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

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

User visible changes:

  o Support S/390 in 'perf kvm stat' (Alexander Yarygin)

Developer Stuff:

  o Various fixes and prep work related to supporting Intel PT (Adrian Hunter)

  o Introduce multiple debug variables control (Jiri Olsa)

  o Add callchain and additional sample information for python scripts (Joseph Schuchart)

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

85 files changed, 1170 insertions, 470 deletions

diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index 6a9a9eb645f5..0e2b54db82bc 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -16,6 +16,7 @@ header-y += ioctls.h
 header-y += ipcbuf.h
 header-y += kvm.h
 header-y += kvm_para.h
+header-y += kvm_perf.h
 header-y += kvm_virtio.h
 header-y += mman.h
 header-y += monwriter.h
diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h
new file mode 100644
index 000000000000..397282727e21
--- /dev/null
+++ b/arch/s390/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,25 @@
+/*
+ * Definitions for perf-kvm on s390
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_KVM_PERF_S390_H
+#define __LINUX_KVM_PERF_S390_H
+
+#include <asm/sie.h>
+
+#define DECODE_STR_LEN 40
+
+#define VCPU_ID "id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_s390_sie_enter"
+#define KVM_EXIT_TRACE "kvm:kvm_s390_sie_exit"
+#define KVM_EXIT_REASON "icptcode"
+
+#endif
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index 09409c44f9a5..3dec769cadf7 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -22,6 +22,7 @@ header-y += ipcbuf.h
 header-y += ist.h
 header-y += kvm.h
 header-y += kvm_para.h
+header-y += kvm_perf.h
 header-y += ldt.h
 header-y += mce.h
 header-y += mman.h
diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h
new file mode 100644
index 000000000000..3bb964f88aa1
--- /dev/null
+++ b/arch/x86/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_KVM_PERF_H
+#define _ASM_X86_KVM_PERF_H
+
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+#define DECODE_STR_LEN 20
+
+#define VCPU_ID "vcpu_id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_entry"
+#define KVM_EXIT_TRACE "kvm:kvm_exit"
+#define KVM_EXIT_REASON "exit_reason"
+
+#endif /* _ASM_X86_KVM_PERF_H */
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 52276a6d2b75..6e689dc89a2f 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -51,9 +51,9 @@ There are a couple of variants of perf kvm:
   'perf kvm stat <command>' to run a command and gather performance counter
   statistics.
   Especially, perf 'kvm stat record/report' generates a statistical analysis
-  of KVM events. Currently, vmexit, mmio and ioport events are supported.
-  'perf kvm stat record <command>' records kvm events and the events between
-  start and end <command>.
+  of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only)
+  events are supported. 'perf kvm stat record <command>' records kvm events
+  and the events between start and end <command>.
   And this command produces a file which contains tracing results of kvm
   events.
 
@@ -103,8 +103,8 @@ STAT REPORT OPTIONS
        analyze events which occures on this vcpu. (default: all vcpus)
 
 --event=<value>::
-       event to be analyzed. Possible values: vmexit, mmio, ioport.
-       (default: vmexit)
+       event to be analyzed. Possible values: vmexit, mmio (x86 only),
+       ioport (x86 only). (default: vmexit)
 -k::
 --key=<value>::
        Sorting key. Possible values: sample (default, sort by samples
@@ -138,7 +138,8 @@ STAT LIVE OPTIONS
 
 
 --event=<value>::
-       event to be analyzed. Possible values: vmexit, mmio, ioport.
+       event to be analyzed. Possible values: vmexit,
+       mmio (x86 only), ioport (x86 only).
        (default: vmexit)
 
 -k::
@@ -147,7 +148,8 @@ STAT LIVE OPTIONS
        number), time (sort by average time).
 
 --duration=<value>::
-       Show events other than HLT that take longer than duration usecs.
+       Show events other than HLT (x86 only) or Wait state (s390 only)
+       that take longer than duration usecs.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 0eeb247dc7d2..d240bb2e5b22 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -8,7 +8,15 @@ perf - Performance analysis tools for Linux
 SYNOPSIS
 --------
 [verse]
-'perf' [--version] [--help] COMMAND [ARGS]
+'perf' [--version] [--help] [OPTIONS] COMMAND [ARGS]
+
+OPTIONS
+-------
+--debug::
+        Setup debug variable (just verbose for now) in value
+        range (0, 10). Use like:
+          --debug verbose   # sets verbose = 1
+          --debug verbose=2 # sets verbose = 2
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 45da209b6ed3..344c4d3d0a4a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -37,3 +37,6 @@ arch/x86/include/asm/kvm_host.h
 arch/x86/include/uapi/asm/svm.h
 arch/x86/include/uapi/asm/vmx.h
 arch/x86/include/uapi/asm/kvm.h
+arch/x86/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/sie.h
+arch/s390/include/uapi/asm/kvm_perf.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9670a16fa577..3308b22a1660 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -295,11 +295,13 @@ LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
 LIB_H += util/unwind.h
 LIB_H += util/vdso.h
+LIB_H += util/tsc.h
 LIB_H += ui/helpline.h
 LIB_H += ui/progress.h
 LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
+LIB_H += util/kvm-stat.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -373,6 +375,7 @@ LIB_OBJS += $(OUTPUT)util/stat.o
 LIB_OBJS += $(OUTPUT)util/record.o
 LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
+LIB_OBJS += $(OUTPUT)util/tsc.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 744e629797be..798ac7379c5f 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -3,3 +3,5 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
new file mode 100644
index 000000000000..a5dbc07ec9dc
--- /dev/null
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -0,0 +1,105 @@
+/*
+ * Arch specific functions for perf kvm stat.
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
+define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
+define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
+define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
+define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
+
+static void event_icpt_insn_get_key(struct perf_evsel *evsel,
+                                    struct perf_sample *sample,
+                                    struct event_key *key)
+{
+        unsigned long insn;
+
+        insn = perf_evsel__intval(evsel, sample, "instruction");
+        key->key = icpt_insn_decoder(insn);
+        key->exit_reasons = sie_icpt_insn_codes;
+}
+
+static void event_sigp_get_key(struct perf_evsel *evsel,
+                               struct perf_sample *sample,
+                               struct event_key *key)
+{
+        key->key = perf_evsel__intval(evsel, sample, "order_code");
+        key->exit_reasons = sie_sigp_order_codes;
+}
+
+static void event_diag_get_key(struct perf_evsel *evsel,
+                               struct perf_sample *sample,
+                               struct event_key *key)
+{
+        key->key = perf_evsel__intval(evsel, sample, "code");
+        key->exit_reasons = sie_diagnose_codes;
+}
+
+static void event_icpt_prog_get_key(struct perf_evsel *evsel,
+                                    struct perf_sample *sample,
+                                    struct event_key *key)
+{
+        key->key = perf_evsel__intval(evsel, sample, "code");
+        key->exit_reasons = sie_icpt_prog_codes;
+}
+
+static struct child_event_ops child_events[] = {
+        { .name = "kvm:kvm_s390_intercept_instruction",
+          .get_key = event_icpt_insn_get_key },
+        { .name = "kvm:kvm_s390_handle_sigp",
+          .get_key = event_sigp_get_key },
+        { .name = "kvm:kvm_s390_handle_diag",
+          .get_key = event_diag_get_key },
+        { .name = "kvm:kvm_s390_intercept_prog",
+          .get_key = event_icpt_prog_get_key },
+        { NULL, NULL },
+};
+
+static struct kvm_events_ops exit_events = {
+        .is_begin_event = exit_event_begin,
+        .is_end_event = exit_event_end,
+        .child_ops = child_events,
+        .decode_key = exit_event_decode_key,
+        .name = "VM-EXIT"
+};
+
+const char * const kvm_events_tp[] = {
+        "kvm:kvm_s390_sie_enter",
+        "kvm:kvm_s390_sie_exit",
+        "kvm:kvm_s390_intercept_instruction",
+        "kvm:kvm_s390_handle_sigp",
+        "kvm:kvm_s390_handle_diag",
+        "kvm:kvm_s390_intercept_prog",
+        NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+        { .name = "vmexit", .ops = &exit_events },
+        { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+        "Wait state",
+        NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+        if (strstr(cpuid, "IBM/S390")) {
+                kvm->exit_reasons = sie_exit_reasons;
+                kvm->exit_reasons_isa = "SIE";
+        } else
+                return -ENOTSUP;
+
+        return 0;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index d3939014a877..9b21881db52f 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -16,3 +16,4 @@ LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
 LIB_H += arch/$(ARCH)/util/tsc.h
 HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 9f89f899ccc7..d8bbf7ad1681 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "thread.h"
 #include "map.h"
 #include "event.h"
+#include "debug.h"
 #include "tests/tests.h"
 
 #define STACK_SIZE 8192
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
new file mode 100644
index 000000000000..14e4e668fad7
--- /dev/null
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -0,0 +1,156 @@
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
+define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
+
+static struct kvm_events_ops exit_events = {
+        .is_begin_event = exit_event_begin,
+        .is_end_event = exit_event_end,
+        .decode_key = exit_event_decode_key,
+        .name = "VM-EXIT"
+};
+
+/*
+ * For the mmio events, we treat:
+ * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+ * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+ */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+                               struct event_key *key)
+{
+        key->key  = perf_evsel__intval(evsel, sample, "gpa");
+        key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+                             struct perf_sample *sample, struct event_key *key)
+{
+        /* MMIO read begin event in kernel. */
+        if (kvm_exit_event(evsel))
+                return true;
+
+        /* MMIO write begin event in kernel. */
+        if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+            perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+                mmio_event_get_key(evsel, sample, key);
+                return true;
+        }
+
+        return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+                           struct event_key *key)
+{
+        /* MMIO write end event in kernel. */
+        if (kvm_entry_event(evsel))
+                return true;
+
+        /* MMIO read end event in kernel.*/
+        if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+            perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+                mmio_event_get_key(evsel, sample, key);
+                return true;
+        }
+
+        return false;
+}
+
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+                                  struct event_key *key,
+                                  char *decode)
+{
+        scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+                  (unsigned long)key->key,
+                  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+        .is_begin_event = mmio_event_begin,
+        .is_end_event = mmio_event_end,
+        .decode_key = mmio_event_decode_key,
+        .name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+                                 struct perf_sample *sample,
+                                 struct event_key *key)
+{
+        key->key  = perf_evsel__intval(evsel, sample, "port");
+        key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+                               struct perf_sample *sample,
+                               struct event_key *key)
+{
+        if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+                ioport_event_get_key(evsel, sample, key);
+                return true;
+        }
+
+        return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+                             struct perf_sample *sample __maybe_unused,
+                             struct event_key *key __maybe_unused)
+{
+        return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+                                    struct event_key *key,
+                                    char *decode)
+{
+        scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+                  (unsigned long long)key->key,
+                  key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+        .is_begin_event = ioport_event_begin,
+        .is_end_event = ioport_event_end,
+        .decode_key = ioport_event_decode_key,
+        .name = "IO Port Access"
+};
+
+const char * const kvm_events_tp[] = {
+        "kvm:kvm_entry",
+        "kvm:kvm_exit",
+        "kvm:kvm_mmio",
+        "kvm:kvm_pio",
+        NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+        { .name = "vmexit", .ops = &exit_events },
+        { .name = "mmio", .ops = &mmio_events },
+        { .name = "ioport", .ops = &ioport_events },
+        { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+        "HLT",
+        NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+        if (strstr(cpuid, "Intel")) {
+                kvm->exit_reasons = vmx_exit_reasons;
+                kvm->exit_reasons_isa = "VMX";
+        } else if (strstr(cpuid, "AMD")) {
+                kvm->exit_reasons = svm_exit_reasons;
+                kvm->exit_reasons_isa = "SVM";
+        } else
+                return -ENOTSUP;
+
+        return 0;
+}
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 40021fa3129b..3655f24c3170 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -6,29 +6,9 @@
 #include "../../perf.h"
 #include <linux/types.h>
 #include "../../util/debug.h"
+#include "../../util/tsc.h"
 #include "tsc.h"
 
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
-{
-        u64 t, quot, rem;
-
-        t = ns - tc->time_zero;
-        quot = t / tc->time_mult;
-        rem  = t % tc->time_mult;
-        return (quot << tc->time_shift) +
-               (rem << tc->time_shift) / tc->time_mult;
-}
-
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
-{
-        u64 quot, rem;
-
-        quot = cyc >> tc->time_shift;
-        rem  = cyc & ((1 << tc->time_shift) - 1);
-        return tc->time_zero + quot * tc->time_mult +
-               ((rem * tc->time_mult) >> tc->time_shift);
-}
-
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
                              struct perf_tsc_conversion *tc)
 {
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
index 2affe0366b59..2edc4d31065c 100644
--- a/tools/perf/arch/x86/util/tsc.h
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -14,7 +14,4 @@ struct perf_event_mmap_page;
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
                              struct perf_tsc_conversion *tc);
 
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
-
 #endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 3261f68c6a7c..db25e93d989c 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 int libunwind__arch_reg_id(int regnum)
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index b22dbb16f877..2a2c78f80876 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -125,7 +125,8 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
         return ret;
 }
 
-static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
+static int build_id_cache__add_kcore(const char *filename, const char *debugdir,
+                                     bool force)
 {
         char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
         char from_dir[PATH_MAX], to_dir[PATH_MAX];
@@ -144,7 +145,8 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
         scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
                   debugdir, sbuildid);
 
-        if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
+        if (!force &&
+            !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
                 pr_debug("same kcore found in %s\n", to_dir);
                 return 0;
         }
@@ -389,7 +391,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         }
 
         if (kcore_filename &&
-            build_id_cache__add_kcore(kcore_filename, debugdir))
+            build_id_cache__add_kcore(kcore_filename, debugdir, force))
                 pr_warning("Couldn't add %s\n", kcore_filename);
 
         return ret;
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index c99e0de7e54a..66e12f55c052 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,6 +15,7 @@
 #include "util/parse-options.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/debug.h"
 
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 178b88ae3d2f..0384d930480b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -11,6 +11,7 @@
 #include "util/parse-options.h"
 #include "util/run-command.h"
 #include "util/help.h"
+#include "util/debug.h"
 
 static struct man_viewer_list {
         struct man_viewer_list *next;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 16c7c11ad06e..cf6a605a13e8 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -389,6 +389,9 @@ static int __cmd_inject(struct perf_inject *inject)
         ret = perf_session__process_events(session, &inject->tool);
 
         if (!file_out->is_pipe) {
+                if (inject->build_ids)
+                        perf_header__set_feat(&session->header,
+                                              HEADER_BUILD_ID);
                 session->header.data_size = inject->bytes_written;
                 perf_session__write_header(session, session->evlist, file_out->fd, true);
         }
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 41dbeaf8cc11..43367eb00510 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -30,112 +30,24 @@
 #include <math.h>
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include <asm/svm.h>
-#include <asm/vmx.h>
-#include <asm/kvm.h>
-
-struct event_key {
-        #define INVALID_KEY     (~0ULL)
-        u64 key;
-        int info;
-};
-
-struct kvm_event_stats {
-        u64 time;
-        struct stats stats;
-};
-
-struct kvm_event {
-        struct list_head hash_entry;
-        struct rb_node rb;
-
-        struct event_key key;
-
-        struct kvm_event_stats total;
-
-        #define DEFAULT_VCPU_NUM 8
-        int max_vcpu;
-        struct kvm_event_stats *vcpu;
-};
-
-typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
-
-struct kvm_event_key {
-        const char *name;
-        key_cmp_fun key;
-};
-
-
-struct perf_kvm_stat;
-
-struct kvm_events_ops {
-        bool (*is_begin_event)(struct perf_evsel *evsel,
-                               struct perf_sample *sample,
-                               struct event_key *key);
-        bool (*is_end_event)(struct perf_evsel *evsel,
-                             struct perf_sample *sample, struct event_key *key);
-        void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
-                           char decode[20]);
-        const char *name;
-};
-
-struct exit_reasons_table {
-        unsigned long exit_code;
-        const char *reason;
-};
-
-#define EVENTS_BITS             12
-#define EVENTS_CACHE_SIZE       (1UL << EVENTS_BITS)
-
-struct perf_kvm_stat {
-        struct perf_tool    tool;
-        struct record_opts  opts;
-        struct perf_evlist  *evlist;
-        struct perf_session *session;
-
-        const char *file_name;
-        const char *report_event;
-        const char *sort_key;
-        int trace_vcpu;
-
-        struct exit_reasons_table *exit_reasons;
-        const char *exit_reasons_isa;
-
-        struct kvm_events_ops *events_ops;
-        key_cmp_fun compare;
-        struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
-
-        u64 total_time;
-        u64 total_count;
-        u64 lost_events;
-        u64 duration;
-
-        const char *pid_str;
-        struct intlist *pid_list;
+#include <asm/kvm_perf.h>
+#include "util/kvm-stat.h"
 
-        struct rb_root result;
-
-        int timerfd;
-        unsigned int display_time;
-        bool live;
-};
-
-
-static void exit_event_get_key(struct perf_evsel *evsel,
-                               struct perf_sample *sample,
-                               struct event_key *key)
+void exit_event_get_key(struct perf_evsel *evsel,
+                        struct perf_sample *sample,
+                        struct event_key *key)
 {
         key->info = 0;
-        key->key = perf_evsel__intval(evsel, sample, "exit_reason");
+        key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
 }
 
-static bool kvm_exit_event(struct perf_evsel *evsel)
+bool kvm_exit_event(struct perf_evsel *evsel)
 {
-        return !strcmp(evsel->name, "kvm:kvm_exit");
+        return !strcmp(evsel->name, KVM_EXIT_TRACE);
 }
 
-static bool exit_event_begin(struct perf_evsel *evsel,
-                             struct perf_sample *sample, struct event_key *key)
+bool exit_event_begin(struct perf_evsel *evsel,
+                      struct perf_sample *sample, struct event_key *key)
 {
         if (kvm_exit_event(evsel)) {
                 exit_event_get_key(evsel, sample, key);
@@ -145,26 +57,18 @@ static bool exit_event_begin(struct perf_evsel *evsel,
         return false;
 }
 
-static bool kvm_entry_event(struct perf_evsel *evsel)
+bool kvm_entry_event(struct perf_evsel *evsel)
 {
-        return !strcmp(evsel->name, "kvm:kvm_entry");
+        return !strcmp(evsel->name, KVM_ENTRY_TRACE);
 }
 
-static bool exit_event_end(struct perf_evsel *evsel,
-                           struct perf_sample *sample __maybe_unused,
-                           struct event_key *key __maybe_unused)
+bool exit_event_end(struct perf_evsel *evsel,
+                    struct perf_sample *sample __maybe_unused,
+                    struct event_key *key __maybe_unused)
 {
         return kvm_entry_event(evsel);
 }
 
-#define define_exit_reasons_table(name, symbols)        \
-        static struct exit_reasons_table name[] = {     \
-                symbols, { -1, NULL }                   \
-        }
-
-define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
-define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
-
 static const char *get_exit_reason(struct perf_kvm_stat *kvm,
                                    struct exit_reasons_table *tbl,
                                    u64 exit_code)
@@ -180,149 +84,30 @@ static const char *get_exit_reason(struct perf_kvm_stat *kvm,
         return "UNKNOWN";
 }
 
-static void exit_event_decode_key(struct perf_kvm_stat *kvm,
-                                  struct event_key *key,
-                                  char decode[20])
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+                           struct event_key *key,
+                           char *decode)
 {
-        const char *exit_reason = get_exit_reason(kvm, kvm->exit_reasons,
+        const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
                                                   key->key);
 
-        scnprintf(decode, 20, "%s", exit_reason);
+        scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
 }
 
-static struct kvm_events_ops exit_events = {
-        .is_begin_event = exit_event_begin,
-        .is_end_event = exit_event_end,
-        .decode_key = exit_event_decode_key,
-        .name = "VM-EXIT"
-};
-
-/*
- * For the mmio events, we treat:
- * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
- * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
- */
-static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
-                               struct event_key *key)
-{
-        key->key  = perf_evsel__intval(evsel, sample, "gpa");
-        key->info = perf_evsel__intval(evsel, sample, "type");
-}
-
-#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
-#define KVM_TRACE_MMIO_READ 1
-#define KVM_TRACE_MMIO_WRITE 2
-
-static bool mmio_event_begin(struct perf_evsel *evsel,
-                             struct perf_sample *sample, struct event_key *key)
-{
-        /* MMIO read begin event in kernel. */
-        if (kvm_exit_event(evsel))
-                return true;
-
-        /* MMIO write begin event in kernel. */
-        if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-            perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
-                mmio_event_get_key(evsel, sample, key);
-                return true;
-        }
-
-        return false;
-}
-
-static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
-                           struct event_key *key)
-{
-        /* MMIO write end event in kernel. */
-        if (kvm_entry_event(evsel))
-                return true;
-
-        /* MMIO read end event in kernel.*/
-        if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-            perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
-                mmio_event_get_key(evsel, sample, key);
-                return true;
-        }
-
-        return false;
-}
-
-static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
-                                  struct event_key *key,
-                                  char decode[20])
-{
-        scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
-                                key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
-}
-
-static struct kvm_events_ops mmio_events = {
-        .is_begin_event = mmio_event_begin,
-        .is_end_event = mmio_event_end,
-        .decode_key = mmio_event_decode_key,
-        .name = "MMIO Access"
-};
-
- /* The time of emulation pio access is from kvm_pio to kvm_entry. */
-static void ioport_event_get_key(struct perf_evsel *evsel,
-                                 struct perf_sample *sample,
-                                 struct event_key *key)
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
 {
-        key->key  = perf_evsel__intval(evsel, sample, "port");
-        key->info = perf_evsel__intval(evsel, sample, "rw");
-}
+        struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops;
 
-static bool ioport_event_begin(struct perf_evsel *evsel,
-                               struct perf_sample *sample,
-                               struct event_key *key)
-{
-        if (!strcmp(evsel->name, "kvm:kvm_pio")) {
-                ioport_event_get_key(evsel, sample, key);
-                return true;
+        for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) {
+                if (!strcmp(events_ops->name, kvm->report_event)) {
+                        kvm->events_ops = events_ops->ops;
+                        return true;
+                }
         }
 
         return false;
 }
 
-static bool ioport_event_end(struct perf_evsel *evsel,
-                             struct perf_sample *sample __maybe_unused,
-                             struct event_key *key __maybe_unused)
-{
-        return kvm_entry_event(evsel);
-}
-
-static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
-                                    struct event_key *key,
-                                    char decode[20])
-{
-        scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
-                                key->info ? "POUT" : "PIN");
-}
-
-static struct kvm_events_ops ioport_events = {
-        .is_begin_event = ioport_event_begin,
-        .is_end_event = ioport_event_end,
-        .decode_key = ioport_event_decode_key,
-        .name = "IO Port Access"
-};
-
-static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
-{
-        bool ret = true;
-
-        if (!strcmp(kvm->report_event, "vmexit"))
-                kvm->events_ops = &exit_events;
-        else if (!strcmp(kvm->report_event, "mmio"))
-                kvm->events_ops = &mmio_events;
-        else if (!strcmp(kvm->report_event, "ioport"))
-                kvm->events_ops = &ioport_events;
-        else {
-                pr_err("Unknown report event:%s\n", kvm->report_event);
-                ret = false;
-        }
-
-        return ret;
-}
-
 struct vcpu_event_record {
         int vcpu_id;
         u64 start_time;
@@ -476,6 +261,54 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
         return true;
 }
 
+static bool is_child_event(struct perf_kvm_stat *kvm,
+                           struct perf_evsel *evsel,
+                           struct perf_sample *sample,
+                           struct event_key *key)
+{
+        struct child_event_ops *child_ops;
+
+        child_ops = kvm->events_ops->child_ops;
+
+        if (!child_ops)
+                return false;
+
+        for (; child_ops->name; child_ops++) {
+                if (!strcmp(evsel->name, child_ops->name)) {
+                        child_ops->get_key(evsel, sample, key);
+                        return true;
+                }
+        }
+
+        return false;
+}
+
+static bool handle_child_event(struct perf_kvm_stat *kvm,
+                               struct vcpu_event_record *vcpu_record,
+                               struct event_key *key,
+                               struct perf_sample *sample __maybe_unused)
+{
+        struct kvm_event *event = NULL;
+
+        if (key->key != INVALID_KEY)
+                event = find_create_kvm_event(kvm, key);
+
+        vcpu_record->last_event = event;
+
+        return true;
+}
+
+static bool skip_event(const char *event)
+{
+        const char * const *skip_events;
+
+        for (skip_events = kvm_skip_events; *skip_events; skip_events++)
+                if (!strcmp(event, *skip_events))
+                        return true;
+
+        return false;
+}
+
 static bool handle_end_event(struct perf_kvm_stat *kvm,
                              struct vcpu_event_record *vcpu_record,
                              struct event_key *key,
@@ -524,10 +357,10 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
         time_diff = sample->time - time_begin;
 
         if (kvm->duration && time_diff > kvm->duration) {
-                char decode[32];
+                char decode[DECODE_STR_LEN];
 
                 kvm->events_ops->decode_key(kvm, &event->key, decode);
-                if (strcmp(decode, "HLT")) {
+                if (!skip_event(decode)) {
                         pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
                                  sample->time, sample->pid, vcpu_record->vcpu_id,
                                  decode, time_diff/1000);
@@ -552,7 +385,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
                         return NULL;
                 }
 
-                vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
+                vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
                 thread->priv = vcpu_record;
         }
 
@@ -565,7 +398,8 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
                              struct perf_sample *sample)
 {
         struct vcpu_event_record *vcpu_record;
-        struct event_key key = {.key = INVALID_KEY};
+        struct event_key key = { .key = INVALID_KEY,
+                                 .exit_reasons = kvm->exit_reasons };
 
         vcpu_record = per_vcpu_record(thread, evsel, sample);
         if (!vcpu_record)
@@ -579,6 +413,9 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
         if (kvm->events_ops->is_begin_event(evsel, sample, &key))
                 return handle_begin_event(kvm, vcpu_record, &key, sample->time);
 
+        if (is_child_event(kvm, evsel, sample, &key))
+                return handle_child_event(kvm, vcpu_record, &key, sample);
+
         if (kvm->events_ops->is_end_event(evsel, sample, &key))
                 return handle_end_event(kvm, vcpu_record, &key, sample);
 
@@ -739,7 +576,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-        char decode[20];
+        char decode[DECODE_STR_LEN];
         struct kvm_event *event;
         int vcpu = kvm->trace_vcpu;
 
@@ -750,7 +587,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
         pr_info("\n\n");
         print_vcpu_info(kvm);
-        pr_info("%20s ", kvm->events_ops->name);
+        pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
         pr_info("%10s ", "Samples");
         pr_info("%9s ", "Samples%");
 
@@ -769,7 +606,7 @@ static void print_result(struct perf_kvm_stat *kvm)
                 min = get_event_min(event, vcpu);
 
                 kvm->events_ops->decode_key(kvm, &event->key, decode);
-                pr_info("%20s ", decode);
+                pr_info("%*s ", DECODE_STR_LEN, decode);
                 pr_info("%10llu ", (unsigned long long)ecount);
                 pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
                 pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -835,20 +672,6 @@ static int process_sample_event(struct perf_tool *tool,
         return 0;
 }
 
-static int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
-{
-        if (strstr(cpuid, "Intel")) {
-                kvm->exit_reasons = vmx_exit_reasons;
-                kvm->exit_reasons_isa = "VMX";
-        } else if (strstr(cpuid, "AMD")) {
-                kvm->exit_reasons = svm_exit_reasons;
-                kvm->exit_reasons_isa = "SVM";
-        } else
-                return -ENOTSUP;
-
-        return 0;
-}
-
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
         char buf[64], *cpuid;
@@ -1307,13 +1130,6 @@ exit:
         return ret;
 }
 
-static const char * const kvm_events_tp[] = {
-        "kvm:kvm_entry",
-        "kvm:kvm_exit",
-        "kvm:kvm_mmio",
-        "kvm:kvm_pio",
-};
-
 #define STRDUP_FAIL_EXIT(s)             \
         ({      char *_p;               \
         _p = strdup(s);         \
@@ -1325,7 +1141,7 @@ static const char * const kvm_events_tp[] = {
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
-        unsigned int rec_argc, i, j;
+        unsigned int rec_argc, i, j, events_tp_size;
         const char **rec_argv;
         const char * const record_args[] = {
                 "record",
@@ -1333,9 +1149,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 "-m", "1024",
                 "-c", "1",
         };
+        const char * const *events_tp;
+        events_tp_size = 0;
+
+        for (events_tp = kvm_events_tp; *events_tp; events_tp++)
+                events_tp_size++;
 
         rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
-                   2 * ARRAY_SIZE(kvm_events_tp);
+                   2 * events_tp_size;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
         if (rec_argv == NULL)
@@ -1344,7 +1165,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
         for (i = 0; i < ARRAY_SIZE(record_args); i++)
                 rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);
 
-        for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+        for (j = 0; j < events_tp_size; j++) {
                 rec_argv[i++] = "-e";
                 rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
         }
@@ -1363,7 +1184,8 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
         const struct option kvm_events_report_options[] = {
                 OPT_STRING(0, "event", &kvm->report_event, "report event",
-                            "event for reporting: vmexit, mmio, ioport"),
+                           "event for reporting: vmexit, "
+                           "mmio (x86 only), ioport (x86 only)"),
                 OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
                             "vcpu id to report"),
                 OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
@@ -1398,16 +1220,16 @@ static struct perf_evlist *kvm_live_event_list(void)
 {
         struct perf_evlist *evlist;
         char *tp, *name, *sys;
-        unsigned int j;
         int err = -1;
+        const char * const *events_tp;
 
         evlist = perf_evlist__new();
         if (evlist == NULL)
                 return NULL;
 
-        for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+        for (events_tp = kvm_events_tp; *events_tp; events_tp++) {
 
-                tp = strdup(kvm_events_tp[j]);
+                tp = strdup(*events_tp);
                 if (tp == NULL)
                         goto out;
 
@@ -1416,7 +1238,7 @@ static struct perf_evlist *kvm_live_event_list(void)
                 name = strchr(tp, ':');
                 if (name == NULL) {
                         pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
-                                kvm_events_tp[j]);
+                               *events_tp);
                         free(tp);
                         goto out;
                 }
@@ -1424,7 +1246,7 @@ static struct perf_evlist *kvm_live_event_list(void)
                 name++;
 
                 if (perf_evlist__add_newtp(evlist, sys, name, NULL)) {
-                        pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]);
+                        pr_err("Failed to add %s tracepoint to the list\n", *events_tp);
                         free(tp);
                         goto out;
                 }
@@ -1469,7 +1291,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
                         "key for sorting: sample(sort by samples number)"
                         " time (sort by avg time)"),
                 OPT_U64(0, "duration", &kvm->duration,
-                    "show events other than HALT that take longer than duration usecs"),
+                        "show events other than"
+                        " HLT (x86 only) or Wait state (s390 only)"
+                        " that take longer than duration usecs"),
                 OPT_END()
         };
         const char * const live_usage[] = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index c38d06c04775..b7f555add0c8 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -935,8 +935,8 @@ static int latency_switch_event(struct perf_sched *sched,
                 return -1;
         }
 
-        sched_out = machine__findnew_thread(machine, 0, prev_pid);
-        sched_in = machine__findnew_thread(machine, 0, next_pid);
+        sched_out = machine__findnew_thread(machine, -1, prev_pid);
+        sched_in = machine__findnew_thread(machine, -1, next_pid);
 
         out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
         if (!out_events) {
@@ -979,7 +979,7 @@ static int latency_runtime_event(struct perf_sched *sched,
 {
         const u32 pid      = perf_evsel__intval(evsel, sample, "pid");
         const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
-        struct thread *thread = machine__findnew_thread(machine, 0, pid);
+        struct thread *thread = machine__findnew_thread(machine, -1, pid);
         struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
         u64 timestamp = sample->time;
         int cpu = sample->cpu;
@@ -1012,7 +1012,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
         struct thread *wakee;
         u64 timestamp = sample->time;
 
-        wakee = machine__findnew_thread(machine, 0, pid);
+        wakee = machine__findnew_thread(machine, -1, pid);
         atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
         if (!atoms) {
                 if (thread_atoms_insert(sched, wakee))
@@ -1072,7 +1072,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
         if (sched->profile_cpu == -1)
                 return 0;
 
-        migrant = machine__findnew_thread(machine, 0, pid);
+        migrant = machine__findnew_thread(machine, -1, pid);
         atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
         if (!atoms) {
                 if (thread_atoms_insert(sched, migrant))
@@ -1290,7 +1290,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
                 return -1;
         }
 
-        sched_in = machine__findnew_thread(machine, 0, next_pid);
+        sched_in = machine__findnew_thread(machine, -1, next_pid);
 
         sched->curr_thread[this_cpu] = sched_in;
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 04c9c53becad..2f1a5220c090 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -37,6 +37,7 @@
 #include "util/svghelper.h"
 #include "util/tool.h"
 #include "util/data.h"
+#include "util/debug.h"
 
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index b7f42d577c4e..1f67aa02d240 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -164,6 +164,7 @@ CORE_FEATURE_TESTS =			\
         backtrace                       \
         dwarf                           \
         fortify-source                  \
+        sync-compare-and-swap           \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \
@@ -199,6 +200,7 @@ LIB_FEATURE_TESTS =			\
 VF_FEATURE_TESTS =                      \
         backtrace                       \
         fortify-source                  \
+        sync-compare-and-swap           \
         gtk2-infobar                    \
         libelf-getphdrnum               \
         libelf-mmap                     \
@@ -272,6 +274,10 @@ CFLAGS += -I$(LIB_INCLUDE)
 
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 
+ifeq ($(feature-sync-compare-and-swap), 1)
+  CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 64c84e5f0514..6088f8d8a434 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -5,6 +5,7 @@ FILES=					\
         test-bionic.bin                 \
         test-dwarf.bin                  \
         test-fortify-source.bin         \
+        test-sync-compare-and-swap.bin  \
         test-glibc.bin                  \
         test-gtk2.bin                   \
         test-gtk2-infobar.bin           \
@@ -141,6 +142,9 @@ test-timerfd.bin:
 test-libdw-dwarf-unwind.bin:
         $(BUILD)
 
+test-sync-compare-and-swap.bin:
+        $(BUILD) -Werror
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index fe5c1e5c952f..a7d022e161c0 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -89,6 +89,10 @@
 # include "test-libdw-dwarf-unwind.c"
 #undef main
 
+#define main main_test_sync_compare_and_swap
+# include "test-sync-compare-and-swap.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -111,6 +115,7 @@ int main(int argc, char *argv[])
         main_test_timerfd();
         main_test_stackprotector_all();
         main_test_libdw_dwarf_unwind();
+        main_test_sync_compare_and_swap(argc, argv);
 
         return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
new file mode 100644
index 000000000000..c34d4ca4af56
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
@@ -0,0 +1,14 @@
+#include <stdint.h>
+
+volatile uint64_t x;
+
+int main(int argc, char *argv[])
+{
+        uint64_t old, new = argc;
+
+        argv = argv;
+        do {
+                old = __sync_val_compare_and_swap(&x, 0, 0);
+        } while (!__sync_bool_compare_and_swap(&x, old, new));
+        return old == new;
+}
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 95c58fc15284..eed3fb2a3af0 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,11 +13,12 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
+#include "util/debug.h"
 #include <api/fs/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
-        "perf [--version] [--help] COMMAND [ARGS]";
+        "perf [--version] [--debug variable[=VALUE]] [--help] COMMAND [ARGS]";
 
 const char perf_more_info_string[] =
         "See 'perf help COMMAND' for more information on a specific command.";
@@ -212,6 +213,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                                 printf("%s ", p->cmd);
                         }
                         exit(0);
+                } else if (!strcmp(cmd, "--debug")) {
+                        if (*argc < 2) {
+                                fprintf(stderr, "No variable specified for --debug.\n");
+                                usage(perf_usage_string);
+                        }
+                        if (perf_debug_option((*argv)[1]))
+                                usage(perf_usage_string);
+
+                        (*argv)++;
+                        (*argc)--;
                 } else {
                         fprintf(stderr, "Unknown option: %s\n", cmd);
                         usage(perf_usage_string);
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index de7211e4fa47..38dfb720fb6f 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -107,12 +107,13 @@ def taskState(state):
 
 class EventHeaders:
         def __init__(self, common_cpu, common_secs, common_nsecs,
-                     common_pid, common_comm):
+                     common_pid, common_comm, common_callchain):
                 self.cpu = common_cpu
                 self.secs = common_secs
                 self.nsecs = common_nsecs
                 self.pid = common_pid
                 self.comm = common_comm
+                self.callchain = common_callchain
 
         def ts(self):
                 return (self.secs * (10 ** 9)) + self.nsecs
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index 4647a7694cf6..334599c6032c 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -27,7 +27,7 @@ def trace_end():
 
 def irq__softirq_entry(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        vec):
+        common_callchain, vec):
                 print_header(event_name, common_cpu, common_secs, common_nsecs,
                         common_pid, common_comm)
 
@@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu,
 
 def kmem__kmalloc(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        call_site, ptr, bytes_req, bytes_alloc,
+        common_callchain, call_site, ptr, bytes_req, bytes_alloc,
         gfp_flags):
                 print_header(event_name, common_cpu, common_secs, common_nsecs,
                         common_pid, common_comm)
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 266a8364bce5..cafeff3d74db 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -39,7 +39,7 @@ def trace_end():
 
 def raw_syscalls__sys_exit(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        id, ret):
+        common_callchain, id, ret):
         if (for_comm and common_comm != for_comm) or \
            (for_pid  and common_pid  != for_pid ):
                 return
diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py
index 11e70a388d41..0f5cf437b602 100644
--- a/tools/perf/scripts/python/futex-contention.py
+++ b/tools/perf/scripts/python/futex-contention.py
@@ -21,7 +21,7 @@ thread_blocktime = {}
 lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
 process_names = {} # long-lived pid-to-execname mapping
 
-def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
                               nr, uaddr, op, val, utime, uaddr2, val3):
         cmd = op & FUTEX_CMD_MASK
         if cmd != FUTEX_WAIT:
@@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
         thread_thislock[tid] = uaddr
         thread_blocktime[tid] = nsecs(s, ns)
 
-def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
                              nr, ret):
         if thread_blocktime.has_key(tid):
                 elapsed = nsecs(s, ns) - thread_blocktime[tid]
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
index b5740599aabd..0b6ce8c253e8 100755
--- a/tools/perf/scripts/python/net_dropmonitor.py
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -66,7 +66,7 @@ def trace_end():
         print_drop_table()
 
 # called from perf, when it finds a correspoinding event
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
                    skbaddr, location, protocol):
         slocation = str(location)
         try:
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
index 9aa0a32972e8..4d21ef2d601d 100644
--- a/tools/perf/scripts/python/netdev-times.py
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -224,75 +224,75 @@ def trace_end():
                         (len(rx_skb_list), of_count_rx_skb_list)
 
 # called from perf, when it finds a correspoinding event
-def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
         if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
                 return
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
         all_event_list.append(event_info)
 
-def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
         if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
                 return
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
         all_event_list.append(event_info)
 
-def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
         if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
                 return
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
         all_event_list.append(event_info)
 
 def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
-                        irq, irq_name):
+                        callchain, irq, irq_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         irq, irq_name)
         all_event_list.append(event_info)
 
-def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
         all_event_list.append(event_info)
 
-def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         napi, dev_name)
         all_event_list.append(event_info)
 
-def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
                         skblen, dev_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, skblen, dev_name)
         all_event_list.append(event_info)
 
-def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
                         skblen, dev_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, skblen, dev_name)
         all_event_list.append(event_info)
 
-def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain,
                         skbaddr, skblen, dev_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, skblen, dev_name)
         all_event_list.append(event_info)
 
-def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain,
                         skbaddr, skblen, rc, dev_name):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, skblen, rc ,dev_name)
         all_event_list.append(event_info)
 
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
                         skbaddr, protocol, location):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, protocol, location)
         all_event_list.append(event_info)
 
-def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr)
         all_event_list.append(event_info)
 
-def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain,
         skbaddr, skblen):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
                         skbaddr, skblen)
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index 74d55ec08aed..de66cb3b72c9 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -369,93 +369,92 @@ def trace_end():
 
 def sched__sched_stat_runtime(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, runtime, vruntime):
+        common_callchain, comm, pid, runtime, vruntime):
         pass
 
 def sched__sched_stat_iowait(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, delay):
+        common_callchain, comm, pid, delay):
         pass
 
 def sched__sched_stat_sleep(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, delay):
+        common_callchain, comm, pid, delay):
         pass
 
 def sched__sched_stat_wait(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, delay):
+        common_callchain, comm, pid, delay):
         pass
 
 def sched__sched_process_fork(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        parent_comm, parent_pid, child_comm, child_pid):
+        common_callchain, parent_comm, parent_pid, child_comm, child_pid):
         pass
 
 def sched__sched_process_wait(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio):
+        common_callchain, comm, pid, prio):
         pass
 
 def sched__sched_process_exit(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio):
+        common_callchain, comm, pid, prio):
         pass
 
 def sched__sched_process_free(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio):
+        common_callchain, comm, pid, prio):
         pass
 
 def sched__sched_migrate_task(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio, orig_cpu,
+        common_callchain, comm, pid, prio, orig_cpu,
         dest_cpu):
         headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-                                common_pid, common_comm)
+                                common_pid, common_comm, common_callchain)
         parser.migrate(headers, pid, prio, orig_cpu, dest_cpu)
 
 def sched__sched_switch(event_name, context, common_cpu,
-        common_secs, common_nsecs, common_pid, common_comm,
+        common_secs, common_nsecs, common_pid, common_comm, common_callchain,
         prev_comm, prev_pid, prev_prio, prev_state,
         next_comm, next_pid, next_prio):
 
         headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-                                common_pid, common_comm)
+                                common_pid, common_comm, common_callchain)
         parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state,
                          next_comm, next_pid, next_prio)
 
 def sched__sched_wakeup_new(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio, success,
+        common_callchain, comm, pid, prio, success,
         target_cpu):
         headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-                                common_pid, common_comm)
+                                common_pid, common_comm, common_callchain)
         parser.wake_up(headers, comm, pid, success, target_cpu, 1)
 
 def sched__sched_wakeup(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio, success,
+        common_callchain, comm, pid, prio, success,
         target_cpu):
         headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-                                common_pid, common_comm)
+                                common_pid, common_comm, common_callchain)
         parser.wake_up(headers, comm, pid, success, target_cpu, 0)
 
 def sched__sched_wait_task(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid, prio):
+        common_callchain, comm, pid, prio):
         pass
 
 def sched__sched_kthread_stop_ret(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        ret):
+        common_callchain, ret):
         pass
 
 def sched__sched_kthread_stop(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        comm, pid):
+        common_callchain, comm, pid):
         pass
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-                common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
         pass
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index c9f3058b7dd4..61621b93affb 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -44,7 +44,7 @@ def trace_begin():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        id, args):
+        common_callchain, id, args):
         if for_comm is not None:
                 if common_comm != for_comm:
                         return
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index cf2054c529c9..daf314cc5dd3 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -38,7 +38,7 @@ def trace_end():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        id, args):
+        common_callchain, id, args):
 
         if (for_comm and common_comm != for_comm) or \
            (for_pid  and common_pid  != for_pid ):
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index 92b29381bd39..e66a7730aeb5 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -35,7 +35,7 @@ def trace_end():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
-        id, args):
+        common_callchain, id, args):
         if for_comm is not None:
                 if common_comm != for_comm:
                         return
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 630808cd7cc2..caaf37f079b1 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -10,6 +10,7 @@
 #include "machine.h"
 #include "symbol.h"
 #include "tests.h"
+#include "debug.h"
 
 static char *test_file(int size)
 {
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 465cdbc345cf..b8d8341b383e 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "parse-events.h"
 #include "tests.h"
+#include "debug.h"
 
 static int perf_evsel__roundtrip_cache_name_test(void)
 {
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 35d7fdb2328d..52162425c969 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,6 +1,7 @@
 #include <traceevent/event-parse.h>
 #include "evsel.h"
 #include "tests.h"
+#include "debug.h"
 
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
                                   int size, bool should_be_signed)
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index c505ef2af245..0785b64ffd6c 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -3,6 +3,7 @@
 #include "evsel.h"
 #include "thread_map.h"
 #include "tests.h"
+#include "debug.h"
 
 int test__syscall_open_tp_fields(void)
 {
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index deba66955f8c..5941927a4b7f 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -5,6 +5,7 @@
 #include <api/fs/fs.h>
 #include <api/fs/debugfs.h>
 #include "tests.h"
+#include "debug.h"
 #include <linux/hw_breakpoint.h>
 
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 905019f9b740..2c63ea658541 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -7,6 +7,7 @@
 #include "evlist.h"
 #include "header.h"
 #include "util.h"
+#include "debug.h"
 
 static int process_event(struct perf_evlist **pevlist, union perf_event *event)
 {
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 3b7cd4d32dcb..0372f6edca20 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -8,10 +8,9 @@
 #include "evsel.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "tsc.h"
 #include "tests.h"
 
-#include "../arch/x86/util/tsc.h"
-
 #define CHECK__(x) {                            \
         while ((x) < 0) {                       \
                 pr_debug(#x " failed!\n");      \
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 7ae8d17db3d9..ca292f9a4ae2 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -4,6 +4,7 @@
 #include "util.h"
 #include "event.h"
 #include "evsel.h"
+#include "debug.h"
 
 #include "tests.h"
 
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 2b2e0dbe114f..b028499dd3cf 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -2,6 +2,7 @@
 #include "machine.h"
 #include "thread.h"
 #include "map.h"
+#include "debug.h"
 
 int test__thread_mg_share(void)
 {
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 90122abd3721..40af0acb4fe9 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -479,7 +479,7 @@ print_entries:
 
                 if (h->ms.map == NULL && verbose > 1) {
                         __map_groups__fprintf_maps(h->thread->mg,
-                                                   MAP__FUNCTION, verbose, fp);
+                                                   MAP__FUNCTION, fp);
                         fprintf(fp, "%.10s end\n", graph_dotted_line);
                 }
         }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 48b6d3f50012..437ee09727e6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -626,7 +626,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
 {
-        if (!symbol_conf.use_callchain)
+        if (!symbol_conf.use_callchain || sample->callchain == NULL)
                 return 0;
         return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index ee370a7f2444..29d720cf5844 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,6 +7,7 @@
 
 #include "data.h"
 #include "util.h"
+#include "debug.h"
 
 static bool check_pipe(struct perf_data_file *file)
 {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 299b55586502..71d419362634 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,11 +16,11 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-static int _eprintf(int level, const char *fmt, va_list args)
+static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
         int ret = 0;
 
-        if (verbose >= level) {
+        if (var >= level) {
                 if (use_browser >= 1)
                         ui_helpline__vshow(fmt, args);
                 else
@@ -30,13 +30,13 @@ static int _eprintf(int level, const char *fmt, va_list args)
         return ret;
 }
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
         va_list args;
         int ret;
 
         va_start(args, fmt);
-        ret = _eprintf(level, fmt, args);
+        ret = _eprintf(level, var, fmt, args);
         va_end(args);
 
         return ret;
@@ -51,9 +51,9 @@ void pr_stat(const char *fmt, ...)
         va_list args;
 
         va_start(args, fmt);
-        _eprintf(1, fmt, args);
+        _eprintf(1, verbose, fmt, args);
         va_end(args);
-        eprintf(1, "\n");
+        eprintf(1, verbose, "\n");
 }
 
 int dump_printf(const char *fmt, ...)
@@ -105,3 +105,47 @@ void trace_event(union perf_event *event)
         }
         printf(".\n");
 }
+
+static struct debug_variable {
+        const char *name;
+        int *ptr;
+} debug_variables[] = {
+        { .name = "verbose", .ptr = &verbose },
+        { .name = NULL, }
+};
+
+int perf_debug_option(const char *str)
+{
+        struct debug_variable *var = &debug_variables[0];
+        char *vstr, *s = strdup(str);
+        int v = 1;
+
+        vstr = strchr(s, '=');
+        if (vstr)
+                *vstr++ = 0;
+
+        while (var->name) {
+                if (!strcmp(s, var->name))
+                        break;
+                var++;
+        }
+
+        if (!var->name) {
+                pr_err("Unknown debug variable name '%s'\n", s);
+                free(s);
+                return -1;
+        }
+
+        if (vstr) {
+                v = atoi(vstr);
+                /*
+                 * Allow only values in range (0, 10),
+                 * otherwise set 0.
+                 */
+                v = (v < 0) || (v > 10) ? 0 : v;
+        }
+
+        *var->ptr = v;
+        free(s);
+        return 0;
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 443694c36b03..89fb6b0f7ab2 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -11,6 +11,24 @@
 extern int verbose;
 extern bool quiet, dump_trace;
 
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+        eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+        eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+        eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+        eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+        eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -19,4 +37,8 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
 void pr_stat(const char *fmt, ...);
 
+int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+
+int perf_debug_option(const char *str);
+
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 819f10414f08..fc006fed8877 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -703,6 +703,7 @@ struct dso *dso__new(const char *name)
                 dso->data.fd = -1;
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
+                dso->is_64_bit = (sizeof(void *) == 8);
                 dso->loaded = 0;
                 dso->rel = 0;
                 dso->sorted_by_name = 0;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ad553ba257bf..c239e86541a3 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -90,6 +90,7 @@ struct dso {
         u8               annotate_warned:1;
         u8               short_name_allocated:1;
         u8               long_name_allocated:1;
+        u8               is_64_bit:1;
         u8               sorted_by_name;
         u8               loaded;
         u8               rel;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index d0281bdfa582..7e0e8ae568ec 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -603,7 +603,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
-        return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
+        const char *s;
+
+        if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
+                s = " exec";
+        else
+                s = "";
+
+        return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid);
 }
 
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
@@ -781,6 +788,7 @@ try_again:
                     cpumode == PERF_RECORD_MISC_USER &&
                     machine && mg != &machine->kmaps) {
                         mg = &machine->kmaps;
+                        load_map = true;
                         goto try_again;
                 }
         } else {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c51223ac25f4..814e954c1318 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -606,12 +606,17 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
         return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist,
-                               int idx, int prot, int mask, int fd)
+struct mmap_params {
+        int prot;
+        int mask;
+};
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
+                               struct mmap_params *mp, int fd)
 {
         evlist->mmap[idx].prev = 0;
-        evlist->mmap[idx].mask = mask;
-        evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+        evlist->mmap[idx].mask = mp->mask;
+        evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
                                       MAP_SHARED, fd, 0);
         if (evlist->mmap[idx].base == MAP_FAILED) {
                 pr_debug2("failed to mmap perf event ring buffer, error %d\n",
@@ -625,8 +630,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-                                       int prot, int mask, int cpu, int thread,
-                                       int *output)
+                                       struct mmap_params *mp, int cpu,
+                                       int thread, int *output)
 {
         struct perf_evsel *evsel;
 
@@ -635,8 +640,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
                 if (*output == -1) {
                         *output = fd;
-                        if (__perf_evlist__mmap(evlist, idx, prot, mask,
-                                                *output) < 0)
+                        if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
                                 return -1;
                 } else {
                         if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
@@ -651,8 +655,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
         return 0;
 }
 
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
-                                     int mask)
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
+                                     struct mmap_params *mp)
 {
         int cpu, thread;
         int nr_cpus = cpu_map__nr(evlist->cpus);
@@ -663,8 +667,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
                 int output = -1;
 
                 for (thread = 0; thread < nr_threads; thread++) {
-                        if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
-                                                        cpu, thread, &output))
+                        if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
+                                                        thread, &output))
                                 goto out_unmap;
                 }
         }
@@ -677,8 +681,8 @@ out_unmap:
         return -1;
 }
 
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
-                                        int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
+                                        struct mmap_params *mp)
 {
         int thread;
         int nr_threads = thread_map__nr(evlist->threads);
@@ -687,8 +691,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
         for (thread = 0; thread < nr_threads; thread++) {
                 int output = -1;
 
-                if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
-                                                thread, &output))
+                if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
+                                                &output))
                         goto out_unmap;
         }
 
@@ -793,7 +797,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         struct perf_evsel *evsel;
         const struct cpu_map *cpus = evlist->cpus;
         const struct thread_map *threads = evlist->threads;
-        int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+        struct mmap_params mp = {
+                .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+        };
 
         if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
                 return -ENOMEM;
@@ -804,7 +810,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         evlist->overwrite = overwrite;
         evlist->mmap_len = perf_evlist__mmap_size(pages);
         pr_debug("mmap size %zuB\n", evlist->mmap_len);
-        mask = evlist->mmap_len - page_size - 1;
+        mp.mask = evlist->mmap_len - page_size - 1;
 
         evlist__for_each(evlist, evsel) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -814,9 +820,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         }
 
         if (cpu_map__empty(cpus))
-                return perf_evlist__mmap_per_thread(evlist, prot, mask);
+                return perf_evlist__mmap_per_thread(evlist, &mp);
 
-        return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+        return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8606175fe1e8..90f58cdd0fb0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -623,7 +623,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                 attr->mmap_data = track;
         }
 
-        if (opts->call_graph_enabled)
+        if (opts->call_graph_enabled && !evsel->no_aux_samples)
                 perf_evsel__config_callgraph(evsel, opts);
 
         if (target__has_cpu(&opts->target))
@@ -637,7 +637,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
              target__has_cpu(&opts->target) || per_cpu))
                 perf_evsel__set_sample_bit(evsel, TIME);
 
-        if (opts->raw_samples) {
+        if (opts->raw_samples && !evsel->no_aux_samples) {
                 perf_evsel__set_sample_bit(evsel, TIME);
                 perf_evsel__set_sample_bit(evsel, RAW);
                 perf_evsel__set_sample_bit(evsel, CPU);
@@ -650,7 +650,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
         }
-        if (opts->branch_stack) {
+        if (opts->branch_stack && !evsel->no_aux_samples) {
                 perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
                 attr->branch_sample_type = opts->branch_stack;
         }
@@ -681,6 +681,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
                 !opts->initial_delay)
                 attr->enable_on_exec = 1;
+
+        if (evsel->immediate) {
+                attr->disabled = 0;
+                attr->enable_on_exec = 0;
+        }
 }
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -960,6 +965,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
         ret += PRINT_ATTR2(exclude_user, exclude_kernel);
         ret += PRINT_ATTR2(exclude_hv, exclude_idle);
         ret += PRINT_ATTR2(mmap, comm);
+        ret += PRINT_ATTR2(mmap2, comm_exec);
         ret += PRINT_ATTR2(freq, inherit_stat);
         ret += PRINT_ATTR2(enable_on_exec, task);
         ret += PRINT_ATTR2(watermark, precise_ip);
@@ -967,7 +973,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
         ret += PRINT_ATTR2(exclude_host, exclude_guest);
         ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
                             "excl.callchain_user", exclude_callchain_user);
-        ret += PRINT_ATTR_U32(mmap2);
 
         ret += PRINT_ATTR_U32(wakeup_events);
         ret += PRINT_ATTR_U32(wakeup_watermark);
@@ -1940,6 +1945,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
                 if_print(mmap);
                 if_print(mmap2);
                 if_print(comm);
+                if_print(comm_exec);
                 if_print(freq);
                 if_print(inherit_stat);
                 if_print(enable_on_exec);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a52e9a5bb2d0..d7f93ce0ebc1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,6 +83,8 @@ struct perf_evsel {
         int                     is_pos;
         bool                    supported;
         bool                    needs_swap;
+        bool                    no_aux_samples;
+        bool                    immediate;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 9844c31b7c2b..09e8e7aea7c6 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
         return (i >= ssize) ? (ssize - 1) : i;
 }
 
-int eprintf(int level,
-            const char *fmt, ...) __attribute__((format(printf, 2, 3)));
-
-#ifndef pr_fmt
-#define pr_fmt(fmt) fmt
-#endif
-
-#define pr_err(fmt, ...) \
-        eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warning(fmt, ...) \
-        eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) \
-        eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug(fmt, ...) \
-        eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debugN(n, fmt, ...) \
-        eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
-
 /*
  * This looks more complex than it should be. But we need to
  * get the type for the ~ right in round_down (it needs to be
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
new file mode 100644
index 000000000000..0b5a8cd2ee79
--- /dev/null
+++ b/tools/perf/util/kvm-stat.h
@@ -0,0 +1,140 @@
+#ifndef __PERF_KVM_STAT_H
+#define __PERF_KVM_STAT_H
+
+#include "../perf.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "session.h"
+#include "tool.h"
+#include "stat.h"
+
+struct event_key {
+        #define INVALID_KEY     (~0ULL)
+        u64 key;
+        int info;
+        struct exit_reasons_table *exit_reasons;
+};
+
+struct kvm_event_stats {
+        u64 time;
+        struct stats stats;
+};
+
+struct kvm_event {
+        struct list_head hash_entry;
+        struct rb_node rb;
+
+        struct event_key key;
+
+        struct kvm_event_stats total;
+
+        #define DEFAULT_VCPU_NUM 8
+        int max_vcpu;
+        struct kvm_event_stats *vcpu;
+};
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+
+struct kvm_event_key {
+        const char *name;
+        key_cmp_fun key;
+};
+
+struct perf_kvm_stat;
+
+struct child_event_ops {
+        void (*get_key)(struct perf_evsel *evsel,
+                        struct perf_sample *sample,
+                        struct event_key *key);
+        const char *name;
+};
+
+struct kvm_events_ops {
+        bool (*is_begin_event)(struct perf_evsel *evsel,
+                               struct perf_sample *sample,
+                               struct event_key *key);
+        bool (*is_end_event)(struct perf_evsel *evsel,
+                             struct perf_sample *sample, struct event_key *key);
+        struct child_event_ops *child_ops;
+        void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+                           char *decode);
+        const char *name;
+};
+
+struct exit_reasons_table {
+        unsigned long exit_code;
+        const char *reason;
+};
+
+#define EVENTS_BITS             12
+#define EVENTS_CACHE_SIZE       (1UL << EVENTS_BITS)
+
+struct perf_kvm_stat {
+        struct perf_tool    tool;
+        struct record_opts  opts;
+        struct perf_evlist  *evlist;
+        struct perf_session *session;
+
+        const char *file_name;
+        const char *report_event;
+        const char *sort_key;
+        int trace_vcpu;
+
+        struct exit_reasons_table *exit_reasons;
+        const char *exit_reasons_isa;
+
+        struct kvm_events_ops *events_ops;
+        key_cmp_fun compare;
+        struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+        u64 total_time;
+        u64 total_count;
+        u64 lost_events;
+        u64 duration;
+
+        const char *pid_str;
+        struct intlist *pid_list;
+
+        struct rb_root result;
+
+        int timerfd;
+        unsigned int display_time;
+        bool live;
+};
+
+struct kvm_reg_events_ops {
+        const char *name;
+        struct kvm_events_ops *ops;
+};
+
+void exit_event_get_key(struct perf_evsel *evsel,
+                        struct perf_sample *sample,
+                        struct event_key *key);
+bool exit_event_begin(struct perf_evsel *evsel,
+                      struct perf_sample *sample,
+                      struct event_key *key);
+bool exit_event_end(struct perf_evsel *evsel,
+                    struct perf_sample *sample,
+                    struct event_key *key);
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+                           struct event_key *key,
+                           char *decode);
+
+bool kvm_exit_event(struct perf_evsel *evsel);
+bool kvm_entry_event(struct perf_evsel *evsel);
+
+#define define_exit_reasons_table(name, symbols)        \
+        static struct exit_reasons_table name[] = {     \
+                symbols, { -1, NULL }                   \
+        }
+
+/*
+ * arch specific callbacks and data structures
+ */
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
+
+extern const char * const kvm_events_tp[];
+extern struct kvm_reg_events_ops kvm_reg_events_ops[];
+extern const char * const kvm_skip_events[];
+
+#endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e9b943acaa5e..93c8b6fbc799 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -34,7 +34,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
                 return -ENOMEM;
 
         if (pid != HOST_KERNEL_ID) {
-                struct thread *thread = machine__findnew_thread(machine, 0,
+                struct thread *thread = machine__findnew_thread(machine, -1,
                                                                 pid);
                 char comm[64];
 
@@ -272,6 +272,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
         return;
 }
 
+static void machine__update_thread_pid(struct machine *machine,
+                                       struct thread *th, pid_t pid)
+{
+        struct thread *leader;
+
+        if (pid == th->pid_ || pid == -1 || th->pid_ != -1)
+                return;
+
+        th->pid_ = pid;
+
+        if (th->pid_ == th->tid)
+                return;
+
+        leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+        if (!leader)
+                goto out_err;
+
+        if (!leader->mg)
+                leader->mg = map_groups__new();
+
+        if (!leader->mg)
+                goto out_err;
+
+        if (th->mg == leader->mg)
+                return;
+
+        if (th->mg) {
+                /*
+                 * Maps are created from MMAP events which provide the pid and
+                 * tid.  Consequently there never should be any maps on a thread
+                 * with an unknown pid.  Just print an error if there are.
+                 */
+                if (!map_groups__empty(th->mg))
+                        pr_err("Discarding thread maps for %d:%d\n",
+                               th->pid_, th->tid);
+                map_groups__delete(th->mg);
+        }
+
+        th->mg = map_groups__get(leader->mg);
+
+        return;
+
+out_err:
+        pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+}
+
 static struct thread *__machine__findnew_thread(struct machine *machine,
                                                 pid_t pid, pid_t tid,
                                                 bool create)
@@ -285,10 +331,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
          * so most of the time we dont have to look up
          * the full rbtree:
          */
-        if (machine->last_match && machine->last_match->tid == tid) {
-                if (pid && pid != machine->last_match->pid_)
-                        machine->last_match->pid_ = pid;
-                return machine->last_match;
+        th = machine->last_match;
+        if (th && th->tid == tid) {
+                machine__update_thread_pid(machine, th, pid);
+                return th;
         }
 
         while (*p != NULL) {
@@ -297,8 +343,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 
                 if (th->tid == tid) {
                         machine->last_match = th;
-                        if (pid && pid != th->pid_)
-                                th->pid_ = pid;
+                        machine__update_thread_pid(machine, th, pid);
                         return th;
                 }
 
@@ -325,8 +370,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
                  * within thread__init_map_groups to find the thread
                  * leader and that would screwed the rb tree.
                  */
-                if (thread__init_map_groups(th, machine))
+                if (thread__init_map_groups(th, machine)) {
+                        thread__delete(th);
                         return NULL;
+                }
         }
 
         return th;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 25c571f4cba6..845f627e45f4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -12,6 +12,7 @@
 #include "vdso.h"
 #include "build-id.h"
 #include "util.h"
+#include "debug.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -454,6 +455,20 @@ void map_groups__exit(struct map_groups *mg)
         }
 }
 
+bool map_groups__empty(struct map_groups *mg)
+{
+        int i;
+
+        for (i = 0; i < MAP__NR_TYPES; ++i) {
+                if (maps__first(&mg->maps[i]))
+                        return false;
+                if (!list_empty(&mg->removed_maps[i]))
+                        return false;
+        }
+
+        return true;
+}
+
 struct map_groups *map_groups__new(void)
 {
         struct map_groups *mg = malloc(sizeof(*mg));
@@ -554,8 +569,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
         return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-                                  enum map_type type, int verbose, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+                                  FILE *fp)
 {
         size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
         struct rb_node *nd;
@@ -573,17 +588,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg,
         return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
+static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
 {
         size_t printed = 0, i;
         for (i = 0; i < MAP__NR_TYPES; ++i)
-                printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
+                printed += __map_groups__fprintf_maps(mg, i, fp);
         return printed;
 }
 
 static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-                                                 enum map_type type,
-                                                 int verbose, FILE *fp)
+                                                 enum map_type type, FILE *fp)
 {
         struct map *pos;
         size_t printed = 0;
@@ -600,23 +614,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 }
 
 static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-                                               int verbose, FILE *fp)
+                                               FILE *fp)
 {
         size_t printed = 0, i;
         for (i = 0; i < MAP__NR_TYPES; ++i)
-                printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
+                printed += __map_groups__fprintf_removed_maps(mg, i, fp);
         return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
-        size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
+        size_t printed = map_groups__fprintf_maps(mg, fp);
         printed += fprintf(fp, "Removed maps:\n");
-        return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
+        return printed + map_groups__fprintf_removed_maps(mg, fp);
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-                                   int verbose, FILE *fp)
+                                   FILE *fp)
 {
         struct rb_root *root = &mg->maps[map->type];
         struct rb_node *next = rb_first(root);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7758c72522ef..22d13a219590 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -66,6 +66,7 @@ struct map_groups {
 
 struct map_groups *map_groups__new(void);
 void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
@@ -141,8 +142,8 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-                                  enum map_type type, int verbose, FILE *fp);
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+                                  FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
 void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
@@ -152,8 +153,7 @@ void map_groups__init(struct map_groups *mg);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
                       struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
                                      u64 addr);
@@ -210,7 +210,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-                                   int verbose, FILE *fp);
+                                   FILE *fp);
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
                                      enum map_type type, const char *name);
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index d8dac8ac5f37..b59ba858e73d 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -98,6 +98,7 @@ struct option {
         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 )
@@ -131,6 +132,10 @@ struct option {
         { .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[].
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 98e304766416..dca9145d704c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -26,7 +26,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <unistd.h>
-#include <getopt.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index daa17aeb6c63..a126e6cc6e73 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -6,6 +6,7 @@
 
 #include "util.h"
 #include "pstack.h"
+#include "debug.h"
 #include <linux/kernel.h>
 #include <stdlib.h>
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 122669c18ff4..12aa9b0d0ba1 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,12 +14,12 @@
  */
 int verbose;
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
         va_list args;
         int ret = 0;
 
-        if (verbose >= level) {
+        if (var >= level) {
                 va_start(args, fmt);
                 ret = vfprintf(stderr, fmt, args);
                 va_end(args);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 049e0a09ccd3..165723152cfb 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -69,15 +69,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel)
         evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
 }
 
+static void perf_probe_comm_exec(struct perf_evsel *evsel)
+{
+        evsel->attr.comm_exec = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
         return perf_probe_api(perf_probe_sample_identifier);
 }
 
+static bool perf_can_comm_exec(void)
+{
+        return perf_probe_api(perf_probe_comm_exec);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
         struct perf_evsel *evsel;
         bool use_sample_identifier = false;
+        bool use_comm_exec;
 
         /*
          * Set the evsel leader links before we configure attributes,
@@ -89,8 +100,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
         if (evlist->cpus->map[0] < 0)
                 opts->no_inherit = true;
 
-        evlist__for_each(evlist, evsel)
+        use_comm_exec = perf_can_comm_exec();
+
+        evlist__for_each(evlist, evsel) {
                 perf_evsel__config(evsel, opts);
+                if (!evsel->idx && use_comm_exec)
+                        evsel->attr.comm_exec = 1;
+        }
 
         if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index af7da565a750..b2dba9c0a3a1 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,6 +34,7 @@
 #include "../event.h"
 #include "../trace-event.h"
 #include "../evsel.h"
+#include "../debug.h"
 
 void boot_Perf__Trace__Context(pTHX_ CV *cv);
 void boot_DynaLoader(pTHX_ CV *cv);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e55b65a65558..cbce2545da45 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -27,11 +27,13 @@
 #include <errno.h>
 
 #include "../../perf.h"
+#include "../debug.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
 #include "../trace-event.h"
+#include "../machine.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -50,10 +52,14 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
         PyErr_Print();
         Py_FatalError("problem in Python trace event handler");
+        // Py_FatalError does not return
+        // but we have to make the compiler happy
+        abort();
 }
 
 /*
@@ -97,6 +103,7 @@ static void define_value(enum print_arg_type field_type,
                 retval = PyObject_CallObject(handler, t);
                 if (retval == NULL)
                         handler_call_die(handler_name);
+                Py_DECREF(retval);
         }
 
         Py_DECREF(t);
@@ -143,6 +150,7 @@ static void define_field(enum print_arg_type field_type,
                 retval = PyObject_CallObject(handler, t);
                 if (retval == NULL)
                         handler_call_die(handler_name);
+                Py_DECREF(retval);
         }
 
         Py_DECREF(t);
@@ -272,12 +280,90 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
         return obj;
 }
 
+
+static PyObject *python_process_callchain(struct perf_sample *sample,
+                                         struct perf_evsel *evsel,
+                                         struct addr_location *al)
+{
+        PyObject *pylist;
+
+        pylist = PyList_New(0);
+        if (!pylist)
+                Py_FatalError("couldn't create Python list");
+
+        if (!symbol_conf.use_callchain || !sample->callchain)
+                goto exit;
+
+        if (machine__resolve_callchain(al->machine, evsel, al->thread,
+                                           sample, NULL, NULL,
+                                           PERF_MAX_STACK_DEPTH) != 0) {
+                pr_err("Failed to resolve callchain. Skipping\n");
+                goto exit;
+        }
+        callchain_cursor_commit(&callchain_cursor);
+
+
+        while (1) {
+                PyObject *pyelem;
+                struct callchain_cursor_node *node;
+                node = callchain_cursor_current(&callchain_cursor);
+                if (!node)
+                        break;
+
+                pyelem = PyDict_New();
+                if (!pyelem)
+                        Py_FatalError("couldn't create Python dictionary");
+
+
+                pydict_set_item_string_decref(pyelem, "ip",
+                                PyLong_FromUnsignedLongLong(node->ip));
+
+                if (node->sym) {
+                        PyObject *pysym  = PyDict_New();
+                        if (!pysym)
+                                Py_FatalError("couldn't create Python dictionary");
+                        pydict_set_item_string_decref(pysym, "start",
+                                        PyLong_FromUnsignedLongLong(node->sym->start));
+                        pydict_set_item_string_decref(pysym, "end",
+                                        PyLong_FromUnsignedLongLong(node->sym->end));
+                        pydict_set_item_string_decref(pysym, "binding",
+                                        PyInt_FromLong(node->sym->binding));
+                        pydict_set_item_string_decref(pysym, "name",
+                                        PyString_FromStringAndSize(node->sym->name,
+                                                        node->sym->namelen));
+                        pydict_set_item_string_decref(pyelem, "sym", pysym);
+                }
+
+                if (node->map) {
+                        struct map *map = node->map;
+                        const char *dsoname = "[unknown]";
+                        if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+                                if (symbol_conf.show_kernel_path && map->dso->long_name)
+                                        dsoname = map->dso->long_name;
+                                else if (map->dso->name)
+                                        dsoname = map->dso->name;
+                        }
+                        pydict_set_item_string_decref(pyelem, "dso",
+                                        PyString_FromString(dsoname));
+                }
+
+                callchain_cursor_advance(&callchain_cursor);
+                PyList_Append(pylist, pyelem);
+                Py_DECREF(pyelem);
+        }
+
+exit:
+        return pylist;
+}
+
+
 static void python_process_tracepoint(struct perf_sample *sample,
                                       struct perf_evsel *evsel,
                                       struct thread *thread,
                                       struct addr_location *al)
 {
-        PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
+        PyObject *handler, *retval, *context, *t, *obj, *callchain;
+        PyObject *dict = NULL;
         static char handler_name[256];
         struct format_field *field;
         unsigned long s, ns;
@@ -320,18 +406,23 @@ static void python_process_tracepoint(struct perf_sample *sample,
         PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
         PyTuple_SetItem(t, n++, context);
 
+        /* ip unwinding */
+        callchain = python_process_callchain(sample, evsel, al);
+
         if (handler) {
                 PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(s));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
                 PyTuple_SetItem(t, n++, PyString_FromString(comm));
+                PyTuple_SetItem(t, n++, callchain);
         } else {
                 pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
                 pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
                 pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
                 pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
                 pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+                pydict_set_item_string_decref(dict, "common_callchain", callchain);
         }
         for (field = event->format.fields; field; field = field->next) {
                 if (field->flags & FIELD_IS_STRING) {
@@ -351,6 +442,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
                         pydict_set_item_string_decref(dict, field->name, obj);
 
         }
+
         if (!handler)
                 PyTuple_SetItem(t, n++, dict);
 
@@ -361,6 +453,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
                 retval = PyObject_CallObject(handler, t);
                 if (retval == NULL)
                         handler_call_die(handler_name);
+                Py_DECREF(retval);
         } else {
                 handler = PyDict_GetItemString(main_dict, "trace_unhandled");
                 if (handler && PyCallable_Check(handler)) {
@@ -368,6 +461,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
                         retval = PyObject_CallObject(handler, t);
                         if (retval == NULL)
                                 handler_call_die("trace_unhandled");
+                        Py_DECREF(retval);
                 }
                 Py_DECREF(dict);
         }
@@ -380,7 +474,7 @@ static void python_process_general_event(struct perf_sample *sample,
                                          struct thread *thread,
                                          struct addr_location *al)
 {
-        PyObject *handler, *retval, *t, *dict;
+        PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
         static char handler_name[64];
         unsigned n = 0;
 
@@ -396,6 +490,10 @@ static void python_process_general_event(struct perf_sample *sample,
         if (!dict)
                 Py_FatalError("couldn't create Python dictionary");
 
+        dict_sample = PyDict_New();
+        if (!dict_sample)
+                Py_FatalError("couldn't create Python dictionary");
+
         snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
         handler = PyDict_GetItemString(main_dict, handler_name);
@@ -405,8 +503,21 @@ static void python_process_general_event(struct perf_sample *sample,
         pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
         pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
                         (const char *)&evsel->attr, sizeof(evsel->attr)));
-        pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
-                        (const char *)sample, sizeof(*sample)));
+
+        pydict_set_item_string_decref(dict_sample, "pid",
+                        PyInt_FromLong(sample->pid));
+        pydict_set_item_string_decref(dict_sample, "tid",
+                        PyInt_FromLong(sample->tid));
+        pydict_set_item_string_decref(dict_sample, "cpu",
+                        PyInt_FromLong(sample->cpu));
+        pydict_set_item_string_decref(dict_sample, "ip",
+                        PyLong_FromUnsignedLongLong(sample->ip));
+        pydict_set_item_string_decref(dict_sample, "time",
+                        PyLong_FromUnsignedLongLong(sample->time));
+        pydict_set_item_string_decref(dict_sample, "period",
+                        PyLong_FromUnsignedLongLong(sample->period));
+        pydict_set_item_string_decref(dict, "sample", dict_sample);
+
         pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
                         (const char *)sample->raw_data, sample->raw_size));
         pydict_set_item_string_decref(dict, "comm",
@@ -420,6 +531,10 @@ static void python_process_general_event(struct perf_sample *sample,
                         PyString_FromString(al->sym->name));
         }
 
+        /* ip unwinding */
+        callchain = python_process_callchain(sample, evsel, al);
+        pydict_set_item_string_decref(dict, "callchain", callchain);
+
         PyTuple_SetItem(t, n++, dict);
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
@@ -427,6 +542,7 @@ static void python_process_general_event(struct perf_sample *sample,
         retval = PyObject_CallObject(handler, t);
         if (retval == NULL)
                 handler_call_die(handler_name);
+        Py_DECREF(retval);
 exit:
         Py_DECREF(dict);
         Py_DECREF(t);
@@ -548,8 +664,7 @@ static int python_stop_script(void)
         retval = PyObject_CallObject(handler, NULL);
         if (retval == NULL)
                 handler_call_die("trace_end");
-        else
-                Py_DECREF(retval);
+        Py_DECREF(retval);
 out:
         Py_XDECREF(main_dict);
         Py_XDECREF(main_module);
@@ -616,6 +731,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
                 fprintf(ofp, "common_nsecs, ");
                 fprintf(ofp, "common_pid, ");
                 fprintf(ofp, "common_comm,\n\t");
+                fprintf(ofp, "common_callchain, ");
 
                 not_first = 0;
                 count = 0;
@@ -659,7 +775,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
                                 fprintf(ofp, "%%u");
                 }
 
-                fprintf(ofp, "\\n\" %% \\\n\t\t(");
+                fprintf(ofp, "\" %% \\\n\t\t(");
 
                 not_first = 0;
                 count = 0;
@@ -695,7 +811,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
                                 fprintf(ofp, "%s", f->name);
                 }
 
-                fprintf(ofp, "),\n\n");
+                fprintf(ofp, ")\n\n");
+
+                fprintf(ofp, "\t\tfor node in common_callchain:");
+                fprintf(ofp, "\n\t\t\tif 'sym' in node:");
+                fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+                fprintf(ofp, "\n\t\t\telse:");
+                fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
+                fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+
         }
 
         fprintf(ofp, "def trace_unhandled(event_name, context, "
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64a186edc7be..eac14ce0ae8d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1083,13 +1083,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-        return machine__findnew_thread(&session->machines.host, 0, pid);
+        return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, 0);
+        struct thread *thread;
 
+        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;
@@ -1296,8 +1297,10 @@ int __perf_session__process_events(struct perf_session *session,
         ui_progress__init(&prog, file_size, "Processing events...");
 
         mmap_size = MMAP_SIZE;
-        if (mmap_size > file_size)
+        if (mmap_size > file_size) {
                 mmap_size = file_size;
+                session->one_mmap = true;
+        }
 
         memset(mmaps, 0, sizeof(mmaps));
 
@@ -1319,6 +1322,10 @@ remap:
         mmaps[map_idx] = buf;
         map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
         file_pos = file_offset + head;
+        if (session->one_mmap) {
+                session->one_mmap_addr = buf;
+                session->one_mmap_offset = file_offset;
+        }
 
 more:
         event = fetch_mmaped_event(session, head, mmap_size, buf);
@@ -1364,6 +1371,7 @@ out_err:
         ui_progress__finish();
         perf_session__warn_about_errors(session, tool);
         perf_session_free_sample_buffers(session);
+        session->one_mmap = false;
         return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3140f8ae6148..0321013bd9fd 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -36,6 +36,9 @@ struct perf_session {
         struct trace_event      tevent;
         struct events_stats     stats;
         bool                    repipe;
+        bool                    one_mmap;
+        void                    *one_mmap_addr;
+        u64                     one_mmap_offset;
         struct ordered_samples  ordered_samples;
         struct perf_data_file   *file;
 };
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6864661a79dd..cef8f426356e 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -49,7 +49,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 
 static inline int elf_sym__is_function(const GElf_Sym *sym)
 {
-        return elf_sym__type(sym) == STT_FUNC &&
+        return (elf_sym__type(sym) == STT_FUNC ||
+                elf_sym__type(sym) == STT_GNU_IFUNC) &&
                sym->st_name != 0 &&
                sym->st_shndx != SHN_UNDEF;
 }
@@ -598,6 +599,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
                         goto out_elf_end;
         }
 
+        ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
         ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
                         NULL);
         if (ss->symshdr.sh_type != SHT_SYMTAB)
@@ -698,6 +701,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
         bool remap_kernel = false, adjust_kernel_syms = false;
 
         dso->symtab_type = syms_ss->type;
+        dso->is_64_bit = syms_ss->is_64_bit;
         dso->rel = syms_ss->ehdr.e_type == ET_REL;
 
         /*
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index bd15f490d04f..101f55d407d0 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,6 +288,23 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
         return 0;
 }
 
+static int fd__is_64_bit(int fd)
+{
+        u8 e_ident[EI_NIDENT];
+
+        if (lseek(fd, 0, SEEK_SET))
+                return -1;
+
+        if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident))
+                return -1;
+
+        if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+            e_ident[EI_VERSION] != EV_CURRENT)
+                return -1;
+
+        return e_ident[EI_CLASS] == ELFCLASS64;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
                   struct symsrc *ss,
                   struct symsrc *runtime_ss __maybe_unused,
@@ -295,6 +312,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
                   int kmodule __maybe_unused)
 {
         unsigned char *build_id[BUILD_ID_SIZE];
+        int ret;
+
+        ret = fd__is_64_bit(ss->fd);
+        if (ret >= 0)
+                dso->is_64_bit = ret;
 
         if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
                 dso__set_build_id(dso, build_id);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 2e6a2e219eb9..eb06746b06b2 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -342,6 +342,16 @@ static struct symbol *symbols__first(struct rb_root *symbols)
         return NULL;
 }
 
+static struct symbol *symbols__next(struct symbol *sym)
+{
+        struct rb_node *n = rb_next(&sym->rb_node);
+
+        if (n)
+                return rb_entry(n, struct symbol, rb_node);
+
+        return NULL;
+}
+
 struct symbol_name_rb_node {
         struct rb_node  rb_node;
         struct symbol   sym;
@@ -412,11 +422,16 @@ struct symbol *dso__find_symbol(struct dso *dso,
         return symbols__find(&dso->symbols[type], addr);
 }
 
-static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
         return symbols__first(&dso->symbols[type]);
 }
 
+struct symbol *dso__next_symbol(struct symbol *sym)
+{
+        return symbols__next(sym);
+}
+
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name)
 {
@@ -1065,6 +1080,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
                               &is_64_bit);
         if (err)
                 goto out_err;
+        dso->is_64_bit = is_64_bit;
 
         if (list_empty(&md.maps)) {
                 err = -EINVAL;
@@ -1663,6 +1679,7 @@ do_kallsyms:
         free(kallsyms_allocated_filename);
 
         if (err > 0 && !dso__is_kcore(dso)) {
+                dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
                 dso__set_long_name(dso, "[kernel.kallsyms]", false);
                 map__fixup_start(map);
                 map__fixup_end(map);
@@ -1710,6 +1727,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
         if (err > 0)
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
         if (err > 0 && !dso__is_kcore(dso)) {
+                dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
                 machine__mmap_name(machine, path, sizeof(path));
                 dso__set_long_name(dso, strdup(path), true);
                 map__fixup_start(map);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index a81877b1dee0..ee2d3ccd3ad1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -216,6 +216,7 @@ struct symsrc {
         GElf_Shdr dynshdr;
 
         bool adjust_symbols;
+        bool is_64_bit;
 #endif
 };
 
@@ -239,6 +240,9 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name);
 
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__next_symbol(struct symbol *sym);
+
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2fde0d5e40b5..9692c06a9e21 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -13,7 +13,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
         struct thread *leader;
         pid_t pid = thread->pid_;
 
-        if (pid == thread->tid) {
+        if (pid == thread->tid || pid == -1) {
                 thread->mg = map_groups__new();
         } else {
                 leader = machine__findnew_thread(machine, pid, pid);
@@ -60,8 +60,10 @@ void thread__delete(struct thread *thread)
 {
         struct comm *comm, *tmp;
 
-        map_groups__put(thread->mg);
-        thread->mg = NULL;
+        if (thread->mg) {
+                map_groups__put(thread->mg);
+                thread->mg = NULL;
+        }
         list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
                 list_del(&comm->list);
                 comm__free(comm);
@@ -127,12 +129,12 @@ int thread__comm_len(struct thread *thread)
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
         return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
-               map_groups__fprintf(thread->mg, verbose, fp);
+               map_groups__fprintf(thread->mg, fp);
 }
 
 void thread__insert_map(struct thread *thread, struct map *map)
 {
-        map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+        map_groups__fixup_overlappings(thread->mg, map, stderr);
         map_groups__insert(thread->mg, map);
 }
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c3bba883f5c3..eb72716017ac 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -40,6 +40,7 @@
 #include "trace-event.h"
 #include <api/fs/debugfs.h>
 #include "evsel.h"
+#include "debug.h"
 
 #define VERSION "0.5"
 
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index e113e180c48f..54d9e9b548a8 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -22,7 +22,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <getopt.h>
 #include <stdarg.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -36,6 +35,7 @@
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
+#include "debug.h"
 
 static int input_fd;
 
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
new file mode 100644
index 000000000000..ef4749836ce9
--- /dev/null
+++ b/tools/perf/util/tsc.c
@@ -0,0 +1,25 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include "tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
+{
+        u64 t, quot, rem;
+
+        t = ns - tc->time_zero;
+        quot = t / tc->time_mult;
+        rem  = t % tc->time_mult;
+        return (quot << tc->time_shift) +
+               (rem << tc->time_shift) / tc->time_mult;
+}
+
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
+{
+        u64 quot, rem;
+
+        quot = cyc >> tc->time_shift;
+        rem  = cyc & ((1 << tc->time_shift) - 1);
+        return tc->time_zero + quot * tc->time_mult +
+               ((rem * tc->time_mult) >> tc->time_shift);
+}
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
new file mode 100644
index 000000000000..4eca84887c8a
--- /dev/null
+++ b/tools/perf/util/tsc.h
@@ -0,0 +1,11 @@
+#ifndef __PERF_TSC_H
+#define __PERF_TSC_H
+
+#include <linux/types.h>
+
+#include "../arch/x86/util/tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+
+#endif
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5ec80a575b50..7419768c38b1 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -3,6 +3,7 @@
 #include <elfutils/libdwfl.h>
 #include <inttypes.h>
 #include <errno.h>
+#include "debug.h"
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 25578b98f5c5..92b56db52471 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -30,6 +30,7 @@
 #include "unwind.h"
 #include "symbol.h"
 #include "util.h"
+#include "debug.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e4132aeeb780..e52e7461911b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,6 @@
 #include "../perf.h"
 #include "util.h"
+#include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0ddb3b8a89ec..290582452da3 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,6 +12,7 @@
 #include "util.h"
 #include "symbol.h"
 #include "linux/string.h"
+#include "debug.h"
 
 static bool vdso_found;
 static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";