpu_map__empty_new(cpus->nr);
+	if (map) {
+		unsigned i;
+
+		for (i = 0; i < cpus->nr; i++) {
+			/*
+			 * Special treatment for -1, which is not real cpu number,
+			 * and we need to use (int) -1 to initialize map[i],
+			 * otherwise it would become 65535.
+			 */
+			if (cpus->cpu[i] == (u16) -1)
+				map->map[i] = -1;
+			else
+				map->map[i] = (int) cpus->cpu[i];
+		}
+	}
+
+	return map;
+}
+
+static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask)
+{
+	struct cpu_map *map;
+	int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE;
+
+	nr = bitmap_weight(mask->mask, nbits);
+
+	map = cpu_map__empty_new(nr);
+	if (map) {
+		int cpu, i = 0;
+
+		for_each_set_bit(cpu, mask->mask, nbits)
+			map->map[i++] = cpu;
+	}
+	return map;
+
+}
+
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
+{
+	if (data->type == PERF_CPU_MAP__CPUS)
+		return cpu_map__from_entries((struct cpu_map_entries *)data->data);
+	else
+		return cpu_map__from_mask((struct cpu_map_mask *)data->data);
+}
+
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
 {
 	int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 85f7772457fa..71c41b9efabb 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -17,6 +17,7 @@ struct cpu_map {
 struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
+struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 5bfc1198ab46..34cd1e4039d3 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -63,6 +63,7 @@ struct ctf_writer {
 			struct bt_ctf_field_type	*s32;
 			struct bt_ctf_field_type	*u32;
 			struct bt_ctf_field_type	*string;
+			struct bt_ctf_field_type	*u32_hex;
 			struct bt_ctf_field_type	*u64_hex;
 		};
 		struct bt_ctf_field_type *array[6];
@@ -982,6 +983,7 @@ do {							\
 	CREATE_INT_TYPE(cw->data.u64, 64, false, false);
 	CREATE_INT_TYPE(cw->data.s32, 32, true,  false);
 	CREATE_INT_TYPE(cw->data.u32, 32, false, false);
+	CREATE_INT_TYPE(cw->data.u32_hex, 32, false, true);
 	CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true);
 
 	cw->data.string  = bt_ctf_field_type_string_create();
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 425df5c86c9c..e8e9a9dbf5e3 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1243,6 +1243,8 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
 	if (dso != NULL) {
 		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
+		/* Put dso here because __dsos_add already got it */
+		dso__put(dso);
 	}
 	return dso;
 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6af4f7c36820..7dd5939dea2e 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -25,15 +25,6 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
 {
 	int i;
 
-	/*
-	 * If env->cmdline_argv has already been set, do not override it.  This allows
-	 * a command to set the cmdline, parse args and then call another
-	 * builtin function that implements a command -- e.g, cmd_kvm calling
-	 * cmd_record.
-	 */
-	if (env->cmdline_argv != NULL)
-		return 0;
-
 	/* do not include NULL termination */
 	env->cmdline_argv = calloc(argc, sizeof(char *));
 	if (env->cmdline_argv == NULL)
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
deleted file mode 100644
index 7405123692f1..000000000000
--- a/tools/perf/util/environment.c
+++ /dev/null
@@ -1,8 +0,0 @@
-/*
- * We put all the perf config variables in this same object
- * file, so that programs can link against the config parser
- * without having to link against all the rest of perf.
- */
-#include "cache.h"
-
-int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8b10621b415c..cd61bb1f3917 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -10,6 +10,8 @@
 #include "thread.h"
 #include "thread_map.h"
 #include "symbol/kallsyms.h"
+#include "asm/bug.h"
+#include "stat.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
@@ -37,6 +39,12 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
 	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
 	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
+	[PERF_RECORD_THREAD_MAP]		= "THREAD_MAP",
+	[PERF_RECORD_CPU_MAP]			= "CPU_MAP",
+	[PERF_RECORD_STAT_CONFIG]		= "STAT_CONFIG",
+	[PERF_RECORD_STAT]			= "STAT",
+	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
+	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -699,6 +707,274 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	union perf_event *event;
+	int i, err, size;
+
+	size  = sizeof(event->thread_map);
+	size +=	threads->nr * sizeof(event->thread_map.entries[0]);
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_THREAD_MAP;
+	event->header.size = size;
+	event->thread_map.nr = threads->nr;
+
+	for (i = 0; i < threads->nr; i++) {
+		struct thread_map_event_entry *entry = &event->thread_map.entries[i];
+		char *comm = thread_map__comm(threads, i);
+
+		if (!comm)
+			comm = (char *) "";
+
+		entry->pid = thread_map__pid(threads, i);
+		strncpy((char *) &entry->comm, comm, sizeof(entry->comm));
+	}
+
+	err = process(tool, event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+static void synthesize_cpus(struct cpu_map_entries *cpus,
+			    struct cpu_map *map)
+{
+	int i;
+
+	cpus->nr = map->nr;
+
+	for (i = 0; i < map->nr; i++)
+		cpus->cpu[i] = map->map[i];
+}
+
+static void synthesize_mask(struct cpu_map_mask *mask,
+			    struct cpu_map *map, int max)
+{
+	int i;
+
+	mask->nr = BITS_TO_LONGS(max);
+	mask->long_size = sizeof(long);
+
+	for (i = 0; i < map->nr; i++)
+		set_bit(map->map[i], mask->mask);
+}
+
+static size_t cpus_size(struct cpu_map *map)
+{
+	return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16);
+}
+
+static size_t mask_size(struct cpu_map *map, int *max)
+{
+	int i;
+
+	*max = 0;
+
+	for (i = 0; i < map->nr; i++) {
+		/* bit possition of the cpu is + 1 */
+		int bit = map->map[i] + 1;
+
+		if (bit > *max)
+			*max = bit;
+	}
+
+	return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long);
+}
+
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max)
+{
+	size_t size_cpus, size_mask;
+	bool is_dummy = cpu_map__empty(map);
+
+	/*
+	 * Both array and mask data have variable size based
+	 * on the number of cpus and their actual values.
+	 * The size of the 'struct cpu_map_data' is:
+	 *
+	 *   array = size of 'struct cpu_map_entries' +
+	 *           number of cpus * sizeof(u64)
+	 *
+	 *   mask  = size of 'struct cpu_map_mask' +
+	 *           maximum cpu bit converted to size of longs
+	 *
+	 * and finaly + the size of 'struct cpu_map_data'.
+	 */
+	size_cpus = cpus_size(map);
+	size_mask = mask_size(map, max);
+
+	if (is_dummy || (size_cpus < size_mask)) {
+		*size += size_cpus;
+		*type  = PERF_CPU_MAP__CPUS;
+	} else {
+		*size += size_mask;
+		*type  = PERF_CPU_MAP__MASK;
+	}
+
+	*size += sizeof(struct cpu_map_data);
+	return zalloc(*size);
+}
+
+void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+			      u16 type, int max)
+{
+	data->type = type;
+
+	switch (type) {
+	case PERF_CPU_MAP__CPUS:
+		synthesize_cpus((struct cpu_map_entries *) data->data, map);
+		break;
+	case PERF_CPU_MAP__MASK:
+		synthesize_mask((struct cpu_map_mask *) data->data, map, max);
+	default:
+		break;
+	};
+}
+
+static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map)
+{
+	size_t size = sizeof(struct cpu_map_event);
+	struct cpu_map_event *event;
+	int max;
+	u16 type;
+
+	event = cpu_map_data__alloc(map, &size, &type, &max);
+	if (!event)
+		return NULL;
+
+	event->header.type = PERF_RECORD_CPU_MAP;
+	event->header.size = size;
+	event->data.type   = type;
+
+	cpu_map_data__synthesize(&event->data, map, type, max);
+	return event;
+}
+
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct cpu_map *map,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	struct cpu_map_event *event;
+	int err;
+
+	event = cpu_map_event__new(map);
+	if (!event)
+		return -ENOMEM;
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	struct stat_config_event *event;
+	int size, i = 0, err;
+
+	size  = sizeof(*event);
+	size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0]));
+
+	event = zalloc(size);
+	if (!event)
+		return -ENOMEM;
+
+	event->header.type = PERF_RECORD_STAT_CONFIG;
+	event->header.size = size;
+	event->nr          = PERF_STAT_CONFIG_TERM__MAX;
+
+#define ADD(__term, __val)					\
+	event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term;	\
+	event->data[i].val = __val;				\
+	i++;
+
+	ADD(AGGR_MODE,	config->aggr_mode)
+	ADD(INTERVAL,	config->interval)
+	ADD(SCALE,	config->scale)
+
+	WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX,
+		  "stat config terms unbalanced\n");
+#undef ADD
+
+	err = process(tool, (union perf_event *) event, NULL, machine);
+
+	free(event);
+	return err;
+}
+
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine)
+{
+	struct stat_event event;
+
+	event.header.type = PERF_RECORD_STAT;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.id        = id;
+	event.cpu       = cpu;
+	event.thread    = thread;
+	event.val       = count->val;
+	event.ena       = count->ena;
+	event.run       = count->run;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 evtime, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine)
+{
+	struct stat_round_event event;
+
+	event.header.type = PERF_RECORD_STAT_ROUND;
+	event.header.size = sizeof(event);
+	event.header.misc = 0;
+
+	event.time = evtime;
+	event.type = type;
+
+	return process(tool, (union perf_event *) &event, NULL, machine);
+}
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct stat_config_event *event)
+{
+	unsigned i;
+
+	for (i = 0; i < event->nr; i++) {
+
+		switch (event->data[i].tag) {
+#define CASE(__term, __val)					\
+		case PERF_STAT_CONFIG_TERM__##__term:		\
+			config->__val = event->data[i].val;	\
+			break;
+
+		CASE(AGGR_MODE, aggr_mode)
+		CASE(SCALE,     scale)
+		CASE(INTERVAL,  interval)
+#undef CASE
+		default:
+			pr_warning("unknown stat config term %" PRIu64 "\n",
+				   event->data[i].tag);
+		}
+	}
+}
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
 	const char *s;
@@ -783,6 +1059,38 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 		       event->mmap2.filename);
 }
 
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
+{
+	struct thread_map *threads = thread_map__new_event(&event->thread_map);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (threads)
+		ret += thread_map__fprintf(threads, fp);
+	else
+		ret += fprintf(fp, "failed to get threads from event\n");
+
+	thread_map__put(threads);
+	return ret;
+}
+
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
+{
+	struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (cpus)
+		ret += cpu_map__fprintf(cpus, fp);
+	else
+		ret += fprintf(fp, "failed to get cpumap from event\n");
+
+	cpu_map__put(cpus);
+	return ret;
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
 			     union perf_event *event,
 			     struct perf_sample *sample,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a0dbcbd4f6d8..b7ffb7ee9971 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -226,6 +226,12 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_AUXTRACE_INFO		= 70,
 	PERF_RECORD_AUXTRACE			= 71,
 	PERF_RECORD_AUXTRACE_ERROR		= 72,
+	PERF_RECORD_THREAD_MAP			= 73,
+	PERF_RECORD_CPU_MAP			= 74,
+	PERF_RECORD_STAT_CONFIG			= 75,
+	PERF_RECORD_STAT			= 76,
+	PERF_RECORD_STAT_ROUND			= 77,
+	PERF_RECORD_EVENT_UPDATE		= 78,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -270,12 +276,61 @@ struct events_stats {
 	u32 nr_proc_map_timeout;
 };
 
+enum {
+	PERF_CPU_MAP__CPUS = 0,
+	PERF_CPU_MAP__MASK = 1,
+};
+
+struct cpu_map_entries {
+	u16	nr;
+	u16	cpu[];
+};
+
+struct cpu_map_mask {
+	u16	nr;
+	u16	long_size;
+	unsigned long mask[];
+};
+
+struct cpu_map_data {
+	u16	type;
+	char	data[];
+};
+
+struct cpu_map_event {
+	struct perf_event_header	header;
+	struct cpu_map_data		data;
+};
+
 struct attr_event {
 	struct perf_event_header header;
 	struct perf_event_attr attr;
 	u64 id[];
 };
 
+enum {
+	PERF_EVENT_UPDATE__UNIT  = 0,
+	PERF_EVENT_UPDATE__SCALE = 1,
+	PERF_EVENT_UPDATE__NAME  = 2,
+	PERF_EVENT_UPDATE__CPUS  = 3,
+};
+
+struct event_update_event_cpus {
+	struct cpu_map_data cpus;
+};
+
+struct event_update_event_scale {
+	double scale;
+};
+
+struct event_update_event {
+	struct perf_event_header header;
+	u64 type;
+	u64 id;
+
+	char data[];
+};
+
 #define MAX_EVENT_NAME 64
 
 struct perf_trace_event_type {
@@ -356,6 +411,63 @@ struct context_switch_event {
 	u32 next_prev_tid;
 };
 
+struct thread_map_event_entry {
+	u64	pid;
+	char	comm[16];
+};
+
+struct thread_map_event {
+	struct perf_event_header	header;
+	u64				nr;
+	struct thread_map_event_entry	entries[];
+};
+
+enum {
+	PERF_STAT_CONFIG_TERM__AGGR_MODE	= 0,
+	PERF_STAT_CONFIG_TERM__INTERVAL		= 1,
+	PERF_STAT_CONFIG_TERM__SCALE		= 2,
+	PERF_STAT_CONFIG_TERM__MAX		= 3,
+};
+
+struct stat_config_event_entry {
+	u64	tag;
+	u64	val;
+};
+
+struct stat_config_event {
+	struct perf_event_header	header;
+	u64				nr;
+	struct stat_config_event_entry	data[];
+};
+
+struct stat_event {
+	struct perf_event_header	header;
+
+	u64	id;
+	u32	cpu;
+	u32	thread;
+
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+enum {
+	PERF_STAT_ROUND_TYPE__INTERVAL	= 0,
+	PERF_STAT_ROUND_TYPE__FINAL	= 1,
+};
+
+struct stat_round_event {
+	struct perf_event_header	header;
+	u64				type;
+	u64				time;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -368,6 +480,7 @@ union perf_event {
 	struct throttle_event		throttle;
 	struct sample_event		sample;
 	struct attr_event		attr;
+	struct event_update_event	event_update;
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
@@ -378,12 +491,20 @@ union perf_event {
 	struct aux_event		aux;
 	struct itrace_start_event	itrace_start;
 	struct context_switch_event	context_switch;
+	struct thread_map_event		thread_map;
+	struct cpu_map_event		cpu_map;
+	struct stat_config_event	stat_config;
+	struct stat_event		stat;
+	struct stat_round_event		stat_round;
 };
 
 void perf_event__print_totals(void);
 
 struct perf_tool;
 struct thread_map;
+struct cpu_map;
+struct perf_stat_config;
+struct perf_counts_values;
 
 typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 				     union perf_event *event,
@@ -395,6 +516,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      perf_event__handler_t process,
 				      struct machine *machine, bool mmap_data,
 				      unsigned int proc_map_timeout);
+int perf_event__synthesize_thread_map2(struct perf_tool *tool,
+				      struct thread_map *threads,
+				      perf_event__handler_t process,
+				      struct machine *machine);
+int perf_event__synthesize_cpu_map(struct perf_tool *tool,
+				   struct cpu_map *cpus,
+				   perf_event__handler_t process,
+				   struct machine *machine);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine, bool mmap_data,
@@ -402,7 +531,21 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
-
+int perf_event__synthesize_stat_config(struct perf_tool *tool,
+				       struct perf_stat_config *config,
+				       perf_event__handler_t process,
+				       struct machine *machine);
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct stat_config_event *event);
+int perf_event__synthesize_stat(struct perf_tool *tool,
+				u32 cpu, u32 thread, u64 id,
+				struct perf_counts_values *count,
+				perf_event__handler_t process,
+				struct machine *machine);
+int perf_event__synthesize_stat_round(struct perf_tool *tool,
+				      u64 time, u64 type,
+				      perf_event__handler_t process,
+				      struct machine *machine);
 int perf_event__synthesize_modules(struct perf_tool *tool,
 				   perf_event__handler_t process,
 				   struct machine *machine);
@@ -499,9 +642,14 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
 				 const char *symbol_name);
 
+void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max);
+void  cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map,
+			       u16 type, int max);
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d1392194a9a9..d81f13de2476 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,7 +18,7 @@
 #include <unistd.h>
 
 #include "parse-events.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 
 #include <sys/mman.h>
 
@@ -68,6 +68,18 @@ struct perf_evlist *perf_evlist__new_default(void)
 	return evlist;
 }
 
+struct perf_evlist *perf_evlist__new_dummy(void)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist && perf_evlist__add_dummy(evlist)) {
+		perf_evlist__delete(evlist);
+		evlist = NULL;
+	}
+
+	return evlist;
+}
+
 /**
  * perf_evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
@@ -248,6 +260,22 @@ error:
 	return -ENOMEM;
 }
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist)
+{
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+		.size	= sizeof(attr), /* to capture ABI version */
+	};
+	struct perf_evsel *evsel = perf_evsel__new(&attr);
+
+	if (evsel == NULL)
+		return -ENOMEM;
+
+	perf_evlist__add(evlist, evsel);
+	return 0;
+}
+
 static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 				  struct perf_event_attr *attrs, size_t nr_attrs)
 {
@@ -336,20 +364,12 @@ static int perf_evlist__nr_threads(struct perf_evlist *evlist,
 
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
-	int cpu, thread;
 	struct perf_evsel *pos;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads;
 
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		evlist__for_each(evlist, pos) {
-			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-				continue;
-			nr_threads = perf_evlist__nr_threads(evlist, pos);
-			for (thread = 0; thread < nr_threads; thread++)
-				ioctl(FD(pos, cpu, thread),
-				      PERF_EVENT_IOC_DISABLE, 0);
-		}
+	evlist__for_each(evlist, pos) {
+		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+			continue;
+		perf_evsel__disable(pos);
 	}
 
 	evlist->enabled = false;
@@ -357,20 +377,12 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 
 void perf_evlist__enable(struct perf_evlist *evlist)
 {
-	int cpu, thread;
 	struct perf_evsel *pos;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads;
 
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		evlist__for_each(evlist, pos) {
-			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
-				continue;
-			nr_threads = perf_evlist__nr_threads(evlist, pos);
-			for (thread = 0; thread < nr_threads; thread++)
-				ioctl(FD(pos, cpu, thread),
-				      PERF_EVENT_IOC_ENABLE, 0);
-		}
+	evlist__for_each(evlist, pos) {
+		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+			continue;
+		perf_evsel__enable(pos);
 	}
 
 	evlist->enabled = true;
@@ -381,48 +393,6 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist)
 	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel)
-{
-	int cpu, thread, err;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-	if (!evsel->fd)
-		return 0;
-
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		for (thread = 0; thread < nr_threads; thread++) {
-			err = ioctl(FD(evsel, cpu, thread),
-				    PERF_EVENT_IOC_DISABLE, 0);
-			if (err)
-				return err;
-		}
-	}
-	return 0;
-}
-
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-			      struct perf_evsel *evsel)
-{
-	int cpu, thread, err;
-	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
-
-	if (!evsel->fd)
-		return -EINVAL;
-
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		for (thread = 0; thread < nr_threads; thread++) {
-			err = ioctl(FD(evsel, cpu, thread),
-				    PERF_EVENT_IOC_ENABLE, 0);
-			if (err)
-				return err;
-		}
-	}
-	return 0;
-}
-
 static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
 					 struct perf_evsel *evsel, int cpu)
 {
@@ -550,9 +520,9 @@ void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 	evsel->id[evsel->ids++] = id;
 }
 
-static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-				  struct perf_evsel *evsel,
-				  int cpu, int thread, int fd)
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd)
 {
 	u64 read_data[4] = { 0, };
 	int id_idx = 1; /* The first entry is the counter value */
@@ -1486,7 +1456,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 	perf_evlist__update_id_pos(evlist);
 
 	evlist__for_each(evlist, evsel) {
-		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
+		err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
 		if (err < 0)
 			goto out_err;
 	}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a459fe71b452..7c4d9a206776 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -67,6 +67,7 @@ struct perf_evsel_str_handler {
 
 struct perf_evlist *perf_evlist__new(void);
 struct perf_evlist *perf_evlist__new_default(void);
+struct perf_evlist *perf_evlist__new_dummy(void);
 void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		       struct thread_map *threads);
 void perf_evlist__exit(struct perf_evlist *evlist);
@@ -81,6 +82,8 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
 #define perf_evlist__add_default_attrs(evlist, array) \
 	__perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
+int perf_evlist__add_dummy(struct perf_evlist *evlist);
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler);
 
@@ -97,6 +100,9 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd);
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
@@ -149,10 +155,6 @@ void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
-int perf_evlist__disable_event(struct perf_evlist *evlist,
-			       struct perf_evsel *evsel);
-int perf_evlist__enable_event(struct perf_evlist *evlist,
-			      struct perf_evsel *evsel);
 int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 				  struct perf_evsel *evsel, int idx);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 397fb4ed3c97..cdbaf9b51e42 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -36,6 +36,7 @@ static struct {
 	bool cloexec;
 	bool clockid;
 	bool clockid_wrong;
+	bool lbr_flags;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -574,7 +575,9 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel,
 			} else {
 				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
-							PERF_SAMPLE_BRANCH_CALL_STACK;
+							PERF_SAMPLE_BRANCH_CALL_STACK |
+							PERF_SAMPLE_BRANCH_NO_CYCLES |
+							PERF_SAMPLE_BRANCH_NO_FLAGS;
 			}
 		} else
 			 pr_warning("Cannot use LBR callstack with branch stack. "
@@ -981,13 +984,26 @@ int perf_evsel__append_filter(struct perf_evsel *evsel,
 	return -1;
 }
 
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+int perf_evsel__enable(struct perf_evsel *evsel)
 {
+	int nthreads = thread_map__nr(evsel->threads);
+	int ncpus = cpu_map__nr(evsel->cpus);
+
 	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
 				     PERF_EVENT_IOC_ENABLE,
 				     0);
 }
 
+int perf_evsel__disable(struct perf_evsel *evsel)
+{
+	int nthreads = thread_map__nr(evsel->threads);
+	int ncpus = cpu_map__nr(evsel->cpus);
+
+	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+				     PERF_EVENT_IOC_DISABLE,
+				     0);
+}
+
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	if (ncpus == 0 || nthreads == 0)
@@ -1192,6 +1208,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
 		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
+		bit_name(WEIGHT),
 		{ .name = NULL, }
 	};
 #undef bit_name
@@ -1323,6 +1340,9 @@ fallback_missing_features:
 		evsel->attr.mmap2 = 0;
 	if (perf_missing_features.exclude_guest)
 		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+	if (perf_missing_features.lbr_flags)
+		evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
+				     PERF_SAMPLE_BRANCH_NO_CYCLES);
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1441,6 +1461,12 @@ try_fallback:
 	} else if (!perf_missing_features.sample_id_all) {
 		perf_missing_features.sample_id_all = true;
 		goto retry_sample_id;
+	} else if (!perf_missing_features.lbr_flags &&
+			(evsel->attr.branch_sample_type &
+			 (PERF_SAMPLE_BRANCH_NO_CYCLES |
+			  PERF_SAMPLE_BRANCH_NO_FLAGS))) {
+		perf_missing_features.lbr_flags = true;
+		goto fallback_missing_features;
 	}
 
 out_close:
@@ -2272,6 +2298,29 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		printed += comma_fprintf(fp, &first, " %s=%" PRIu64,
 					 term, (u64)evsel->attr.sample_freq);
 	}
+
+	if (details->trace_fields) {
+		struct format_field *field;
+
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+			printed += comma_fprintf(fp, &first, " (not a tracepoint)");
+			goto out;
+		}
+
+		field = evsel->tp_format->format.fields;
+		if (field == NULL) {
+			printed += comma_fprintf(fp, &first, " (no trace field)");
+			goto out;
+		}
+
+		printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name);
+
+		field = field->next;
+		while (field) {
+			printed += comma_fprintf(fp, &first, "%s", field->name);
+			field = field->next;
+		}
+	}
 out:
 	fputc('\n', fp);
 	return ++printed;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0e49bd742c63..8e75434bd01c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -227,7 +227,8 @@ int perf_evsel__append_filter(struct perf_evsel *evsel,
 			      const char *op, const char *filter);
 int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			     const char *filter);
-int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__enable(struct perf_evsel *evsel);
+int perf_evsel__disable(struct perf_evsel *evsel);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
 			     struct cpu_map *cpus);
@@ -368,6 +369,7 @@ struct perf_attr_details {
 	bool verbose;
 	bool event_group;
 	bool force;
+	bool trace_fields;
 };
 
 int perf_evsel__fprintf(struct perf_evsel *evsel,
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
deleted file mode 100644
index 7adf4ad15d8f..000000000000
--- a/tools/perf/util/exec_cmd.c
+++ /dev/null
@@ -1,148 +0,0 @@
-#include "cache.h"
-#include "exec_cmd.h"
-#include "quote.h"
-
-#include <string.h>
-
-#define MAX_ARGS	32
-
-static const char *argv_exec_path;
-static const char *argv0_path;
-
-const char *system_path(const char *path)
-{
-	static const char *prefix = PREFIX;
-	struct strbuf d = STRBUF_INIT;
-
-	if (is_absolute_path(path))
-		return path;
-
-	strbuf_addf(&d, "%s/%s", prefix, path);
-	path = strbuf_detach(&d, NULL);
-	return path;
-}
-
-const char *perf_extract_argv0_path(const char *argv0)
-{
-	const char *slash;
-
-	if (!argv0 || !*argv0)
-		return NULL;
-	slash = argv0 + strlen(argv0);
-
-	while (argv0 <= slash && !is_dir_sep(*slash))
-		slash--;
-
-	if (slash >= argv0) {
-		argv0_path = strndup(argv0, slash - argv0);
-		return argv0_path ? slash + 1 : NULL;
-	}
-
-	return argv0;
-}
-
-void perf_set_argv_exec_path(const char *exec_path)
-{
-	argv_exec_path = exec_path;
-	/*
-	 * Propagate this setting to external programs.
-	 */
-	setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1);
-}
-
-
-/* Returns the highest-priority, location to look for perf programs. */
-const char *perf_exec_path(void)
-{
-	const char *env;
-
-	if (argv_exec_path)
-		return argv_exec_path;
-
-	env = getenv(EXEC_PATH_ENVIRONMENT);
-	if (env && *env) {
-		return env;
-	}
-
-	return system_path(PERF_EXEC_PATH);
-}
-
-static void add_path(struct strbuf *out, const char *path)
-{
-	if (path && *path) {
-		if (is_absolute_path(path))
-			strbuf_addstr(out, path);
-		else
-			strbuf_addstr(out, make_nonrelative_path(path));
-
-		strbuf_addch(out, PATH_SEP);
-	}
-}
-
-void setup_path(void)
-{
-	const char *old_path = getenv("PATH");
-	struct strbuf new_path = STRBUF_INIT;
-
-	add_path(&new_path, perf_exec_path());
-	add_path(&new_path, argv0_path);
-
-	if (old_path)
-		strbuf_addstr(&new_path, old_path);
-	else
-		strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin");
-
-	setenv("PATH", new_path.buf, 1);
-
-	strbuf_release(&new_path);
-}
-
-static const char **prepare_perf_cmd(const char **argv)
-{
-	int argc;
-	const char **nargv;
-
-	for (argc = 0; argv[argc]; argc++)
-		; /* just counting */
-	nargv = malloc(sizeof(*nargv) * (argc + 2));
-
-	nargv[0] = "perf";
-	for (argc = 0; argv[argc]; argc++)
-		nargv[argc + 1] = argv[argc];
-	nargv[argc + 1] = NULL;
-	return nargv;
-}
-
-int execv_perf_cmd(const char **argv) {
-	const char **nargv = prepare_perf_cmd(argv);
-
-	/* execvp() can only ever return if it fails */
-	execvp("perf", (char **)nargv);
-
-	free(nargv);
-	return -1;
-}
-
-
-int execl_perf_cmd(const char *cmd,...)
-{
-	int argc;
-	const char *argv[MAX_ARGS + 1];
-	const char *arg;
-	va_list param;
-
-	va_start(param, cmd);
-	argv[0] = cmd;
-	argc = 1;
-	while (argc < MAX_ARGS) {
-		arg = argv[argc++] = va_arg(param, char *);
-		if (!arg)
-			break;
-	}
-	va_end(param);
-	if (MAX_ARGS <= argc)
-		return error("too many args to run %s", cmd);
-
-	argv[argc] = NULL;
-	return execv_perf_cmd(argv);
-}
diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h
deleted file mode 100644
index bc4b915963f5..000000000000
--- a/tools/perf/util/exec_cmd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __PERF_EXEC_CMD_H
-#define __PERF_EXEC_CMD_H
-
-extern void perf_set_argv_exec_path(const char *exec_path);
-extern const char *perf_extract_argv0_path(const char *path);
-extern const char *perf_exec_path(void);
-extern void setup_path(void);
-extern int execv_perf_cmd(const char **argv); /* NULL terminated */
-extern int execl_perf_cmd(const char *cmd, ...);
-extern const char *system_path(const char *path);
-
-#endif /* __PERF_EXEC_CMD_H */
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index 36a885d2cd22..0ac2037c970c 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -36,4 +36,19 @@ do
      }' "Documentation/perf-$cmd.txt"
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
+
+echo "#ifdef HAVE_LIBAUDIT_SUPPORT"
+sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+	    p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBELF_SUPPORT */"
 echo "};"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 43838003c1a1..f50b7235ecb6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -724,7 +724,7 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
 done:
 	free(buf);
 	fclose(fp);
-	free(node_map);
+	cpu_map__put(node_map);
 	return ret;
 }
 
@@ -868,6 +868,13 @@ static int write_auxtrace(int fd, struct perf_header *h,
 	return err;
 }
 
+static int write_stat(int fd __maybe_unused,
+		      struct perf_header *h __maybe_unused,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	return 0;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
 			   FILE *fp)
 {
@@ -1159,6 +1166,12 @@ static void print_auxtrace(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
 }
 
+static void print_stat(struct perf_header *ph __maybe_unused,
+		       int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains stat data\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1948,6 +1961,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
+	FEAT_OPA(HEADER_STAT,		stat),
 };
 
 struct header_print_data {
@@ -2686,6 +2700,152 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 	return err;
 }
 
+static struct event_update_event *
+event_update_event__new(size_t size, u64 type, u64 id)
+{
+	struct event_update_event *ev;
+
+	size += sizeof(*ev);
+	size  = PERF_ALIGN(size, sizeof(u64));
+
+	ev = zalloc(size);
+	if (ev) {
+		ev->header.type = PERF_RECORD_EVENT_UPDATE;
+		ev->header.size = (u16)size;
+		ev->type = type;
+		ev->id = id;
+	}
+	return ev;
+}
+
+int
+perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+					 struct perf_evsel *evsel,
+					 perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	size_t size = strlen(evsel->unit);
+	int err;
+
+	ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strncpy(ev->data, evsel->unit, size);
+	err = process(tool, (union perf_event *)ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+					  struct perf_evsel *evsel,
+					  perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	struct event_update_event_scale *ev_data;
+	int err;
+
+	ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	ev_data = (struct event_update_event_scale *) ev->data;
+	ev_data->scale = evsel->scale;
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_name(struct perf_tool *tool,
+					 struct perf_evsel *evsel,
+					 perf_event__handler_t process)
+{
+	struct event_update_event *ev;
+	size_t len = strlen(evsel->name);
+	int err;
+
+	ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]);
+	if (ev == NULL)
+		return -ENOMEM;
+
+	strncpy(ev->data, evsel->name, len);
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+int
+perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+					struct perf_evsel *evsel,
+					perf_event__handler_t process)
+{
+	size_t size = sizeof(struct event_update_event);
+	struct event_update_event *ev;
+	int max, err;
+	u16 type;
+
+	if (!evsel->own_cpus)
+		return 0;
+
+	ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->header.type = PERF_RECORD_EVENT_UPDATE;
+	ev->header.size = (u16)size;
+	ev->type = PERF_EVENT_UPDATE__CPUS;
+	ev->id   = evsel->id[0];
+
+	cpu_map_data__synthesize((struct cpu_map_data *) ev->data,
+				 evsel->own_cpus,
+				 type, max);
+
+	err = process(tool, (union perf_event*) ev, NULL, NULL);
+	free(ev);
+	return err;
+}
+
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
+{
+	struct event_update_event *ev = &event->event_update;
+	struct event_update_event_scale *ev_scale;
+	struct event_update_event_cpus *ev_cpus;
+	struct cpu_map *map;
+	size_t ret;
+
+	ret = fprintf(fp, "\n... id:    %" PRIu64 "\n", ev->id);
+
+	switch (ev->type) {
+	case PERF_EVENT_UPDATE__SCALE:
+		ev_scale = (struct event_update_event_scale *) ev->data;
+		ret += fprintf(fp, "... scale: %f\n", ev_scale->scale);
+		break;
+	case PERF_EVENT_UPDATE__UNIT:
+		ret += fprintf(fp, "... unit:  %s\n", ev->data);
+		break;
+	case PERF_EVENT_UPDATE__NAME:
+		ret += fprintf(fp, "... name:  %s\n", ev->data);
+		break;
+	case PERF_EVENT_UPDATE__CPUS:
+		ev_cpus = (struct event_update_event_cpus *) ev->data;
+		ret += fprintf(fp, "... ");
+
+		map = cpu_map__new_data(&ev_cpus->cpus);
+		if (map)
+			ret += cpu_map__fprintf(map, fp);
+		else
+			ret += fprintf(fp, "failed to get cpus\n");
+		break;
+	default:
+		ret += fprintf(fp, "... unknown type\n");
+		break;
+	}
+
+	return ret;
+}
+
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				   struct perf_session *session,
 				   perf_event__handler_t process)
@@ -2745,6 +2905,51 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_evlist **pevlist)
+{
+	struct event_update_event *ev = &event->event_update;
+	struct event_update_event_scale *ev_scale;
+	struct event_update_event_cpus *ev_cpus;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct cpu_map *map;
+
+	if (!pevlist || *pevlist == NULL)
+		return -EINVAL;
+
+	evlist = *pevlist;
+
+	evsel = perf_evlist__id2evsel(evlist, ev->id);
+	if (evsel == NULL)
+		return -EINVAL;
+
+	switch (ev->type) {
+	case PERF_EVENT_UPDATE__UNIT:
+		evsel->unit = strdup(ev->data);
+		break;
+	case PERF_EVENT_UPDATE__NAME:
+		evsel->name = strdup(ev->data);
+		break;
+	case PERF_EVENT_UPDATE__SCALE:
+		ev_scale = (struct event_update_event_scale *) ev->data;
+		evsel->scale = ev_scale->scale;
+	case PERF_EVENT_UPDATE__CPUS:
+		ev_cpus = (struct event_update_event_cpus *) ev->data;
+
+		map = cpu_map__new_data(&ev_cpus->cpus);
+		if (map)
+			evsel->own_cpus = map;
+		else
+			pr_err("failed to get event_update cpus\n");
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 					struct perf_evlist *evlist,
 					perf_event__handler_t process)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 05f27cb6b7e3..cff9892452ee 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -31,6 +31,7 @@ enum {
 	HEADER_PMU_MAPPINGS,
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
+	HEADER_STAT,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -105,8 +106,24 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				 struct perf_session *session,
 				 perf_event__handler_t process);
+int perf_event__synthesize_event_update_unit(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
+int perf_event__synthesize_event_update_scale(struct perf_tool *tool,
+					      struct perf_evsel *evsel,
+					      perf_event__handler_t process);
+int perf_event__synthesize_event_update_name(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
+int perf_event__synthesize_event_update_cpus(struct perf_tool *tool,
+					     struct perf_evsel *evsel,
+					     perf_event__handler_t process);
 int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
 			     struct perf_evlist **pevlist);
+int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_evlist **pevlist);
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
 
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
new file mode 100644
index 000000000000..dc1e41c9b054
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -0,0 +1,103 @@
+#include "cache.h"
+#include <subcmd/help.h>
+#include "../builtin.h"
+#include "levenshtein.h"
+
+static int autocorrect;
+static struct cmdnames aliases;
+
+static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "help.autocorrect"))
+		autocorrect = perf_config_int(var,value);
+	/* Also use aliases for command lookup */
+	if (!prefixcmp(var, "alias."))
+		add_cmdname(&aliases, var + 6, strlen(var + 6));
+
+	return perf_default_config(var, value, cb);
+}
+
+static int levenshtein_compare(const void *p1, const void *p2)
+{
+	const struct cmdname *const *c1 = p1, *const *c2 = p2;
+	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
+	int l1 = (*c1)->len;
+	int l2 = (*c2)->len;
+	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
+}
+
+static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
+{
+	unsigned int i;
+
+	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
+
+	for (i = 0; i < old->cnt; i++)
+		cmds->names[cmds->cnt++] = old->names[i];
+	zfree(&old->names);
+	old->cnt = 0;
+}
+
+const char *help_unknown_cmd(const char *cmd)
+{
+	unsigned int i, n = 0, best_similarity = 0;
+	struct cmdnames main_cmds, other_cmds;
+
+	memset(&main_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(main_cmds));
+	memset(&aliases, 0, sizeof(aliases));
+
+	perf_config(perf_unknown_cmd_config, NULL);
+
+	load_command_list("perf-", &main_cmds, &other_cmds);
+
+	add_cmd_list(&main_cmds, &aliases);
+	add_cmd_list(&main_cmds, &other_cmds);
+	qsort(main_cmds.names, main_cmds.cnt,
+	      sizeof(main_cmds.names), cmdname_compare);
+	uniq(&main_cmds);
+
+	if (main_cmds.cnt) {
+		/* This reuses cmdname->len for similarity index */
+		for (i = 0; i < main_cmds.cnt; ++i)
+			main_cmds.names[i]->len =
+				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
+
+		qsort(main_cmds.names, main_cmds.cnt,
+		      sizeof(*main_cmds.names), levenshtein_compare);
+
+		best_similarity = main_cmds.names[0]->len;
+		n = 1;
+		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+			++n;
+	}
+
+	if (autocorrect && n == 1) {
+		const char *assumed = main_cmds.names[0]->name;
+
+		main_cmds.names[0] = NULL;
+		clean_cmdnames(&main_cmds);
+		fprintf(stderr, "WARNING: You called a perf program named '%s', "
+			"which does not exist.\n"
+			"Continuing under the assumption that you meant '%s'\n",
+			cmd, assumed);
+		if (autocorrect > 0) {
+			fprintf(stderr, "in %0.1f seconds automatically...\n",
+				(float)autocorrect/10.0);
+			poll(NULL, 0, autocorrect * 100);
+		}
+		return assumed;
+	}
+
+	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
+
+	if (main_cmds.cnt && best_similarity < 6) {
+		fprintf(stderr, "\nDid you mean %s?\n",
+			n < 2 ? "this": "one of these");
+
+		for (i = 0; i < n; i++)
+			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+	}
+
+	exit(1);
+}
diff --git a/tools/perf/util/help-unknown-cmd.h b/tools/perf/util/help-unknown-cmd.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/perf/util/help-unknown-cmd.h
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
deleted file mode 100644
index 86c37c472263..000000000000
--- a/tools/perf/util/help.c
+++ /dev/null
@@ -1,339 +0,0 @@
-#include "cache.h"
-#include "../builtin.h"
-#include "exec_cmd.h"
-#include "levenshtein.h"
-#include "help.h"
-#include <termios.h>
-
-void add_cmdname(struct cmdnames *cmds, const char *name, size_t len)
-{
-	struct cmdname *ent = malloc(sizeof(*ent) + len + 1);
-
-	ent->len = len;
-	memcpy(ent->name, name, len);
-	ent->name[len] = 0;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + 1, cmds->alloc);
-	cmds->names[cmds->cnt++] = ent;
-}
-
-static void clean_cmdnames(struct cmdnames *cmds)
-{
-	unsigned int i;
-
-	for (i = 0; i < cmds->cnt; ++i)
-		zfree(&cmds->names[i]);
-	zfree(&cmds->names);
-	cmds->cnt = 0;
-	cmds->alloc = 0;
-}
-
-static int cmdname_compare(const void *a_, const void *b_)
-{
-	struct cmdname *a = *(struct cmdname **)a_;
-	struct cmdname *b = *(struct cmdname **)b_;
-	return strcmp(a->name, b->name);
-}
-
-static void uniq(struct cmdnames *cmds)
-{
-	unsigned int i, j;
-
-	if (!cmds->cnt)
-		return;
-
-	for (i = j = 1; i < cmds->cnt; i++)
-		if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name))
-			cmds->names[j++] = cmds->names[i];
-
-	cmds->cnt = j;
-}
-
-void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
-{
-	size_t ci, cj, ei;
-	int cmp;
-
-	ci = cj = ei = 0;
-	while (ci < cmds->cnt && ei < excludes->cnt) {
-		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
-		if (cmp < 0)
-			cmds->names[cj++] = cmds->names[ci++];
-		else if (cmp == 0)
-			ci++, ei++;
-		else if (cmp > 0)
-			ei++;
-	}
-
-	while (ci < cmds->cnt)
-		cmds->names[cj++] = cmds->names[ci++];
-
-	cmds->cnt = cj;
-}
-
-static void pretty_print_string_list(struct cmdnames *cmds, int longest)
-{
-	int cols = 1, rows;
-	int space = longest + 1; /* min 1 SP between words */
-	struct winsize win;
-	int max_cols;
-	int i, j;
-
-	get_term_dimensions(&win);
-	max_cols = win.ws_col - 1; /* don't print *on* the edge */
-
-	if (space < max_cols)
-		cols = max_cols / space;
-	rows = (cmds->cnt + cols - 1) / cols;
-
-	for (i = 0; i < rows; i++) {
-		printf("  ");
-
-		for (j = 0; j < cols; j++) {
-			unsigned int n = j * rows + i;
-			unsigned int size = space;
-
-			if (n >= cmds->cnt)
-				break;
-			if (j == cols-1 || n + rows >= cmds->cnt)
-				size = 1;
-			printf("%-*s", size, cmds->names[n]->name);
-		}
-		putchar('\n');
-	}
-}
-
-static int is_executable(const char *name)
-{
-	struct stat st;
-
-	if (stat(name, &st) || /* stat, not lstat */
-	    !S_ISREG(st.st_mode))
-		return 0;
-
-	return st.st_mode & S_IXUSR;
-}
-
-static void list_commands_in_dir(struct cmdnames *cmds,
-					 const char *path,
-					 const char *prefix)
-{
-	int prefix_len;
-	DIR *dir = opendir(path);
-	struct dirent *de;
-	struct strbuf buf = STRBUF_INIT;
-	int len;
-
-	if (!dir)
-		return;
-	if (!prefix)
-		prefix = "perf-";
-	prefix_len = strlen(prefix);
-
-	strbuf_addf(&buf, "%s/", path);
-	len = buf.len;
-
-	while ((de = readdir(dir)) != NULL) {
-		int entlen;
-
-		if (prefixcmp(de->d_name, prefix))
-			continue;
-
-		strbuf_setlen(&buf, len);
-		strbuf_addstr(&buf, de->d_name);
-		if (!is_executable(buf.buf))
-			continue;
-
-		entlen = strlen(de->d_name) - prefix_len;
-		if (has_extension(de->d_name, ".exe"))
-			entlen -= 4;
-
-		add_cmdname(cmds, de->d_name + prefix_len, entlen);
-	}
-	closedir(dir);
-	strbuf_release(&buf);
-}
-
-void load_command_list(const char *prefix,
-		struct cmdnames *main_cmds,
-		struct cmdnames *other_cmds)
-{
-	const char *env_path = getenv("PATH");
-	const char *exec_path = perf_exec_path();
-
-	if (exec_path) {
-		list_commands_in_dir(main_cmds, exec_path, prefix);
-		qsort(main_cmds->names, main_cmds->cnt,
-		      sizeof(*main_cmds->names), cmdname_compare);
-		uniq(main_cmds);
-	}
-
-	if (env_path) {
-		char *paths, *path, *colon;
-		path = paths = strdup(env_path);
-		while (1) {
-			if ((colon = strchr(path, PATH_SEP)))
-				*colon = 0;
-			if (!exec_path || strcmp(path, exec_path))
-				list_commands_in_dir(other_cmds, path, prefix);
-
-			if (!colon)
-				break;
-			path = colon + 1;
-		}
-		free(paths);
-
-		qsort(other_cmds->names, other_cmds->cnt,
-		      sizeof(*other_cmds->names), cmdname_compare);
-		uniq(other_cmds);
-	}
-	exclude_cmds(other_cmds, main_cmds);
-}
-
-void list_commands(const char *title, struct cmdnames *main_cmds,
-		   struct cmdnames *other_cmds)
-{
-	unsigned int i, longest = 0;
-
-	for (i = 0; i < main_cmds->cnt; i++)
-		if (longest < main_cmds->names[i]->len)
-			longest = main_cmds->names[i]->len;
-	for (i = 0; i < other_cmds->cnt; i++)
-		if (longest < other_cmds->names[i]->len)
-			longest = other_cmds->names[i]->len;
-
-	if (main_cmds->cnt) {
-		const char *exec_path = perf_exec_path();
-		printf("available %s in '%s'\n", title, exec_path);
-		printf("----------------");
-		mput_char('-', strlen(title) + strlen(exec_path));
-		putchar('\n');
-		pretty_print_string_list(main_cmds, longest);
-		putchar('\n');
-	}
-
-	if (other_cmds->cnt) {
-		printf("%s available from elsewhere on your $PATH\n", title);
-		printf("---------------------------------------");
-		mput_char('-', strlen(title));
-		putchar('\n');
-		pretty_print_string_list(other_cmds, longest);
-		putchar('\n');
-	}
-}
-
-int is_in_cmdlist(struct cmdnames *c, const char *s)
-{
-	unsigned int i;
-
-	for (i = 0; i < c->cnt; i++)
-		if (!strcmp(s, c->names[i]->name))
-			return 1;
-	return 0;
-}
-
-static int autocorrect;
-static struct cmdnames aliases;
-
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
-{
-	if (!strcmp(var, "help.autocorrect"))
-		autocorrect = perf_config_int(var,value);
-	/* Also use aliases for command lookup */
-	if (!prefixcmp(var, "alias."))
-		add_cmdname(&aliases, var + 6, strlen(var + 6));
-
-	return perf_default_config(var, value, cb);
-}
-
-static int levenshtein_compare(const void *p1, const void *p2)
-{
-	const struct cmdname *const *c1 = p1, *const *c2 = p2;
-	const char *s1 = (*c1)->name, *s2 = (*c2)->name;
-	int l1 = (*c1)->len;
-	int l2 = (*c2)->len;
-	return l1 != l2 ? l1 - l2 : strcmp(s1, s2);
-}
-
-static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
-{
-	unsigned int i;
-
-	ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc);
-
-	for (i = 0; i < old->cnt; i++)
-		cmds->names[cmds->cnt++] = old->names[i];
-	zfree(&old->names);
-	old->cnt = 0;
-}
-
-const char *help_unknown_cmd(const char *cmd)
-{
-	unsigned int i, n = 0, best_similarity = 0;
-	struct cmdnames main_cmds, other_cmds;
-
-	memset(&main_cmds, 0, sizeof(main_cmds));
-	memset(&other_cmds, 0, sizeof(main_cmds));
-	memset(&aliases, 0, sizeof(aliases));
-
-	perf_config(perf_unknown_cmd_config, NULL);
-
-	load_command_list("perf-", &main_cmds, &other_cmds);
-
-	add_cmd_list(&main_cmds, &aliases);
-	add_cmd_list(&main_cmds, &other_cmds);
-	qsort(main_cmds.names, main_cmds.cnt,
-	      sizeof(main_cmds.names), cmdname_compare);
-	uniq(&main_cmds);
-
-	if (main_cmds.cnt) {
-		/* This reuses cmdname->len for similarity index */
-		for (i = 0; i < main_cmds.cnt; ++i)
-			main_cmds.names[i]->len =
-				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-		qsort(main_cmds.names, main_cmds.cnt,
-		      sizeof(*main_cmds.names), levenshtein_compare);
-
-		best_similarity = main_cmds.names[0]->len;
-		n = 1;
-		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
-			++n;
-	}
-
-	if (autocorrect && n == 1) {
-		const char *assumed = main_cmds.names[0]->name;
-
-		main_cmds.names[0] = NULL;
-		clean_cmdnames(&main_cmds);
-		fprintf(stderr, "WARNING: You called a perf program named '%s', "
-			"which does not exist.\n"
-			"Continuing under the assumption that you meant '%s'\n",
-			cmd, assumed);
-		if (autocorrect > 0) {
-			fprintf(stderr, "in %0.1f seconds automatically...\n",
-				(float)autocorrect/10.0);
-			poll(NULL, 0, autocorrect * 100);
-		}
-		return assumed;
-	}
-
-	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
-
-	if (main_cmds.cnt && best_similarity < 6) {
-		fprintf(stderr, "\nDid you mean %s?\n",
-			n < 2 ? "this": "one of these");
-
-		for (i = 0; i < n; i++)
-			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
-	}
-
-	exit(1);
-}
-
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-		const char *prefix __maybe_unused)
-{
-	printf("perf version %s\n", perf_version_string);
-	return 0;
-}
diff --git a/tools/perf/util/help.h b/tools/perf/util/help.h
deleted file mode 100644
index 7f5c6dedd714..000000000000
--- a/tools/perf/util/help.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __PERF_HELP_H
-#define __PERF_HELP_H
-
-struct cmdnames {
-	size_t alloc;
-	size_t cnt;
-	struct cmdname {
-		size_t len; /* also used for similarity index in help.c */
-		char name[FLEX_ARRAY];
-	} **names;
-};
-
-static inline void mput_char(char c, unsigned int num)
-{
-	while(num--)
-		putchar(c);
-}
-
-void load_command_list(const char *prefix,
-		struct cmdnames *main_cmds,
-		struct cmdnames *other_cmds);
-void add_cmdname(struct cmdnames *cmds, const char *name, size_t len);
-/* Here we require that excludes is a sorted list. */
-void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes);
-int is_in_cmdlist(struct cmdnames *c, const char *s);
-void list_commands(const char *title, struct cmdnames *main_cmds,
-		   struct cmdnames *other_cmds);
-
-#endif /* __PERF_HELP_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4fd37d6708cb..c226303e3da0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -254,6 +254,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	he_stat__decay(&he->stat);
 	if (symbol_conf.cumulate_callchain)
 		he_stat__decay(he->stat_acc);
+	decay_callchain(he->callchain);
 
 	diff = prev_period - he->stat.period;
 
@@ -270,6 +271,8 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 
 	if (sort__need_collapse)
 		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
+	else
+		rb_erase(&he->rb_node_in, hists->entries_in);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -367,6 +370,25 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 		if (symbol_conf.use_callchain)
 			callchain_init(he->callchain);
 
+		if (he->raw_data) {
+			he->raw_data = memdup(he->raw_data, he->raw_size);
+
+			if (he->raw_data == NULL) {
+				map__put(he->ms.map);
+				if (he->branch_info) {
+					map__put(he->branch_info->from.map);
+					map__put(he->branch_info->to.map);
+					free(he->branch_info);
+				}
+				if (he->mem_info) {
+					map__put(he->mem_info->iaddr.map);
+					map__put(he->mem_info->daddr.map);
+				}
+				free(he->stat_acc);
+				free(he);
+				return NULL;
+			}
+		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
 	}
@@ -459,7 +481,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction,
+				      struct perf_sample *sample,
 				      bool sample_self)
 {
 	struct hist_entry entry = {
@@ -476,15 +498,17 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
-			.period	= period,
-			.weight = weight,
+			.period	= sample->period,
+			.weight = sample->weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,
-		.transaction = transaction,
+		.transaction = sample->transaction,
+		.raw_data = sample->raw_data,
+		.raw_size = sample->raw_size,
 	};
 
 	return hists__findnew_entry(hists, &entry, al, sample_self);
@@ -524,12 +548,13 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	u64 cost;
 	struct mem_info *mi = iter->priv;
 	struct hists *hists = evsel__hists(iter->evsel);
+	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he;
 
 	if (mi == NULL)
 		return -EINVAL;
 
-	cost = iter->sample->weight;
+	cost = sample->weight;
 	if (!cost)
 		cost = 1;
 
@@ -540,8 +565,10 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
 	 * and this is indirectly achieved by passing period=weight here
 	 * and the he_stat__add_period() function.
 	 */
+	sample->period = cost;
+
 	he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-				cost, cost, 0, true);
+				sample, true);
 	if (!he)
 		return -ENOMEM;
 
@@ -628,6 +655,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	struct branch_info *bi;
 	struct perf_evsel *evsel = iter->evsel;
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_sample *sample = iter->sample;
 	struct hist_entry *he = NULL;
 	int i = iter->curr;
 	int err = 0;
@@ -641,9 +669,11 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	 * The report shows the percentage of total branches captured
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
+	sample->period = 1;
+	sample->weight = bi->flags.cycles ? bi->flags.cycles : 1;
+
 	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-				1, bi->flags.cycles ? bi->flags.cycles : 1,
-				0, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -680,8 +710,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
 	struct hist_entry *he;
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -742,8 +771,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	int err = 0;
 
 	he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, true);
+				sample, true);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -795,6 +823,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 			.sym = al->sym,
 		},
 		.parent = iter->parent,
+		.raw_data = sample->raw_data,
+		.raw_size = sample->raw_size,
 	};
 	int i;
 	struct callchain_cursor cursor;
@@ -816,8 +846,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	}
 
 	he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction, false);
+				sample, false);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -924,9 +953,6 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
-			continue;
-
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -942,9 +968,6 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
-			continue;
-
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -975,6 +998,8 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->srcfile && he->srcfile[0])
 		free(he->srcfile);
 	free_callchain(he->callchain);
+	free(he->trace_output);
+	free(he->raw_data);
 	free(he);
 }
 
@@ -982,9 +1007,8 @@ void hist_entry__delete(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-					 struct rb_root *root,
-					 struct hist_entry *he)
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+				  struct rb_root *root, struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
@@ -1024,7 +1048,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 	return true;
 }
 
-static struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
 {
 	struct rb_root *root;
 
@@ -1088,7 +1112,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 	int64_t cmp = 0;
 
 	perf_hpp__for_each_sort_list(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, a->hists))
 			continue;
 
 		cmp = fmt->sort(fmt, a, b);
@@ -1559,10 +1583,8 @@ int perf_hist_config(const char *var, const char *value)
 	return 0;
 }
 
-static int hists_evsel__init(struct perf_evsel *evsel)
+int __hists__init(struct hists *hists)
 {
-	struct hists *hists = evsel__hists(evsel);
-
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
 	hists->entries_in = &hists->entries_in_array[0];
@@ -1573,6 +1595,43 @@ static int hists_evsel__init(struct perf_evsel *evsel)
 	return 0;
 }
 
+static void hists__delete_remaining_entries(struct rb_root *root)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		node = rb_first(root);
+		rb_erase(node, root);
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		hist_entry__delete(he);
+	}
+}
+
+static void hists__delete_all_entries(struct hists *hists)
+{
+	hists__delete_entries(hists);
+	hists__delete_remaining_entries(&hists->entries_in_array[0]);
+	hists__delete_remaining_entries(&hists->entries_in_array[1]);
+	hists__delete_remaining_entries(&hists->entries_collapsed);
+}
+
+static void hists_evsel__exit(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	hists__delete_all_entries(hists);
+}
+
+static int hists_evsel__init(struct perf_evsel *evsel)
+{
+	struct hists *hists = evsel__hists(evsel);
+
+	__hists__init(hists);
+	return 0;
+}
+
 /*
  * XXX We probably need a hists_evsel__exit() to free the hist_entries
  * stored in the rbtree...
@@ -1581,7 +1640,8 @@ static int hists_evsel__init(struct perf_evsel *evsel)
 int hists__init(void)
 {
 	int err = perf_evsel__object_config(sizeof(struct hists_evsel),
-					    hists_evsel__init, NULL);
+					    hists_evsel__init,
+					    hists_evsel__exit);
 	if (err)
 		fputs("FATAL ERROR: Couldn't setup hists class\n", stderr);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a48a2078d288..d4ec4822a103 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,6 +52,7 @@ enum hist_column {
 	HISTC_MEM_IADDR_SYMBOL,
 	HISTC_TRANSACTION,
 	HISTC_CYCLES,
+	HISTC_TRACE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -114,8 +115,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
-				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction,
+				      struct mem_info *mi,
+				      struct perf_sample *sample,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
@@ -184,6 +185,11 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
+int __hists__init(struct hists *hists);
+
+struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
+bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
 	char *buf;
@@ -261,10 +267,20 @@ void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
 
-static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
+					 struct hists *hists)
 {
-	return format->elide;
+	if (format->elide)
+		return true;
+
+	if (perf_hpp__is_dynamic_entry(format) &&
+	    !perf_hpp__defined_dynamic_entry(format, hists))
+		return true;
+
+	return false;
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
deleted file mode 100644
index 40bd21488032..000000000000
--- a/tools/perf/util/include/linux/bitmap.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef _PERF_BITOPS_H
-#define _PERF_BITOPS_H
-
-#include <string.h>
-#include <linux/bitops.h>
-
-#define DECLARE_BITMAP(name,bits) \
-	unsigned long name[BITS_TO_LONGS(bits)]
-
-int __bitmap_weight(const unsigned long *bitmap, int bits);
-void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-		 const unsigned long *bitmap2, int bits);
-
-#define BITMAP_LAST_WORD_MASK(nbits)					\
-(									\
-	((nbits) % BITS_PER_LONG) ?					\
-		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
-)
-
-#define small_const_nbits(nbits) \
-	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
-
-static inline void bitmap_zero(unsigned long *dst, int nbits)
-{
-	if (small_const_nbits(nbits))
-		*dst = 0UL;
-	else {
-		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-		memset(dst, 0, len);
-	}
-}
-
-static inline int bitmap_weight(const unsigned long *src, int nbits)
-{
-	if (small_const_nbits(nbits))
-		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
-	return __bitmap_weight(src, nbits);
-}
-
-static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			     const unsigned long *src2, int nbits)
-{
-	if (small_const_nbits(nbits))
-		*dst = *src1 | *src2;
-	else
-		__bitmap_or(dst, src1, src2, nbits);
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- */
-static inline int test_and_set_bit(int nr, unsigned long *addr)
-{
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-
-	old = *p;
-	*p = old | mask;
-
-	return (old & mask) != 0;
-}
-
-#endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
deleted file mode 100644
index 6f19c548ecc0..000000000000
--- a/tools/perf/util/include/linux/string.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <string.h>
-
-void *memdup(const void *src, size_t len);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 97f963a3dcb9..81a2eb77ba7f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1744,7 +1744,7 @@ static void intel_pt_free(struct perf_session *session)
 	auxtrace_heap__free(&pt->heap);
 	intel_pt_free_events(session);
 	session->auxtrace = NULL;
-	thread__delete(pt->unknown_thread);
+	thread__put(pt->unknown_thread);
 	free(pt);
 }
 
@@ -2153,7 +2153,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	return 0;
 
 err_delete_thread:
-	thread__delete(pt->unknown_thread);
+	thread__zput(pt->unknown_thread);
 err_free_queues:
 	intel_pt_log_disable();
 	auxtrace_queues__free(&pt->queues);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8b303ff20289..ad79297c76c8 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -25,6 +25,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
+	memset(machine, 0, sizeof(*machine));
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->dsos);
@@ -44,6 +45,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
 
+	memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
 		return -ENOMEM;
@@ -122,6 +125,7 @@ void machine__delete_threads(struct machine *machine)
 
 void machine__exit(struct machine *machine)
 {
+	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
@@ -348,13 +352,18 @@ static void machine__update_thread_pid(struct machine *machine,
 	}
 
 	th->mg = map_groups__get(leader->mg);
-
+out_put:
+	thread__put(leader);
 	return;
-
 out_err:
 	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+	goto out_put;
 }
 
+/*
+ * Caller must eventually drop thread->refcnt returned with a successfull
+ * lookup/new thread inserted.
+ */
 static struct thread *____machine__findnew_thread(struct machine *machine,
 						  pid_t pid, pid_t tid,
 						  bool create)
@@ -372,7 +381,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 	if (th != NULL) {
 		if (th->tid == tid) {
 			machine__update_thread_pid(machine, th, pid);
-			return th;
+			return thread__get(th);
 		}
 
 		machine->last_match = NULL;
@@ -385,7 +394,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		if (th->tid == tid) {
 			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
-			return th;
+			return thread__get(th);
 		}
 
 		if (tid < th->tid)
@@ -413,7 +422,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		if (thread__init_map_groups(th, machine)) {
 			rb_erase_init(&th->rb_node, &machine->threads);
 			RB_CLEAR_NODE(&th->rb_node);
-			thread__delete(th);
+			thread__put(th);
 			return NULL;
 		}
 		/*
@@ -437,7 +446,7 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 	struct thread *th;
 
 	pthread_rwlock_wrlock(&machine->threads_lock);
-	th = thread__get(__machine__findnew_thread(machine, pid, tid));
+	th = __machine__findnew_thread(machine, pid, tid);
 	pthread_rwlock_unlock(&machine->threads_lock);
 	return th;
 }
@@ -447,7 +456,7 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 {
 	struct thread *th;
 	pthread_rwlock_rdlock(&machine->threads_lock);
-	th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+	th =  ____machine__findnew_thread(machine, pid, tid, false);
 	pthread_rwlock_unlock(&machine->threads_lock);
 	return th;
 }
@@ -560,11 +569,29 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
+{
+	const char *dup_filename;
+
+	if (!filename || !dso || !dso->long_name)
+		return;
+	if (dso->long_name[0] != '[')
+		return;
+	if (!strchr(filename, '/'))
+		return;
+
+	dup_filename = strdup(filename);
+	if (!dup_filename)
+		return;
+
+	dso__set_long_name(dso, dup_filename, true);
+}
+
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename)
 {
 	struct map *map = NULL;
-	struct dso *dso;
+	struct dso *dso = NULL;
 	struct kmod_path m;
 
 	if (kmod_path__parse_name(&m, filename))
@@ -572,8 +599,15 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 
 	map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
 				       m.name);
-	if (map)
+	if (map) {
+		/*
+		 * If the map's dso is an offline module, give dso__load()
+		 * a chance to find the file path of that module by fixing
+		 * long_name.
+		 */
+		dso__adjust_kmod_long_name(map->dso, filename);
 		goto out;
+	}
 
 	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
@@ -585,7 +619,11 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 
 	map_groups__insert(&machine->kmaps, map);
 
+	/* Put the map here because map_groups__insert alread got it */
+	map__put(map);
 out:
+	/* put the dso here, corresponding to  machine__findnew_module_dso */
+	dso__put(dso);
 	free(m.name);
 	return map;
 }
@@ -740,6 +778,9 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 	enum map_type type;
 	u64 start = machine__get_running_kernel_start(machine, NULL);
 
+	/* In case of renewal the kernel map, destroy previous one */
+	machine__destroy_kernel_maps(machine);
+
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
 		struct map *map;
@@ -788,6 +829,7 @@ void machine__destroy_kernel_maps(struct machine *machine)
 				kmap->ref_reloc_sym = NULL;
 		}
 
+		map__put(machine->vmlinux_maps[type]);
 		machine->vmlinux_maps[type] = NULL;
 	}
 }
@@ -1084,11 +1126,14 @@ int machine__create_kernel_maps(struct machine *machine)
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
 	u64 addr = machine__get_running_kernel_start(machine, &name);
-	if (!addr)
+	int ret;
+
+	if (!addr || kernel == NULL)
 		return -1;
 
-	if (kernel == NULL ||
-	    __machine__create_kernel_maps(machine, kernel) < 0)
+	ret = __machine__create_kernel_maps(machine, kernel);
+	dso__put(kernel);
+	if (ret < 0)
 		return -1;
 
 	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
@@ -1609,6 +1654,8 @@ static int add_callchain_ip(struct thread *thread,
 		}
 	}
 
+	if (symbol_conf.hide_unresolved && al.sym == NULL)
+		return 0;
 	return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
 }
 
@@ -1863,6 +1910,9 @@ check_calls:
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
+
+	if (symbol_conf.hide_unresolved && entry->sym == NULL)
+		return 0;
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym);
 }
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index afc6b56cf749..171b6d10a04b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -26,8 +26,8 @@ const char *map_type__name[MAP__NR_TYPES] = {
 static inline int is_anon_memory(const char *filename)
 {
 	return !strcmp(filename, "//anon") ||
-	       !strcmp(filename, "/dev/zero (deleted)") ||
-	       !strcmp(filename, "/anon_hugepage (deleted)");
+	       !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+	       !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
 }
 
 static inline int is_no_dso_memory(const char *filename)
@@ -691,6 +691,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			__map_groups__insert(pos->groups, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
+			map__put(before);
 		}
 
 		if (map->end < pos->end) {
@@ -705,6 +706,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
+			map__put(after);
 		}
 put_map:
 		map__put(pos);
@@ -742,6 +744,7 @@ int map_groups__clone(struct map_groups *mg,
 		if (new == NULL)
 			goto out_unlock;
 		map_groups__insert(mg, new);
+		map__put(new);
 	}
 
 	err = 0;
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
deleted file mode 100644
index 53ef006a951c..000000000000
--- a/tools/perf/util/pager.c
+++ /dev/null
@@ -1,95 +0,0 @@
-#include "cache.h"
-#include "run-command.h"
-#include "sigchain.h"
-
-/*
- * This is split up from the rest of git so that we can do
- * something different on Windows.
- */
-
-static int spawned_pager;
-
-static void pager_preexec(void)
-{
-	/*
-	 * Work around bug in "less" by not starting it until we
-	 * have real input
-	 */
-	fd_set in;
-
-	FD_ZERO(&in);
-	FD_SET(0, &in);
-	select(1, &in, NULL, &in, NULL);
-
-	setenv("LESS", "FRSX", 0);
-}
-
-static const char *pager_argv[] = { "sh", "-c", NULL, NULL };
-static struct child_process pager_process;
-
-static void wait_for_pager(void)
-{
-	fflush(stdout);
-	fflush(stderr);
-	/* signal EOF to pager */
-	close(1);
-	close(2);
-	finish_command(&pager_process);
-}
-
-static void wait_for_pager_signal(int signo)
-{
-	wait_for_pager();
-	sigchain_pop(signo);
-	raise(signo);
-}
-
-void setup_pager(void)
-{
-	const char *pager = getenv("PERF_PAGER");
-
-	if (!isatty(1))
-		return;
-	if (!pager)
-		pager = getenv("PAGER");
-	if (!(pager || access("/usr/bin/pager", X_OK)))
-		pager = "/usr/bin/pager";
-	if (!(pager || access("/usr/bin/less", X_OK)))
-		pager = "/usr/bin/less";
-	if (!pager)
-		pager = "cat";
-	if (!*pager || !strcmp(pager, "cat"))
-		return;
-
-	spawned_pager = 1; /* means we are emitting to terminal */
-
-	/* spawn the pager */
-	pager_argv[2] = pager;
-	pager_process.argv = pager_argv;
-	pager_process.in = -1;
-	pager_process.preexec_cb = pager_preexec;
-
-	if (start_command(&pager_process))
-		return;
-
-	/* original process continues, but writes to the pipe */
-	dup2(pager_process.in, 1);
-	if (isatty(2))
-		dup2(pager_process.in, 2);
-	close(pager_process.in);
-
-	/* this makes sure that the parent terminates after the pager */
-	sigchain_push_common(wait_for_pager_signal);
-	atexit(wait_for_pager);
-}
-
-int pager_in_use(void)
-{
-	const char *env;
-
-	if (spawned_pager)
-		return 1;
-
-	env = getenv("PERF_PAGER_IN_USE");
-	return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0;
-}
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 355eecf6bf59..afc088dd7d20 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
 
 #define BRANCH_OPT(n, m) \
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6fc8cd753e1a..4f7b0efdde2f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -4,9 +4,9 @@
 #include "../perf.h"
 #include "evlist.h"
 #include "evsel.h"
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
-#include "exec_cmd.h"
+#include <subcmd/exec-cmd.h>
 #include "string.h"
 #include "symbol.h"
 #include "cache.h"
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
deleted file mode 100644
index 9fca09296eb3..000000000000
--- a/tools/perf/util/parse-options.c
+++ /dev/null
@@ -1,867 +0,0 @@
-#include "util.h"
-#include "parse-options.h"
-#include "cache.h"
-#include "header.h"
-#include <linux/string.h>
-
-#define OPT_SHORT 1
-#define OPT_UNSET 2
-
-static struct strbuf error_buf = STRBUF_INIT;
-
-static int opterror(const struct option *opt, const char *reason, int flags)
-{
-	if (flags & OPT_SHORT)
-		return error("switch `%c' %s", opt->short_name, reason);
-	if (flags & OPT_UNSET)
-		return error("option `no-%s' %s", opt->long_name, reason);
-	return error("option `%s' %s", opt->long_name, reason);
-}
-
-static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
-		   int flags, const char **arg)
-{
-	if (p->opt) {
-		*arg = p->opt;
-		p->opt = NULL;
-	} else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 ||
-		    **(p->argv + 1) == '-')) {
-		*arg = (const char *)opt->defval;
-	} else if (p->argc > 1) {
-		p->argc--;
-		*arg = *++p->argv;
-	} else
-		return opterror(opt, "requires a value", flags);
-	return 0;
-}
-
-static int get_value(struct parse_opt_ctx_t *p,
-		     const struct option *opt, int flags)
-{
-	const char *s, *arg = NULL;
-	const int unset = flags & OPT_UNSET;
-	int err;
-
-	if (unset && p->opt)
-		return opterror(opt, "takes no value", flags);
-	if (unset && (opt->flags & PARSE_OPT_NONEG))
-		return opterror(opt, "isn't available", flags);
-	if (opt->flags & PARSE_OPT_DISABLED)
-		return opterror(opt, "is not usable", flags);
-
-	if (opt->flags & PARSE_OPT_EXCLUSIVE) {
-		if (p->excl_opt && p->excl_opt != opt) {
-			char msg[128];
-
-			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
-			    p->excl_opt->long_name == NULL) {
-				scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
-					  p->excl_opt->short_name);
-			} else {
-				scnprintf(msg, sizeof(msg), "cannot be used with %s",
-					  p->excl_opt->long_name);
-			}
-			opterror(opt, msg, flags);
-			return -3;
-		}
-		p->excl_opt = opt;
-	}
-	if (!(flags & OPT_SHORT) && p->opt) {
-		switch (opt->type) {
-		case OPTION_CALLBACK:
-			if (!(opt->flags & PARSE_OPT_NOARG))
-				break;
-			/* FALLTHROUGH */
-		case OPTION_BOOLEAN:
-		case OPTION_INCR:
-		case OPTION_BIT:
-		case OPTION_SET_UINT:
-		case OPTION_SET_PTR:
-			return opterror(opt, "takes no value", flags);
-		case OPTION_END:
-		case OPTION_ARGUMENT:
-		case OPTION_GROUP:
-		case OPTION_STRING:
-		case OPTION_INTEGER:
-		case OPTION_UINTEGER:
-		case OPTION_LONG:
-		case OPTION_U64:
-		default:
-			break;
-		}
-	}
-
-	switch (opt->type) {
-	case OPTION_BIT:
-		if (unset)
-			*(int *)opt->value &= ~opt->defval;
-		else
-			*(int *)opt->value |= opt->defval;
-		return 0;
-
-	case OPTION_BOOLEAN:
-		*(bool *)opt->value = unset ? false : true;
-		if (opt->set)
-			*(bool *)opt->set = true;
-		return 0;
-
-	case OPTION_INCR:
-		*(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
-		return 0;
-
-	case OPTION_SET_UINT:
-		*(unsigned int *)opt->value = unset ? 0 : opt->defval;
-		return 0;
-
-	case OPTION_SET_PTR:
-		*(void **)opt->value = unset ? NULL : (void *)opt->defval;
-		return 0;
-
-	case OPTION_STRING:
-		err = 0;
-		if (unset)
-			*(const char **)opt->value = NULL;
-		else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
-			*(const char **)opt->value = (const char *)opt->defval;
-		else
-			err = get_arg(p, opt, flags, (const char **)opt->value);
-
-		/* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
-		if (opt->flags & PARSE_OPT_NOEMPTY) {
-			const char *val = *(const char **)opt->value;
-
-			if (!val)
-				return err;
-
-			/* Similar to unset if we are given an empty string. */
-			if (val[0] == '\0') {
-				*(const char **)opt->value = NULL;
-				return 0;
-			}
-		}
-
-		return err;
-
-	case OPTION_CALLBACK:
-		if (unset)
-			return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
-		if (opt->flags & PARSE_OPT_NOARG)
-			return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
-		if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
-			return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
-		if (get_arg(p, opt, flags, &arg))
-			return -1;
-		return (*opt->callback)(opt, arg, 0) ? (-1) : 0;
-
-	case OPTION_INTEGER:
-		if (unset) {
-			*(int *)opt->value = 0;
-			return 0;
-		}
-		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
-			*(int *)opt->value = opt->defval;
-			return 0;
-		}
-		if (get_arg(p, opt, flags, &arg))
-			return -1;
-		*(int *)opt->value = strtol(arg, (char **)&s, 10);
-		if (*s)
-			return opterror(opt, "expects a numerical value", flags);
-		return 0;
-
-	case OPTION_UINTEGER:
-		if (unset) {
-			*(unsigned int *)opt->value = 0;
-			return 0;
-		}
-		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
-			*(unsigned int *)opt->value = opt->defval;
-			return 0;
-		}
-		if (get_arg(p, opt, flags, &arg))
-			return -1;
-		*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
-		if (*s)
-			return opterror(opt, "expects a numerical value", flags);
-		return 0;
-
-	case OPTION_LONG:
-		if (unset) {
-			*(long *)opt->value = 0;
-			return 0;
-		}
-		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
-			*(long *)opt->value = opt->defval;
-			return 0;
-		}
-		if (get_arg(p, opt, flags, &arg))
-			return -1;
-		*(long *)opt->value = strtol(arg, (char **)&s, 10);
-		if (*s)
-			return opterror(opt, "expects a numerical value", flags);
-		return 0;
-
-	case OPTION_U64:
-		if (unset) {
-			*(u64 *)opt->value = 0;
-			return 0;
-		}
-		if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
-			*(u64 *)opt->value = opt->defval;
-			return 0;
-		}
-		if (get_arg(p, opt, flags, &arg))
-			return -1;
-		*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
-		if (*s)
-			return opterror(opt, "expects a numerical value", flags);
-		return 0;
-
-	case OPTION_END:
-	case OPTION_ARGUMENT:
-	case OPTION_GROUP:
-	default:
-		die("should not happen, someone must be hit on the forehead");
-	}
-}
-
-static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options)
-{
-	for (; options->type != OPTION_END; options++) {
-		if (options->short_name == *p->opt) {
-			p->opt = p->opt[1] ? p->opt + 1 : NULL;
-			return get_value(p, options, OPT_SHORT);
-		}
-	}
-	return -2;
-}
-
-static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
-                          const struct option *options)
-{
-	const char *arg_end = strchr(arg, '=');
-	const struct option *abbrev_option = NULL, *ambiguous_option = NULL;
-	int abbrev_flags = 0, ambiguous_flags = 0;
-
-	if (!arg_end)
-		arg_end = arg + strlen(arg);
-
-	for (; options->type != OPTION_END; options++) {
-		const char *rest;
-		int flags = 0;
-
-		if (!options->long_name)
-			continue;
-
-		rest = skip_prefix(arg, options->long_name);
-		if (options->type == OPTION_ARGUMENT) {
-			if (!rest)
-				continue;
-			if (*rest == '=')
-				return opterror(options, "takes no value", flags);
-			if (*rest)
-				continue;
-			p->out[p->cpidx++] = arg - 2;
-			return 0;
-		}
-		if (!rest) {
-			if (!prefixcmp(options->long_name, "no-")) {
-				/*
-				 * The long name itself starts with "no-", so
-				 * accept the option without "no-" so that users
-				 * do not have to enter "no-no-" to get the
-				 * negation.
-				 */
-				rest = skip_prefix(arg, options->long_name + 3);
-				if (rest) {
-					flags |= OPT_UNSET;
-					goto match;
-				}
-				/* Abbreviated case */
-				if (!prefixcmp(options->long_name + 3, arg)) {
-					flags |= OPT_UNSET;
-					goto is_abbreviated;
-				}
-			}
-			/* abbreviated? */
-			if (!strncmp(options->long_name, arg, arg_end - arg)) {
-is_abbreviated:
-				if (abbrev_option) {
-					/*
-					 * If this is abbreviated, it is
-					 * ambiguous. So when there is no
-					 * exact match later, we need to
-					 * error out.
-					 */
-					ambiguous_option = abbrev_option;
-					ambiguous_flags = abbrev_flags;
-				}
-				if (!(flags & OPT_UNSET) && *arg_end)
-					p->opt = arg_end + 1;
-				abbrev_option = options;
-				abbrev_flags = flags;
-				continue;
-			}
-			/* negated and abbreviated very much? */
-			if (!prefixcmp("no-", arg)) {
-				flags |= OPT_UNSET;
-				goto is_abbreviated;
-			}
-			/* negated? */
-			if (strncmp(arg, "no-", 3))
-				continue;
-			flags |= OPT_UNSET;
-			rest = skip_prefix(arg + 3, options->long_name);
-			/* abbreviated and negated? */
-			if (!rest && !prefixcmp(options->long_name, arg + 3))
-				goto is_abbreviated;
-			if (!rest)
-				continue;
-		}
-match:
-		if (*rest) {
-			if (*rest != '=')
-				continue;
-			p->opt = rest + 1;
-		}
-		return get_value(p, options, flags);
-	}
-
-	if (ambiguous_option)
-		return error("Ambiguous option: %s "
-			"(could be --%s%s or --%s%s)",
-			arg,
-			(ambiguous_flags & OPT_UNSET) ?  "no-" : "",
-			ambiguous_option->long_name,
-			(abbrev_flags & OPT_UNSET) ?  "no-" : "",
-			abbrev_option->long_name);
-	if (abbrev_option)
-		return get_value(p, abbrev_option, abbrev_flags);
-	return -2;
-}
-
-static void check_typos(const char *arg, const struct option *options)
-{
-	if (strlen(arg) < 3)
-		return;
-
-	if (!prefixcmp(arg, "no-")) {
-		error ("did you mean `--%s` (with two dashes ?)", arg);
-		exit(129);
-	}
-
-	for (; options->type != OPTION_END; options++) {
-		if (!options->long_name)
-			continue;
-		if (!prefixcmp(options->long_name, arg)) {
-			error ("did you mean `--%s` (with two dashes ?)", arg);
-			exit(129);
-		}
-	}
-}
-
-void parse_options_start(struct parse_opt_ctx_t *ctx,
-			 int argc, const char **argv, int flags)
-{
-	memset(ctx, 0, sizeof(*ctx));
-	ctx->argc = argc - 1;
-	ctx->argv = argv + 1;
-	ctx->out  = argv;
-	ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0);
-	ctx->flags = flags;
-	if ((flags & PARSE_OPT_KEEP_UNKNOWN) &&
-	    (flags & PARSE_OPT_STOP_AT_NON_OPTION))
-		die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together");
-}
-
-static int usage_with_options_internal(const char * const *,
-				       const struct option *, int,
-				       struct parse_opt_ctx_t *);
-
-int parse_options_step(struct parse_opt_ctx_t *ctx,
-		       const struct option *options,
-		       const char * const usagestr[])
-{
-	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
-	int excl_short_opt = 1;
-	const char *arg;
-
-	/* we must reset ->opt, unknown short option leave it dangling */
-	ctx->opt = NULL;
-
-	for (; ctx->argc; ctx->argc--, ctx->argv++) {
-		arg = ctx->argv[0];
-		if (*arg != '-' || !arg[1]) {
-			if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
-				break;
-			ctx->out[ctx->cpidx++] = ctx->argv[0];
-			continue;
-		}
-
-		if (arg[1] != '-') {
-			ctx->opt = ++arg;
-			if (internal_help && *ctx->opt == 'h') {
-				return usage_with_options_internal(usagestr, options, 0, ctx);
-			}
-			switch (parse_short_opt(ctx, options)) {
-			case -1:
-				return parse_options_usage(usagestr, options, arg, 1);
-			case -2:
-				goto unknown;
-			case -3:
-				goto exclusive;
-			default:
-				break;
-			}
-			if (ctx->opt)
-				check_typos(arg, options);
-			while (ctx->opt) {
-				if (internal_help && *ctx->opt == 'h')
-					return usage_with_options_internal(usagestr, options, 0, ctx);
-				arg = ctx->opt;
-				switch (parse_short_opt(ctx, options)) {
-				case -1:
-					return parse_options_usage(usagestr, options, arg, 1);
-				case -2:
-					/* fake a short option thing to hide the fact that we may have
-					 * started to parse aggregated stuff
-					 *
-					 * This is leaky, too bad.
-					 */
-					ctx->argv[0] = strdup(ctx->opt - 1);
-					*(char *)ctx->argv[0] = '-';
-					goto unknown;
-				case -3:
-					goto exclusive;
-				default:
-					break;
-				}
-			}
-			continue;
-		}
-
-		if (!arg[2]) { /* "--" */
-			if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) {
-				ctx->argc--;
-				ctx->argv++;
-			}
-			break;
-		}
-
-		arg += 2;
-		if (internal_help && !strcmp(arg, "help-all"))
-			return usage_with_options_internal(usagestr, options, 1, ctx);
-		if (internal_help && !strcmp(arg, "help"))
-			return usage_with_options_internal(usagestr, options, 0, ctx);
-		if (!strcmp(arg, "list-opts"))
-			return PARSE_OPT_LIST_OPTS;
-		if (!strcmp(arg, "list-cmds"))
-			return PARSE_OPT_LIST_SUBCMDS;
-		switch (parse_long_opt(ctx, arg, options)) {
-		case -1:
-			return parse_options_usage(usagestr, options, arg, 0);
-		case -2:
-			goto unknown;
-		case -3:
-			excl_short_opt = 0;
-			goto exclusive;
-		default:
-			break;
-		}
-		continue;
-unknown:
-		if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN))
-			return PARSE_OPT_UNKNOWN;
-		ctx->out[ctx->cpidx++] = ctx->argv[0];
-		ctx->opt = NULL;
-	}
-	return PARSE_OPT_DONE;
-
-exclusive:
-	parse_options_usage(usagestr, options, arg, excl_short_opt);
-	if ((excl_short_opt && ctx->excl_opt->short_name) ||
-	    ctx->excl_opt->long_name == NULL) {
-		char opt = ctx->excl_opt->short_name;
-		parse_options_usage(NULL, options, &opt, 1);
-	} else {
-		parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0);
-	}
-	return PARSE_OPT_HELP;
-}
-
-int parse_options_end(struct parse_opt_ctx_t *ctx)
-{
-	memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
-	ctx->out[ctx->cpidx + ctx->argc] = NULL;
-	return ctx->cpidx + ctx->argc;
-}
-
-int parse_options_subcommand(int argc, const char **argv, const struct option *options,
-			const char *const subcommands[], const char *usagestr[], int flags)
-{
-	struct parse_opt_ctx_t ctx;
-
-	perf_env__set_cmdline(&perf_env, argc, argv);
-
-	/* build usage string if it's not provided */
-	if (subcommands && !usagestr[0]) {
-		struct strbuf buf = STRBUF_INIT;
-
-		strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
-		for (int i = 0; subcommands[i]; i++) {
-			if (i)
-				strbuf_addstr(&buf, "|");
-			strbuf_addstr(&buf, subcommands[i]);
-		}
-		strbuf_addstr(&buf, "}");
-
-		usagestr[0] = strdup(buf.buf);
-		strbuf_release(&buf);
-	}
-
-	parse_options_start(&ctx, argc, argv, flags);
-	switch (parse_options_step(&ctx, options, usagestr)) {
-	case PARSE_OPT_HELP:
-		exit(129);
-	case PARSE_OPT_DONE:
-		break;
-	case PARSE_OPT_LIST_OPTS:
-		while (options->type != OPTION_END) {
-			if (options->long_name)
-				printf("--%s ", options->long_name);
-			options++;
-		}
-		putchar('\n');
-		exit(130);
-	case PARSE_OPT_LIST_SUBCMDS:
-		if (subcommands) {
-			for (int i = 0; subcommands[i]; i++)
-				printf("%s ", subcommands[i]);
-		}
-		putchar('\n');
-		exit(130);
-	default: /* PARSE_OPT_UNKNOWN */
-		if (ctx.argv[0][1] == '-') {
-			strbuf_addf(&error_buf, "unknown option `%s'",
-				    ctx.argv[0] + 2);
-		} else {
-			strbuf_addf(&error_buf, "unknown switch `%c'",
-				    *ctx.opt);
-		}
-		usage_with_options(usagestr, options);
-	}
-
-	return parse_options_end(&ctx);
-}
-
-int parse_options(int argc, const char **argv, const struct option *options,
-		  const char * const usagestr[], int flags)
-{
-	return parse_options_subcommand(argc, argv, options, NULL,
-					(const char **) usagestr, flags);
-}
-
-#define USAGE_OPTS_WIDTH 24
-#define USAGE_GAP         2
-
-static void print_option_help(const struct option *opts, int full)
-{
-	size_t pos;
-	int pad;
-
-	if (opts->type == OPTION_GROUP) {
-		fputc('\n', stderr);
-		if (*opts->help)
-			fprintf(stderr, "%s\n", opts->help);
-		return;
-	}
-	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
-		return;
-	if (opts->flags & PARSE_OPT_DISABLED)
-		return;
-
-	pos = fprintf(stderr, "    ");
-	if (opts->short_name)
-		pos += fprintf(stderr, "-%c", opts->short_name);
-	else
-		pos += fprintf(stderr, "    ");
-
-	if (opts->long_name && opts->short_name)
-		pos += fprintf(stderr, ", ");
-	if (opts->long_name)
-		pos += fprintf(stderr, "--%s", opts->long_name);
-
-	switch (opts->type) {
-	case OPTION_ARGUMENT:
-		break;
-	case OPTION_LONG:
-	case OPTION_U64:
-	case OPTION_INTEGER:
-	case OPTION_UINTEGER:
-		if (opts->flags & PARSE_OPT_OPTARG)
-			if (opts->long_name)
-				pos += fprintf(stderr, "[=<n>]");
-			else
-				pos += fprintf(stderr, "[<n>]");
-		else
-			pos += fprintf(stderr, " <n>");
-		break;
-	case OPTION_CALLBACK:
-		if (opts->flags & PARSE_OPT_NOARG)
-			break;
-		/* FALLTHROUGH */
-	case OPTION_STRING:
-		if (opts->argh) {
-			if (opts->flags & PARSE_OPT_OPTARG)
-				if (opts->long_name)
-					pos += fprintf(stderr, "[=<%s>]", opts->argh);
-				else
-					pos += fprintf(stderr, "[<%s>]", opts->argh);
-			else
-				pos += fprintf(stderr, " <%s>", opts->argh);
-		} else {
-			if (opts->flags & PARSE_OPT_OPTARG)
-				if (opts->long_name)
-					pos += fprintf(stderr, "[=...]");
-				else
-					pos += fprintf(stderr, "[...]");
-			else
-				pos += fprintf(stderr, " ...");
-		}
-		break;
-	default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
-	case OPTION_END:
-	case OPTION_GROUP:
-	case OPTION_BIT:
-	case OPTION_BOOLEAN:
-	case OPTION_INCR:
-	case OPTION_SET_UINT:
-	case OPTION_SET_PTR:
-		break;
-	}
-
-	if (pos <= USAGE_OPTS_WIDTH)
-		pad = USAGE_OPTS_WIDTH - pos;
-	else {
-		fputc('\n', stderr);
-		pad = USAGE_OPTS_WIDTH;
-	}
-	fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
-}
-
-static int option__cmp(const void *va, const void *vb)
-{
-	const struct option *a = va, *b = vb;
-	int sa = tolower(a->short_name), sb = tolower(b->short_name), ret;
-
-	if (sa == 0)
-		sa = 'z' + 1;
-	if (sb == 0)
-		sb = 'z' + 1;
-
-	ret = sa - sb;
-
-	if (ret == 0) {
-		const char *la = a->long_name ?: "",
-			   *lb = b->long_name ?: "";
-		ret = strcmp(la, lb);
-	}
-
-	return ret;
-}
-
-static struct option *options__order(const struct option *opts)
-{
-	int nr_opts = 0;
-	const struct option *o = opts;
-	struct option *ordered;
-
-	for (o = opts; o->type != OPTION_END; o++)
-		++nr_opts;
-
-	ordered = memdup(opts, sizeof(*o) * (nr_opts + 1));
-	if (ordered == NULL)
-		goto out;
-
-	qsort(ordered, nr_opts, sizeof(*o), option__cmp);
-out:
-	return ordered;
-}
-
-static bool option__in_argv(const struct option *opt, const struct parse_opt_ctx_t *ctx)
-{
-	int i;
-
-	for (i = 1; i < ctx->argc; ++i) {
-		const char *arg = ctx->argv[i];
-
-		if (arg[0] != '-') {
-			if (arg[1] == '\0') {
-				if (arg[0] == opt->short_name)
-					return true;
-				continue;
-			}
-
-			if (opt->long_name && strcmp(opt->long_name, arg) == 0)
-				return true;
-
-			if (opt->help && strcasestr(opt->help, arg) != NULL)
-				return true;
-
-			continue;
-		}
-
-		if (arg[1] == opt->short_name ||
-		    (arg[1] == '-' && opt->long_name && strcmp(opt->long_name, arg + 2) == 0))
-			return true;
-	}
-
-	return false;
-}
-
-int usage_with_options_internal(const char * const *usagestr,
-				const struct option *opts, int full,
-				struct parse_opt_ctx_t *ctx)
-{
-	struct option *ordered;
-
-	if (!usagestr)
-		return PARSE_OPT_HELP;
-
-	setup_pager();
-
-	if (strbuf_avail(&error_buf)) {
-		fprintf(stderr, "  Error: %s\n", error_buf.buf);
-		strbuf_release(&error_buf);
-	}
-
-	fprintf(stderr, "\n Usage: %s\n", *usagestr++);
-	while (*usagestr && **usagestr)
-		fprintf(stderr, "    or: %s\n", *usagestr++);
-	while (*usagestr) {
-		fprintf(stderr, "%s%s\n",
-				**usagestr ? "    " : "",
-				*usagestr);
-		usagestr++;
-	}
-
-	if (opts->type != OPTION_GROUP)
-		fputc('\n', stderr);
-
-	ordered = options__order(opts);
-	if (ordered)
-		opts = ordered;
-
-	for (  ; opts->type != OPTION_END; opts++) {
-		if (ctx && ctx->argc > 1 && !option__in_argv(opts, ctx))
-			continue;
-		print_option_help(opts, full);
-	}
-
-	fputc('\n', stderr);
-
-	free(ordered);
-
-	return PARSE_OPT_HELP;
-}
-
-void usage_with_options(const char * const *usagestr,
-			const struct option *opts)
-{
-	exit_browser(false);
-	usage_with_options_internal(usagestr, opts, 0, NULL);
-	exit(129);
-}
-
-void usage_with_options_msg(const char * const *usagestr,
-			    const struct option *opts, const char *fmt, ...)
-{
-	va_list ap;
-
-	exit_browser(false);
-
-	va_start(ap, fmt);
-	strbuf_addv(&error_buf, fmt, ap);
-	va_end(ap);
-
-	usage_with_options_internal(usagestr, opts, 0, NULL);
-	exit(129);
-}
-
-int parse_options_usage(const char * const *usagestr,
-			const struct option *opts,
-			const char *optstr, bool short_opt)
-{
-	if (!usagestr)
-		goto opt;
-
-	fprintf(stderr, "\n Usage: %s\n", *usagestr++);
-	while (*usagestr && **usagestr)
-		fprintf(stderr, "    or: %s\n", *usagestr++);
-	while (*usagestr) {
-		fprintf(stderr, "%s%s\n",
-				**usagestr ? "    " : "",
-				*usagestr);
-		usagestr++;
-	}
-	fputc('\n', stderr);
-
-opt:
-	for (  ; opts->type != OPTION_END; opts++) {
-		if (short_opt) {
-			if (opts->short_name == *optstr) {
-				print_option_help(opts, 0);
-				break;
-			}
-			continue;
-		}
-
-		if (opts->long_name == NULL)
-			continue;
-
-		if (!prefixcmp(opts->long_name, optstr))
-			print_option_help(opts, 0);
-		if (!prefixcmp("no-", optstr) &&
-		    !prefixcmp(opts->long_name, optstr + 3))
-			print_option_help(opts, 0);
-	}
-
-	return PARSE_OPT_HELP;
-}
-
-
-int parse_opt_verbosity_cb(const struct option *opt,
-			   const char *arg __maybe_unused,
-			   int unset)
-{
-	int *target = opt->value;
-
-	if (unset)
-		/* --no-quiet, --no-verbose */
-		*target = 0;
-	else if (opt->short_name == 'v') {
-		if (*target >= 0)
-			(*target)++;
-		else
-			*target = 1;
-	} else {
-		if (*target <= 0)
-			(*target)--;
-		else
-			*target = -1;
-	}
-	return 0;
-}
-
-void set_option_flag(struct option *opts, int shortopt, const char *longopt,
-		     int flag)
-{
-	for (; opts->type != OPTION_END; opts++) {
-		if ((shortopt && opts->short_name == shortopt) ||
-		    (opts->long_name && longopt &&
-		     !strcmp(opts->long_name, longopt))) {
-			opts->flags |= flag;
-			break;
-		}
-	}
-}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
deleted file mode 100644
index a8e407bc251e..000000000000
--- a/tools/perf/util/parse-options.h
+++ /dev/null
@@ -1,229 +0,0 @@
-#ifndef __PERF_PARSE_OPTIONS_H
-#define __PERF_PARSE_OPTIONS_H
-
-#include <linux/kernel.h>
-#include <stdbool.h>
-
-enum parse_opt_type {
-	/* special types */
-	OPTION_END,
-	OPTION_ARGUMENT,
-	OPTION_GROUP,
-	/* options with no arguments */
-	OPTION_BIT,
-	OPTION_BOOLEAN,
-	OPTION_INCR,
-	OPTION_SET_UINT,
-	OPTION_SET_PTR,
-	/* options with arguments (usually) */
-	OPTION_STRING,
-	OPTION_INTEGER,
-	OPTION_LONG,
-	OPTION_CALLBACK,
-	OPTION_U64,
-	OPTION_UINTEGER,
-};
-
-enum parse_opt_flags {
-	PARSE_OPT_KEEP_DASHDASH = 1,
-	PARSE_OPT_STOP_AT_NON_OPTION = 2,
-	PARSE_OPT_KEEP_ARGV0 = 4,
-	PARSE_OPT_KEEP_UNKNOWN = 8,
-	PARSE_OPT_NO_INTERNAL_HELP = 16,
-};
-
-enum parse_opt_option_flags {
-	PARSE_OPT_OPTARG  = 1,
-	PARSE_OPT_NOARG   = 2,
-	PARSE_OPT_NONEG   = 4,
-	PARSE_OPT_HIDDEN  = 8,
-	PARSE_OPT_LASTARG_DEFAULT = 16,
-	PARSE_OPT_DISABLED = 32,
-	PARSE_OPT_EXCLUSIVE = 64,
-	PARSE_OPT_NOEMPTY  = 128,
-};
-
-struct option;
-typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
-
-/*
- * `type`::
- *   holds the type of the option, you must have an OPTION_END last in your
- *   array.
- *
- * `short_name`::
- *   the character to use as a short option name, '\0' if none.
- *
- * `long_name`::
- *   the long option name, without the leading dashes, NULL if none.
- *
- * `value`::
- *   stores pointers to the values to be filled.
- *
- * `argh`::
- *   token to explain the kind of argument this option wants. Keep it
- *   homogenous across the repository.
- *
- * `help`::
- *   the short help associated to what the option does.
- *   Must never be NULL (except for OPTION_END).
- *   OPTION_GROUP uses this pointer to store the group header.
- *
- * `flags`::
- *   mask of parse_opt_option_flags.
- *   PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs)
- *   PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs
- *   PARSE_OPT_NONEG: says that this option cannot be negated
- *   PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in
- *                    the long one.
- *
- * `callback`::
- *   pointer to the callback to use for OPTION_CALLBACK.
- *
- * `defval`::
- *   default value to fill (*->value) with for PARSE_OPT_OPTARG.
- *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
- *   the value when met.
- *   CALLBACKS can use it like they want.
- *
- * `set`::
- *   whether an option was set by the user
- */
-struct option {
-	enum parse_opt_type type;
-	int short_name;
-	const char *long_name;
-	void *value;
-	const char *argh;
-	const char *help;
-
-	int flags;
-	parse_opt_cb *callback;
-	intptr_t defval;
-	bool *set;
-	void *data;
-};
-
-#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
-
-#define OPT_END()                   { .type = OPTION_END }
-#define OPT_ARGUMENT(l, h)          { .type = OPTION_ARGUMENT, .long_name = (l), .help = (h) }
-#define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
-#define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
-#define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
-#define OPT_BOOLEAN_FLAG(s, l, v, h, f)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h), .flags = (f) }
-#define OPT_BOOLEAN_SET(s, l, v, os, h) \
-	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
-	.value = check_vtype(v, bool *), .help = (h), \
-	.set = check_vtype(os, bool *)}
-#define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
-#define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
-#define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
-#define OPT_INTEGER(s, l, v, h)     { .type = OPTION_INTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
-#define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
-#define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
-#define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
-#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
-	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
-	  .value = check_vtype(v, const char **), (a), .help = (h), \
-	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
-#define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
-#define OPT_DATE(s, l, v, h) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
-#define OPT_CALLBACK(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
-#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
-#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
-#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
-	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
-	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
-#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
-	  .value = (v), (a), .help = (h), .callback = (f), \
-	  .flags = PARSE_OPT_OPTARG, .data = (d) }
-
-/* parse_options() will filter out the processed options and leave the
- * non-option argments in argv[].
- * Returns the number of arguments left in argv[].
- */
-extern int parse_options(int argc, const char **argv,
-                         const struct option *options,
-                         const char * const usagestr[], int flags);
-
-extern int parse_options_subcommand(int argc, const char **argv,
-				const struct option *options,
-				const char *const subcommands[],
-				const char *usagestr[], int flags);
-
-extern NORETURN void usage_with_options(const char * const *usagestr,
-                                        const struct option *options);
-extern NORETURN __attribute__((format(printf,3,4)))
-void usage_with_options_msg(const char * const *usagestr,
-			    const struct option *options,
-			    const char *fmt, ...);
-
-/*----- incremantal advanced APIs -----*/
-
-enum {
-	PARSE_OPT_HELP = -1,
-	PARSE_OPT_DONE,
-	PARSE_OPT_LIST_OPTS,
-	PARSE_OPT_LIST_SUBCMDS,
-	PARSE_OPT_UNKNOWN,
-};
-
-/*
- * It's okay for the caller to consume argv/argc in the usual way.
- * Other fields of that structure are private to parse-options and should not
- * be modified in any way.
- */
-struct parse_opt_ctx_t {
-	const char **argv;
-	const char **out;
-	int argc, cpidx;
-	const char *opt;
-	const struct option *excl_opt;
-	int flags;
-};
-
-extern int parse_options_usage(const char * const *usagestr,
-			       const struct option *opts,
-			       const char *optstr,
-			       bool short_opt);
-
-extern void parse_options_start(struct parse_opt_ctx_t *ctx,
-				int argc, const char **argv, int flags);
-
-extern int parse_options_step(struct parse_opt_ctx_t *ctx,
-			      const struct option *options,
-			      const char * const usagestr[]);
-
-extern int parse_options_end(struct parse_opt_ctx_t *ctx);
-
-
-/*----- some often used options -----*/
-extern int parse_opt_abbrev_cb(const struct option *, const char *, int);
-extern int parse_opt_approxidate_cb(const struct option *, const char *, int);
-extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
-
-#define OPT__VERBOSE(var)  OPT_BOOLEAN('v', "verbose", (var), "be verbose")
-#define OPT__QUIET(var)    OPT_BOOLEAN('q', "quiet",   (var), "be quiet")
-#define OPT__VERBOSITY(var) \
-	{ OPTION_CALLBACK, 'v', "verbose", (var), NULL, "be more verbose", \
-	  PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }, \
-	{ OPTION_CALLBACK, 'q', "quiet", (var), NULL, "be more quiet", \
-	  PARSE_OPT_NOARG, &parse_opt_verbosity_cb, 0 }
-#define OPT__DRY_RUN(var)  OPT_BOOLEAN('n', "dry-run", (var), "dry run")
-#define OPT__ABBREV(var)  \
-	{ OPTION_CALLBACK, 0, "abbrev", (var), "n", \
-	  "use <n> digits to display SHA-1s", \
-	  PARSE_OPT_OPTARG, &parse_opt_abbrev_cb, 0 }
-
-extern const char *parse_options_fix_filename(const char *prefix, const char *file);
-
-void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
-#endif /* __PERF_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index 4f2c1c255d81..646ecf736aad 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,7 +1,7 @@
 #include "perf.h"
 #include "util/util.h"
 #include "util/debug.h"
-#include "util/parse-options.h"
+#include <subcmd/parse-options.h>
 #include "util/parse-regs-options.h"
 
 int
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 5d13cb45b317..3654d964e49d 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,24 +22,6 @@ static const char *get_perf_dir(void)
 	return ".";
 }
 
-/*
- * If libc has strlcpy() then that version will override this
- * implementation:
- */
-size_t __weak strlcpy(char *dest, const char *src, size_t size)
-{
-	size_t ret = strlen(src);
-
-	if (size) {
-		size_t len = (ret >= size) ? size - 1 : ret;
-
-		memcpy(dest, src, len);
-		dest[len] = '\0';
-	}
-
-	return ret;
-}
-
 static char *get_pathname(void)
 {
 	static char pathname_array[4][PATH_MAX];
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e4b173dec4b9..b597bcc8fc78 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -220,6 +220,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
 	alias->per_pkg = false;
+	alias->snapshot = false;
 
 	ret = parse_events_terms(&alias->terms, val);
 	if (ret) {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 03875f9154e7..93996ec4bbe3 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2326,8 +2326,11 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		goto out;
 
 	if (!allow_suffix) {
-		pr_warning("Error: event \"%s\" already exists. "
-			   "(Use -f to force duplicates.)\n", buf);
+		pr_warning("Error: event \"%s\" already exists.\n"
+			   " Hint: Remove existing event by 'perf probe -d'\n"
+			   "       or force duplicates by 'perf probe -f'\n"
+			   "       or set 'force=yes' in BPF source.\n",
+			   buf);
 		ret = -EEXIST;
 		goto out;
 	}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 05012bb178d7..2be10fb27172 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -654,6 +654,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 {
 	Dwarf_Attribute fb_attr;
+	Dwarf_Frame *frame = NULL;
 	size_t nops;
 	int ret;
 
@@ -686,11 +687,11 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 #if _ELFUTILS_PREREQ(0, 142)
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
 		   pf->cfi != NULL) {
-		Dwarf_Frame *frame;
 		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
 			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
+			free(frame);
 			return -ENOENT;
 		}
 #endif
@@ -699,7 +700,8 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* Call finder's callback handler */
 	ret = pf->callback(sc_die, pf);
 
-	/* *pf->fb_ops will be cached in libdw. Don't free it. */
+	/* Since *pf->fb_ops can be a part of frame. we should free it here. */
+	free(frame);
 	pf->fb_ops = NULL;
 
 	return ret;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 51be28b1bca2..8162ba0e2e57 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,8 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+../lib/bitmap.c
+../lib/find_bit.c
 ../lib/hweight.c
 util/thread_map.c
 util/util.c
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
deleted file mode 100644
index 34622b53e733..000000000000
--- a/tools/perf/util/run-command.c
+++ /dev/null
@@ -1,219 +0,0 @@
-#include "cache.h"
-#include "run-command.h"
-#include "exec_cmd.h"
-#include "debug.h"
-
-static inline void close_pair(int fd[2])
-{
-	close(fd[0]);
-	close(fd[1]);
-}
-
-static inline void dup_devnull(int to)
-{
-	int fd = open("/dev/null", O_RDWR);
-	dup2(fd, to);
-	close(fd);
-}
-
-int start_command(struct child_process *cmd)
-{
-	int need_in, need_out, need_err;
-	int fdin[2], fdout[2], fderr[2];
-	char sbuf[STRERR_BUFSIZE];
-
-	/*
-	 * In case of errors we must keep the promise to close FDs
-	 * that have been passed in via ->in and ->out.
-	 */
-
-	need_in = !cmd->no_stdin && cmd->in < 0;
-	if (need_in) {
-		if (pipe(fdin) < 0) {
-			if (cmd->out > 0)
-				close(cmd->out);
-			return -ERR_RUN_COMMAND_PIPE;
-		}
-		cmd->in = fdin[1];
-	}
-
-	need_out = !cmd->no_stdout
-		&& !cmd->stdout_to_stderr
-		&& cmd->out < 0;
-	if (need_out) {
-		if (pipe(fdout) < 0) {
-			if (need_in)
-				close_pair(fdin);
-			else if (cmd->in)
-				close(cmd->in);
-			return -ERR_RUN_COMMAND_PIPE;
-		}
-		cmd->out = fdout[0];
-	}
-
-	need_err = !cmd->no_stderr && cmd->err < 0;
-	if (need_err) {
-		if (pipe(fderr) < 0) {
-			if (need_in)
-				close_pair(fdin);
-			else if (cmd->in)
-				close(cmd->in);
-			if (need_out)
-				close_pair(fdout);
-			else if (cmd->out)
-				close(cmd->out);
-			return -ERR_RUN_COMMAND_PIPE;
-		}
-		cmd->err = fderr[0];
-	}
-
-	fflush(NULL);
-	cmd->pid = fork();
-	if (!cmd->pid) {
-		if (cmd->no_stdin)
-			dup_devnull(0);
-		else if (need_in) {
-			dup2(fdin[0], 0);
-			close_pair(fdin);
-		} else if (cmd->in) {
-			dup2(cmd->in, 0);
-			close(cmd->in);
-		}
-
-		if (cmd->no_stderr)
-			dup_devnull(2);
-		else if (need_err) {
-			dup2(fderr[1], 2);
-			close_pair(fderr);
-		}
-
-		if (cmd->no_stdout)
-			dup_devnull(1);
-		else if (cmd->stdout_to_stderr)
-			dup2(2, 1);
-		else if (need_out) {
-			dup2(fdout[1], 1);
-			close_pair(fdout);
-		} else if (cmd->out > 1) {
-			dup2(cmd->out, 1);
-			close(cmd->out);
-		}
-
-		if (cmd->dir && chdir(cmd->dir))
-			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-			    cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
-		if (cmd->env) {
-			for (; *cmd->env; cmd->env++) {
-				if (strchr(*cmd->env, '='))
-					putenv((char*)*cmd->env);
-				else
-					unsetenv(*cmd->env);
-			}
-		}
-		if (cmd->preexec_cb)
-			cmd->preexec_cb();
-		if (cmd->perf_cmd) {
-			execv_perf_cmd(cmd->argv);
-		} else {
-			execvp(cmd->argv[0], (char *const*) cmd->argv);
-		}
-		exit(127);
-	}
-
-	if (cmd->pid < 0) {
-		int err = errno;
-		if (need_in)
-			close_pair(fdin);
-		else if (cmd->in)
-			close(cmd->in);
-		if (need_out)
-			close_pair(fdout);
-		else if (cmd->out)
-			close(cmd->out);
-		if (need_err)
-			close_pair(fderr);
-		return err == ENOENT ?
-			-ERR_RUN_COMMAND_EXEC :
-			-ERR_RUN_COMMAND_FORK;
-	}
-
-	if (need_in)
-		close(fdin[0]);
-	else if (cmd->in)
-		close(cmd->in);
-
-	if (need_out)
-		close(fdout[1]);
-	else if (cmd->out)
-		close(cmd->out);
-
-	if (need_err)
-		close(fderr[1]);
-
-	return 0;
-}
-
-static int wait_or_whine(pid_t pid)
-{
-	char sbuf[STRERR_BUFSIZE];
-
-	for (;;) {
-		int status, code;
-		pid_t waiting = waitpid(pid, &status, 0);
-
-		if (waiting < 0) {
-			if (errno == EINTR)
-				continue;
-			error("waitpid failed (%s)",
-			      strerror_r(errno, sbuf, sizeof(sbuf)));
-			return -ERR_RUN_COMMAND_WAITPID;
-		}
-		if (waiting != pid)
-			return -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
-		if (WIFSIGNALED(status))
-			return -ERR_RUN_COMMAND_WAITPID_SIGNAL;
-
-		if (!WIFEXITED(status))
-			return -ERR_RUN_COMMAND_WAITPID_NOEXIT;
-		code = WEXITSTATUS(status);
-		switch (code) {
-		case 127:
-			return -ERR_RUN_COMMAND_EXEC;
-		case 0:
-			return 0;
-		default:
-			return -code;
-		}
-	}
-}
-
-int finish_command(struct child_process *cmd)
-{
-	return wait_or_whine(cmd->pid);
-}
-
-int run_command(struct child_process *cmd)
-{
-	int code = start_command(cmd);
-	if (code)
-		return code;
-	return finish_command(cmd);
-}
-
-static void prepare_run_command_v_opt(struct child_process *cmd,
-				      const char **argv,
-				      int opt)
-{
-	memset(cmd, 0, sizeof(*cmd));
-	cmd->argv = argv;
-	cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0;
-	cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0;
-	cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0;
-}
-
-int run_command_v_opt(const char **argv, int opt)
-{
-	struct child_process cmd;
-	prepare_run_command_v_opt(&cmd, argv, opt);
-	return run_command(&cmd);
-}
diff --git a/tools/perf/util/run-command.h b/tools/perf/util/run-command.h
deleted file mode 100644
index 1ef264d5069c..000000000000
--- a/tools/perf/util/run-command.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef __PERF_RUN_COMMAND_H
-#define __PERF_RUN_COMMAND_H
-
-enum {
-	ERR_RUN_COMMAND_FORK = 10000,
-	ERR_RUN_COMMAND_EXEC,
-	ERR_RUN_COMMAND_PIPE,
-	ERR_RUN_COMMAND_WAITPID,
-	ERR_RUN_COMMAND_WAITPID_WRONG_PID,
-	ERR_RUN_COMMAND_WAITPID_SIGNAL,
-	ERR_RUN_COMMAND_WAITPID_NOEXIT,
-};
-#define IS_RUN_COMMAND_ERR(x) (-(x) >= ERR_RUN_COMMAND_FORK)
-
-struct child_process {
-	const char **argv;
-	pid_t pid;
-	/*
-	 * Using .in, .out, .err:
-	 * - Specify 0 for no redirections (child inherits stdin, stdout,
-	 *   stderr from parent).
-	 * - Specify -1 to have a pipe allocated as follows:
-	 *     .in: returns the writable pipe end; parent writes to it,
-	 *          the readable pipe end becomes child's stdin
-	 *     .out, .err: returns the readable pipe end; parent reads from
-	 *          it, the writable pipe end becomes child's stdout/stderr
-	 *   The caller of start_command() must close the returned FDs
-	 *   after it has completed reading from/writing to it!
-	 * - Specify > 0 to set a channel to a particular FD as follows:
-	 *     .in: a readable FD, becomes child's stdin
-	 *     .out: a writable FD, becomes child's stdout/stderr
-	 *     .err > 0 not supported
-	 *   The specified FD is closed by start_command(), even in case
-	 *   of errors!
-	 */
-	int in;
-	int out;
-	int err;
-	const char *dir;
-	const char *const *env;
-	unsigned no_stdin:1;
-	unsigned no_stdout:1;
-	unsigned no_stderr:1;
-	unsigned perf_cmd:1; /* if this is to be perf sub-command */
-	unsigned stdout_to_stderr:1;
-	void (*preexec_cb)(void);
-};
-
-int start_command(struct child_process *);
-int finish_command(struct child_process *);
-int run_command(struct child_process *);
-
-#define RUN_COMMAND_NO_STDIN 1
-#define RUN_PERF_CMD	     2	/*If this is to be perf sub-command */
-#define RUN_COMMAND_STDOUT_TO_STDERR 4
-int run_command_v_opt(const char **argv, int opt);
-
-#endif /* __PERF_RUN_COMMAND_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8e825fca42a..d72fafc1c800 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -41,6 +41,9 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "stat.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -859,6 +862,104 @@ static void python_process_event(union perf_event *event,
 	}
 }
 
+static void get_handler_name(char *str, size_t size,
+			     struct perf_evsel *evsel)
+{
+	char *p = str;
+
+	scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+
+	while ((p = strchr(p, ':'))) {
+		*p = '_';
+		p++;
+	}
+}
+
+static void
+process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
+	     struct perf_counts_values *count)
+{
+	PyObject *handler, *t;
+	static char handler_name[256];
+	int n = 0;
+
+	t = PyTuple_New(MAX_FIELDS);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+
+	get_handler_name(handler_name, sizeof(handler_name),
+			 counter);
+
+	handler = get_handler(handler_name);
+	if (!handler) {
+		pr_debug("can't find python handler %s\n", handler_name);
+		return;
+	}
+
+	PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+	PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+
+	tuple_set_u64(t, n++, tstamp);
+	tuple_set_u64(t, n++, count->val);
+	tuple_set_u64(t, n++, count->ena);
+	tuple_set_u64(t, n++, count->run);
+
+	if (_PyTuple_Resize(&t, n) == -1)
+		Py_FatalError("error resizing Python tuple");
+
+	call_object(handler, t, handler_name);
+
+	Py_DECREF(t);
+}
+
+static void python_process_stat(struct perf_stat_config *config,
+				struct perf_evsel *counter, u64 tstamp)
+{
+	struct thread_map *threads = counter->threads;
+	struct cpu_map *cpus = counter->cpus;
+	int cpu, thread;
+
+	if (config->aggr_mode == AGGR_GLOBAL) {
+		process_stat(counter, -1, -1, tstamp,
+			     &counter->counts->aggr);
+		return;
+	}
+
+	for (thread = 0; thread < threads->nr; thread++) {
+		for (cpu = 0; cpu < cpus->nr; cpu++) {
+			process_stat(counter, cpus->map[cpu],
+				     thread_map__pid(threads, thread), tstamp,
+				     perf_counts(counter->counts, cpu, thread));
+		}
+	}
+}
+
+static void python_process_stat_interval(u64 tstamp)
+{
+	PyObject *handler, *t;
+	static const char handler_name[] = "stat__interval";
+	int n = 0;
+
+	t = PyTuple_New(MAX_FIELDS);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+
+	handler = get_handler(handler_name);
+	if (!handler) {
+		pr_debug("can't find python handler %s\n", handler_name);
+		return;
+	}
+
+	tuple_set_u64(t, n++, tstamp);
+
+	if (_PyTuple_Resize(&t, n) == -1)
+		Py_FatalError("error resizing Python tuple");
+
+	call_object(handler, t, handler_name);
+
+	Py_DECREF(t);
+}
+
 static int run_start_sub(void)
 {
 	main_module = PyImport_AddModule("__main__");
@@ -1201,10 +1302,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 }
 
 struct scripting_ops python_scripting_ops = {
-	.name = "Python",
-	.start_script = python_start_script,
-	.flush_script = python_flush_script,
-	.stop_script = python_stop_script,
-	.process_event = python_process_event,
-	.generate_script = python_generate_script,
+	.name			= "Python",
+	.start_script		= python_start_script,
+	.flush_script		= python_flush_script,
+	.stop_script		= python_stop_script,
+	.process_event		= python_process_event,
+	.process_stat		= python_process_stat,
+	.process_stat_interval	= python_process_stat_interval,
+	.generate_script	= python_generate_script,
 };
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c35ffdd360fe..d5636ba94b20 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
 #include "asm/bug.h"
 #include "auxtrace.h"
 #include "thread-stack.h"
+#include "stat.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
@@ -36,6 +37,9 @@ static int perf_session__open(struct perf_session *session)
 	if (perf_data_file__is_pipe(file))
 		return 0;
 
+	if (perf_header__has_feat(&session->header, HEADER_STAT))
+		return 0;
+
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
 		pr_err("non matching sample_type\n");
 		return -1;
@@ -205,6 +209,18 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused,
+						 union perf_event *event __maybe_unused,
+						 struct perf_evlist **pevlist
+						 __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_event_update(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample __maybe_unused,
@@ -296,6 +312,67 @@ int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+
+static
+int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_thread_map(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static
+int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event __maybe_unused,
+			       struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_cpu_map(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static
+int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event __maybe_unused,
+				   struct perf_session *session __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat_config(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_stat_stub(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event __maybe_unused,
+			     struct perf_session *perf_session
+			     __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int process_stat_round_stub(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event __maybe_unused,
+				   struct perf_session *perf_session
+				   __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_stat_round(event, stdout);
+
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -328,6 +405,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->unthrottle = process_event_stub;
 	if (tool->attr == NULL)
 		tool->attr = process_event_synth_attr_stub;
+	if (tool->event_update == NULL)
+		tool->event_update = process_event_synth_event_update_stub;
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
@@ -346,6 +425,16 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
 		tool->auxtrace_error = process_event_auxtrace_error_stub;
+	if (tool->thread_map == NULL)
+		tool->thread_map = process_event_thread_map_stub;
+	if (tool->cpu_map == NULL)
+		tool->cpu_map = process_event_cpu_map_stub;
+	if (tool->stat_config == NULL)
+		tool->stat_config = process_event_stat_config_stub;
+	if (tool->stat == NULL)
+		tool->stat = process_stat_stub;
+	if (tool->stat_round == NULL)
+		tool->stat_round = process_stat_round_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -569,6 +658,13 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 	mem_bswap_64(event->attr.id, size);
 }
 
+static void perf_event__event_update_swap(union perf_event *event,
+					  bool sample_id_all __maybe_unused)
+{
+	event->event_update.type = bswap_64(event->event_update.type);
+	event->event_update.id   = bswap_64(event->event_update.id);
+}
+
 static void perf_event__event_type_swap(union perf_event *event,
 					bool sample_id_all __maybe_unused)
 {
@@ -616,6 +712,81 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
 }
 
+static void perf_event__thread_map_swap(union perf_event *event,
+					bool sample_id_all __maybe_unused)
+{
+	unsigned i;
+
+	event->thread_map.nr = bswap_64(event->thread_map.nr);
+
+	for (i = 0; i < event->thread_map.nr; i++)
+		event->thread_map.entries[i].pid = bswap_64(event->thread_map.entries[i].pid);
+}
+
+static void perf_event__cpu_map_swap(union perf_event *event,
+				     bool sample_id_all __maybe_unused)
+{
+	struct cpu_map_data *data = &event->cpu_map.data;
+	struct cpu_map_entries *cpus;
+	struct cpu_map_mask *mask;
+	unsigned i;
+
+	data->type = bswap_64(data->type);
+
+	switch (data->type) {
+	case PERF_CPU_MAP__CPUS:
+		cpus = (struct cpu_map_entries *)data->data;
+
+		cpus->nr = bswap_16(cpus->nr);
+
+		for (i = 0; i < cpus->nr; i++)
+			cpus->cpu[i] = bswap_16(cpus->cpu[i]);
+		break;
+	case PERF_CPU_MAP__MASK:
+		mask = (struct cpu_map_mask *) data->data;
+
+		mask->nr = bswap_16(mask->nr);
+		mask->long_size = bswap_16(mask->long_size);
+
+		switch (mask->long_size) {
+		case 4: mem_bswap_32(&mask->mask, mask->nr); break;
+		case 8: mem_bswap_64(&mask->mask, mask->nr); break;
+		default:
+			pr_err("cpu_map swap: unsupported long size\n");
+		}
+	default:
+		break;
+	}
+}
+
+static void perf_event__stat_config_swap(union perf_event *event,
+					 bool sample_id_all __maybe_unused)
+{
+	u64 size;
+
+	size  = event->stat_config.nr * sizeof(event->stat_config.data[0]);
+	size += 1; /* nr item itself */
+	mem_bswap_64(&event->stat_config.nr, size);
+}
+
+static void perf_event__stat_swap(union perf_event *event,
+				  bool sample_id_all __maybe_unused)
+{
+	event->stat.id     = bswap_64(event->stat.id);
+	event->stat.thread = bswap_32(event->stat.thread);
+	event->stat.cpu    = bswap_32(event->stat.cpu);
+	event->stat.val    = bswap_64(event->stat.val);
+	event->stat.ena    = bswap_64(event->stat.ena);
+	event->stat.run    = bswap_64(event->stat.run);
+}
+
+static void perf_event__stat_round_swap(union perf_event *event,
+					bool sample_id_all __maybe_unused)
+{
+	event->stat_round.type = bswap_64(event->stat_round.type);
+	event->stat_round.time = bswap_64(event->stat_round.time);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -643,6 +814,12 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
 	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
 	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
+	[PERF_RECORD_THREAD_MAP]	  = perf_event__thread_map_swap,
+	[PERF_RECORD_CPU_MAP]		  = perf_event__cpu_map_swap,
+	[PERF_RECORD_STAT_CONFIG]	  = perf_event__stat_config_swap,
+	[PERF_RECORD_STAT]		  = perf_event__stat_swap,
+	[PERF_RECORD_STAT_ROUND]	  = perf_event__stat_round_swap,
+	[PERF_RECORD_EVENT_UPDATE]	  = perf_event__event_update_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -1154,6 +1331,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 			perf_session__set_comm_exec(session);
 		}
 		return err;
+	case PERF_RECORD_EVENT_UPDATE:
+		return tool->event_update(tool, event, &session->evlist);
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
 		 * Depreceated, but we need to handle it for sake
@@ -1179,6 +1358,16 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	case PERF_RECORD_AUXTRACE_ERROR:
 		perf_session__auxtrace_error_inc(session, event);
 		return tool->auxtrace_error(tool, event, session);
+	case PERF_RECORD_THREAD_MAP:
+		return tool->thread_map(tool, event, session);
+	case PERF_RECORD_CPU_MAP:
+		return tool->cpu_map(tool, event, session);
+	case PERF_RECORD_STAT_CONFIG:
+		return tool->stat_config(tool, event, session);
+	case PERF_RECORD_STAT:
+		return tool->stat(tool, event, session);
+	case PERF_RECORD_STAT_ROUND:
+		return tool->stat_round(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1311,17 +1500,20 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
-struct thread *perf_session__register_idle_thread(struct perf_session *session)
+int perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;
+	int err = 0;
 
 	thread = machine__findnew_thread(&session->machines.host, 0, 0);
 	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
-		thread = NULL;
+		err = -1;
 	}
 
-	return thread;
+	/* machine__findnew_thread() got the thread, so put it */
+	thread__put(thread);
+	return err;
 }
 
 static void perf_session__warn_about_errors(const struct perf_session *session)
@@ -1676,7 +1868,7 @@ int perf_session__process_events(struct perf_session *session)
 	u64 size = perf_data_file__size(session->file);
 	int err;
 
-	if (perf_session__register_idle_thread(session) == NULL)
+	if (perf_session__register_idle_thread(session) < 0)
 		return -ENOMEM;
 
 	if (!perf_data_file__is_pipe(session->file))
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3e900c0efc73..5f792e35d4c1 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -89,7 +89,7 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_
 }
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
-struct thread *perf_session__register_idle_thread(struct perf_session *session);
+int perf_session__register_idle_thread(struct perf_session *session);
 
 size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
 
diff --git a/tools/perf/util/sigchain.c b/tools/perf/util/sigchain.c
deleted file mode 100644
index ba785e9b1841..000000000000
--- a/tools/perf/util/sigchain.c
+++ /dev/null
@@ -1,52 +0,0 @@
-#include "sigchain.h"
-#include "cache.h"
-
-#define SIGCHAIN_MAX_SIGNALS 32
-
-struct sigchain_signal {
-	sigchain_fun *old;
-	int n;
-	int alloc;
-};
-static struct sigchain_signal signals[SIGCHAIN_MAX_SIGNALS];
-
-static void check_signum(int sig)
-{
-	if (sig < 1 || sig >= SIGCHAIN_MAX_SIGNALS)
-		die("BUG: signal out of range: %d", sig);
-}
-
-static int sigchain_push(int sig, sigchain_fun f)
-{
-	struct sigchain_signal *s = signals + sig;
-	check_signum(sig);
-
-	ALLOC_GROW(s->old, s->n + 1, s->alloc);
-	s->old[s->n] = signal(sig, f);
-	if (s->old[s->n] == SIG_ERR)
-		return -1;
-	s->n++;
-	return 0;
-}
-
-int sigchain_pop(int sig)
-{
-	struct sigchain_signal *s = signals + sig;
-	check_signum(sig);
-	if (s->n < 1)
-		return 0;
-
-	if (signal(sig, s->old[s->n - 1]) == SIG_ERR)
-		return -1;
-	s->n--;
-	return 0;
-}
-
-void sigchain_push_common(sigchain_fun f)
-{
-	sigchain_push(SIGINT, f);
-	sigchain_push(SIGHUP, f);
-	sigchain_push(SIGTERM, f);
-	sigchain_push(SIGQUIT, f);
-	sigchain_push(SIGPIPE, f);
-}
diff --git a/tools/perf/util/sigchain.h b/tools/perf/util/sigchain.h
deleted file mode 100644
index 959d64eb5557..000000000000
--- a/tools/perf/util/sigchain.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __PERF_SIGCHAIN_H
-#define __PERF_SIGCHAIN_H
-
-typedef void (*sigchain_fun)(int);
-
-int sigchain_pop(int sig);
-
-void sigchain_push_common(sigchain_fun f);
-
-#endif /* __PERF_SIGCHAIN_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2d8ccd4d9e1b..ec722346e6ff 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -4,6 +4,8 @@
 #include "comm.h"
 #include "symbol.h"
 #include "evsel.h"
+#include "evlist.h"
+#include <traceevent/event-parse.h>
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -13,6 +15,7 @@ const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cy
 const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
+const char	default_tracepoint_sort_order[] = "trace";
 const char	*sort_order;
 const char	*field_order;
 regex_t		ignore_callees_regex;
@@ -443,6 +446,70 @@ struct sort_entry sort_socket = {
 	.se_width_idx	= HISTC_SOCKET,
 };
 
+/* --sort trace */
+
+static char *get_trace_output(struct hist_entry *he)
+{
+	struct trace_seq seq;
+	struct perf_evsel *evsel;
+	struct pevent_record rec = {
+		.data = he->raw_data,
+		.size = he->raw_size,
+	};
+
+	evsel = hists_to_evsel(he->hists);
+
+	trace_seq_init(&seq);
+	if (symbol_conf.raw_trace) {
+		pevent_print_fields(&seq, he->raw_data, he->raw_size,
+				    evsel->tp_format);
+	} else {
+		pevent_event_info(&seq, evsel->tp_format, &rec);
+	}
+	return seq.buffer;
+}
+
+static int64_t
+sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct perf_evsel *evsel;
+
+	evsel = hists_to_evsel(left->hists);
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return 0;
+
+	if (left->trace_output == NULL)
+		left->trace_output = get_trace_output(left);
+	if (right->trace_output == NULL)
+		right->trace_output = get_trace_output(right);
+
+	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
+	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
+
+	return strcmp(right->trace_output, left->trace_output);
+}
+
+static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	struct perf_evsel *evsel;
+
+	evsel = hists_to_evsel(he->hists);
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+
+	if (he->trace_output == NULL)
+		he->trace_output = get_trace_output(he);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+}
+
+struct sort_entry sort_trace = {
+	.se_header      = "Trace output",
+	.se_cmp	        = sort__trace_cmp,
+	.se_snprintf    = hist_entry__trace_snprintf,
+	.se_width_idx	= HISTC_TRACE,
+};
+
 /* sort keys for branch stacks */
 
 static int64_t
@@ -1312,6 +1379,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
 	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
+	DIM(SORT_TRACE, "trace", sort_trace),
 };
 
 #undef DIM
@@ -1529,6 +1597,455 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
 	return 0;
 }
 
+struct hpp_dynamic_entry {
+	struct perf_hpp_fmt hpp;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+	unsigned dynamic_len;
+	bool raw_trace;
+};
+
+static int hde_width(struct hpp_dynamic_entry *hde)
+{
+	if (!hde->hpp.len) {
+		int len = hde->dynamic_len;
+		int namelen = strlen(hde->field->name);
+		int fieldlen = hde->field->size;
+
+		if (namelen > len)
+			len = namelen;
+
+		if (!(hde->field->flags & FIELD_IS_STRING)) {
+			/* length for print hex numbers */
+			fieldlen = hde->field->size * 2 + 2;
+		}
+		if (fieldlen > len)
+			len = fieldlen;
+
+		hde->hpp.len = len;
+	}
+	return hde->hpp.len;
+}
+
+static void update_dynamic_len(struct hpp_dynamic_entry *hde,
+			       struct hist_entry *he)
+{
+	char *str, *pos;
+	struct format_field *field = hde->field;
+	size_t namelen;
+	bool last = false;
+
+	if (hde->raw_trace)
+		return;
+
+	/* parse pretty print result and update max length */
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
+	namelen = strlen(field->name);
+	str = he->trace_output;
+
+	while (str) {
+		pos = strchr(str, ' ');
+		if (pos == NULL) {
+			last = true;
+			pos = str + strlen(str);
+		}
+
+		if (!strncmp(str, field->name, namelen)) {
+			size_t len;
+
+			str += namelen + 1;
+			len = pos - str;
+
+			if (len > hde->dynamic_len)
+				hde->dynamic_len = len;
+			break;
+		}
+
+		if (last)
+			str = NULL;
+		else
+			str = pos + 1;
+	}
+}
+
+static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			      struct perf_evsel *evsel __maybe_unused)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, hde->field->name);
+}
+
+static int __sort__hde_width(struct perf_hpp_fmt *fmt,
+			     struct perf_hpp *hpp __maybe_unused,
+			     struct perf_evsel *evsel __maybe_unused)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	return len;
+}
+
+bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	return hists_to_evsel(hists) == hde->evsel;
+}
+
+static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			     struct hist_entry *he)
+{
+	struct hpp_dynamic_entry *hde;
+	size_t len = fmt->user_len;
+	char *str, *pos;
+	struct format_field *field;
+	size_t namelen;
+	bool last = false;
+	int ret;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	if (!len)
+		len = hde_width(hde);
+
+	if (hde->raw_trace)
+		goto raw_field;
+
+	field = hde->field;
+	namelen = strlen(field->name);
+	str = he->trace_output;
+
+	while (str) {
+		pos = strchr(str, ' ');
+		if (pos == NULL) {
+			last = true;
+			pos = str + strlen(str);
+		}
+
+		if (!strncmp(str, field->name, namelen)) {
+			str += namelen + 1;
+			str = strndup(str, pos - str);
+
+			if (str == NULL)
+				return scnprintf(hpp->buf, hpp->size,
+						 "%*.*s", len, len, "ERROR");
+			break;
+		}
+
+		if (last)
+			str = NULL;
+		else
+			str = pos + 1;
+	}
+
+	if (str == NULL) {
+		struct trace_seq seq;
+raw_field:
+		trace_seq_init(&seq);
+		pevent_print_field(&seq, he->raw_data, hde->field);
+		str = seq.buffer;
+	}
+
+	ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, str);
+	free(str);
+	return ret;
+}
+
+static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
+			       struct hist_entry *a, struct hist_entry *b)
+{
+	struct hpp_dynamic_entry *hde;
+	struct format_field *field;
+	unsigned offset, size;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+
+	field = hde->field;
+	if (field->flags & FIELD_IS_DYNAMIC) {
+		unsigned long long dyn;
+
+		pevent_read_number_field(field, a->raw_data, &dyn);
+		offset = dyn & 0xffff;
+		size = (dyn >> 16) & 0xffff;
+
+		/* record max width for output */
+		if (size > hde->dynamic_len)
+			hde->dynamic_len = size;
+	} else {
+		offset = field->offset;
+		size = field->size;
+
+		update_dynamic_len(hde, a);
+		update_dynamic_len(hde, b);
+	}
+
+	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
+}
+
+bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
+{
+	return fmt->cmp == __sort__hde_cmp;
+}
+
+static struct hpp_dynamic_entry *
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = malloc(sizeof(*hde));
+	if (hde == NULL) {
+		pr_debug("Memory allocation failed\n");
+		return NULL;
+	}
+
+	hde->evsel = evsel;
+	hde->field = field;
+	hde->dynamic_len = 0;
+
+	hde->hpp.name = field->name;
+	hde->hpp.header = __sort__hde_header;
+	hde->hpp.width  = __sort__hde_width;
+	hde->hpp.entry  = __sort__hde_entry;
+	hde->hpp.color  = NULL;
+
+	hde->hpp.cmp = __sort__hde_cmp;
+	hde->hpp.collapse = __sort__hde_cmp;
+	hde->hpp.sort = __sort__hde_cmp;
+
+	INIT_LIST_HEAD(&hde->hpp.list);
+	INIT_LIST_HEAD(&hde->hpp.sort_list);
+	hde->hpp.elide = false;
+	hde->hpp.len = 0;
+	hde->hpp.user_len = 0;
+
+	return hde;
+}
+
+static int parse_field_name(char *str, char **event, char **field, char **opt)
+{
+	char *event_name, *field_name, *opt_name;
+
+	event_name = str;
+	field_name = strchr(str, '.');
+
+	if (field_name) {
+		*field_name++ = '\0';
+	} else {
+		event_name = NULL;
+		field_name = str;
+	}
+
+	opt_name = strchr(field_name, '/');
+	if (opt_name)
+		*opt_name++ = '\0';
+
+	*event = event_name;
+	*field = field_name;
+	*opt   = opt_name;
+
+	return 0;
+}
+
+/* find match evsel using a given event name.  The event name can be:
+ *   1. '%' + event index (e.g. '%1' for first event)
+ *   2. full event name (e.g. sched:sched_switch)
+ *   3. partial event name (should not contain ':')
+ */
+static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name)
+{
+	struct perf_evsel *evsel = NULL;
+	struct perf_evsel *pos;
+	bool full_name;
+
+	/* case 1 */
+	if (event_name[0] == '%') {
+		int nr = strtol(event_name+1, NULL, 0);
+
+		if (nr > evlist->nr_entries)
+			return NULL;
+
+		evsel = perf_evlist__first(evlist);
+		while (--nr > 0)
+			evsel = perf_evsel__next(evsel);
+
+		return evsel;
+	}
+
+	full_name = !!strchr(event_name, ':');
+	evlist__for_each(evlist, pos) {
+		/* case 2 */
+		if (full_name && !strcmp(pos->name, event_name))
+			return pos;
+		/* case 3 */
+		if (!full_name && strstr(pos->name, event_name)) {
+			if (evsel) {
+				pr_debug("'%s' event is ambiguous: it can be %s or %s\n",
+					 event_name, evsel->name, pos->name);
+				return NULL;
+			}
+			evsel = pos;
+		}
+	}
+
+	return evsel;
+}
+
+static int __dynamic_dimension__add(struct perf_evsel *evsel,
+				    struct format_field *field,
+				    bool raw_trace)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = __alloc_dynamic_entry(evsel, field);
+	if (hde == NULL)
+		return -ENOMEM;
+
+	hde->raw_trace = raw_trace;
+
+	perf_hpp__register_sort_field(&hde->hpp);
+	return 0;
+}
+
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+{
+	int ret;
+	struct format_field *field;
+
+	field = evsel->tp_format->format.fields;
+	while (field) {
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		if (ret < 0)
+			return ret;
+
+		field = field->next;
+	}
+	return 0;
+}
+
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+{
+	int ret;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
+		ret = add_evsel_fields(evsel, raw_trace);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int add_all_matching_fields(struct perf_evlist *evlist,
+				   char *field_name, bool raw_trace)
+{
+	int ret = -ESRCH;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
+		field = pevent_find_any_field(evsel->tp_format, field_name);
+		if (field == NULL)
+			continue;
+
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		if (ret < 0)
+			break;
+	}
+	return ret;
+}
+
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+{
+	char *str, *event_name, *field_name, *opt_name;
+	struct perf_evsel *evsel;
+	struct format_field *field;
+	bool raw_trace = symbol_conf.raw_trace;
+	int ret = 0;
+
+	if (evlist == NULL)
+		return -ENOENT;
+
+	str = strdup(tok);
+	if (str == NULL)
+		return -ENOMEM;
+
+	if (parse_field_name(str, &event_name, &field_name, &opt_name) < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (opt_name) {
+		if (strcmp(opt_name, "raw")) {
+			pr_debug("unsupported field option %s\n", opt_name);
+			ret = -EINVAL;
+			goto out;
+		}
+		raw_trace = true;
+	}
+
+	if (!strcmp(field_name, "trace_fields")) {
+		ret = add_all_dynamic_fields(evlist, raw_trace);
+		goto out;
+	}
+
+	if (event_name == NULL) {
+		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		goto out;
+	}
+
+	evsel = find_evsel(evlist, event_name);
+	if (evsel == NULL) {
+		pr_debug("Cannot find event: %s\n", event_name);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		pr_debug("%s is not a tracepoint event\n", event_name);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!strcmp(field_name, "*")) {
+		ret = add_evsel_fields(evsel, raw_trace);
+	} else {
+		field = pevent_find_any_field(evsel->tp_format, field_name);
+		if (field == NULL) {
+			pr_debug("Cannot find event field for %s.%s\n",
+				 event_name, field_name);
+			return -ENOENT;
+		}
+
+		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+	}
+
+out:
+	free(str);
+	return ret;
+}
+
 static int __sort_dimension__add(struct sort_dimension *sd)
 {
 	if (sd->taken)
@@ -1583,7 +2100,8 @@ int hpp_dimension__add_output(unsigned col)
 	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
 }
 
-int sort_dimension__add(const char *tok)
+static int sort_dimension__add(const char *tok,
+			       struct perf_evlist *evlist __maybe_unused)
 {
 	unsigned int i;
 
@@ -1664,10 +2182,13 @@ int sort_dimension__add(const char *tok)
 		return 0;
 	}
 
+	if (!add_dynamic_entry(evlist, tok))
+		return 0;
+
 	return -ESRCH;
 }
 
-static const char *get_default_sort_order(void)
+static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
 	const char *default_sort_orders[] = {
 		default_sort_order,
@@ -1675,14 +2196,33 @@ static const char *get_default_sort_order(void)
 		default_mem_sort_order,
 		default_top_sort_order,
 		default_diff_sort_order,
+		default_tracepoint_sort_order,
 	};
+	bool use_trace = true;
+	struct perf_evsel *evsel;
 
 	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
+	if (evlist == NULL)
+		goto out_no_evlist;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+			use_trace = false;
+			break;
+		}
+	}
+
+	if (use_trace) {
+		sort__mode = SORT_MODE__TRACEPOINT;
+		if (symbol_conf.raw_trace)
+			return "trace_fields";
+	}
+out_no_evlist:
 	return default_sort_orders[sort__mode];
 }
 
-static int setup_sort_order(void)
+static int setup_sort_order(struct perf_evlist *evlist)
 {
 	char *new_sort_order;
 
@@ -1703,7 +2243,7 @@ static int setup_sort_order(void)
 	 * because it's checked over the rest of the code.
 	 */
 	if (asprintf(&new_sort_order, "%s,%s",
-		     get_default_sort_order(), sort_order + 1) < 0) {
+		     get_default_sort_order(evlist), sort_order + 1) < 0) {
 		error("Not enough memory to set up --sort");
 		return -ENOMEM;
 	}
@@ -1712,13 +2252,41 @@ static int setup_sort_order(void)
 	return 0;
 }
 
-static int __setup_sorting(void)
+/*
+ * Adds 'pre,' prefix into 'str' is 'pre' is
+ * not already part of 'str'.
+ */
+static char *prefix_if_not_in(const char *pre, char *str)
+{
+	char *n;
+
+	if (!str || strstr(str, pre))
+		return str;
+
+	if (asprintf(&n, "%s,%s", pre, str) < 0)
+		return NULL;
+
+	free(str);
+	return n;
+}
+
+static char *setup_overhead(char *keys)
+{
+	keys = prefix_if_not_in("overhead", keys);
+
+	if (symbol_conf.cumulate_callchain)
+		keys = prefix_if_not_in("overhead_children", keys);
+
+	return keys;
+}
+
+static int __setup_sorting(struct perf_evlist *evlist)
 {
 	char *tmp, *tok, *str;
 	const char *sort_keys;
 	int ret = 0;
 
-	ret = setup_sort_order();
+	ret = setup_sort_order(evlist);
 	if (ret)
 		return ret;
 
@@ -1732,7 +2300,7 @@ static int __setup_sorting(void)
 			return 0;
 		}
 
-		sort_keys = get_default_sort_order();
+		sort_keys = get_default_sort_order(evlist);
 	}
 
 	str = strdup(sort_keys);
@@ -1741,9 +2309,20 @@ static int __setup_sorting(void)
 		return -ENOMEM;
 	}
 
+	/*
+	 * Prepend overhead fields for backward compatibility.
+	 */
+	if (!is_strict_order(field_order)) {
+		str = setup_overhead(str);
+		if (str == NULL) {
+			error("Not enough memory to setup overhead keys");
+			return -ENOMEM;
+		}
+	}
+
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok);
+		ret = sort_dimension__add(tok, evlist);
 		if (ret == -EINVAL) {
 			error("Invalid --sort key: `%s'", tok);
 			break;
@@ -1954,16 +2533,16 @@ out:
 	return ret;
 }
 
-int setup_sorting(void)
+int setup_sorting(struct perf_evlist *evlist)
 {
 	int err;
 
-	err = __setup_sorting();
+	err = __setup_sorting(evlist);
 	if (err < 0)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent");
+		err = sort_dimension__add("parent", evlist);
 		if (err < 0)
 			return err;
 	}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 31228851e397..687bbb124428 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -18,7 +18,7 @@
 #include "debug.h"
 #include "header.h"
 
-#include "parse-options.h"
+#include <subcmd/parse-options.h>
 #include "parse-events.h"
 #include "hist.h"
 #include "thread.h"
@@ -122,6 +122,9 @@ struct hist_entry {
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
+	void			*raw_data;
+	u32			raw_size;
+	void			*trace_output;
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -164,6 +167,7 @@ enum sort_mode {
 	SORT_MODE__MEMORY,
 	SORT_MODE__TOP,
 	SORT_MODE__DIFF,
+	SORT_MODE__TRACEPOINT,
 };
 
 enum sort_type {
@@ -180,6 +184,7 @@ enum sort_type {
 	SORT_LOCAL_WEIGHT,
 	SORT_GLOBAL_WEIGHT,
 	SORT_TRANSACTION,
+	SORT_TRACE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
@@ -209,8 +214,6 @@ enum sort_type {
  */
 
 struct sort_entry {
-	struct list_head list;
-
 	const char *se_header;
 
 	int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
@@ -224,10 +227,11 @@ struct sort_entry {
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-int setup_sorting(void);
+struct perf_evlist;
+struct pevent;
+int setup_sorting(struct perf_evlist *evlist);
 int setup_output_field(void);
 void reset_output_field(void);
-extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 void perf_hpp__set_elide(int idx, bool elide);
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2d9d8306dbd3..2f901d15e063 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -341,3 +341,65 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
 	return 0;
 }
+
+int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_session *session)
+{
+	struct perf_counts_values count;
+	struct stat_event *st = &event->stat;
+	struct perf_evsel *counter;
+
+	count.val = st->val;
+	count.ena = st->ena;
+	count.run = st->run;
+
+	counter = perf_evlist__id2evsel(session->evlist, st->id);
+	if (!counter) {
+		pr_err("Failed to resolve counter for stat event.\n");
+		return -EINVAL;
+	}
+
+	*perf_counts(counter->counts, st->cpu, st->thread) = count;
+	counter->supported = true;
+	return 0;
+}
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
+{
+	struct stat_event *st = (struct stat_event *) event;
+	size_t ret;
+
+	ret  = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n",
+		       st->id, st->cpu, st->thread);
+	ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n",
+		       st->val, st->ena, st->run);
+
+	return ret;
+}
+
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
+{
+	struct stat_round_event *rd = (struct stat_round_event *)event;
+	size_t ret;
+
+	ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time,
+		      rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");
+
+	return ret;
+}
+
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
+{
+	struct perf_stat_config sc;
+	size_t ret;
+
+	perf_event__read_stat_config(&sc, &event->stat_config);
+
+	ret  = fprintf(fp, "\n");
+	ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
+	ret += fprintf(fp, "... scale     %d\n", sc.scale);
+	ret += fprintf(fp, "... interval  %u\n", sc.interval);
+
+	return ret;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index da1d11c4f8c1..086f4e128d63 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,4 +90,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct perf_evsel *counter);
+struct perf_tool;
+union perf_event;
+struct perf_session;
+int perf_event__process_stat_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_session *session);
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
+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);
 #endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index fc8781de62db..7f7e072be746 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -342,22 +342,6 @@ char *rtrim(char *s)
 	return s;
 }
 
-/**
- * memdup - duplicate region of memory
- * @src: memory region to duplicate
- * @len: memory region length
- */
-void *memdup(const void *src, size_t len)
-{
-	void *p;
-
-	p = malloc(len);
-	if (p)
-		memcpy(p, src, len);
-
-	return p;
-}
-
 char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints)
 {
 	/*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 475d88d0a1c9..562b8ebeae5b 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1026,8 +1026,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				curr_dso->long_name_len = dso->long_name_len;
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
+				dso__put(curr_dso);
 				if (curr_map == NULL) {
-					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {
@@ -1042,7 +1042,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmaps, curr_map);
+				/*
+				 * Add it before we drop the referece to curr_map,
+				 * i.e. while we still are sure to have a reference
+				 * to this DSO via curr_map->dso.
+				 */
 				dsos__add(&map->groups->machine->dsos, curr_dso);
+				/* kmaps already got it */
+				map__put(curr_map);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cd08027a6d2c..3b2de6eb3376 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -39,6 +39,7 @@ struct symbol_conf symbol_conf = {
 	.cumulate_callchain	= true,
 	.show_hist_headers	= true,
 	.symfs			= "",
+	.event_group		= true,
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -1860,24 +1861,44 @@ static void vmlinux_path__exit(void)
 	zfree(&vmlinux_path);
 }
 
+static const char * const vmlinux_paths[] = {
+	"vmlinux",
+	"/boot/vmlinux"
+};
+
+static const char * const vmlinux_paths_upd[] = {
+	"/boot/vmlinux-%s",
+	"/usr/lib/debug/boot/vmlinux-%s",
+	"/lib/modules/%s/build/vmlinux",
+	"/usr/lib/debug/lib/modules/%s/vmlinux",
+	"/usr/lib/debug/boot/vmlinux-%s.debug"
+};
+
+static int vmlinux_path__add(const char *new_entry)
+{
+	vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry);
+	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+		return -1;
+	++vmlinux_path__nr_entries;
+
+	return 0;
+}
+
 static int vmlinux_path__init(struct perf_env *env)
 {
 	struct utsname uts;
 	char bf[PATH_MAX];
 	char *kernel_version;
+	unsigned int i;
 
-	vmlinux_path = malloc(sizeof(char *) * 6);
+	vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) +
+			      ARRAY_SIZE(vmlinux_paths_upd)));
 	if (vmlinux_path == NULL)
 		return -1;
 
-	vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux");
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux");
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
+	for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++)
+		if (vmlinux_path__add(vmlinux_paths[i]) < 0)
+			goto out_fail;
 
 	/* only try kernel version if no symfs was given */
 	if (symbol_conf.symfs[0] != 0)
@@ -1892,28 +1913,11 @@ static int vmlinux_path__init(struct perf_env *env)
 		kernel_version = uts.release;
 	}
 
-	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
-		 kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-        ++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-		 kernel_version);
-	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
-	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
-		goto out_fail;
-	++vmlinux_path__nr_entries;
+	for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) {
+		snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version);
+		if (vmlinux_path__add(bf) < 0)
+			goto out_fail;
+	}
 
 	return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index dcd786e364f2..ccd1caa40e11 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -108,7 +108,9 @@ struct symbol_conf {
 			show_hist_headers,
 			branch_callstack,
 			has_filter,
-			show_ref_callgraph;
+			show_ref_callgraph,
+			hide_unresolved,
+			raw_trace;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c
new file mode 100644
index 000000000000..90b47d8aa19c
--- /dev/null
+++ b/tools/perf/util/term.c
@@ -0,0 +1,35 @@
+#include "util.h"
+
+void get_term_dimensions(struct winsize *ws)
+{
+	char *s = getenv("LINES");
+
+	if (s != NULL) {
+		ws->ws_row = atoi(s);
+		s = getenv("COLUMNS");
+		if (s != NULL) {
+			ws->ws_col = atoi(s);
+			if (ws->ws_row && ws->ws_col)
+				return;
+		}
+	}
+#ifdef TIOCGWINSZ
+	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+	    ws->ws_row && ws->ws_col)
+		return;
+#endif
+	ws->ws_row = 25;
+	ws->ws_col = 80;
+}
+
+void set_term_quiet_input(struct termios *old)
+{
+	struct termios tc;
+
+	tcgetattr(0, old);
+	tc = *old;
+	tc.c_lflag &= ~(ICANON | ECHO);
+	tc.c_cc[VMIN] = 0;
+	tc.c_cc[VTIME] = 0;
+	tcsetattr(0, TCSANOW, &tc);
+}
diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h
new file mode 100644
index 000000000000..2c06a61846a1
--- /dev/null
+++ b/tools/perf/util/term.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_TERM_H
+#define __PERF_TERM_H
+
+struct termios;
+struct winsize;
+
+void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
+
+#endif /* __PERF_TERM_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0a9ae8014729..dfd00c6dad6e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -19,8 +19,10 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 		thread->mg = map_groups__new(machine);
 	} else {
 		leader = __machine__findnew_thread(machine, pid, pid);
-		if (leader)
+		if (leader) {
 			thread->mg = map_groups__get(leader->mg);
+			thread__put(leader);
+		}
 	}
 
 	return thread->mg ? 0 : -1;
@@ -53,7 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-		atomic_set(&thread->refcnt, 0);
+		atomic_set(&thread->refcnt, 1);
 		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
@@ -95,6 +97,10 @@ struct thread *thread__get(struct thread *thread)
 void thread__put(struct thread *thread)
 {
 	if (thread && atomic_dec_and_test(&thread->refcnt)) {
+		/*
+		 * Remove it from the dead_threads list, as last reference
+		 * is gone.
+		 */
 		list_del_init(&thread->node);
 		thread__delete(thread);
 	}
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 6ec3c5ca438f..08afc6909953 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -13,6 +13,7 @@
 #include "thread_map.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -304,6 +305,7 @@ out:
 
 out_free_threads:
 	zfree(&threads);
+	strlist__delete(slist);
 	goto out;
 }
 
@@ -408,3 +410,29 @@ void thread_map__read_comms(struct thread_map *threads)
 	for (i = 0; i < threads->nr; ++i)
 		comm_init(threads, i);
 }
+
+static void thread_map__copy_event(struct thread_map *threads,
+				   struct thread_map_event *event)
+{
+	unsigned i;
+
+	threads->nr = (int) event->nr;
+
+	for (i = 0; i < event->nr; i++) {
+		thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid);
+		threads->map[i].comm = strndup(event->entries[i].comm, 16);
+	}
+
+	atomic_set(&threads->refcnt, 1);
+}
+
+struct thread_map *thread_map__new_event(struct thread_map_event *event)
+{
+	struct thread_map *threads;
+
+	threads = thread_map__alloc(event->nr);
+	if (threads)
+		thread_map__copy_event(threads, event);
+
+	return threads;
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index af679d8a50f8..85e4c7c4fbde 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -16,11 +16,14 @@ struct thread_map {
 	struct thread_map_data map[];
 };
 
+struct thread_map_event;
+
 struct thread_map *thread_map__new_dummy(void);
 struct thread_map *thread_map__new_by_pid(pid_t pid);
 struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
+struct thread_map *thread_map__new_event(struct thread_map_event *event);
 
 struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index cab8cc24831b..55de4cffcd4e 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -50,12 +50,18 @@ struct perf_tool {
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
+	event_attr_op	event_update;
 	event_op2	tracing_data;
 	event_oe	finished_round;
 	event_op2	build_id,
 			id_index,
 			auxtrace_info,
-			auxtrace_error;
+			auxtrace_error,
+			thread_map,
+			cpu_map,
+			stat_config,
+			stat,
+			stat_round;
 	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b85ee55cca0c..bce5b1dac268 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -65,6 +65,7 @@ int tracing_data_put(struct tracing_data *tdata);
 struct addr_location;
 
 struct perf_session;
+struct perf_stat_config;
 
 struct scripting_ops {
 	const char *name;
@@ -75,6 +76,9 @@ struct scripting_ops {
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct addr_location *al);
+	void (*process_stat)(struct perf_stat_config *config,
+			     struct perf_evsel *evsel, u64 tstamp);
+	void (*process_stat_interval)(u64 tstamp);
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 2dcfe9a7c8d0..cf5e250bc78e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
+#include "callchain.h"
 
 static char *debuginfo_path;
 
@@ -52,25 +53,28 @@ static int report_module(u64 ip, struct unwind_info *ui)
 	return __report_module(&al, ip, ui);
 }
 
+/*
+ * Store all entries within entries array,
+ * we will process it after we finish unwind.
+ */
 static int entry(u64 ip, struct unwind_info *ui)
 
 {
-	struct unwind_entry e;
+	struct unwind_entry *e = &ui->entries[ui->idx++];
 	struct addr_location al;
 
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e.ip  = ip;
-	e.map = al.map;
-	e.sym = al.sym;
+	e->ip  = ip;
+	e->map = al.map;
+	e->sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
 		 ip,
 		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-	return ui->cb(&e, ui->arg);
+	return 0;
 }
 
 static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
@@ -92,6 +96,16 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
+		/*
+		 * We've seen cases (softice) where DWARF unwinder went
+		 * through non executable mmaps, which we need to lookup
+		 * in MAP__VARIABLE tree.
+		 */
+		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+				      MAP__VARIABLE, addr, &al);
+	}
+
+	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
@@ -168,7 +182,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct perf_sample *data,
 			int max_stack)
 {
-	struct unwind_info ui = {
+	struct unwind_info *ui, ui_buf = {
 		.sample		= data,
 		.thread		= thread,
 		.machine	= thread->mg->machine,
@@ -177,35 +191,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 		.max_stack	= max_stack,
 	};
 	Dwarf_Word ip;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ui.dwfl = dwfl_begin(&offline_callbacks);
-	if (!ui.dwfl)
+	ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+	if (!ui)
+		return -ENOMEM;
+
+	*ui = ui_buf;
+
+	ui->dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui->dwfl)
 		goto out;
 
 	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (err)
 		goto out;
 
-	err = report_module(ip, &ui);
+	err = report_module(ip, ui);
 	if (err)
 		goto out;
 
-	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+	if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
 		goto out;
 
-	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui.max_stack)
+	if (err && !ui->max_stack)
 		err = 0;
 
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < ui->idx && !err; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = ui->idx - i - 1;
+
+		err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0;
+	}
+
  out:
 	if (err)
 		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
 
-	dwfl_end(ui.dwfl);
+	dwfl_end(ui->dwfl);
+	free(ui);
 	return 0;
 }
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 417a1426f3ad..58328669ed16 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -16,6 +16,8 @@ struct unwind_info {
 	unwind_entry_cb_t	cb;
 	void			*arg;
 	int			max_stack;
+	int			idx;
+	struct unwind_entry	entries[];
 };
 
 #endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index c83832b555e5..ee7e372297e5 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -319,6 +319,15 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 
 	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, ip, &al);
+	if (!al.map) {
+		/*
+		 * We've seen cases (softice) where DWARF unwinder went
+		 * through non executable mmaps, which we need to lookup
+		 * in MAP__VARIABLE tree.
+		 */
+		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+				      MAP__VARIABLE, ip, &al);
+	}
 	return al.map;
 }
 
@@ -416,20 +425,19 @@ get_proc_name(unw_addr_space_t __maybe_unused as,
 static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 			  unw_word_t *data)
 {
-	struct addr_location al;
+	struct map *map;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, addr, &al);
-	if (!al.map) {
+	map = find_map(addr, ui);
+	if (!map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
 
-	if (!al.map->dso)
+	if (!map->dso)
 		return -1;
 
-	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+	size = dso__data_read_addr(map->dso, map, ui->machine,
 				   addr, (u8 *) data, sizeof(*data));
 
 	return !(size == sizeof(*data));
@@ -614,23 +622,48 @@ void unwind__finish_access(struct thread *thread)
 static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		       void *arg, int max_stack)
 {
+	u64 val;
+	unw_word_t ips[max_stack];
 	unw_addr_space_t addr_space;
 	unw_cursor_t c;
-	int ret;
-
-	addr_space = thread__priv(ui->thread);
-	if (addr_space == NULL)
-		return -1;
+	int ret, i = 0;
 
-	ret = unw_init_remote(&c, addr_space, ui);
+	ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
 	if (ret)
-		display_error(ret);
+		return ret;
 
-	while (!ret && (unw_step(&c) > 0) && max_stack--) {
-		unw_word_t ip;
+	ips[i++] = (unw_word_t) val;
 
-		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
+	/*
+	 * If we need more than one entry, do the DWARF
+	 * unwind itself.
+	 */
+	if (max_stack - 1 > 0) {
+		addr_space = thread__priv(ui->thread);
+		if (addr_space == NULL)
+			return -1;
+
+		ret = unw_init_remote(&c, addr_space, ui);
+		if (ret)
+			display_error(ret);
+
+		while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+			unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+			++i;
+		}
+
+		max_stack = i;
+	}
+
+	/*
+	 * Display what we got based on the order setup.
+	 */
+	for (i = 0; i < max_stack && !ret; i++) {
+		int j = i;
+
+		if (callchain_param.order == ORDER_CALLER)
+			j = max_stack - i - 1;
+		ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
 	}
 
 	return ret;
@@ -640,24 +673,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
-	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
 		.machine      = thread->mg->machine,
 	};
-	int ret;
 
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
-	if (ret)
-		return ret;
-
-	ret = entry(ip, thread, cb, arg);
-	if (ret)
-		return -ENOMEM;
+	if (max_stack <= 0)
+		return -EINVAL;
 
-	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
+	return get_entries(&ui, cb, arg, max_stack);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 47b1e36c7ea0..88b8f8d21f58 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -16,12 +16,15 @@
 #include <linux/kernel.h>
 #include <unistd.h>
 #include "callchain.h"
+#include "strlist.h"
+#include <subcmd/exec-cmd.h>
 
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_ABS,
 	.min_percent = 0.5,
 	.order  = ORDER_CALLEE,
-	.key	= CCKEY_FUNCTION
+	.key	= CCKEY_FUNCTION,
+	.value	= CCVAL_PERCENT,
 };
 
 /*
@@ -351,41 +354,8 @@ void sighandler_dump_stack(int sig)
 {
 	psignal(sig, "perf");
 	dump_stack();
-	exit(sig);
-}
-
-void get_term_dimensions(struct winsize *ws)
-{
-	char *s = getenv("LINES");
-
-	if (s != NULL) {
-		ws->ws_row = atoi(s);
-		s = getenv("COLUMNS");
-		if (s != NULL) {
-			ws->ws_col = atoi(s);
-			if (ws->ws_row && ws->ws_col)
-				return;
-		}
-	}
-#ifdef TIOCGWINSZ
-	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
-	    ws->ws_row && ws->ws_col)
-		return;
-#endif
-	ws->ws_row = 25;
-	ws->ws_col = 80;
-}
-
-void set_term_quiet_input(struct termios *old)
-{
-	struct termios tc;
-
-	tcgetattr(0, old);
-	tc = *old;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-	tcsetattr(0, TCSANOW, &tc);
+	signal(sig, SIG_DFL);
+	raise(sig);
 }
 
 int parse_nsec_time(const char *str, u64 *ptime)
@@ -695,3 +665,28 @@ fetch_kernel_version(unsigned int *puint, char *str,
 		*puint = (version << 16) + (patchlevel << 8) + sublevel;
 	return 0;
 }
+
+const char *perf_tip(const char *dirpath)
+{
+	struct strlist *tips;
+	struct str_node *node;
+	char *tip = NULL;
+	struct strlist_config conf = {
+		.dirname = system_path(dirpath) ,
+	};
+
+	tips = strlist__new("tips.txt", &conf);
+	if (tips == NULL || strlist__nr_entries(tips) == 1) {
+		tip = (char *)"Cannot find tips.txt file";
+		goto out;
+	}
+
+	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
+	if (asprintf(&tip, "Tip: %s", node->s) < 0)
+		tip = (char *)"Tip: get more memory! ;-)";
+
+out:
+	strlist__delete(tips);
+
+	return tip;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index dcc659017976..fe915e616f9b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -53,6 +53,7 @@
 #include <stdlib.h>
 #include <stdarg.h>
 #include <string.h>
+#include <term.h>
 #include <errno.h>
 #include <limits.h>
 #include <sys/param.h>
@@ -150,12 +151,6 @@ extern void set_warning_routine(void (*routine)(const char *err, va_list params)
 extern int prefixcmp(const char *str, const char *prefix);
 extern void set_buildid_dir(const char *dir);
 
-static inline const char *skip_prefix(const char *str, const char *prefix)
-{
-	size_t len = strlen(prefix);
-	return strncmp(str, prefix, len) ? NULL : str + len;
-}
-
 #ifdef __GLIBC_PREREQ
 #if __GLIBC_PREREQ(2, 1)
 #define HAVE_STRCHRNUL
@@ -186,14 +181,6 @@ static inline void *zalloc(size_t size)
 
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
 
-static inline int has_extension(const char *filename, const char *ext)
-{
-	size_t len = strlen(filename);
-	size_t extlen = strlen(ext);
-
-	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
-}
-
 /* Sane ctype - no locale, and works with signed chars */
 #undef isascii
 #undef isspace
@@ -282,9 +269,6 @@ void sighandler_dump_stack(int sig);
 extern unsigned int page_size;
 extern int cacheline_size;
 
-void get_term_dimensions(struct winsize *ws);
-void set_term_quiet_input(struct termios *old);
-
 struct parse_tag {
 	char tag;
 	int mult;
@@ -358,4 +342,6 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_FMT	"%d.%d.%d"
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
+const char *perf_tip(const char *dirpath);
+
 #endif /* GIT_COMPAT_UTIL_H */