113 files changed, 7241 insertions, 1762 deletions

diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 5b3123d5721f..fdfceee0ffd0 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -3,17 +3,17 @@ perf-diff(1)
 
 NAME
 ----
-perf-diff - Read two perf.data files and display the differential profile
+perf-diff - Read perf.data files and display the differential profile
 
 SYNOPSIS
 --------
 [verse]
-'perf diff' [oldfile] [newfile]
+'perf diff' [baseline file] [data file1] [[data file2] ... ]
 
 DESCRIPTION
 -----------
-This command displays the performance difference amongst two perf.data files
-captured via perf record.
+This command displays the performance difference amongst two or more perf.data
+files captured via perf record.
 
 If no parameters are passed it will assume perf.data.old and perf.data.
 
@@ -75,8 +75,6 @@ OPTIONS
 -c::
 --compute::
         Differential computation selection - delta,ratio,wdiff (default is delta).
-        If '+' is specified as a first character, the output is sorted based
-        on the computation results.
         See COMPARISON METHODS section for more info.
 
 -p::
@@ -87,6 +85,63 @@ OPTIONS
 --formula::
         Show formula for given computation.
 
+-o::
+--order::
+       Specify compute sorting column number.
+
+COMPARISON
+----------
+The comparison is governed by the baseline file. The baseline perf.data
+file is iterated for samples. All other perf.data files specified on
+the command line are searched for the baseline sample pair. If the pair
+is found, specified computation is made and result is displayed.
+
+All samples from non-baseline perf.data files, that do not match any
+baseline entry, are displayed with empty space within baseline column
+and possible computation results (delta) in their related column.
+
+Example files samples:
+- file A with samples f1, f2, f3, f4,    f6
+- file B with samples     f2,     f4, f5
+- file C with samples f1, f2,         f5
+
+Example output:
+  x - computation takes place for pair
+  b - baseline sample percentage
+
+- perf diff A B C
+
+  baseline/A compute/B compute/C  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b                               f3
+  b          x                    f4
+  b                               f6
+             x         x          f5
+
+- perf diff B A C
+
+  baseline/B compute/A compute/C  samples
+  ---------------------------------------
+  b          x         x          f2
+  b          x                    f4
+  b                    x          f5
+             x         x          f1
+             x                    f3
+             x                    f6
+
+- perf diff C B A
+
+  baseline/C compute/B compute/A  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b          x                    f5
+                       x          f3
+             x         x          f4
+                       x          f6
+
 COMPARISON METHODS
 ------------------
 delta
@@ -96,7 +151,7 @@ If specified the 'Delta' column is displayed with value 'd' computed as:
   d = A->period_percent - B->period_percent
 
 with:
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period_percent being the % of the hist entry period value within
@@ -109,24 +164,26 @@ If specified the 'Ratio' column is displayed with value 'r' computed as:
   r = A->period / B->period
 
 with:
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period being the hist entry period value
 
-wdiff
-~~~~~
+wdiff:WEIGHT-B,WEIGHT-A
+~~~~~~~~~~~~~~~~~~~~~~~
 If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
    d = B->period * WEIGHT-A - A->period * WEIGHT-B
 
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period being the hist entry period value
 
   - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
     behind ':' separator like '-c wdiff:1,2'.
+    - WIEGHT-A being the weight of the data file
+    - WIEGHT-B being the weight of the baseline data file
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 326f2cb333cb..ac84db2d2334 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -13,6 +13,7 @@ SYNOPSIS
         {top|record|report|diff|buildid-list}
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
         | --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
+'perf kvm stat [record|report|live] [<options>]
 
 DESCRIPTION
 -----------
@@ -50,6 +51,10 @@ There are a couple of variants of perf kvm:
   'perf kvm stat report' reports statistical data which includes events
   handled time, samples, and so on.
 
+  'perf kvm stat live' reports statistical data in a live mode (similar to
+  record + report but with statistical data updated live at a given display
+  rate).
+
 OPTIONS
 -------
 -i::
@@ -85,13 +90,50 @@ STAT REPORT OPTIONS
 --vcpu=<value>::
        analyze events which occures on this vcpu. (default: all vcpus)
 
---events=<value>::
-       events to be analyzed. Possible values: vmexit, mmio, ioport.
+--event=<value>::
+       event to be analyzed. Possible values: vmexit, mmio, ioport.
        (default: vmexit)
 -k::
 --key=<value>::
        Sorting key. Possible values: sample (default, sort by samples
        number), time (sort by average time).
+-p::
+--pid=::
+    Analyze events only for given process ID(s) (comma separated list).
+
+STAT LIVE OPTIONS
+-----------------
+-d::
+--display::
+        Time in seconds between display updates
+
+-m::
+--mmap-pages=::
+    Number of mmap data pages. Must be a power of two.
+
+-a::
+--all-cpus::
+        System-wide collection from all CPUs.
+
+-p::
+--pid=::
+    Analyze events only for given process ID(s) (comma separated list).
+
+--vcpu=<value>::
+       analyze events which occures on this vcpu. (default: all vcpus)
+
+
+--event=<value>::
+       event to be analyzed. Possible values: vmexit, mmio, ioport.
+       (default: vmexit)
+
+-k::
+--key=<value>::
+       Sorting key. Possible values: sample (default, sort by samples
+       number), time (sort by average time).
+
+--duration=<value>::
+       Show events other than HLT that take longer than duration usecs.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index d1e39dc8c810..6fce6a622206 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [hw|sw|cache|tracepoint|event_glob]
+'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
@@ -29,6 +29,8 @@ counted. The following modifiers exist:
  G - guest counting (in KVM guests)
  H - host counting (not in KVM guests)
  p - precise level
+ S - read sample value (PERF_SAMPLE_READ)
+ D - pin the event to the PMU
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
@@ -104,6 +106,8 @@ To limit the list use:
   'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
   block, etc.
 
+. 'pmu' to print the kernel supplied PMU events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 66dab7410c1d..2b8097ee39d8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -115,7 +115,7 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min[,limit],order]::
+-g [type,min[,limit],order[,key]]::
 --call-graph::
         Display call chains using type, min percent threshold, optional print
         limit and order.
@@ -129,12 +129,21 @@ OPTIONS
         - callee: callee based call graph.
         - caller: inverted caller based call graph.
 
-        Default: fractal,0.5,callee.
+        key can be:
+        - function: compare on functions
+        - address: compare on individual code addresses
+
+        Default: fractal,0.5,callee,function.
 
 -G::
 --inverted::
         alias for inverted caller based call graph.
 
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
 --pretty=<key>::
         Pretty printing style.  key: normal, raw
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 2fe87fb558f0..73c9759005a3 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -132,6 +132,11 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+-D msecs::
+--initial-delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 7fdd1909e376..58d6598a9686 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -155,6 +155,11 @@ Default is to monitor all CPUS.
 
         Default: fractal,0.5,callee.
 
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
 --percent-limit::
         Do not show entries which have an overhead under that percent.
         (Default: 0).
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 68718ccdd178..daccd2c0a48f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -23,25 +23,45 @@ analysis phases.
 OPTIONS
 -------
 
+-a::
 --all-cpus::
         System-wide collection from all CPUs.
 
+-e::
+--expr::
+        List of events to show, currently only syscall names.
+        Prefixing with ! shows all syscalls but the ones specified.  You may
+        need to escape it.
+
+-o::
+--output=::
+        Output file name.
+
 -p::
 --pid=::
         Record events on existing process ID (comma separated list).
 
+-t::
 --tid=::
         Record events on existing thread ID (comma separated list).
 
+-u::
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+-v::
+--verbose=::
+        Verbosity level.
+
+-i::
 --no-inherit::
         Child tasks do not inherit counters.
 
+-m::
 --mmap-pages=::
         Number of mmap data pages. Must be a power of two.
 
+-C::
 --cpu::
 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
@@ -54,6 +74,10 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --sched:
         Accrue thread runtime and provide a summary at the end of the session.
 
+-i
+--input
+        Process events from a given perf data file.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 641fccddb249..3a0ff7fb71b6 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -124,7 +124,7 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(objtree)/lib/lk/
+  LK_PATH=$(OUTPUT)/../lib/lk/
 else
   LK_PATH=$(OUTPUT)
 endif
@@ -281,7 +281,7 @@ LIB_H += util/cpumap.h
 LIB_H += util/top.h
 LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
-LIB_H += $(TRACE_EVENT_DIR)event-parse.h
+LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h
 LIB_H += util/target.h
 LIB_H += util/rblist.h
 LIB_H += util/intlist.h
@@ -360,6 +360,7 @@ LIB_OBJS += $(OUTPUT)util/rblist.o
 LIB_OBJS += $(OUTPUT)util/intlist.o
 LIB_OBJS += $(OUTPUT)util/vdso.o
 LIB_OBJS += $(OUTPUT)util/stat.o
+LIB_OBJS += $(OUTPUT)util/record.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -389,6 +390,12 @@ LIB_OBJS += $(OUTPUT)tests/bp_signal.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
 LIB_OBJS += $(OUTPUT)tests/task-exit.o
 LIB_OBJS += $(OUTPUT)tests/sw-clock.o
+ifeq ($(ARCH),x86)
+LIB_OBJS += $(OUTPUT)tests/perf-time-to-tsc.o
+endif
+LIB_OBJS += $(OUTPUT)tests/code-reading.o
+LIB_OBJS += $(OUTPUT)tests/sample-parsing.o
+LIB_OBJS += $(OUTPUT)tests/parse-no-sample-id-all.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -459,6 +466,7 @@ endif # NO_LIBELF
 ifndef NO_LIBUNWIND
   LIB_OBJS += $(OUTPUT)util/unwind.o
 endif
+LIB_OBJS += $(OUTPUT)tests/keep-tracking.o
 
 ifndef NO_LIBAUDIT
   BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
@@ -631,10 +639,10 @@ $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-redundant-decls $<
 
 $(OUTPUT)util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default $<
 
 $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default $<
 
 $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
@@ -762,17 +770,21 @@ check: $(OUTPUT)common-cmds.h
 install-bin: all
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
         $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
+        $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBPERL
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
-        $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
         $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
+endif
+ifndef NO_LIBPYTHON
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
         $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
         $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+endif
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'
         $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 815841c04eb2..8801fe02f206 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -6,3 +6,5 @@ ifndef NO_LIBUNWIND
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
+LIB_H += arch/$(ARCH)/util/tsc.h
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
new file mode 100644
index 000000000000..b2519e49424f
--- /dev/null
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -0,0 +1,59 @@
+#include <stdbool.h>
+#include <errno.h>
+
+#include <linux/perf_event.h>
+
+#include "../../perf.h"
+#include "../../util/types.h"
+#include "../../util/debug.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)
+{
+        bool cap_user_time_zero;
+        u32 seq;
+        int i = 0;
+
+        while (1) {
+                seq = pc->lock;
+                rmb();
+                tc->time_mult = pc->time_mult;
+                tc->time_shift = pc->time_shift;
+                tc->time_zero = pc->time_zero;
+                cap_user_time_zero = pc->cap_user_time_zero;
+                rmb();
+                if (pc->lock == seq && !(seq & 1))
+                        break;
+                if (++i > 10000) {
+                        pr_debug("failed to get perf_event_mmap_page lock\n");
+                        return -EINVAL;
+                }
+        }
+
+        if (!cap_user_time_zero)
+                return -EOPNOTSUPP;
+
+        return 0;
+}
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
new file mode 100644
index 000000000000..a24dec81c795
--- /dev/null
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -0,0 +1,20 @@
+#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
+#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
+
+#include "../../util/types.h"
+
+struct perf_tsc_conversion {
+        u16 time_shift;
+        u32 time_mult;
+        u64 time_zero;
+};
+
+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/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 25fd3f1966f1..8cdca43016b2 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -117,6 +117,8 @@ static void alloc_mem(void **dst, void **src, size_t length)
         *src = zalloc(length);
         if (!*src)
                 die("memory allocation failed - maybe length is too large?\n");
+        /* Make sure to always replace the zero pages even if MMAP_THRESH is crossed */
+        memset(*src, 0, length);
 }
 
 static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index db491e9a812b..5ebd0c3b71b6 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -90,8 +90,7 @@ static int process_sample_event(struct perf_tool *tool,
         struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
         struct addr_location al;
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample,
-                                          symbol__annotate_init) < 0) {
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -195,6 +194,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
         if (session == NULL)
                 return -ENOMEM;
 
+        machines__set_symbol_filter(&session->machines, symbol__annotate_init);
+
         if (ann->cpu_list) {
                 ret = perf_session__cpu_bitmap(session, ann->cpu_list,
                                                ann->cpu_bitmap);
@@ -276,6 +277,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                 .tool = {
                         .sample = process_sample_event,
                         .mmap   = perf_event__process_mmap,
+                        .mmap2  = perf_event__process_mmap2,
                         .comm   = perf_event__process_comm,
                         .exit   = perf_event__process_exit,
                         .fork   = perf_event__process_fork,
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 0aac5f3e594d..f28799e94f2a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -18,15 +18,53 @@
 #include "util/util.h"
 
 #include <stdlib.h>
+#include <math.h>
 
-static char const *input_old = "perf.data.old",
-                  *input_new = "perf.data";
-static char       diff__default_sort_order[] = "dso,symbol";
-static bool  force;
+/* Diff command specific HPP columns. */
+enum {
+        PERF_HPP_DIFF__BASELINE,
+        PERF_HPP_DIFF__PERIOD,
+        PERF_HPP_DIFF__PERIOD_BASELINE,
+        PERF_HPP_DIFF__DELTA,
+        PERF_HPP_DIFF__RATIO,
+        PERF_HPP_DIFF__WEIGHTED_DIFF,
+        PERF_HPP_DIFF__FORMULA,
+
+        PERF_HPP_DIFF__MAX_INDEX
+};
+
+struct diff_hpp_fmt {
+        struct perf_hpp_fmt      fmt;
+        int                      idx;
+        char                    *header;
+        int                      header_width;
+};
+
+struct data__file {
+        struct perf_session     *session;
+        const char              *file;
+        int                      idx;
+        struct hists            *hists;
+        struct diff_hpp_fmt      fmt[PERF_HPP_DIFF__MAX_INDEX];
+};
+
+static struct data__file *data__files;
+static int data__files_cnt;
+
+#define data__for_each_file_start(i, d, s)      \
+        for (i = s, d = &data__files[s];        \
+             i < data__files_cnt;               \
+             i++, d = &data__files[i])
+
+#define data__for_each_file(i, d) data__for_each_file_start(i, d, 0)
+#define data__for_each_file_new(i, d) data__for_each_file_start(i, d, 1)
+
+static char diff__default_sort_order[] = "dso,symbol";
+static bool force;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
-static bool sort_compute;
+static unsigned int sort_compute;
 
 static s64 compute_wdiff_w1;
 static s64 compute_wdiff_w2;
@@ -46,6 +84,47 @@ const char *compute_names[COMPUTE_MAX] = {
 
 static int compute;
 
+static int compute_2_hpp[COMPUTE_MAX] = {
+        [COMPUTE_DELTA]         = PERF_HPP_DIFF__DELTA,
+        [COMPUTE_RATIO]         = PERF_HPP_DIFF__RATIO,
+        [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
+};
+
+#define MAX_COL_WIDTH 70
+
+static struct header_column {
+        const char *name;
+        int width;
+} columns[PERF_HPP_DIFF__MAX_INDEX] = {
+        [PERF_HPP_DIFF__BASELINE] = {
+                .name  = "Baseline",
+        },
+        [PERF_HPP_DIFF__PERIOD] = {
+                .name  = "Period",
+                .width = 14,
+        },
+        [PERF_HPP_DIFF__PERIOD_BASELINE] = {
+                .name  = "Base period",
+                .width = 14,
+        },
+        [PERF_HPP_DIFF__DELTA] = {
+                .name  = "Delta",
+                .width = 7,
+        },
+        [PERF_HPP_DIFF__RATIO] = {
+                .name  = "Ratio",
+                .width = 14,
+        },
+        [PERF_HPP_DIFF__WEIGHTED_DIFF] = {
+                .name  = "Weighted diff",
+                .width = 14,
+        },
+        [PERF_HPP_DIFF__FORMULA] = {
+                .name  = "Formula",
+                .width = MAX_COL_WIDTH,
+        }
+};
+
 static int setup_compute_opt_wdiff(char *opt)
 {
         char *w1_str = opt;
@@ -109,13 +188,6 @@ static int setup_compute(const struct option *opt, const char *str,
                 return 0;
         }
 
-        if (*str == '+') {
-                sort_compute = true;
-                cstr = (char *) ++str;
-                if (!*str)
-                        return 0;
-        }
-
         option = strchr(str, ':');
         if (option) {
                 unsigned len = option++ - str;
@@ -145,42 +217,42 @@ static int setup_compute(const struct option *opt, const char *str,
         return -EINVAL;
 }
 
-double perf_diff__period_percent(struct hist_entry *he, u64 period)
+static double period_percent(struct hist_entry *he, u64 period)
 {
         u64 total = he->hists->stats.total_period;
         return (period * 100.0) / total;
 }
 
-double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair)
+static double compute_delta(struct hist_entry *he, struct hist_entry *pair)
 {
-        double new_percent = perf_diff__period_percent(he, he->stat.period);
-        double old_percent = perf_diff__period_percent(pair, pair->stat.period);
+        double old_percent = period_percent(he, he->stat.period);
+        double new_percent = period_percent(pair, pair->stat.period);
 
-        he->diff.period_ratio_delta = new_percent - old_percent;
-        he->diff.computed = true;
-        return he->diff.period_ratio_delta;
+        pair->diff.period_ratio_delta = new_percent - old_percent;
+        pair->diff.computed = true;
+        return pair->diff.period_ratio_delta;
 }
 
-double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair)
+static double compute_ratio(struct hist_entry *he, struct hist_entry *pair)
 {
-        double new_period = he->stat.period;
-        double old_period = pair->stat.period;
+        double old_period = he->stat.period ?: 1;
+        double new_period = pair->stat.period;
 
-        he->diff.computed = true;
-        he->diff.period_ratio = new_period / old_period;
-        return he->diff.period_ratio;
+        pair->diff.computed = true;
+        pair->diff.period_ratio = new_period / old_period;
+        return pair->diff.period_ratio;
 }
 
-s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
+static s64 compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
 {
-        u64 new_period = he->stat.period;
-        u64 old_period = pair->stat.period;
+        u64 old_period = he->stat.period;
+        u64 new_period = pair->stat.period;
 
-        he->diff.computed = true;
-        he->diff.wdiff = new_period * compute_wdiff_w2 -
-                         old_period * compute_wdiff_w1;
+        pair->diff.computed = true;
+        pair->diff.wdiff = new_period * compute_wdiff_w2 -
+                           old_period * compute_wdiff_w1;
 
-        return he->diff.wdiff;
+        return pair->diff.wdiff;
 }
 
 static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
@@ -189,15 +261,15 @@ static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
         return scnprintf(buf, size,
                          "(%" PRIu64 " * 100 / %" PRIu64 ") - "
                          "(%" PRIu64 " * 100 / %" PRIu64 ")",
-                          he->stat.period, he->hists->stats.total_period,
-                          pair->stat.period, pair->hists->stats.total_period);
+                          pair->stat.period, pair->hists->stats.total_period,
+                          he->stat.period, he->hists->stats.total_period);
 }
 
 static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
                          char *buf, size_t size)
 {
-        double new_period = he->stat.period;
-        double old_period = pair->stat.period;
+        double old_period = he->stat.period;
+        double new_period = pair->stat.period;
 
         return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
 }
@@ -205,16 +277,16 @@ static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
 static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair,
                          char *buf, size_t size)
 {
-        u64 new_period = he->stat.period;
-        u64 old_period = pair->stat.period;
+        u64 old_period = he->stat.period;
+        u64 new_period = pair->stat.period;
 
         return scnprintf(buf, size,
                   "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
                   new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
 }
 
-int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
-                       char *buf, size_t size)
+static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
+                           char *buf, size_t size)
 {
         switch (compute) {
         case COMPUTE_DELTA:
@@ -247,7 +319,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 {
         struct addr_location al;
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) {
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -299,6 +371,29 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
         }
 }
 
+static struct hist_entry*
+get_pair_data(struct hist_entry *he, struct data__file *d)
+{
+        if (hist_entry__has_pairs(he)) {
+                struct hist_entry *pair;
+
+                list_for_each_entry(pair, &he->pairs.head, pairs.node)
+                        if (pair->hists == d->hists)
+                                return pair;
+        }
+
+        return NULL;
+}
+
+static struct hist_entry*
+get_pair_fmt(struct hist_entry *he, struct diff_hpp_fmt *dfmt)
+{
+        void *ptr = dfmt - dfmt->idx;
+        struct data__file *d = container_of(ptr, struct data__file, fmt);
+
+        return get_pair_data(he, d);
+}
+
 static void hists__baseline_only(struct hists *hists)
 {
         struct rb_root *root;
@@ -333,22 +428,24 @@ static void hists__precompute(struct hists *hists)
 
         next = rb_first(root);
         while (next != NULL) {
-                struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
-                struct hist_entry *pair = hist_entry__next_pair(he);
+                struct hist_entry *he, *pair;
 
+                he   = rb_entry(next, struct hist_entry, rb_node_in);
                 next = rb_next(&he->rb_node_in);
+
+                pair = get_pair_data(he, &data__files[sort_compute]);
                 if (!pair)
                         continue;
 
                 switch (compute) {
                 case COMPUTE_DELTA:
-                        perf_diff__compute_delta(he, pair);
+                        compute_delta(he, pair);
                         break;
                 case COMPUTE_RATIO:
-                        perf_diff__compute_ratio(he, pair);
+                        compute_ratio(he, pair);
                         break;
                 case COMPUTE_WEIGHTED_DIFF:
-                        perf_diff__compute_wdiff(he, pair);
+                        compute_wdiff(he, pair);
                         break;
                 default:
                         BUG_ON(1);
@@ -367,7 +464,7 @@ static int64_t cmp_doubles(double l, double r)
 }
 
 static int64_t
-hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
+__hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
                         int c)
 {
         switch (c) {
@@ -399,6 +496,36 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
         return 0;
 }
 
+static int64_t
+hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
+                        int c)
+{
+        bool pairs_left  = hist_entry__has_pairs(left);
+        bool pairs_right = hist_entry__has_pairs(right);
+        struct hist_entry *p_right, *p_left;
+
+        if (!pairs_left && !pairs_right)
+                return 0;
+
+        if (!pairs_left || !pairs_right)
+                return pairs_left ? -1 : 1;
+
+        p_left  = get_pair_data(left,  &data__files[sort_compute]);
+        p_right = get_pair_data(right, &data__files[sort_compute]);
+
+        if (!p_left && !p_right)
+                return 0;
+
+        if (!p_left || !p_right)
+                return p_left ? -1 : 1;
+
+        /*
+         * We have 2 entries of same kind, let's
+         * make the data comparison.
+         */
+        return __hist_entry__cmp_compute(p_left, p_right, c);
+}
+
 static void insert_hist_entry_by_compute(struct rb_root *root,
                                          struct hist_entry *he,
                                          int c)
@@ -448,75 +575,121 @@ static void hists__compute_resort(struct hists *hists)
         }
 }
 
-static void hists__process(struct hists *old, struct hists *new)
+static void hists__process(struct hists *hists)
 {
-        hists__match(new, old);
-
         if (show_baseline_only)
-                hists__baseline_only(new);
-        else
-                hists__link(new, old);
+                hists__baseline_only(hists);
 
         if (sort_compute) {
-                hists__precompute(new);
-                hists__compute_resort(new);
+                hists__precompute(hists);
+                hists__compute_resort(hists);
         } else {
-                hists__output_resort(new);
+                hists__output_resort(hists);
         }
 
-        hists__fprintf(new, true, 0, 0, 0, stdout);
+        hists__fprintf(hists, true, 0, 0, 0, stdout);
 }
 
-static int __cmd_diff(void)
+static void data__fprintf(void)
 {
-        int ret, i;
-#define older (session[0])
-#define newer (session[1])
-        struct perf_session *session[2];
-        struct perf_evlist *evlist_new, *evlist_old;
-        struct perf_evsel *evsel;
+        struct data__file *d;
+        int i;
+
+        fprintf(stdout, "# Data files:\n");
+
+        data__for_each_file(i, d)
+                fprintf(stdout, "#  [%d] %s %s\n",
+                        d->idx, d->file,
+                        !d->idx ? "(Baseline)" : "");
+
+        fprintf(stdout, "#\n");
+}
+
+static void data_process(void)
+{
+        struct perf_evlist *evlist_base = data__files[0].session->evlist;
+        struct perf_evsel *evsel_base;
         bool first = true;
 
-        older = perf_session__new(input_old, O_RDONLY, force, false,
-                                  &tool);
-        newer = perf_session__new(input_new, O_RDONLY, force, false,
-                                  &tool);
-        if (session[0] == NULL || session[1] == NULL)
-                return -ENOMEM;
+        list_for_each_entry(evsel_base, &evlist_base->entries, node) {
+                struct data__file *d;
+                int i;
 
-        for (i = 0; i < 2; ++i) {
-                ret = perf_session__process_events(session[i], &tool);
-                if (ret)
-                        goto out_delete;
-        }
+                data__for_each_file_new(i, d) {
+                        struct perf_evlist *evlist = d->session->evlist;
+                        struct perf_evsel *evsel;
 
-        evlist_old = older->evlist;
-        evlist_new = newer->evlist;
+                        evsel = evsel_match(evsel_base, evlist);
+                        if (!evsel)
+                                continue;
 
-        perf_evlist__collapse_resort(evlist_old);
-        perf_evlist__collapse_resort(evlist_new);
+                        d->hists = &evsel->hists;
 
-        list_for_each_entry(evsel, &evlist_new->entries, node) {
-                struct perf_evsel *evsel_old;
+                        hists__match(&evsel_base->hists, &evsel->hists);
 
-                evsel_old = evsel_match(evsel, evlist_old);
-                if (!evsel_old)
-                        continue;
+                        if (!show_baseline_only)
+                                hists__link(&evsel_base->hists,
+                                            &evsel->hists);
+                }
 
                 fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
-                        perf_evsel__name(evsel));
+                        perf_evsel__name(evsel_base));
 
                 first = false;
 
-                hists__process(&evsel_old->hists, &evsel->hists);
+                if (verbose || data__files_cnt > 2)
+                        data__fprintf();
+
+                hists__process(&evsel_base->hists);
+        }
+}
+
+static void data__free(struct data__file *d)
+{
+        int col;
+
+        for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
+                struct diff_hpp_fmt *fmt = &d->fmt[col];
+
+                free(fmt->header);
         }
+}
 
-out_delete:
-        for (i = 0; i < 2; ++i)
-                perf_session__delete(session[i]);
+static int __cmd_diff(void)
+{
+        struct data__file *d;
+        int ret = -EINVAL, i;
+
+        data__for_each_file(i, d) {
+                d->session = perf_session__new(d->file, O_RDONLY, force,
+                                               false, &tool);
+                if (!d->session) {
+                        pr_err("Failed to open %s\n", d->file);
+                        ret = -ENOMEM;
+                        goto out_delete;
+                }
+
+                ret = perf_session__process_events(d->session, &tool);
+                if (ret) {
+                        pr_err("Failed to process %s\n", d->file);
+                        goto out_delete;
+                }
+
+                perf_evlist__collapse_resort(d->session->evlist);
+        }
+
+        data_process();
+
+ out_delete:
+        data__for_each_file(i, d) {
+                if (d->session)
+                        perf_session__delete(d->session);
+
+                data__free(d);
+        }
+
+        free(data__files);
         return ret;
-#undef older
-#undef newer
 }
 
 static const char * const diff_usage[] = {
@@ -555,61 +728,310 @@ static const struct option options[] = {
                    "columns '.' is reserved."),
         OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
                     "Look for files with symbols relative to this directory"),
+        OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
         OPT_END()
 };
 
-static void ui_init(void)
+static double baseline_percent(struct hist_entry *he)
 {
-        /*
-         * Display baseline/delta/ratio
-         * formula/periods columns.
-         */
-        perf_hpp__column_enable(PERF_HPP__BASELINE);
+        struct hists *hists = he->hists;
+        return 100.0 * he->stat.period / hists->stats.total_period;
+}
 
-        switch (compute) {
-        case COMPUTE_DELTA:
-                perf_hpp__column_enable(PERF_HPP__DELTA);
+static int hpp__color_baseline(struct perf_hpp_fmt *fmt,
+                               struct perf_hpp *hpp, struct hist_entry *he)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(fmt, struct diff_hpp_fmt, fmt);
+        double percent = baseline_percent(he);
+        char pfmt[20] = " ";
+
+        if (!he->dummy) {
+                scnprintf(pfmt, 20, "%%%d.2f%%%%", dfmt->header_width - 1);
+                return percent_color_snprintf(hpp->buf, hpp->size,
+                                              pfmt, percent);
+        } else
+                return scnprintf(hpp->buf, hpp->size, "%*s",
+                                 dfmt->header_width, pfmt);
+}
+
+static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
+{
+        double percent = baseline_percent(he);
+        const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
+        int ret = 0;
+
+        if (!he->dummy)
+                ret = scnprintf(buf, size, fmt, percent);
+
+        return ret;
+}
+
+static void
+hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
+{
+        switch (idx) {
+        case PERF_HPP_DIFF__PERIOD_BASELINE:
+                scnprintf(buf, size, "%" PRIu64, he->stat.period);
                 break;
-        case COMPUTE_RATIO:
-                perf_hpp__column_enable(PERF_HPP__RATIO);
+
+        default:
                 break;
-        case COMPUTE_WEIGHTED_DIFF:
-                perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF);
+        }
+}
+
+static void
+hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
+                int idx, char *buf, size_t size)
+{
+        double diff;
+        double ratio;
+        s64 wdiff;
+
+        switch (idx) {
+        case PERF_HPP_DIFF__DELTA:
+                if (pair->diff.computed)
+                        diff = pair->diff.period_ratio_delta;
+                else
+                        diff = compute_delta(he, pair);
+
+                if (fabs(diff) >= 0.01)
+                        scnprintf(buf, size, "%+4.2F%%", diff);
+                break;
+
+        case PERF_HPP_DIFF__RATIO:
+                /* No point for ratio number if we are dummy.. */
+                if (he->dummy)
+                        break;
+
+                if (pair->diff.computed)
+                        ratio = pair->diff.period_ratio;
+                else
+                        ratio = compute_ratio(he, pair);
+
+                if (ratio > 0.0)
+                        scnprintf(buf, size, "%14.6F", ratio);
+                break;
+
+        case PERF_HPP_DIFF__WEIGHTED_DIFF:
+                /* No point for wdiff number if we are dummy.. */
+                if (he->dummy)
+                        break;
+
+                if (pair->diff.computed)
+                        wdiff = pair->diff.wdiff;
+                else
+                        wdiff = compute_wdiff(he, pair);
+
+                if (wdiff != 0)
+                        scnprintf(buf, size, "%14ld", wdiff);
+                break;
+
+        case PERF_HPP_DIFF__FORMULA:
+                formula_fprintf(he, pair, buf, size);
+                break;
+
+        case PERF_HPP_DIFF__PERIOD:
+                scnprintf(buf, size, "%" PRIu64, pair->stat.period);
                 break;
+
         default:
                 BUG_ON(1);
         };
+}
+
+static void
+__hpp__entry_global(struct hist_entry *he, struct diff_hpp_fmt *dfmt,
+                    char *buf, size_t size)
+{
+        struct hist_entry *pair = get_pair_fmt(he, dfmt);
+        int idx = dfmt->idx;
+
+        /* baseline is special */
+        if (idx == PERF_HPP_DIFF__BASELINE)
+                hpp__entry_baseline(he, buf, size);
+        else {
+                if (pair)
+                        hpp__entry_pair(he, pair, idx, buf, size);
+                else
+                        hpp__entry_unpair(he, idx, buf, size);
+        }
+}
+
+static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
+                             struct hist_entry *he)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(_fmt, struct diff_hpp_fmt, fmt);
+        char buf[MAX_COL_WIDTH] = " ";
+
+        __hpp__entry_global(he, dfmt, buf, MAX_COL_WIDTH);
+
+        if (symbol_conf.field_sep)
+                return scnprintf(hpp->buf, hpp->size, "%s", buf);
+        else
+                return scnprintf(hpp->buf, hpp->size, "%*s",
+                                 dfmt->header_width, buf);
+}
+
+static int hpp__header(struct perf_hpp_fmt *fmt,
+                       struct perf_hpp *hpp)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(fmt, struct diff_hpp_fmt, fmt);
 
-        if (show_formula)
-                perf_hpp__column_enable(PERF_HPP__FORMULA);
+        BUG_ON(!dfmt->header);
+        return scnprintf(hpp->buf, hpp->size, dfmt->header);
+}
 
-        if (show_period) {
-                perf_hpp__column_enable(PERF_HPP__PERIOD);
-                perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE);
+static int hpp__width(struct perf_hpp_fmt *fmt,
+                      struct perf_hpp *hpp __maybe_unused)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(fmt, struct diff_hpp_fmt, fmt);
+
+        BUG_ON(dfmt->header_width <= 0);
+        return dfmt->header_width;
+}
+
+static void init_header(struct data__file *d, struct diff_hpp_fmt *dfmt)
+{
+#define MAX_HEADER_NAME 100
+        char buf_indent[MAX_HEADER_NAME];
+        char buf[MAX_HEADER_NAME];
+        const char *header = NULL;
+        int width = 0;
+
+        BUG_ON(dfmt->idx >= PERF_HPP_DIFF__MAX_INDEX);
+        header = columns[dfmt->idx].name;
+        width  = columns[dfmt->idx].width;
+
+        /* Only our defined HPP fmts should appear here. */
+        BUG_ON(!header);
+
+        if (data__files_cnt > 2)
+                scnprintf(buf, MAX_HEADER_NAME, "%s/%d", header, d->idx);
+
+#define NAME (data__files_cnt > 2 ? buf : header)
+        dfmt->header_width = width;
+        width = (int) strlen(NAME);
+        if (dfmt->header_width < width)
+                dfmt->header_width = width;
+
+        scnprintf(buf_indent, MAX_HEADER_NAME, "%*s",
+                  dfmt->header_width, NAME);
+
+        dfmt->header = strdup(buf_indent);
+#undef MAX_HEADER_NAME
+#undef NAME
+}
+
+static void data__hpp_register(struct data__file *d, int idx)
+{
+        struct diff_hpp_fmt *dfmt = &d->fmt[idx];
+        struct perf_hpp_fmt *fmt = &dfmt->fmt;
+
+        dfmt->idx = idx;
+
+        fmt->header = hpp__header;
+        fmt->width  = hpp__width;
+        fmt->entry  = hpp__entry_global;
+
+        /* TODO more colors */
+        if (idx == PERF_HPP_DIFF__BASELINE)
+                fmt->color = hpp__color_baseline;
+
+        init_header(d, dfmt);
+        perf_hpp__column_register(fmt);
+}
+
+static void ui_init(void)
+{
+        struct data__file *d;
+        int i;
+
+        data__for_each_file(i, d) {
+
+                /*
+                 * Baseline or compute realted columns:
+                 *
+                 *   PERF_HPP_DIFF__BASELINE
+                 *   PERF_HPP_DIFF__DELTA
+                 *   PERF_HPP_DIFF__RATIO
+                 *   PERF_HPP_DIFF__WEIGHTED_DIFF
+                 */
+                data__hpp_register(d, i ? compute_2_hpp[compute] :
+                                          PERF_HPP_DIFF__BASELINE);
+
+                /*
+                 * And the rest:
+                 *
+                 * PERF_HPP_DIFF__FORMULA
+                 * PERF_HPP_DIFF__PERIOD
+                 * PERF_HPP_DIFF__PERIOD_BASELINE
+                 */
+                if (show_formula && i)
+                        data__hpp_register(d, PERF_HPP_DIFF__FORMULA);
+
+                if (show_period)
+                        data__hpp_register(d, i ? PERF_HPP_DIFF__PERIOD :
+                                                  PERF_HPP_DIFF__PERIOD_BASELINE);
         }
 }
 
-int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+static int data_init(int argc, const char **argv)
 {
-        sort_order = diff__default_sort_order;
-        argc = parse_options(argc, argv, options, diff_usage, 0);
+        struct data__file *d;
+        static const char *defaults[] = {
+                "perf.data.old",
+                "perf.data",
+        };
+        bool use_default = true;
+        int i;
+
+        data__files_cnt = 2;
+
         if (argc) {
-                if (argc > 2)
-                        usage_with_options(diff_usage, options);
-                if (argc == 2) {
-                        input_old = argv[0];
-                        input_new = argv[1];
-                } else
-                        input_new = argv[0];
+                if (argc == 1)
+                        defaults[1] = argv[0];
+                else {
+                        data__files_cnt = argc;
+                        use_default = false;
+                }
         } else if (symbol_conf.default_guest_vmlinux_name ||
                    symbol_conf.default_guest_kallsyms) {
-                input_old = "perf.data.host";
-                input_new = "perf.data.guest";
+                defaults[0] = "perf.data.host";
+                defaults[1] = "perf.data.guest";
         }
 
+        if (sort_compute >= (unsigned int) data__files_cnt) {
+                pr_err("Order option out of limit.\n");
+                return -EINVAL;
+        }
+
+        data__files = zalloc(sizeof(*data__files) * data__files_cnt);
+        if (!data__files)
+                return -ENOMEM;
+
+        data__for_each_file(i, d) {
+                d->file = use_default ? defaults[i] : argv[i];
+                d->idx  = i;
+        }
+
+        return 0;
+}
+
+int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+        sort_order = diff__default_sort_order;
+        argc = parse_options(argc, argv, options, diff_usage, 0);
+
         if (symbol__init() < 0)
                 return -1;
 
+        if (data_init(argc, argv) < 0)
+                return -1;
+
         ui_init();
 
         if (setup_sorting() < 0)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 84ad6abe4258..afe377b2884f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,8 +38,7 @@ struct event_entry {
 };
 
 static int perf_event__repipe_synth(struct perf_tool *tool,
-                                    union perf_event *event,
-                                    struct machine *machine __maybe_unused)
+                                    union perf_event *event)
 {
         struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
         uint32_t size;
@@ -65,39 +64,28 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool,
                                         struct perf_session *session
                                         __maybe_unused)
 {
-        return perf_event__repipe_synth(tool, event, NULL);
+        return perf_event__repipe_synth(tool, event);
 }
 
-static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
-                                               union perf_event *event)
-{
-        return perf_event__repipe_synth(tool, event, NULL);
-}
-
-static int perf_event__repipe_tracing_data_synth(union perf_event *event,
-                                                 struct perf_session *session
-                                                 __maybe_unused)
-{
-        return perf_event__repipe_synth(NULL, event, NULL);
-}
-
-static int perf_event__repipe_attr(union perf_event *event,
-                                   struct perf_evlist **pevlist __maybe_unused)
+static int perf_event__repipe_attr(struct perf_tool *tool,
+                                   union perf_event *event,
+                                   struct perf_evlist **pevlist)
 {
         int ret;
-        ret = perf_event__process_attr(event, pevlist);
+
+        ret = perf_event__process_attr(tool, event, pevlist);
         if (ret)
                 return ret;
 
-        return perf_event__repipe_synth(NULL, event, NULL);
+        return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
                               union perf_event *event,
                               struct perf_sample *sample __maybe_unused,
-                              struct machine *machine)
+                              struct machine *machine __maybe_unused)
 {
-        return perf_event__repipe_synth(tool, event, machine);
+        return perf_event__repipe_synth(tool, event);
 }
 
 typedef int (*inject_handler)(struct perf_tool *tool,
@@ -119,7 +107,7 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 
         build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-        return perf_event__repipe_synth(tool, event, machine);
+        return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_mmap(struct perf_tool *tool,
@@ -135,6 +123,19 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
         return err;
 }
 
+static int perf_event__repipe_mmap2(struct perf_tool *tool,
+                                   union perf_event *event,
+                                   struct perf_sample *sample,
+                                   struct machine *machine)
+{
+        int err;
+
+        err = perf_event__process_mmap2(tool, event, sample, machine);
+        perf_event__repipe(tool, event, sample, machine);
+
+        return err;
+}
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
                                    union perf_event *event,
                                    struct perf_sample *sample,
@@ -148,13 +149,14 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
         return err;
 }
 
-static int perf_event__repipe_tracing_data(union perf_event *event,
+static int perf_event__repipe_tracing_data(struct perf_tool *tool,
+                                           union perf_event *event,
                                            struct perf_session *session)
 {
         int err;
 
-        perf_event__repipe_synth(NULL, event, NULL);
-        err = perf_event__process_tracing_data(event, session);
+        perf_event__repipe_synth(tool, event);
+        err = perf_event__process_tracing_data(tool, event, session);
 
         return err;
 }
@@ -209,7 +211,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 
         cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-        thread = machine__findnew_thread(machine, event->ip.pid);
+        thread = machine__findnew_thread(machine, sample->pid, sample->pid);
         if (thread == NULL) {
                 pr_err("problem processing %d event, skipping it.\n",
                        event->header.type);
@@ -217,7 +219,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
         }
 
         thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              event->ip.ip, &al);
+                              sample->ip, &al);
 
         if (al.map != NULL) {
                 if (!al.map->dso->hit) {
@@ -312,13 +314,13 @@ found:
         sample_sw.period = sample->period;
         sample_sw.time   = sample->time;
         perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
-                                      &sample_sw, false);
+                                      evsel->attr.sample_regs_user,
+                                      evsel->attr.read_format, &sample_sw,
+                                      false);
         build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
         return perf_event__repipe(tool, event_sw, &sample_sw, machine);
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
         session_done = 1;
@@ -348,6 +350,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
         if (inject->build_ids || inject->sched_stat) {
                 inject->tool.mmap         = perf_event__repipe_mmap;
+                inject->tool.mmap2        = perf_event__repipe_mmap2;
                 inject->tool.fork         = perf_event__repipe_fork;
                 inject->tool.tracing_data = perf_event__repipe_tracing_data;
         }
@@ -399,6 +402,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 .tool = {
                         .sample         = perf_event__repipe_sample,
                         .mmap           = perf_event__repipe,
+                        .mmap2          = perf_event__repipe,
                         .comm           = perf_event__repipe,
                         .fork           = perf_event__repipe,
                         .exit           = perf_event__repipe,
@@ -407,8 +411,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                         .throttle       = perf_event__repipe,
                         .unthrottle     = perf_event__repipe,
                         .attr           = perf_event__repipe_attr,
-                        .event_type     = perf_event__repipe_event_type_synth,
-                        .tracing_data   = perf_event__repipe_tracing_data_synth,
+                        .tracing_data   = perf_event__repipe_op2_synth,
+                        .finished_round = perf_event__repipe_op2_synth,
                         .build_id       = perf_event__repipe_op2_synth,
                 },
                 .input_name  = "-",
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0259502638b4..9b5f077fee5b 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -101,7 +101,7 @@ static int setup_cpunode_map(void)
 
         dir1 = opendir(PATH_SYS_NODE);
         if (!dir1)
-                return -1;
+                return 0;
 
         while ((dent1 = readdir(dir1)) != NULL) {
                 if (dent1->d_type != DT_DIR ||
@@ -305,7 +305,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                                 struct perf_evsel *evsel,
                                 struct machine *machine)
 {
-        struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+        struct thread *thread = machine__findnew_thread(machine, sample->pid,
+                                                        sample->pid);
 
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
@@ -313,7 +314,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                 return -1;
         }
 
-        dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+        dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 
         if (evsel->handler.func != NULL) {
                 tracepoint_handler f = evsel->handler.func;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 24b78aecc928..935d52216c89 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -2,22 +2,26 @@
 #include "perf.h"
 
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
 #include "util/session.h"
-
+#include "util/intlist.h"
 #include "util/parse-options.h"
 #include "util/trace-event.h"
 #include "util/debug.h"
 #include <lk/debugfs.h>
 #include "util/tool.h"
 #include "util/stat.h"
+#include "util/top.h"
 
 #include <sys/prctl.h>
+#include <sys/timerfd.h>
 
+#include <termios.h>
 #include <semaphore.h>
 #include <pthread.h>
 #include <math.h>
@@ -82,6 +86,8 @@ struct exit_reasons_table {
 
 struct perf_kvm_stat {
         struct perf_tool    tool;
+        struct perf_record_opts opts;
+        struct perf_evlist  *evlist;
         struct perf_session *session;
 
         const char *file_name;
@@ -96,10 +102,20 @@ struct perf_kvm_stat {
         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;
 };
 
 
@@ -320,6 +336,28 @@ static void init_kvm_event_record(struct perf_kvm_stat *kvm)
                 INIT_LIST_HEAD(&kvm->kvm_events_cache[i]);
 }
 
+static void clear_events_cache_stats(struct list_head *kvm_events_cache)
+{
+        struct list_head *head;
+        struct kvm_event *event;
+        unsigned int i;
+        int j;
+
+        for (i = 0; i < EVENTS_CACHE_SIZE; i++) {
+                head = &kvm_events_cache[i];
+                list_for_each_entry(event, head, hash_entry) {
+                        /* reset stats for event */
+                        event->total.time = 0;
+                        init_stats(&event->total.stats);
+
+                        for (j = 0; j < event->max_vcpu; ++j) {
+                                event->vcpu[j].time = 0;
+                                init_stats(&event->vcpu[j].stats);
+                        }
+                }
+        }
+}
+
 static int kvm_events_hash_fn(u64 key)
 {
         return key & (EVENTS_CACHE_SIZE - 1);
@@ -436,7 +474,7 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
 static bool handle_end_event(struct perf_kvm_stat *kvm,
                              struct vcpu_event_record *vcpu_record,
                              struct event_key *key,
-                             u64 timestamp)
+                             struct perf_sample *sample)
 {
         struct kvm_event *event;
         u64 time_begin, time_diff;
@@ -472,9 +510,25 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
         vcpu_record->last_event = NULL;
         vcpu_record->start_time = 0;
 
-        BUG_ON(timestamp < time_begin);
+        /* seems to happen once in a while during live mode */
+        if (sample->time < time_begin) {
+                pr_debug("End time before begin time; skipping event.\n");
+                return true;
+        }
+
+        time_diff = sample->time - time_begin;
+
+        if (kvm->duration && time_diff > kvm->duration) {
+                char decode[32];
+
+                kvm->events_ops->decode_key(kvm, &event->key, decode);
+                if (strcmp(decode, "HLT")) {
+                        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);
+                }
+        }
 
-        time_diff = timestamp - time_begin;
         return update_kvm_event(event, vcpu, time_diff);
 }
 
@@ -521,7 +575,7 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
                 return handle_begin_event(kvm, vcpu_record, &key, sample->time);
 
         if (kvm->events_ops->is_end_event(evsel, sample, &key))
-                return handle_end_event(kvm, vcpu_record, &key, sample->time);
+                return handle_end_event(kvm, vcpu_record, &key, sample);
 
         return true;
 }
@@ -550,6 +604,8 @@ static int compare_kvm_event_ ## func(struct kvm_event *one,		\
 GET_EVENT_KEY(time, time);
 COMPARE_EVENT_KEY(count, stats.n);
 COMPARE_EVENT_KEY(mean, stats.mean);
+GET_EVENT_KEY(max, stats.max);
+GET_EVENT_KEY(min, stats.min);
 
 #define DEF_SORT_NAME_KEY(name, compare_key)                            \
         { #name, compare_kvm_event_ ## compare_key }
@@ -639,43 +695,81 @@ static struct kvm_event *pop_from_result(struct rb_root *result)
         return container_of(node, struct kvm_event, rb);
 }
 
-static void print_vcpu_info(int vcpu)
+static void print_vcpu_info(struct perf_kvm_stat *kvm)
 {
+        int vcpu = kvm->trace_vcpu;
+
         pr_info("Analyze events for ");
 
+        if (kvm->live) {
+                if (kvm->opts.target.system_wide)
+                        pr_info("all VMs, ");
+                else if (kvm->opts.target.pid)
+                        pr_info("pid(s) %s, ", kvm->opts.target.pid);
+                else
+                        pr_info("dazed and confused on what is monitored, ");
+        }
+
         if (vcpu == -1)
                 pr_info("all VCPUs:\n\n");
         else
                 pr_info("VCPU %d:\n\n", vcpu);
 }
 
+static void show_timeofday(void)
+{
+        char date[64];
+        struct timeval tv;
+        struct tm ltime;
+
+        gettimeofday(&tv, NULL);
+        if (localtime_r(&tv.tv_sec, &ltime)) {
+                strftime(date, sizeof(date), "%H:%M:%S", &ltime);
+                pr_info("%s.%06ld", date, tv.tv_usec);
+        } else
+                pr_info("00:00:00.000000");
+
+        return;
+}
+
 static void print_result(struct perf_kvm_stat *kvm)
 {
         char decode[20];
         struct kvm_event *event;
         int vcpu = kvm->trace_vcpu;
 
+        if (kvm->live) {
+                puts(CONSOLE_CLEAR);
+                show_timeofday();
+        }
+
         pr_info("\n\n");
-        print_vcpu_info(vcpu);
+        print_vcpu_info(kvm);
         pr_info("%20s ", kvm->events_ops->name);
         pr_info("%10s ", "Samples");
         pr_info("%9s ", "Samples%");
 
         pr_info("%9s ", "Time%");
+        pr_info("%10s ", "Min Time");
+        pr_info("%10s ", "Max Time");
         pr_info("%16s ", "Avg time");
         pr_info("\n\n");
 
         while ((event = pop_from_result(&kvm->result))) {
-                u64 ecount, etime;
+                u64 ecount, etime, max, min;
 
                 ecount = get_event_count(event, vcpu);
                 etime = get_event_time(event, vcpu);
+                max = get_event_max(event, vcpu);
+                min = get_event_min(event, vcpu);
 
                 kvm->events_ops->decode_key(kvm, &event->key, decode);
                 pr_info("%20s ", 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);
+                pr_info("%8" PRIu64 "us ", min / 1000);
+                pr_info("%8" PRIu64 "us ", max / 1000);
                 pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
                         kvm_event_rel_stddev(vcpu, event));
                 pr_info("\n");
@@ -683,6 +777,29 @@ static void print_result(struct perf_kvm_stat *kvm)
 
         pr_info("\nTotal Samples:%" PRIu64 ", Total events handled time:%.2fus.\n\n",
                 kvm->total_count, kvm->total_time / 1e3);
+
+        if (kvm->lost_events)
+                pr_info("\nLost events: %" PRIu64 "\n\n", kvm->lost_events);
+}
+
+static int process_lost_event(struct perf_tool *tool,
+                              union perf_event *event __maybe_unused,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
+{
+        struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat, tool);
+
+        kvm->lost_events++;
+        return 0;
+}
+
+static bool skip_sample(struct perf_kvm_stat *kvm,
+                        struct perf_sample *sample)
+{
+        if (kvm->pid_list && intlist__find(kvm->pid_list, sample->pid) == NULL)
+                return true;
+
+        return false;
 }
 
 static int process_sample_event(struct perf_tool *tool,
@@ -691,10 +808,14 @@ static int process_sample_event(struct perf_tool *tool,
                                 struct perf_evsel *evsel,
                                 struct machine *machine)
 {
-        struct thread *thread = machine__findnew_thread(machine, sample->tid);
+        struct thread *thread;
         struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
                                                  tool);
 
+        if (skip_sample(kvm, sample))
+                return 0;
+
+        thread = machine__findnew_thread(machine, sample->pid, sample->tid);
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
                         event->header.type);
@@ -707,10 +828,20 @@ static int process_sample_event(struct perf_tool *tool,
         return 0;
 }
 
-static int get_cpu_isa(struct perf_session *session)
+static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
-        char *cpuid = session->header.env.cpuid;
-        int isa;
+        char buf[64], *cpuid;
+        int err, isa;
+
+        if (kvm->live) {
+                err = get_cpuid(buf, sizeof(buf));
+                if (err != 0) {
+                        pr_err("Failed to look up CPU type (Intel or AMD)\n");
+                        return err;
+                }
+                cpuid = buf;
+        } else
+                cpuid = kvm->session->header.env.cpuid;
 
         if (strstr(cpuid, "Intel"))
                 isa = 1;
@@ -718,10 +849,361 @@ static int get_cpu_isa(struct perf_session *session)
                 isa = 0;
         else {
                 pr_err("CPU %s is not supported.\n", cpuid);
-                isa = -ENOTSUP;
+                return -ENOTSUP;
+        }
+
+        if (isa == 1) {
+                kvm->exit_reasons = vmx_exit_reasons;
+                kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
+                kvm->exit_reasons_isa = "VMX";
+        }
+
+        return 0;
+}
+
+static bool verify_vcpu(int vcpu)
+{
+        if (vcpu != -1 && vcpu < 0) {
+                pr_err("Invalid vcpu:%d.\n", vcpu);
+                return false;
+        }
+
+        return true;
+}
+
+/* keeping the max events to a modest level to keep
+ * the processing of samples per mmap smooth.
+ */
+#define PERF_KVM__MAX_EVENTS_PER_MMAP  25
+
+static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
+                                   u64 *mmap_time)
+{
+        union perf_event *event;
+        struct perf_sample sample;
+        s64 n = 0;
+        int err;
+
+        *mmap_time = ULLONG_MAX;
+        while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
+                err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
+                if (err) {
+                        pr_err("Failed to parse sample\n");
+                        return -1;
+                }
+
+                err = perf_session_queue_event(kvm->session, event, &sample, 0);
+                if (err) {
+                        pr_err("Failed to enqueue sample: %d\n", err);
+                        return -1;
+                }
+
+                /* save time stamp of our first sample for this mmap */
+                if (n == 0)
+                        *mmap_time = sample.time;
+
+                /* limit events per mmap handled all at once */
+                n++;
+                if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
+                        break;
+        }
+
+        return n;
+}
+
+static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
+{
+        int i, err, throttled = 0;
+        s64 n, ntotal = 0;
+        u64 flush_time = ULLONG_MAX, mmap_time;
+
+        for (i = 0; i < kvm->evlist->nr_mmaps; i++) {
+                n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time);
+                if (n < 0)
+                        return -1;
+
+                /* flush time is going to be the minimum of all the individual
+                 * mmap times. Essentially, we flush all the samples queued up
+                 * from the last pass under our minimal start time -- that leaves
+                 * a very small race for samples to come in with a lower timestamp.
+                 * The ioctl to return the perf_clock timestamp should close the
+                 * race entirely.
+                 */
+                if (mmap_time < flush_time)
+                        flush_time = mmap_time;
+
+                ntotal += n;
+                if (n == PERF_KVM__MAX_EVENTS_PER_MMAP)
+                        throttled = 1;
+        }
+
+        /* flush queue after each round in which we processed events */
+        if (ntotal) {
+                kvm->session->ordered_samples.next_flush = flush_time;
+                err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
+                if (err) {
+                        if (kvm->lost_events)
+                                pr_info("\nLost events: %" PRIu64 "\n\n",
+                                        kvm->lost_events);
+                        return err;
+                }
+        }
+
+        return throttled;
+}
+
+static volatile int done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+        done = 1;
+}
+
+static int perf_kvm__timerfd_create(struct perf_kvm_stat *kvm)
+{
+        struct itimerspec new_value;
+        int rc = -1;
+
+        kvm->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
+        if (kvm->timerfd < 0) {
+                pr_err("timerfd_create failed\n");
+                goto out;
+        }
+
+        new_value.it_value.tv_sec = kvm->display_time;
+        new_value.it_value.tv_nsec = 0;
+        new_value.it_interval.tv_sec = kvm->display_time;
+        new_value.it_interval.tv_nsec = 0;
+
+        if (timerfd_settime(kvm->timerfd, 0, &new_value, NULL) != 0) {
+                pr_err("timerfd_settime failed: %d\n", errno);
+                close(kvm->timerfd);
+                goto out;
+        }
+
+        rc = 0;
+out:
+        return rc;
+}
+
+static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm)
+{
+        uint64_t c;
+        int rc;
+
+        rc = read(kvm->timerfd, &c, sizeof(uint64_t));
+        if (rc < 0) {
+                if (errno == EAGAIN)
+                        return 0;
+
+                pr_err("Failed to read timer fd: %d\n", errno);
+                return -1;
+        }
+
+        if (rc != sizeof(uint64_t)) {
+                pr_err("Error reading timer fd - invalid size returned\n");
+                return -1;
+        }
+
+        if (c != 1)
+                pr_debug("Missed timer beats: %" PRIu64 "\n", c-1);
+
+        /* update display */
+        sort_result(kvm);
+        print_result(kvm);
+
+        /* reset counts */
+        clear_events_cache_stats(kvm->kvm_events_cache);
+        kvm->total_count = 0;
+        kvm->total_time = 0;
+        kvm->lost_events = 0;
+
+        return 0;
+}
+
+static int fd_set_nonblock(int fd)
+{
+        long arg = 0;
+
+        arg = fcntl(fd, F_GETFL);
+        if (arg < 0) {
+                pr_err("Failed to get current flags for fd %d\n", fd);
+                return -1;
+        }
+
+        if (fcntl(fd, F_SETFL, arg | O_NONBLOCK) < 0) {
+                pr_err("Failed to set non-block option on fd %d\n", fd);
+                return -1;
+        }
+
+        return 0;
+}
+
+static
+int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+{
+        int c;
+
+        tcsetattr(0, TCSANOW, tc_now);
+        c = getc(stdin);
+        tcsetattr(0, TCSAFLUSH, tc_save);
+
+        if (c == 'q')
+                return 1;
+
+        return 0;
+}
+
+static int kvm_events_live_report(struct perf_kvm_stat *kvm)
+{
+        struct pollfd *pollfds = NULL;
+        int nr_fds, nr_stdin, ret, err = -EINVAL;
+        struct termios tc, save;
+
+        /* live flag must be set first */
+        kvm->live = true;
+
+        ret = cpu_isa_config(kvm);
+        if (ret < 0)
+                return ret;
+
+        if (!verify_vcpu(kvm->trace_vcpu) ||
+            !select_key(kvm) ||
+            !register_kvm_events_ops(kvm)) {
+                goto out;
+        }
+
+        init_kvm_event_record(kvm);
+
+        tcgetattr(0, &save);
+        tc = save;
+        tc.c_lflag &= ~(ICANON | ECHO);
+        tc.c_cc[VMIN] = 0;
+        tc.c_cc[VTIME] = 0;
+
+        signal(SIGINT, sig_handler);
+        signal(SIGTERM, sig_handler);
+
+        /* copy pollfds -- need to add timerfd and stdin */
+        nr_fds = kvm->evlist->nr_fds;
+        pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
+        if (!pollfds) {
+                err = -ENOMEM;
+                goto out;
         }
+        memcpy(pollfds, kvm->evlist->pollfd,
+                sizeof(struct pollfd) * kvm->evlist->nr_fds);
+
+        /* add timer fd */
+        if (perf_kvm__timerfd_create(kvm) < 0) {
+                err = -1;
+                goto out;
+        }
+
+        pollfds[nr_fds].fd = kvm->timerfd;
+        pollfds[nr_fds].events = POLLIN;
+        nr_fds++;
+
+        pollfds[nr_fds].fd = fileno(stdin);
+        pollfds[nr_fds].events = POLLIN;
+        nr_stdin = nr_fds;
+        nr_fds++;
+        if (fd_set_nonblock(fileno(stdin)) != 0)
+                goto out;
+
+        /* everything is good - enable the events and process */
+        perf_evlist__enable(kvm->evlist);
+
+        while (!done) {
+                int rc;
+
+                rc = perf_kvm__mmap_read(kvm);
+                if (rc < 0)
+                        break;
+
+                err = perf_kvm__handle_timerfd(kvm);
+                if (err)
+                        goto out;
+
+                if (pollfds[nr_stdin].revents & POLLIN)
+                        done = perf_kvm__handle_stdin(&tc, &save);
+
+                if (!rc && !done)
+                        err = poll(pollfds, nr_fds, 100);
+        }
+
+        perf_evlist__disable(kvm->evlist);
+
+        if (err == 0) {
+                sort_result(kvm);
+                print_result(kvm);
+        }
+
+out:
+        if (kvm->timerfd >= 0)
+                close(kvm->timerfd);
+
+        if (pollfds)
+                free(pollfds);
 
-        return isa;
+        return err;
+}
+
+static int kvm_live_open_events(struct perf_kvm_stat *kvm)
+{
+        int err, rc = -1;
+        struct perf_evsel *pos;
+        struct perf_evlist *evlist = kvm->evlist;
+
+        perf_evlist__config(evlist, &kvm->opts);
+
+        /*
+         * Note: exclude_{guest,host} do not apply here.
+         *       This command processes KVM tracepoints from host only
+         */
+        list_for_each_entry(pos, &evlist->entries, node) {
+                struct perf_event_attr *attr = &pos->attr;
+
+                /* make sure these *are* set */
+                perf_evsel__set_sample_bit(pos, TID);
+                perf_evsel__set_sample_bit(pos, TIME);
+                perf_evsel__set_sample_bit(pos, CPU);
+                perf_evsel__set_sample_bit(pos, RAW);
+                /* make sure these are *not*; want as small a sample as possible */
+                perf_evsel__reset_sample_bit(pos, PERIOD);
+                perf_evsel__reset_sample_bit(pos, IP);
+                perf_evsel__reset_sample_bit(pos, CALLCHAIN);
+                perf_evsel__reset_sample_bit(pos, ADDR);
+                perf_evsel__reset_sample_bit(pos, READ);
+                attr->mmap = 0;
+                attr->comm = 0;
+                attr->task = 0;
+
+                attr->sample_period = 1;
+
+                attr->watermark = 0;
+                attr->wakeup_events = 1000;
+
+                /* will enable all once we are ready */
+                attr->disabled = 1;
+        }
+
+        err = perf_evlist__open(evlist);
+        if (err < 0) {
+                printf("Couldn't create the events: %s\n", strerror(errno));
+                goto out;
+        }
+
+        if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
+                ui__error("Failed to mmap the events: %s\n", strerror(errno));
+                perf_evlist__close(evlist);
+                goto out;
+        }
+
+        rc = 0;
+
+out:
+        return rc;
 }
 
 static int read_events(struct perf_kvm_stat *kvm)
@@ -749,28 +1231,24 @@ static int read_events(struct perf_kvm_stat *kvm)
          * Do not use 'isa' recorded in kvm_exit tracepoint since it is not
          * traced in the old kernel.
          */
-        ret = get_cpu_isa(kvm->session);
-
+        ret = cpu_isa_config(kvm);
         if (ret < 0)
                 return ret;
 
-        if (ret == 1) {
-                kvm->exit_reasons = vmx_exit_reasons;
-                kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
-                kvm->exit_reasons_isa = "VMX";
-        }
-
         return perf_session__process_events(kvm->session, &kvm->tool);
 }
 
-static bool verify_vcpu(int vcpu)
+static int parse_target_str(struct perf_kvm_stat *kvm)
 {
-        if (vcpu != -1 && vcpu < 0) {
-                pr_err("Invalid vcpu:%d.\n", vcpu);
-                return false;
+        if (kvm->pid_str) {
+                kvm->pid_list = intlist__new(kvm->pid_str);
+                if (kvm->pid_list == NULL) {
+                        pr_err("Error parsing process id string\n");
+                        return -EINVAL;
+                }
         }
 
-        return true;
+        return 0;
 }
 
 static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
@@ -778,6 +1256,9 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm)
         int ret = -EINVAL;
         int vcpu = kvm->trace_vcpu;
 
+        if (parse_target_str(kvm) != 0)
+                goto exit;
+
         if (!verify_vcpu(vcpu))
                 goto exit;
 
@@ -801,16 +1282,11 @@ exit:
         return ret;
 }
 
-static const char * const record_args[] = {
-        "record",
-        "-R",
-        "-f",
-        "-m", "1024",
-        "-c", "1",
-        "-e", "kvm:kvm_entry",
-        "-e", "kvm:kvm_exit",
-        "-e", "kvm:kvm_mmio",
-        "-e", "kvm:kvm_pio",
+static const char * const kvm_events_tp[] = {
+        "kvm:kvm_entry",
+        "kvm:kvm_exit",
+        "kvm:kvm_mmio",
+        "kvm:kvm_pio",
 };
 
 #define STRDUP_FAIL_EXIT(s)             \
@@ -826,8 +1302,15 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
         unsigned int rec_argc, i, j;
         const char **rec_argv;
+        const char * const record_args[] = {
+                "record",
+                "-R",
+                "-m", "1024",
+                "-c", "1",
+        };
 
-        rec_argc = ARRAY_SIZE(record_args) + argc + 2;
+        rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
+                   2 * ARRAY_SIZE(kvm_events_tp);
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
         if (rec_argv == NULL)
@@ -836,6 +1319,11 @@ 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++) {
+                rec_argv[i++] = "-e";
+                rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
+        }
+
         rec_argv[i++] = STRDUP_FAIL_EXIT("-o");
         rec_argv[i++] = STRDUP_FAIL_EXIT(kvm->file_name);
 
@@ -856,6 +1344,8 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
                             "key for sorting: sample(sort by samples number)"
                             " time (sort by avg time)"),
+                OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+                           "analyze events only for given process id(s)"),
                 OPT_END()
         };
 
@@ -878,6 +1368,190 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
         return kvm_events_report_vcpu(kvm);
 }
 
+static struct perf_evlist *kvm_live_event_list(void)
+{
+        struct perf_evlist *evlist;
+        char *tp, *name, *sys;
+        unsigned int j;
+        int err = -1;
+
+        evlist = perf_evlist__new();
+        if (evlist == NULL)
+                return NULL;
+
+        for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+
+                tp = strdup(kvm_events_tp[j]);
+                if (tp == NULL)
+                        goto out;
+
+                /* split tracepoint into subsystem and name */
+                sys = tp;
+                name = strchr(tp, ':');
+                if (name == NULL) {
+                        pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
+                                kvm_events_tp[j]);
+                        free(tp);
+                        goto out;
+                }
+                *name = '\0';
+                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]);
+                        free(tp);
+                        goto out;
+                }
+
+                free(tp);
+        }
+
+        err = 0;
+
+out:
+        if (err) {
+                perf_evlist__delete(evlist);
+                evlist = NULL;
+        }
+
+        return evlist;
+}
+
+static int kvm_events_live(struct perf_kvm_stat *kvm,
+                           int argc, const char **argv)
+{
+        char errbuf[BUFSIZ];
+        int err;
+
+        const struct option live_options[] = {
+                OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
+                        "record events on existing process id"),
+                OPT_UINTEGER('m', "mmap-pages", &kvm->opts.mmap_pages,
+                        "number of mmap data pages"),
+                OPT_INCR('v', "verbose", &verbose,
+                        "be more verbose (show counter open errors, etc)"),
+                OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide,
+                        "system-wide collection from all CPUs"),
+                OPT_UINTEGER('d', "display", &kvm->display_time,
+                        "time in seconds between display updates"),
+                OPT_STRING(0, "event", &kvm->report_event, "report event",
+                        "event for reporting: vmexit, mmio, ioport"),
+                OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
+                        "vcpu id to report"),
+                OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
+                        "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"),
+                OPT_END()
+        };
+        const char * const live_usage[] = {
+                "perf kvm stat live [<options>]",
+                NULL
+        };
+
+
+        /* event handling */
+        kvm->tool.sample = process_sample_event;
+        kvm->tool.comm   = perf_event__process_comm;
+        kvm->tool.exit   = perf_event__process_exit;
+        kvm->tool.fork   = perf_event__process_fork;
+        kvm->tool.lost   = process_lost_event;
+        kvm->tool.ordered_samples = true;
+        perf_tool__fill_defaults(&kvm->tool);
+
+        /* set defaults */
+        kvm->display_time = 1;
+        kvm->opts.user_interval = 1;
+        kvm->opts.mmap_pages = 512;
+        kvm->opts.target.uses_mmap = false;
+        kvm->opts.target.uid_str = NULL;
+        kvm->opts.target.uid = UINT_MAX;
+
+        symbol__init();
+        disable_buildid_cache();
+
+        use_browser = 0;
+        setup_browser(false);
+
+        if (argc) {
+                argc = parse_options(argc, argv, live_options,
+                                     live_usage, 0);
+                if (argc)
+                        usage_with_options(live_usage, live_options);
+        }
+
+        kvm->duration *= NSEC_PER_USEC;   /* convert usec to nsec */
+
+        /*
+         * target related setups
+         */
+        err = perf_target__validate(&kvm->opts.target);
+        if (err) {
+                perf_target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ);
+                ui__warning("%s", errbuf);
+        }
+
+        if (perf_target__none(&kvm->opts.target))
+                kvm->opts.target.system_wide = true;
+
+
+        /*
+         * generate the event list
+         */
+        kvm->evlist = kvm_live_event_list();
+        if (kvm->evlist == NULL) {
+                err = -1;
+                goto out;
+        }
+
+        symbol_conf.nr_events = kvm->evlist->nr_entries;
+
+        if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0)
+                usage_with_options(live_usage, live_options);
+
+        /*
+         * perf session
+         */
+        kvm->session = perf_session__new(NULL, O_WRONLY, false, false, &kvm->tool);
+        if (kvm->session == NULL) {
+                err = -ENOMEM;
+                goto out;
+        }
+        kvm->session->evlist = kvm->evlist;
+        perf_session__set_id_hdr_size(kvm->session);
+
+
+        if (perf_target__has_task(&kvm->opts.target))
+                perf_event__synthesize_thread_map(&kvm->tool,
+                                                  kvm->evlist->threads,
+                                                  perf_event__process,
+                                                  &kvm->session->machines.host);
+        else
+                perf_event__synthesize_threads(&kvm->tool, perf_event__process,
+                                               &kvm->session->machines.host);
+
+
+        err = kvm_live_open_events(kvm);
+        if (err)
+                goto out;
+
+        err = kvm_events_live_report(kvm);
+
+out:
+        exit_browser(0);
+
+        if (kvm->session)
+                perf_session__delete(kvm->session);
+        kvm->session = NULL;
+        if (kvm->evlist) {
+                perf_evlist__delete_maps(kvm->evlist);
+                perf_evlist__delete(kvm->evlist);
+        }
+
+        return err;
+}
+
 static void print_kvm_stat_usage(void)
 {
         printf("Usage: perf kvm stat <command>\n\n");
@@ -885,6 +1559,7 @@ static void print_kvm_stat_usage(void)
         printf("# Available commands:\n");
         printf("\trecord: record kvm events\n");
         printf("\treport: report statistical data of kvm events\n");
+        printf("\tlive:   live reporting of statistical data of kvm events\n");
 
         printf("\nOtherwise, it is the alias of 'perf stat':\n");
 }
@@ -914,6 +1589,9 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
         if (!strncmp(argv[1], "rep", 3))
                 return kvm_events_report(&kvm, argc - 1 , argv + 1);
 
+        if (!strncmp(argv[1], "live", 4))
+                return kvm_events_live(&kvm, argc - 1 , argv + 1);
+
 perf_stat:
         return cmd_stat(argc, argv, NULL);
 }
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 1948eceb517a..e79f423cc302 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -13,6 +13,7 @@
 
 #include "util/parse-events.h"
 #include "util/cache.h"
+#include "util/pmu.h"
 
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -37,6 +38,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                         else if (strcmp(argv[i], "cache") == 0 ||
                                  strcmp(argv[i], "hwcache") == 0)
                                 print_hwcache_events(NULL, false);
+                        else if (strcmp(argv[i], "pmu") == 0)
+                                print_pmu_events(NULL, false);
                         else if (strcmp(argv[i], "--raw-dump") == 0)
                                 print_events(NULL, true);
                         else {
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 76543a4a7a30..ee33ba2f05dd 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -805,7 +805,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                                 struct perf_evsel *evsel,
                                 struct machine *machine)
 {
-        struct thread *thread = machine__findnew_thread(machine, sample->tid);
+        struct thread *thread = machine__findnew_thread(machine, sample->pid,
+                                                        sample->tid);
 
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index a8ff6d264e50..253133a6251d 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -14,7 +14,6 @@ static const char	*mem_operation		= MEM_OPERATION_LOAD;
 struct perf_mem {
         struct perf_tool        tool;
         char const              *input_name;
-        symbol_filter_t         annotate_init;
         bool                    hide_unresolved;
         bool                    dump_raw;
         const char              *cpu_list;
@@ -69,8 +68,7 @@ dump_raw_samples(struct perf_tool *tool,
         struct addr_location al;
         const char *fmt;
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample,
-                                mem->annotate_init) < 0) {
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                                 event->header.type);
                 return -1;
@@ -96,7 +94,7 @@ dump_raw_samples(struct perf_tool *tool,
                 symbol_conf.field_sep,
                 sample->tid,
                 symbol_conf.field_sep,
-                event->ip.ip,
+                sample->ip,
                 symbol_conf.field_sep,
                 sample->addr,
                 symbol_conf.field_sep,
@@ -192,6 +190,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
                 .tool = {
                         .sample         = process_sample_event,
                         .mmap           = perf_event__process_mmap,
+                        .mmap2          = perf_event__process_mmap2,
                         .comm           = perf_event__process_comm,
                         .lost           = perf_event__process_lost,
                         .fork           = perf_event__process_fork,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ecca62e27b28..a41ac41546c9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -474,13 +474,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
                         goto out_delete_session;
                 }
 
-                err = perf_event__synthesize_event_types(tool, process_synthesized_event,
-                                                         machine);
-                if (err < 0) {
-                        pr_err("Couldn't synthesize event_types.\n");
-                        goto out_delete_session;
-                }
-
                 if (have_tracepoints(&evsel_list->entries)) {
                         /*
                          * FIXME err <= 0 here actually means that
@@ -904,7 +897,6 @@ const struct option record_options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int err = -ENOMEM;
-        struct perf_evsel *pos;
         struct perf_evlist *evsel_list;
         struct perf_record *rec = &record;
         char errbuf[BUFSIZ];
@@ -968,11 +960,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
                 usage_with_options(record_usage, record_options);
 
-        list_for_each_entry(pos, &evsel_list->entries, node) {
-                if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos)))
-                        goto out_free_fd;
-        }
-
         if (rec->opts.user_interval != ULLONG_MAX)
                 rec->opts.default_interval = rec->opts.user_interval;
         if (rec->opts.user_freq != UINT_MAX)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3662047cc6b1..72eae7498c09 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -49,7 +49,6 @@ struct perf_report {
         bool                    mem_mode;
         struct perf_read_values show_threads_values;
         const char              *pretty_printing_style;
-        symbol_filter_t         annotate_init;
         const char              *cpu_list;
         const char              *symbol_filter_str;
         float                   min_percent;
@@ -89,7 +88,7 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
         if ((sort__has_parent || symbol_conf.use_callchain) &&
             sample->callchain) {
                 err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent);
+                                                 sample, &parent, al);
                 if (err)
                         return err;
         }
@@ -180,7 +179,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
         if ((sort__has_parent || symbol_conf.use_callchain)
             && sample->callchain) {
                 err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent);
+                                                 sample, &parent, al);
                 if (err)
                         return err;
         }
@@ -254,7 +253,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 
         if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
                 err = machine__resolve_callchain(machine, evsel, al->thread,
-                                                 sample, &parent);
+                                                 sample, &parent, al);
                 if (err)
                         return err;
         }
@@ -305,8 +304,7 @@ static int process_sample_event(struct perf_tool *tool,
         struct addr_location al;
         int ret;
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample,
-                                          rep->annotate_init) < 0) {
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                         event->header.type);
                 return -1;
@@ -367,7 +365,7 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
         struct perf_session *self = rep->session;
-        u64 sample_type = perf_evlist__sample_type(self->evlist);
+        u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
 
         if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
                 if (sort__has_parent) {
@@ -403,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep)
         return 0;
 }
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
         session_done = 1;
@@ -497,7 +493,7 @@ static int __cmd_report(struct perf_report *rep)
                 ret = perf_session__cpu_bitmap(session, rep->cpu_list,
                                                rep->cpu_bitmap);
                 if (ret)
-                        goto out_delete;
+                        return ret;
         }
 
         if (use_browser <= 0)
@@ -508,11 +504,11 @@ static int __cmd_report(struct perf_report *rep)
 
         ret = perf_report__setup_sample_type(rep);
         if (ret)
-                goto out_delete;
+                return ret;
 
         ret = perf_session__process_events(session, &rep->tool);
         if (ret)
-                goto out_delete;
+                return ret;
 
         kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
         kernel_kmap = map__kmap(kernel_map);
@@ -547,7 +543,7 @@ static int __cmd_report(struct perf_report *rep)
 
         if (dump_trace) {
                 perf_session__fprintf_nr_events(session, stdout);
-                goto out_delete;
+                return 0;
         }
 
         nr_samples = 0;
@@ -570,9 +566,12 @@ static int __cmd_report(struct perf_report *rep)
                 }
         }
 
+        if (session_done())
+                return 0;
+
         if (nr_samples == 0) {
                 ui__error("The %s file has no samples!\n", session->filename);
-                goto out_delete;
+                return 0;
         }
 
         list_for_each_entry(pos, &session->evlist->entries, node)
@@ -598,19 +597,6 @@ static int __cmd_report(struct perf_report *rep)
         } else
                 perf_evlist__tty_browse_hists(session->evlist, rep, help);
 
-out_delete:
-        /*
-         * Speed up the exit process, for large files this can
-         * take quite a while.
-         *
-         * XXX Enable this when using valgrind or if we ever
-         * librarize this command.
-         *
-         * Also experiment with obstacks to see how much speed
-         * up we'll get here.
-         *
-         * perf_session__delete(session);
-         */
         return ret;
 }
 
@@ -680,12 +666,23 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
         }
 
         /* get the call chain order */
-        if (!strcmp(tok2, "caller"))
+        if (!strncmp(tok2, "caller", strlen("caller")))
                 callchain_param.order = ORDER_CALLER;
-        else if (!strcmp(tok2, "callee"))
+        else if (!strncmp(tok2, "callee", strlen("callee")))
                 callchain_param.order = ORDER_CALLEE;
         else
                 return -1;
+
+        /* Get the sort key */
+        tok2 = strtok(NULL, ",");
+        if (!tok2)
+                goto setup;
+        if (!strncmp(tok2, "function", strlen("function")))
+                callchain_param.key = CCKEY_FUNCTION;
+        else if (!strncmp(tok2, "address", strlen("address")))
+                callchain_param.key = CCKEY_ADDRESS;
+        else
+                return -1;
 setup:
         if (callchain_register_param(&callchain_param) < 0) {
                 fprintf(stderr, "Can't register callchain params\n");
@@ -694,6 +691,24 @@ setup:
         return 0;
 }
 
+int
+report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
+                                const char *arg, int unset __maybe_unused)
+{
+        if (arg) {
+                int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
+                if (err) {
+                        char buf[BUFSIZ];
+                        regerror(err, &ignore_callees_regex, buf, sizeof(buf));
+                        pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
+                        return -1;
+                }
+                have_ignore_callees = 1;
+        }
+
+        return 0;
+}
+
 static int
 parse_branch_mode(const struct option *opt __maybe_unused,
                   const char *str __maybe_unused, int unset)
@@ -730,13 +745,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                 .tool = {
                         .sample          = process_sample_event,
                         .mmap            = perf_event__process_mmap,
+                        .mmap2           = perf_event__process_mmap2,
                         .comm            = perf_event__process_comm,
                         .exit            = perf_event__process_exit,
                         .fork            = perf_event__process_fork,
                         .lost            = perf_event__process_lost,
                         .read            = process_read_event,
                         .attr            = perf_event__process_attr,
-                        .event_type      = perf_event__process_event_type,
                         .tracing_data    = perf_event__process_tracing_data,
                         .build_id        = perf_event__process_build_id,
                         .ordered_samples = true,
@@ -780,10 +795,13 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
                     "Only display entries with parent-match"),
         OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
-                     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit and callchain order. "
-                     "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
+                     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
+                     "Default: fractal,0.5,callee,function", &parse_callchain_opt, callchain_default_opt),
         OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
                     "alias for inverted call graph"),
+        OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+                   "ignore callees of these functions in call graphs",
+                   report_parse_ignore_callees_opt),
         OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
                    "only consider symbols in these dsos"),
         OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
@@ -853,7 +871,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                 setup_browser(true);
         else {
                 use_browser = 0;
-                perf_hpp__column_enable(PERF_HPP__OVERHEAD);
                 perf_hpp__init();
         }
 
@@ -907,7 +924,8 @@ repeat:
          */
         if (use_browser == 1 && sort__has_sym) {
                 symbol_conf.priv_size = sizeof(struct annotation);
-                report.annotate_init  = symbol__annotate_init;
+                machines__set_symbol_filter(&session->machines,
+                                            symbol__annotate_init);
                 /*
                  * For searching by name on the "Browse map details".
                  * providing it only in verbose mode not to bloat too
@@ -931,14 +949,6 @@ repeat:
         if (parent_pattern != default_parent_pattern) {
                 if (sort_dimension__add("parent") < 0)
                         goto error;
-
-                /*
-                 * Only show the parent fields if we explicitly
-                 * sort that way. If we only use parent machinery
-                 * for filtering, we don't want it.
-                 */
-                if (!strstr(sort_order, "parent"))
-                        sort_parent.elide = 1;
         }
 
         if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index fed9ae432c16..d8c51b2f263f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -109,8 +109,9 @@ struct trace_sched_handler {
         int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
                             struct perf_sample *sample, struct machine *machine);
 
-        int (*fork_event)(struct perf_sched *sched, struct perf_evsel *evsel,
-                          struct perf_sample *sample);
+        /* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
+        int (*fork_event)(struct perf_sched *sched, union perf_event *event,
+                          struct machine *machine);
 
         int (*migrate_task_event)(struct perf_sched *sched,
                                   struct perf_evsel *evsel,
@@ -717,22 +718,31 @@ static int replay_switch_event(struct perf_sched *sched,
         return 0;
 }
 
-static int replay_fork_event(struct perf_sched *sched, struct perf_evsel *evsel,
-                             struct perf_sample *sample)
+static int replay_fork_event(struct perf_sched *sched,
+                             union perf_event *event,
+                             struct machine *machine)
 {
-        const char *parent_comm = perf_evsel__strval(evsel, sample, "parent_comm"),
-                   *child_comm  = perf_evsel__strval(evsel, sample, "child_comm");
-        const u32 parent_pid  = perf_evsel__intval(evsel, sample, "parent_pid"),
-                  child_pid  = perf_evsel__intval(evsel, sample, "child_pid");
+        struct thread *child, *parent;
+
+        child = machine__findnew_thread(machine, event->fork.pid,
+                                        event->fork.tid);
+        parent = machine__findnew_thread(machine, event->fork.ppid,
+                                         event->fork.ptid);
+
+        if (child == NULL || parent == NULL) {
+                pr_debug("thread does not exist on fork event: child %p, parent %p\n",
+                                 child, parent);
+                return 0;
+        }
 
         if (verbose) {
-                printf("sched_fork event %p\n", evsel);
-                printf("... parent: %s/%d\n", parent_comm, parent_pid);
-                printf("...  child: %s/%d\n", child_comm, child_pid);
+                printf("fork event\n");
+                printf("... parent: %s/%d\n", parent->comm, parent->tid);
+                printf("...  child: %s/%d\n", child->comm, child->tid);
         }
 
-        register_pid(sched, parent_pid, parent_comm);
-        register_pid(sched, child_pid, child_comm);
+        register_pid(sched, parent->tid, parent->comm);
+        register_pid(sched, child->tid, child->comm);
         return 0;
 }
 
@@ -824,14 +834,6 @@ static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
         return 0;
 }
 
-static int latency_fork_event(struct perf_sched *sched __maybe_unused,
-                              struct perf_evsel *evsel __maybe_unused,
-                              struct perf_sample *sample __maybe_unused)
-{
-        /* should insert the newcomer */
-        return 0;
-}
-
 static char sched_out_state(u64 prev_state)
 {
         const char *str = TASK_STATE_TO_CHAR_STR;
@@ -934,8 +936,8 @@ static int latency_switch_event(struct perf_sched *sched,
                 return -1;
         }
 
-        sched_out = machine__findnew_thread(machine, prev_pid);
-        sched_in = machine__findnew_thread(machine, next_pid);
+        sched_out = machine__findnew_thread(machine, 0, prev_pid);
+        sched_in = machine__findnew_thread(machine, 0, next_pid);
 
         out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
         if (!out_events) {
@@ -978,7 +980,7 @@ 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, pid);
+        struct thread *thread = machine__findnew_thread(machine, 0, pid);
         struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
         u64 timestamp = sample->time;
         int cpu = sample->cpu;
@@ -1016,7 +1018,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
         if (!success)
                 return 0;
 
-        wakee = machine__findnew_thread(machine, pid);
+        wakee = machine__findnew_thread(machine, 0, pid);
         atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
         if (!atoms) {
                 if (thread_atoms_insert(sched, wakee))
@@ -1070,12 +1072,12 @@ static int latency_migrate_task_event(struct perf_sched *sched,
         if (sched->profile_cpu == -1)
                 return 0;
 
-        migrant = machine__findnew_thread(machine, pid);
+        migrant = machine__findnew_thread(machine, 0, pid);
         atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
         if (!atoms) {
                 if (thread_atoms_insert(sched, migrant))
                         return -1;
-                register_pid(sched, migrant->pid, migrant->comm);
+                register_pid(sched, migrant->tid, migrant->comm);
                 atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
                 if (!atoms) {
                         pr_err("migration-event: Internal tree error");
@@ -1115,7 +1117,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
         sched->all_runtime += work_list->total_runtime;
         sched->all_count   += work_list->nb_atoms;
 
-        ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
+        ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->tid);
 
         for (i = 0; i < 24 - ret; i++)
                 printf(" ");
@@ -1131,9 +1133,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
-        if (l->thread->pid < r->thread->pid)
+        if (l->thread->tid < r->thread->tid)
                 return -1;
-        if (l->thread->pid > r->thread->pid)
+        if (l->thread->tid > r->thread->tid)
                 return 1;
 
         return 0;
@@ -1289,8 +1291,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
                 return -1;
         }
 
-        sched_out = machine__findnew_thread(machine, prev_pid);
-        sched_in = machine__findnew_thread(machine, next_pid);
+        sched_out = machine__findnew_thread(machine, 0, prev_pid);
+        sched_in = machine__findnew_thread(machine, 0, next_pid);
 
         sched->curr_thread[this_cpu] = sched_in;
 
@@ -1321,7 +1323,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
                         printf("*");
 
                 if (sched->curr_thread[cpu]) {
-                        if (sched->curr_thread[cpu]->pid)
+                        if (sched->curr_thread[cpu]->tid)
                                 printf("%2s ", sched->curr_thread[cpu]->shortname);
                         else
                                 printf(".  ");
@@ -1332,7 +1334,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
         printf("  %12.6f secs ", (double)timestamp/1e9);
         if (new_shortname) {
                 printf("%s => %s:%d\n",
-                        sched_in->shortname, sched_in->comm, sched_in->pid);
+                        sched_in->shortname, sched_in->comm, sched_in->tid);
         } else {
                 printf("\n");
         }
@@ -1379,25 +1381,20 @@ static int process_sched_runtime_event(struct perf_tool *tool,
         return 0;
 }
 
-static int process_sched_fork_event(struct perf_tool *tool,
-                                    struct perf_evsel *evsel,
-                                    struct perf_sample *sample,
-                                    struct machine *machine __maybe_unused)
+static int perf_sched__process_fork_event(struct perf_tool *tool,
+                                          union perf_event *event,
+                                          struct perf_sample *sample,
+                                          struct machine *machine)
 {
         struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
-        if (sched->tp_handler->fork_event)
-                return sched->tp_handler->fork_event(sched, evsel, sample);
+        /* run the fork event through the perf machineruy */
+        perf_event__process_fork(tool, event, sample, machine);
 
-        return 0;
-}
+        /* and then run additional processing needed for this command */
+        if (sched->tp_handler->fork_event)
+                return sched->tp_handler->fork_event(sched, event, machine);
 
-static int process_sched_exit_event(struct perf_tool *tool __maybe_unused,
-                                    struct perf_evsel *evsel,
-                                    struct perf_sample *sample __maybe_unused,
-                                    struct machine *machine __maybe_unused)
-{
-        pr_debug("sched_exit event %p\n", evsel);
         return 0;
 }
 
@@ -1425,15 +1422,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
                                                  struct perf_evsel *evsel,
                                                  struct machine *machine)
 {
-        struct thread *thread = machine__findnew_thread(machine, sample->tid);
         int err = 0;
 
-        if (thread == NULL) {
-                pr_debug("problem processing %s event, skipping it.\n",
-                         perf_evsel__name(evsel));
-                return -1;
-        }
-
         evsel->hists.stats.total_period += sample->period;
         hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 
@@ -1445,7 +1435,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
         return err;
 }
 
-static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
+static int perf_sched__read_events(struct perf_sched *sched,
                                    struct perf_session **psession)
 {
         const struct perf_evsel_str_handler handlers[] = {
@@ -1453,8 +1443,6 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
                 { "sched:sched_stat_runtime", process_sched_runtime_event, },
                 { "sched:sched_wakeup",       process_sched_wakeup_event, },
                 { "sched:sched_wakeup_new",   process_sched_wakeup_event, },
-                { "sched:sched_process_fork", process_sched_fork_event, },
-                { "sched:sched_process_exit", process_sched_exit_event, },
                 { "sched:sched_migrate_task", process_sched_migrate_task_event, },
         };
         struct perf_session *session;
@@ -1480,11 +1468,10 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy,
                 sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
         }
 
-        if (destroy)
-                perf_session__delete(session);
-
         if (psession)
                 *psession = session;
+        else
+                perf_session__delete(session);
 
         return 0;
 
@@ -1529,8 +1516,11 @@ static int perf_sched__lat(struct perf_sched *sched)
         struct perf_session *session;
 
         setup_pager();
-        if (perf_sched__read_events(sched, false, &session))
+
+        /* save session -- references to threads are held in work_list */
+        if (perf_sched__read_events(sched, &session))
                 return -1;
+
         perf_sched__sort_lat(sched);
 
         printf("\n ---------------------------------------------------------------------------------------------------------------\n");
@@ -1565,7 +1555,7 @@ static int perf_sched__map(struct perf_sched *sched)
         sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
 
         setup_pager();
-        if (perf_sched__read_events(sched, true, NULL))
+        if (perf_sched__read_events(sched, NULL))
                 return -1;
         print_bad_events(sched);
         return 0;
@@ -1580,7 +1570,7 @@ static int perf_sched__replay(struct perf_sched *sched)
 
         test_calibrations(sched);
 
-        if (perf_sched__read_events(sched, true, NULL))
+        if (perf_sched__read_events(sched, NULL))
                 return -1;
 
         printf("nr_run_events:        %ld\n", sched->nr_run_events);
@@ -1639,7 +1629,6 @@ static int __cmd_record(int argc, const char **argv)
                 "-e", "sched:sched_stat_sleep",
                 "-e", "sched:sched_stat_iowait",
                 "-e", "sched:sched_stat_runtime",
-                "-e", "sched:sched_process_exit",
                 "-e", "sched:sched_process_fork",
                 "-e", "sched:sched_wakeup",
                 "-e", "sched:sched_migrate_task",
@@ -1662,28 +1651,29 @@ static int __cmd_record(int argc, const char **argv)
         return cmd_record(i, rec_argv, NULL);
 }
 
+static const char default_sort_order[] = "avg, max, switch, runtime";
+static struct perf_sched sched = {
+        .tool = {
+                .sample          = perf_sched__process_tracepoint_sample,
+                .comm            = perf_event__process_comm,
+                .lost            = perf_event__process_lost,
+                .fork            = perf_sched__process_fork_event,
+                .ordered_samples = true,
+        },
+        .cmp_pid              = LIST_HEAD_INIT(sched.cmp_pid),
+        .sort_list            = LIST_HEAD_INIT(sched.sort_list),
+        .start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
+        .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
+        .curr_pid             = { [0 ... MAX_CPUS - 1] = -1 },
+        .sort_order           = default_sort_order,
+        .replay_repeat        = 10,
+        .profile_cpu          = -1,
+        .next_shortname1      = 'A',
+        .next_shortname2      = '0',
+};
+
 int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-        const char default_sort_order[] = "avg, max, switch, runtime";
-        struct perf_sched sched = {
-                .tool = {
-                        .sample          = perf_sched__process_tracepoint_sample,
-                        .comm            = perf_event__process_comm,
-                        .lost            = perf_event__process_lost,
-                        .fork            = perf_event__process_fork,
-                        .ordered_samples = true,
-                },
-                .cmp_pid              = LIST_HEAD_INIT(sched.cmp_pid),
-                .sort_list            = LIST_HEAD_INIT(sched.sort_list),
-                .start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
-                .work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
-                .curr_pid             = { [0 ... MAX_CPUS - 1] = -1 },
-                .sort_order           = default_sort_order,
-                .replay_repeat        = 10,
-                .profile_cpu          = -1,
-                .next_shortname1      = 'A',
-                .next_shortname2      = '0',
-        };
         const struct option latency_options[] = {
         OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
                    "sort by key(s): runtime, switch, avg, max"),
@@ -1729,7 +1719,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
                 .wakeup_event       = latency_wakeup_event,
                 .switch_event       = latency_switch_event,
                 .runtime_event      = latency_runtime_event,
-                .fork_event         = latency_fork_event,
                 .migrate_task_event = latency_migrate_task_event,
         };
         struct trace_sched_handler map_ops  = {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 92d4658f56fb..9c333ff3dfeb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -24,6 +24,7 @@ static u64			last_timestamp;
 static u64                      nr_unordered;
 extern const struct option      record_options[];
 static bool                     no_callchain;
+static bool                     latency_format;
 static bool                     system_wide;
 static const char               *cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -65,6 +66,7 @@ struct output_option {
 static struct {
         bool user_set;
         bool wildcard_set;
+        unsigned int print_ip_opts;
         u64 fields;
         u64 invalid_fields;
 } output[PERF_TYPE_MAX] = {
@@ -234,6 +236,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 {
         int j;
         struct perf_evsel *evsel;
+        struct perf_event_attr *attr;
 
         for (j = 0; j < PERF_TYPE_MAX; ++j) {
                 evsel = perf_session__find_first_evtype(session, j);
@@ -252,6 +255,24 @@ static int perf_session__check_output_opt(struct perf_session *session)
                 if (evsel && output[j].fields &&
                         perf_evsel__check_attr(evsel, session))
                         return -1;
+
+                if (evsel == NULL)
+                        continue;
+
+                attr = &evsel->attr;
+
+                output[j].print_ip_opts = 0;
+                if (PRINT_FIELD(IP))
+                        output[j].print_ip_opts |= PRINT_IP_OPT_IP;
+
+                if (PRINT_FIELD(SYM))
+                        output[j].print_ip_opts |= PRINT_IP_OPT_SYM;
+
+                if (PRINT_FIELD(DSO))
+                        output[j].print_ip_opts |= PRINT_IP_OPT_DSO;
+
+                if (PRINT_FIELD(SYMOFFSET))
+                        output[j].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
         }
 
         return 0;
@@ -381,8 +402,8 @@ static void print_sample_bts(union perf_event *event,
                 else
                         printf("\n");
                 perf_evsel__print_ip(evsel, event, sample, machine,
-                                     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
-                                     PRINT_FIELD(SYMOFFSET));
+                                     output[attr->type].print_ip_opts,
+                                     PERF_MAX_STACK_DEPTH);
         }
 
         printf(" => ");
@@ -396,10 +417,10 @@ static void print_sample_bts(union perf_event *event,
 
 static void process_event(union perf_event *event, struct perf_sample *sample,
                           struct perf_evsel *evsel, struct machine *machine,
-                          struct addr_location *al)
+                          struct thread *thread,
+                          struct addr_location *al __maybe_unused)
 {
         struct perf_event_attr *attr = &evsel->attr;
-        struct thread *thread = al->thread;
 
         if (output[attr->type].fields == 0)
                 return;
@@ -422,9 +443,10 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
                         printf(" ");
                 else
                         printf("\n");
+
                 perf_evsel__print_ip(evsel, event, sample, machine,
-                                     PRINT_FIELD(SYM), PRINT_FIELD(DSO),
-                                     PRINT_FIELD(SYMOFFSET));
+                                     output[attr->type].print_ip_opts,
+                                     PERF_MAX_STACK_DEPTH);
         }
 
         printf("\n");
@@ -479,7 +501,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                                 struct machine *machine)
 {
         struct addr_location al;
-        struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
+        struct thread *thread = machine__findnew_thread(machine, sample->pid,
+                                                        sample->tid);
 
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
@@ -498,7 +521,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                 return 0;
         }
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample, 0) < 0) {
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 pr_err("problem processing %d event, skipping it.\n",
                        event->header.type);
                 return -1;
@@ -510,7 +533,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
         if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
                 return 0;
 
-        scripting_ops->process_event(event, sample, evsel, machine, &al);
+        scripting_ops->process_event(event, sample, evsel, machine, thread, &al);
 
         evsel->hists.stats.total_period += sample->period;
         return 0;
@@ -519,19 +542,17 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_script = {
         .sample          = process_sample_event,
         .mmap            = perf_event__process_mmap,
+        .mmap2           = perf_event__process_mmap2,
         .comm            = perf_event__process_comm,
         .exit            = perf_event__process_exit,
         .fork            = perf_event__process_fork,
         .attr            = perf_event__process_attr,
-        .event_type      = perf_event__process_event_type,
         .tracing_data    = perf_event__process_tracing_data,
         .build_id        = perf_event__process_build_id,
         .ordered_samples = true,
         .ordering_requires_timestamps = true,
 };
 
-extern volatile int session_done;
-
 static void sig_handler(int sig __maybe_unused)
 {
         session_done = 1;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 352fbd7ff4a1..f686d5ff594e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -100,6 +100,7 @@ static const char		*pre_cmd			= NULL;
 static const char               *post_cmd                       = NULL;
 static bool                     sync_run                        = false;
 static unsigned int             interval                        = 0;
+static unsigned int             initial_delay                   = 0;
 static bool                     forever                         = false;
 static struct timespec          ref_time;
 static struct cpu_map           *aggr_map;
@@ -254,7 +255,8 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
         if (!perf_target__has_task(&target) &&
             perf_evsel__is_group_leader(evsel)) {
                 attr->disabled = 1;
-                attr->enable_on_exec = 1;
+                if (!initial_delay)
+                        attr->enable_on_exec = 1;
         }
 
         return perf_evsel__open_per_thread(evsel, evsel_list->threads);
@@ -414,6 +416,22 @@ static void print_interval(void)
                 list_for_each_entry(counter, &evsel_list->entries, node)
                         print_counter_aggr(counter, prefix);
         }
+
+        fflush(output);
+}
+
+static void handle_initial_delay(void)
+{
+        struct perf_evsel *counter;
+
+        if (initial_delay) {
+                const int ncpus = cpu_map__nr(evsel_list->cpus),
+                        nthreads = thread_map__nr(evsel_list->threads);
+
+                usleep(initial_delay * 1000);
+                list_for_each_entry(counter, &evsel_list->entries, node)
+                        perf_evsel__enable(counter, ncpus, nthreads);
+        }
 }
 
 static int __run_perf_stat(int argc, const char **argv)
@@ -486,6 +504,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
         if (forks) {
                 perf_evlist__start_workload(evsel_list);
+                handle_initial_delay();
 
                 if (interval) {
                         while (!waitpid(child_pid, &status, WNOHANG)) {
@@ -497,6 +516,7 @@ static int __run_perf_stat(int argc, const char **argv)
                 if (WIFSIGNALED(status))
                         psignal(WTERMSIG(status), argv[0]);
         } else {
+                handle_initial_delay();
                 while (!done) {
                         nanosleep(&ts, NULL);
                         if (interval)
@@ -1419,6 +1439,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
                      "aggregate counts per processor socket", AGGR_SOCKET),
         OPT_SET_UINT(0, "per-core", &aggr_mode,
                      "aggregate counts per physical processor core", AGGR_CORE),
+        OPT_UINTEGER('D', "delay", &initial_delay,
+                     "ms to wait before starting measurement after program start"),
         OPT_END()
         };
         const char * const stat_usage[] = {
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 4536a92b18f3..c2e02319347a 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -12,6 +12,8 @@
  * of the License.
  */
 
+#include <traceevent/event-parse.h>
+
 #include "builtin.h"
 
 #include "util/util.h"
@@ -19,6 +21,7 @@
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
@@ -328,25 +331,6 @@ struct wakeup_entry {
         int   success;
 };
 
-/*
- * trace_flag_type is an enumeration that holds different
- * states when a trace occurs. These are:
- *  IRQS_OFF            - interrupts were disabled
- *  IRQS_NOSUPPORT      - arch does not support irqs_disabled_flags
- *  NEED_RESCED         - reschedule is requested
- *  HARDIRQ             - inside an interrupt handler
- *  SOFTIRQ             - inside a softirq handler
- */
-enum trace_flag_type {
-        TRACE_FLAG_IRQS_OFF             = 0x01,
-        TRACE_FLAG_IRQS_NOSUPPORT       = 0x02,
-        TRACE_FLAG_NEED_RESCHED         = 0x04,
-        TRACE_FLAG_HARDIRQ              = 0x08,
-        TRACE_FLAG_SOFTIRQ              = 0x10,
-};
-
-
-
 struct sched_switch {
         struct trace_entry te;
         char prev_comm[TASK_COMM_LEN];
@@ -479,6 +463,8 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
         }
 }
 
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+                                  struct perf_sample *sample);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
                                 union perf_event *event __maybe_unused,
@@ -486,8 +472,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                                 struct perf_evsel *evsel,
                                 struct machine *machine __maybe_unused)
 {
-        struct trace_entry *te;
-
         if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
                 if (!first_time || first_time > sample->time)
                         first_time = sample->time;
@@ -495,69 +479,90 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                         last_time = sample->time;
         }
 
-        te = (void *)sample->raw_data;
-        if ((evsel->attr.sample_type & PERF_SAMPLE_RAW) && sample->raw_size > 0) {
-                char *event_str;
-#ifdef SUPPORT_OLD_POWER_EVENTS
-                struct power_entry_old *peo;
-                peo = (void *)te;
-#endif
-                /*
-                 * FIXME: use evsel, its already mapped from id to perf_evsel,
-                 * remove perf_header__find_event infrastructure bits.
-                 * Mapping all these "power:cpu_idle" strings to the tracepoint
-                 * ID and then just comparing against evsel->attr.config.
-                 *
-                 * e.g.:
-                 *
-                 * if (evsel->attr.config == power_cpu_idle_id)
-                 */
-                event_str = perf_header__find_event(te->type);
-
-                if (!event_str)
-                        return 0;
-
-                if (sample->cpu > numcpus)
-                        numcpus = sample->cpu;
-
-                if (strcmp(event_str, "power:cpu_idle") == 0) {
-                        struct power_processor_entry *ppe = (void *)te;
-                        if (ppe->state == (u32)PWR_EVENT_EXIT)
-                                c_state_end(ppe->cpu_id, sample->time);
-                        else
-                                c_state_start(ppe->cpu_id, sample->time,
-                                              ppe->state);
-                }
-                else if (strcmp(event_str, "power:cpu_frequency") == 0) {
-                        struct power_processor_entry *ppe = (void *)te;
-                        p_state_change(ppe->cpu_id, sample->time, ppe->state);
-                }
+        if (sample->cpu > numcpus)
+                numcpus = sample->cpu;
+
+        if (evsel->handler.func != NULL) {
+                tracepoint_handler f = evsel->handler.func;
+                return f(evsel, sample);
+        }
+
+        return 0;
+}
+
+static int
+process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
+                        struct perf_sample *sample)
+{
+        struct power_processor_entry *ppe = sample->raw_data;
+
+        if (ppe->state == (u32) PWR_EVENT_EXIT)
+                c_state_end(ppe->cpu_id, sample->time);
+        else
+                c_state_start(ppe->cpu_id, sample->time, ppe->state);
+        return 0;
+}
+
+static int
+process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
+                             struct perf_sample *sample)
+{
+        struct power_processor_entry *ppe = sample->raw_data;
+
+        p_state_change(ppe->cpu_id, sample->time, ppe->state);
+        return 0;
+}
+
+static int
+process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
+                            struct perf_sample *sample)
+{
+        struct trace_entry *te = sample->raw_data;
+
+        sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+        return 0;
+}
 
-                else if (strcmp(event_str, "sched:sched_wakeup") == 0)
-                        sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+static int
+process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
+                            struct perf_sample *sample)
+{
+        struct trace_entry *te = sample->raw_data;
 
-                else if (strcmp(event_str, "sched:sched_switch") == 0)
-                        sched_switch(sample->cpu, sample->time, te);
+        sched_switch(sample->cpu, sample->time, te);
+        return 0;
+}
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
-                if (use_old_power_events) {
-                        if (strcmp(event_str, "power:power_start") == 0)
-                                c_state_start(peo->cpu_id, sample->time,
-                                              peo->value);
-
-                        else if (strcmp(event_str, "power:power_end") == 0)
-                                c_state_end(sample->cpu, sample->time);
-
-                        else if (strcmp(event_str,
-                                        "power:power_frequency") == 0)
-                                p_state_change(peo->cpu_id, sample->time,
-                                               peo->value);
-                }
-#endif
-        }
+static int
+process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
+                           struct perf_sample *sample)
+{
+        struct power_entry_old *peo = sample->raw_data;
+
+        c_state_start(peo->cpu_id, sample->time, peo->value);
         return 0;
 }
 
+static int
+process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
+                         struct perf_sample *sample)
+{
+        c_state_end(sample->cpu, sample->time);
+        return 0;
+}
+
+static int
+process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
+                               struct perf_sample *sample)
+{
+        struct power_entry_old *peo = sample->raw_data;
+
+        p_state_change(peo->cpu_id, sample->time, peo->value);
+        return 0;
+}
+#endif /* SUPPORT_OLD_POWER_EVENTS */
+
 /*
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
@@ -974,6 +979,17 @@ static int __cmd_timechart(const char *output_name)
                 .sample          = process_sample_event,
                 .ordered_samples = true,
         };
+        const struct perf_evsel_str_handler power_tracepoints[] = {
+                { "power:cpu_idle",             process_sample_cpu_idle },
+                { "power:cpu_frequency",        process_sample_cpu_frequency },
+                { "sched:sched_wakeup",         process_sample_sched_wakeup },
+                { "sched:sched_switch",         process_sample_sched_switch },
+#ifdef SUPPORT_OLD_POWER_EVENTS
+                { "power:power_start",          process_sample_power_start },
+                { "power:power_end",            process_sample_power_end },
+                { "power:power_frequency",      process_sample_power_frequency },
+#endif
+        };
         struct perf_session *session = perf_session__new(input_name, O_RDONLY,
                                                          0, false, &perf_timechart);
         int ret = -EINVAL;
@@ -984,6 +1000,12 @@ static int __cmd_timechart(const char *output_name)
         if (!perf_session__has_traces(session, "timechart record"))
                 goto out_delete;
 
+        if (perf_session__set_tracepoints_handlers(session,
+                                                   power_tracepoints)) {
+                pr_err("Initializing session tracepoint handlers failed\n");
+                goto out_delete;
+        }
+
         ret = perf_session__process_events(session, &perf_timechart);
         if (ret)
                 goto out_delete;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e06c4f869330..212214162bb2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -40,6 +40,7 @@
 #include "util/xyarray.h"
 #include "util/sort.h"
 #include "util/intlist.h"
+#include "arch/common.h"
 
 #include "util/debug.h"
 
@@ -102,7 +103,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
         /*
          * We can't annotate with just /proc/kallsyms
          */
-        if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+        if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+            !dso__is_kcore(map->dso)) {
                 pr_err("Can't annotate %s: No vmlinux file was found in the "
                        "path\n", sym->name);
                 sleep(1);
@@ -237,8 +239,6 @@ out_unlock:
         pthread_mutex_unlock(&notes->lock);
 }
 
-static const char               CONSOLE_CLEAR[] = "";
-
 static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
                                                      struct addr_location *al,
                                                      struct perf_sample *sample)
@@ -689,7 +689,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 {
         struct perf_top *top = container_of(tool, struct perf_top, tool);
         struct symbol *parent = NULL;
-        u64 ip = event->ip.ip;
+        u64 ip = sample->ip;
         struct addr_location al;
         int err;
 
@@ -699,10 +699,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
                 if (!seen)
                         seen = intlist__new(NULL);
 
-                if (!intlist__has_entry(seen, event->ip.pid)) {
+                if (!intlist__has_entry(seen, sample->pid)) {
                         pr_err("Can't find guest [%d]'s kernel information\n",
-                                event->ip.pid);
-                        intlist__add(seen, event->ip.pid);
+                                sample->pid);
+                        intlist__add(seen, sample->pid);
                 }
                 return;
         }
@@ -716,8 +716,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
         if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
                 top->exact_samples++;
 
-        if (perf_event__preprocess_sample(event, machine, &al, sample,
-                                          symbol_filter) < 0 ||
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0 ||
             al.filtered)
                 return;
 
@@ -772,8 +771,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
                     sample->callchain) {
                         err = machine__resolve_callchain(machine, evsel,
                                                          al.thread, sample,
-                                                         &parent);
-
+                                                         &parent, &al);
                         if (err)
                                 return;
                 }
@@ -838,7 +836,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                         break;
                 case PERF_RECORD_MISC_GUEST_KERNEL:
                         ++top->guest_kernel_samples;
-                        machine = perf_session__find_machine(session, event->ip.pid);
+                        machine = perf_session__find_machine(session,
+                                                             sample.pid);
                         break;
                 case PERF_RECORD_MISC_GUEST_USER:
                         ++top->guest_us_samples;
@@ -939,6 +938,14 @@ static int __cmd_top(struct perf_top *top)
         if (top->session == NULL)
                 return -ENOMEM;
 
+        machines__set_symbol_filter(&top->session->machines, symbol_filter);
+
+        if (!objdump_path) {
+                ret = perf_session_env__lookup_objdump(&top->session->header.env);
+                if (ret)
+                        goto out_delete;
+        }
+
         ret = perf_top__setup_sample_type(top);
         if (ret)
                 goto out_delete;
@@ -1102,6 +1109,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
                              "mode[,dump_size]", record_callchain_help,
                              &parse_callchain_opt, "fp"),
+        OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+                   "ignore callees of these functions in call graphs",
+                   report_parse_ignore_callees_opt),
         OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
                     "Show a column with the sum of periods"),
         OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
@@ -1114,6 +1124,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Interleave source code with assembly code (default)"),
         OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
                     "Display raw encoding of assembly instructions (default)"),
+        OPT_STRING(0, "objdump", &objdump_path, "path",
+                    "objdump binary to use for disassembly and annotations"),
         OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
                    "Specify disassembler style (e.g. -M intel for intel syntax)"),
         OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ab3ed4af1466..71aa3e35406b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1,34 +1,350 @@
+#include <traceevent/event-parse.h>
 #include "builtin.h"
 #include "util/color.h"
+#include "util/debug.h"
 #include "util/evlist.h"
 #include "util/machine.h"
+#include "util/session.h"
 #include "util/thread.h"
 #include "util/parse-options.h"
+#include "util/strlist.h"
+#include "util/intlist.h"
 #include "util/thread_map.h"
-#include "event-parse.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
+#include <sys/mman.h>
+#include <linux/futex.h>
+
+/* For older distros: */
+#ifndef MAP_STACK
+# define MAP_STACK              0x20000
+#endif
+
+#ifndef MADV_HWPOISON
+# define MADV_HWPOISON          100
+#endif
+
+#ifndef MADV_MERGEABLE
+# define MADV_MERGEABLE         12
+#endif
+
+#ifndef MADV_UNMERGEABLE
+# define MADV_UNMERGEABLE       13
+#endif
+
+static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
+                                         unsigned long arg,
+                                         u8 arg_idx __maybe_unused,
+                                         u8 *arg_mask __maybe_unused)
+{
+        return scnprintf(bf, size, "%#lx", arg);
+}
+
+#define SCA_HEX syscall_arg__scnprintf_hex
+
+static size_t syscall_arg__scnprintf_whence(char *bf, size_t size,
+                                            unsigned long arg,
+                                            u8 arg_idx __maybe_unused,
+                                            u8 *arg_mask __maybe_unused)
+{
+        int whence = arg;
+
+        switch (whence) {
+#define P_WHENCE(n) case SEEK_##n: return scnprintf(bf, size, #n)
+        P_WHENCE(SET);
+        P_WHENCE(CUR);
+        P_WHENCE(END);
+#ifdef SEEK_DATA
+        P_WHENCE(DATA);
+#endif
+#ifdef SEEK_HOLE
+        P_WHENCE(HOLE);
+#endif
+#undef P_WHENCE
+        default: break;
+        }
+
+        return scnprintf(bf, size, "%#x", whence);
+}
+
+#define SCA_WHENCE syscall_arg__scnprintf_whence
+
+static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
+                                               unsigned long arg,
+                                               u8 arg_idx __maybe_unused,
+                                               u8 *arg_mask __maybe_unused)
+{
+        int printed = 0, prot = arg;
+
+        if (prot == PROT_NONE)
+                return scnprintf(bf, size, "NONE");
+#define P_MMAP_PROT(n) \
+        if (prot & PROT_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                prot &= ~PROT_##n; \
+        }
+
+        P_MMAP_PROT(EXEC);
+        P_MMAP_PROT(READ);
+        P_MMAP_PROT(WRITE);
+#ifdef PROT_SEM
+        P_MMAP_PROT(SEM);
+#endif
+        P_MMAP_PROT(GROWSDOWN);
+        P_MMAP_PROT(GROWSUP);
+#undef P_MMAP_PROT
+
+        if (prot)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot);
+
+        return printed;
+}
+
+#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
+
+static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
+                                                unsigned long arg, u8 arg_idx __maybe_unused,
+                                                u8 *arg_mask __maybe_unused)
+{
+        int printed = 0, flags = arg;
+
+#define P_MMAP_FLAG(n) \
+        if (flags & MAP_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                flags &= ~MAP_##n; \
+        }
+
+        P_MMAP_FLAG(SHARED);
+        P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
+        P_MMAP_FLAG(32BIT);
+#endif
+        P_MMAP_FLAG(ANONYMOUS);
+        P_MMAP_FLAG(DENYWRITE);
+        P_MMAP_FLAG(EXECUTABLE);
+        P_MMAP_FLAG(FILE);
+        P_MMAP_FLAG(FIXED);
+        P_MMAP_FLAG(GROWSDOWN);
+#ifdef MAP_HUGETLB
+        P_MMAP_FLAG(HUGETLB);
+#endif
+        P_MMAP_FLAG(LOCKED);
+        P_MMAP_FLAG(NONBLOCK);
+        P_MMAP_FLAG(NORESERVE);
+        P_MMAP_FLAG(POPULATE);
+        P_MMAP_FLAG(STACK);
+#ifdef MAP_UNINITIALIZED
+        P_MMAP_FLAG(UNINITIALIZED);
+#endif
+#undef P_MMAP_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+        return printed;
+}
+
+#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
+
+static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
+                                                      unsigned long arg, u8 arg_idx __maybe_unused,
+                                                      u8 *arg_mask __maybe_unused)
+{
+        int behavior = arg;
+
+        switch (behavior) {
+#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
+        P_MADV_BHV(NORMAL);
+        P_MADV_BHV(RANDOM);
+        P_MADV_BHV(SEQUENTIAL);
+        P_MADV_BHV(WILLNEED);
+        P_MADV_BHV(DONTNEED);
+        P_MADV_BHV(REMOVE);
+        P_MADV_BHV(DONTFORK);
+        P_MADV_BHV(DOFORK);
+        P_MADV_BHV(HWPOISON);
+#ifdef MADV_SOFT_OFFLINE
+        P_MADV_BHV(SOFT_OFFLINE);
+#endif
+        P_MADV_BHV(MERGEABLE);
+        P_MADV_BHV(UNMERGEABLE);
+#ifdef MADV_HUGEPAGE
+        P_MADV_BHV(HUGEPAGE);
+#endif
+#ifdef MADV_NOHUGEPAGE
+        P_MADV_BHV(NOHUGEPAGE);
+#endif
+#ifdef MADV_DONTDUMP
+        P_MADV_BHV(DONTDUMP);
+#endif
+#ifdef MADV_DODUMP
+        P_MADV_BHV(DODUMP);
+#endif
+#undef P_MADV_PHV
+        default: break;
+        }
+
+        return scnprintf(bf, size, "%#x", behavior);
+}
+
+#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior
+
+static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, unsigned long arg,
+                                              u8 arg_idx __maybe_unused, u8 *arg_mask)
+{
+        enum syscall_futex_args {
+                SCF_UADDR   = (1 << 0),
+                SCF_OP      = (1 << 1),
+                SCF_VAL     = (1 << 2),
+                SCF_TIMEOUT = (1 << 3),
+                SCF_UADDR2  = (1 << 4),
+                SCF_VAL3    = (1 << 5),
+        };
+        int op = arg;
+        int cmd = op & FUTEX_CMD_MASK;
+        size_t printed = 0;
+
+        switch (cmd) {
+#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
+        P_FUTEX_OP(WAIT);           *arg_mask |= SCF_VAL3|SCF_UADDR2;             break;
+        P_FUTEX_OP(WAKE);           *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+        P_FUTEX_OP(FD);             *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+        P_FUTEX_OP(REQUEUE);        *arg_mask |= SCF_VAL3|SCF_TIMEOUT;            break;
+        P_FUTEX_OP(CMP_REQUEUE);    *arg_mask |= SCF_TIMEOUT;                     break;
+        P_FUTEX_OP(CMP_REQUEUE_PI); *arg_mask |= SCF_TIMEOUT;                     break;
+        P_FUTEX_OP(WAKE_OP);                                                      break;
+        P_FUTEX_OP(LOCK_PI);        *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+        P_FUTEX_OP(UNLOCK_PI);      *arg_mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+        P_FUTEX_OP(TRYLOCK_PI);     *arg_mask |= SCF_VAL3|SCF_UADDR2;             break;
+        P_FUTEX_OP(WAIT_BITSET);    *arg_mask |= SCF_UADDR2;                      break;
+        P_FUTEX_OP(WAKE_BITSET);    *arg_mask |= SCF_UADDR2;                      break;
+        P_FUTEX_OP(WAIT_REQUEUE_PI);                                              break;
+        default: printed = scnprintf(bf, size, "%#x", cmd);                       break;
+        }
+
+        if (op & FUTEX_PRIVATE_FLAG)
+                printed += scnprintf(bf + printed, size - printed, "|PRIV");
+
+        if (op & FUTEX_CLOCK_REALTIME)
+                printed += scnprintf(bf + printed, size - printed, "|CLKRT");
+
+        return printed;
+}
+
+#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op
+
+static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
+                                               unsigned long arg,
+                                               u8 arg_idx, u8 *arg_mask)
+{
+        int printed = 0, flags = arg;
+
+        if (!(flags & O_CREAT))
+                *arg_mask |= 1 << (arg_idx + 1); /* Mask the mode parm */
+
+        if (flags == 0)
+                return scnprintf(bf, size, "RDONLY");
+#define P_FLAG(n) \
+        if (flags & O_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                flags &= ~O_##n; \
+        }
+
+        P_FLAG(APPEND);
+        P_FLAG(ASYNC);
+        P_FLAG(CLOEXEC);
+        P_FLAG(CREAT);
+        P_FLAG(DIRECT);
+        P_FLAG(DIRECTORY);
+        P_FLAG(EXCL);
+        P_FLAG(LARGEFILE);
+        P_FLAG(NOATIME);
+        P_FLAG(NOCTTY);
+#ifdef O_NONBLOCK
+        P_FLAG(NONBLOCK);
+#elif O_NDELAY
+        P_FLAG(NDELAY);
+#endif
+#ifdef O_PATH
+        P_FLAG(PATH);
+#endif
+        P_FLAG(RDWR);
+#ifdef O_DSYNC
+        if ((flags & O_SYNC) == O_SYNC)
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
+        else {
+                P_FLAG(DSYNC);
+        }
+#else
+        P_FLAG(SYNC);
+#endif
+        P_FLAG(TRUNC);
+        P_FLAG(WRONLY);
+#undef P_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+        return printed;
+}
+
+#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 
 static struct syscall_fmt {
         const char *name;
         const char *alias;
+        size_t     (*arg_scnprintf[6])(char *bf, size_t size, unsigned long arg, u8 arg_idx, u8 *arg_mask);
         bool       errmsg;
         bool       timeout;
+        bool       hexret;
 } syscall_fmts[] = {
         { .name     = "access",     .errmsg = true, },
         { .name     = "arch_prctl", .errmsg = true, .alias = "prctl", },
+        { .name     = "brk",        .hexret = true,
+          .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
+        { .name     = "mmap",       .hexret = true, },
+        { .name     = "connect",    .errmsg = true, },
         { .name     = "fstat",      .errmsg = true, .alias = "newfstat", },
         { .name     = "fstatat",    .errmsg = true, .alias = "newfstatat", },
-        { .name     = "futex",      .errmsg = true, },
-        { .name     = "open",       .errmsg = true, },
+        { .name     = "futex",      .errmsg = true,
+          .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
+        { .name     = "ioctl",      .errmsg = true,
+          .arg_scnprintf = { [2] = SCA_HEX, /* arg */ }, },
+        { .name     = "lseek",      .errmsg = true,
+          .arg_scnprintf = { [2] = SCA_WHENCE, /* whence */ }, },
+        { .name     = "lstat",      .errmsg = true, .alias = "newlstat", },
+        { .name     = "madvise",    .errmsg = true,
+          .arg_scnprintf = { [0] = SCA_HEX,      /* start */
+                             [2] = SCA_MADV_BHV, /* behavior */ }, },
+        { .name     = "mmap",       .hexret = true,
+          .arg_scnprintf = { [0] = SCA_HEX,       /* addr */
+                             [2] = SCA_MMAP_PROT, /* prot */
+                             [3] = SCA_MMAP_FLAGS, /* flags */ }, },
+        { .name     = "mprotect",   .errmsg = true,
+          .arg_scnprintf = { [0] = SCA_HEX, /* start */
+                             [2] = SCA_MMAP_PROT, /* prot */ }, },
+        { .name     = "mremap",     .hexret = true,
+          .arg_scnprintf = { [0] = SCA_HEX, /* addr */
+                             [4] = SCA_HEX, /* new_addr */ }, },
+        { .name     = "munmap",     .errmsg = true,
+          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+        { .name     = "open",       .errmsg = true,
+          .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
+        { .name     = "open_by_handle_at", .errmsg = true,
+          .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+        { .name     = "openat",     .errmsg = true,
+          .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
         { .name     = "poll",       .errmsg = true, .timeout = true, },
         { .name     = "ppoll",      .errmsg = true, .timeout = true, },
+        { .name     = "pread",      .errmsg = true, .alias = "pread64", },
+        { .name     = "pwrite",     .errmsg = true, .alias = "pwrite64", },
         { .name     = "read",       .errmsg = true, },
         { .name     = "recvfrom",   .errmsg = true, },
         { .name     = "select",     .errmsg = true, .timeout = true, },
         { .name     = "socket",     .errmsg = true, },
         { .name     = "stat",       .errmsg = true, .alias = "newstat", },
+        { .name     = "uname",      .errmsg = true, .alias = "newuname", },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -46,7 +362,10 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 struct syscall {
         struct event_format *tp_format;
         const char          *name;
+        bool                filtered;
         struct syscall_fmt  *fmt;
+        size_t              (**arg_scnprintf)(char *bf, size_t size,
+                                              unsigned long arg, u8 arg_idx, u8 *args_mask);
 };
 
 static size_t fprintf_duration(unsigned long t, FILE *fp)
@@ -60,7 +379,7 @@ static size_t fprintf_duration(unsigned long t, FILE *fp)
                 printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
         else
                 printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration);
-        return printed + fprintf(stdout, "): ");
+        return printed + fprintf(fp, "): ");
 }
 
 struct thread_trace {
@@ -77,7 +396,7 @@ static struct thread_trace *thread_trace__new(void)
         return zalloc(sizeof(struct thread_trace));
 }
 
-static struct thread_trace *thread__trace(struct thread *thread)
+static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
 {
         struct thread_trace *ttrace;
 
@@ -95,12 +414,13 @@ static struct thread_trace *thread__trace(struct thread *thread)
 
         return ttrace;
 fail:
-        color_fprintf(stdout, PERF_COLOR_RED,
+        color_fprintf(fp, PERF_COLOR_RED,
                       "WARNING: not enough memory, dropping samples!\n");
         return NULL;
 }
 
 struct trace {
+        struct perf_tool        tool;
         int                     audit_machine;
         struct {
                 int             max;
@@ -109,7 +429,12 @@ struct trace {
         struct perf_record_opts opts;
         struct machine          host;
         u64                     base_time;
+        FILE                    *output;
         unsigned long           nr_events;
+        struct strlist          *ev_qualifier;
+        bool                    not_ev_qualifier;
+        struct intlist          *tid_list;
+        struct intlist          *pid_list;
         bool                    sched;
         bool                    multiple_threads;
         double                  duration_filter;
@@ -142,18 +467,19 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
         printed += fprintf_duration(duration, fp);
 
         if (trace->multiple_threads)
-                printed += fprintf(fp, "%d ", thread->pid);
+                printed += fprintf(fp, "%d ", thread->tid);
 
         return printed;
 }
 
-static int trace__process_event(struct machine *machine, union perf_event *event)
+static int trace__process_event(struct trace *trace, struct machine *machine,
+                                union perf_event *event)
 {
         int ret = 0;
 
         switch (event->header.type) {
         case PERF_RECORD_LOST:
-                color_fprintf(stdout, PERF_COLOR_RED,
+                color_fprintf(trace->output, PERF_COLOR_RED,
                               "LOST %" PRIu64 " events!\n", event->lost.lost);
                 ret = machine__process_lost_event(machine, event);
         default:
@@ -164,12 +490,13 @@ static int trace__process_event(struct machine *machine, union perf_event *event
         return ret;
 }
 
-static int trace__tool_process(struct perf_tool *tool __maybe_unused,
+static int trace__tool_process(struct perf_tool *tool,
                                union perf_event *event,
                                struct perf_sample *sample __maybe_unused,
                                struct machine *machine)
 {
-        return trace__process_event(machine, event);
+        struct trace *trace = container_of(tool, struct trace, tool);
+        return trace__process_event(trace, machine, event);
 }
 
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
@@ -183,11 +510,11 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
         machine__create_kernel_maps(&trace->host);
 
         if (perf_target__has_task(&trace->opts.target)) {
-                err = perf_event__synthesize_thread_map(NULL, evlist->threads,
+                err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
                                                         trace__tool_process,
                                                         &trace->host);
         } else {
-                err = perf_event__synthesize_threads(NULL, trace__tool_process,
+                err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
                                                      &trace->host);
         }
 
@@ -197,6 +524,26 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
         return err;
 }
 
+static int syscall__set_arg_fmts(struct syscall *sc)
+{
+        struct format_field *field;
+        int idx = 0;
+
+        sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *));
+        if (sc->arg_scnprintf == NULL)
+                return -1;
+
+        for (field = sc->tp_format->format.fields->next; field; field = field->next) {
+                if (sc->fmt && sc->fmt->arg_scnprintf[idx])
+                        sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
+                else if (field->flags & FIELD_IS_POINTER)
+                        sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+                ++idx;
+        }
+
+        return 0;
+}
+
 static int trace__read_syscall_info(struct trace *trace, int id)
 {
         char tp_name[128];
@@ -225,6 +572,20 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 
         sc = trace->syscalls.table + id;
         sc->name = name;
+
+        if (trace->ev_qualifier) {
+                bool in = strlist__find(trace->ev_qualifier, name) != NULL;
+
+                if (!(in ^ trace->not_ev_qualifier)) {
+                        sc->filtered = true;
+                        /*
+                         * No need to do read tracepoint information since this will be
+                         * filtered out.
+                         */
+                        return 0;
+                }
+        }
+
         sc->fmt  = syscall_fmt__find(sc->name);
 
         snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
@@ -235,7 +596,10 @@ static int trace__read_syscall_info(struct trace *trace, int id)
                 sc->tp_format = event_format__new("syscalls", tp_name);
         }
 
-        return sc->tp_format != NULL ? 0 : -1;
+        if (sc->tp_format == NULL)
+                return -1;
+
+        return syscall__set_arg_fmts(sc);
 }
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
@@ -246,11 +610,23 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 
         if (sc->tp_format != NULL) {
                 struct format_field *field;
+                u8 mask = 0, bit = 1;
+
+                for (field = sc->tp_format->format.fields->next; field;
+                     field = field->next, ++i, bit <<= 1) {
+                        if (mask & bit)
+                                continue;
 
-                for (field = sc->tp_format->format.fields->next; field; field = field->next) {
                         printed += scnprintf(bf + printed, size - printed,
-                                             "%s%s: %ld", printed ? ", " : "",
-                                             field->name, args[i++]);
+                                             "%s%s: ", printed ? ", " : "", field->name);
+
+                        if (sc->arg_scnprintf && sc->arg_scnprintf[i]) {
+                                printed += sc->arg_scnprintf[i](bf + printed, size - printed,
+                                                                args[i], i, &mask);
+                        } else {
+                                printed += scnprintf(bf + printed, size - printed,
+                                                     "%ld", args[i]);
+                        }
                 }
         } else {
                 while (i < 6) {
@@ -274,7 +650,22 @@ static struct syscall *trace__syscall_info(struct trace *trace,
         int id = perf_evsel__intval(evsel, sample, "id");
 
         if (id < 0) {
-                printf("Invalid syscall %d id, skipping...\n", id);
+
+                /*
+                 * XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
+                 * before that, leaving at a higher verbosity level till that is
+                 * explained. Reproduced with plain ftrace with:
+                 *
+                 * echo 1 > /t/events/raw_syscalls/sys_exit/enable
+                 * grep "NR -1 " /t/trace_pipe
+                 *
+                 * After generating some load on the machine.
+                 */
+                if (verbose > 1) {
+                        static u64 n;
+                        fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
+                                id, perf_evsel__name(evsel), ++n);
+                }
                 return NULL;
         }
 
@@ -288,10 +679,12 @@ static struct syscall *trace__syscall_info(struct trace *trace,
         return &trace->syscalls.table[id];
 
 out_cant_read:
-        printf("Problems reading syscall %d", id);
-        if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
-                printf("(%s)", trace->syscalls.table[id].name);
-        puts(" information");
+        if (verbose) {
+                fprintf(trace->output, "Problems reading syscall %d", id);
+                if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
+                        fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
+                fputs(" information\n", trace->output);
+        }
         return NULL;
 }
 
@@ -301,16 +694,25 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
         char *msg;
         void *args;
         size_t printed = 0;
-        struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
+        struct thread *thread;
         struct syscall *sc = trace__syscall_info(trace, evsel, sample);
-        struct thread_trace *ttrace = thread__trace(thread);
+        struct thread_trace *ttrace;
 
-        if (ttrace == NULL || sc == NULL)
+        if (sc == NULL)
+                return -1;
+
+        if (sc->filtered)
+                return 0;
+
+        thread = machine__findnew_thread(&trace->host, sample->pid,
+                                         sample->tid);
+        ttrace = thread__trace(thread, trace->output);
+        if (ttrace == NULL)
                 return -1;
 
         args = perf_evsel__rawptr(evsel, sample, "args");
         if (args == NULL) {
-                printf("Problems reading syscall arguments\n");
+                fprintf(trace->output, "Problems reading syscall arguments\n");
                 return -1;
         }
 
@@ -330,8 +732,8 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
         if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
                 if (!trace->duration_filter) {
-                        trace__fprintf_entry_head(trace, thread, 1, sample->time, stdout);
-                        printf("%-70s\n", ttrace->entry_str);
+                        trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
+                        fprintf(trace->output, "%-70s\n", ttrace->entry_str);
                 }
         } else
                 ttrace->entry_pending = true;
@@ -344,11 +746,20 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 {
         int ret;
         u64 duration = 0;
-        struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
-        struct thread_trace *ttrace = thread__trace(thread);
+        struct thread *thread;
         struct syscall *sc = trace__syscall_info(trace, evsel, sample);
+        struct thread_trace *ttrace;
 
-        if (ttrace == NULL || sc == NULL)
+        if (sc == NULL)
+                return -1;
+
+        if (sc->filtered)
+                return 0;
+
+        thread = machine__findnew_thread(&trace->host, sample->pid,
+                                         sample->tid);
+        ttrace = thread__trace(thread, trace->output);
+        if (ttrace == NULL)
                 return -1;
 
         ret = perf_evsel__intval(evsel, sample, "ret");
@@ -364,28 +775,33 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
         } else if (trace->duration_filter)
                 goto out;
 
-        trace__fprintf_entry_head(trace, thread, duration, sample->time, stdout);
+        trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
 
         if (ttrace->entry_pending) {
-                printf("%-70s", ttrace->entry_str);
+                fprintf(trace->output, "%-70s", ttrace->entry_str);
         } else {
-                printf(" ... [");
-                color_fprintf(stdout, PERF_COLOR_YELLOW, "continued");
-                printf("]: %s()", sc->name);
+                fprintf(trace->output, " ... [");
+                color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
+                fprintf(trace->output, "]: %s()", sc->name);
         }
 
-        if (ret < 0 && sc->fmt && sc->fmt->errmsg) {
+        if (sc->fmt == NULL) {
+signed_print:
+                fprintf(trace->output, ") = %d", ret);
+        } else if (ret < 0 && sc->fmt->errmsg) {
                 char bf[256];
                 const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
 
-                printf(") = -1 %s %s", e, emsg);
-        } else if (ret == 0 && sc->fmt && sc->fmt->timeout)
-                printf(") = 0 Timeout");
+                fprintf(trace->output, ") = -1 %s %s", e, emsg);
+        } else if (ret == 0 && sc->fmt->timeout)
+                fprintf(trace->output, ") = 0 Timeout");
+        else if (sc->fmt->hexret)
+                fprintf(trace->output, ") = %#x", ret);
         else
-                printf(") = %d", ret);
+                goto signed_print;
 
-        putchar('\n');
+        fputc('\n', trace->output);
 out:
         ttrace->entry_pending = false;
 
@@ -397,8 +813,10 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 {
         u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
         double runtime_ms = (double)runtime / NSEC_PER_MSEC;
-        struct thread *thread = machine__findnew_thread(&trace->host, sample->tid);
-        struct thread_trace *ttrace = thread__trace(thread);
+        struct thread *thread = machine__findnew_thread(&trace->host,
+                                                        sample->pid,
+                                                        sample->tid);
+        struct thread_trace *ttrace = thread__trace(thread, trace->output);
 
         if (ttrace == NULL)
                 goto out_dump;
@@ -408,7 +826,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
         return 0;
 
 out_dump:
-        printf("%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
+        fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
                evsel->name,
                perf_evsel__strval(evsel, sample, "comm"),
                (pid_t)perf_evsel__intval(evsel, sample, "pid"),
@@ -417,6 +835,72 @@ out_dump:
         return 0;
 }
 
+static bool skip_sample(struct trace *trace, struct perf_sample *sample)
+{
+        if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
+            (trace->tid_list && intlist__find(trace->tid_list, sample->tid)))
+                return false;
+
+        if (trace->pid_list || trace->tid_list)
+                return true;
+
+        return false;
+}
+
+static int trace__process_sample(struct perf_tool *tool,
+                                 union perf_event *event __maybe_unused,
+                                 struct perf_sample *sample,
+                                 struct perf_evsel *evsel,
+                                 struct machine *machine __maybe_unused)
+{
+        struct trace *trace = container_of(tool, struct trace, tool);
+        int err = 0;
+
+        tracepoint_handler handler = evsel->handler.func;
+
+        if (skip_sample(trace, sample))
+                return 0;
+
+        if (trace->base_time == 0)
+                trace->base_time = sample->time;
+
+        if (handler)
+                handler(trace, evsel, sample);
+
+        return err;
+}
+
+static bool
+perf_session__has_tp(struct perf_session *session, const char *name)
+{
+        struct perf_evsel *evsel;
+
+        evsel = perf_evlist__find_tracepoint_by_name(session->evlist, name);
+
+        return evsel != NULL;
+}
+
+static int parse_target_str(struct trace *trace)
+{
+        if (trace->opts.target.pid) {
+                trace->pid_list = intlist__new(trace->opts.target.pid);
+                if (trace->pid_list == NULL) {
+                        pr_err("Error parsing process id string\n");
+                        return -EINVAL;
+                }
+        }
+
+        if (trace->opts.target.tid) {
+                trace->tid_list = intlist__new(trace->opts.target.tid);
+                if (trace->tid_list == NULL) {
+                        pr_err("Error parsing thread id string\n");
+                        return -EINVAL;
+                }
+        }
+
+        return 0;
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
         struct perf_evlist *evlist = perf_evlist__new();
@@ -426,32 +910,32 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         const bool forks = argc > 0;
 
         if (evlist == NULL) {
-                printf("Not enough memory to run!\n");
+                fprintf(trace->output, "Not enough memory to run!\n");
                 goto out;
         }
 
         if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) ||
             perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit)) {
-                printf("Couldn't read the raw_syscalls tracepoints information!\n");
+                fprintf(trace->output, "Couldn't read the raw_syscalls tracepoints information!\n");
                 goto out_delete_evlist;
         }
 
         if (trace->sched &&
             perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
                                    trace__sched_stat_runtime)) {
-                printf("Couldn't read the sched_stat_runtime tracepoint information!\n");
+                fprintf(trace->output, "Couldn't read the sched_stat_runtime tracepoint information!\n");
                 goto out_delete_evlist;
         }
 
         err = perf_evlist__create_maps(evlist, &trace->opts.target);
         if (err < 0) {
-                printf("Problems parsing the target to trace, check your options!\n");
+                fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
                 goto out_delete_evlist;
         }
 
         err = trace__symbols_init(trace, evlist);
         if (err < 0) {
-                printf("Problems initializing symbol libraries!\n");
+                fprintf(trace->output, "Problems initializing symbol libraries!\n");
                 goto out_delete_maps;
         }
 
@@ -464,20 +948,20 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
                 err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
                                                     argv, false, false);
                 if (err < 0) {
-                        printf("Couldn't run the workload!\n");
+                        fprintf(trace->output, "Couldn't run the workload!\n");
                         goto out_delete_maps;
                 }
         }
 
         err = perf_evlist__open(evlist);
         if (err < 0) {
-                printf("Couldn't create the events: %s\n", strerror(errno));
+                fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
                 goto out_delete_maps;
         }
 
         err = perf_evlist__mmap(evlist, UINT_MAX, false);
         if (err < 0) {
-                printf("Couldn't mmap the events: %s\n", strerror(errno));
+                fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
                 goto out_close_evlist;
         }
 
@@ -502,7 +986,7 @@ again:
 
                         err = perf_evlist__parse_sample(evlist, event, &sample);
                         if (err) {
-                                printf("Can't parse sample, err = %d, skipping...\n", err);
+                                fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
                                 continue;
                         }
 
@@ -510,18 +994,18 @@ again:
                                 trace->base_time = sample.time;
 
                         if (type != PERF_RECORD_SAMPLE) {
-                                trace__process_event(&trace->host, event);
+                                trace__process_event(trace, &trace->host, event);
                                 continue;
                         }
 
                         evsel = perf_evlist__id2evsel(evlist, sample.id);
                         if (evsel == NULL) {
-                                printf("Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
+                                fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
                                 continue;
                         }
 
                         if (sample.raw_data == NULL) {
-                                printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+                                fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
                                        perf_evsel__name(evsel), sample.tid,
                                        sample.cpu, sample.raw_size);
                                 continue;
@@ -529,6 +1013,9 @@ again:
 
                         handler = evsel->handler.func;
                         handler(trace, evsel, &sample);
+
+                        if (done)
+                                goto out_unmap_evlist;
                 }
         }
 
@@ -556,6 +1043,70 @@ out:
         return err;
 }
 
+static int trace__replay(struct trace *trace)
+{
+        const struct perf_evsel_str_handler handlers[] = {
+                { "raw_syscalls:sys_enter",  trace__sys_enter, },
+                { "raw_syscalls:sys_exit",   trace__sys_exit, },
+        };
+
+        struct perf_session *session;
+        int err = -1;
+
+        trace->tool.sample        = trace__process_sample;
+        trace->tool.mmap          = perf_event__process_mmap;
+        trace->tool.mmap2         = perf_event__process_mmap2;
+        trace->tool.comm          = perf_event__process_comm;
+        trace->tool.exit          = perf_event__process_exit;
+        trace->tool.fork          = perf_event__process_fork;
+        trace->tool.attr          = perf_event__process_attr;
+        trace->tool.tracing_data = perf_event__process_tracing_data;
+        trace->tool.build_id      = perf_event__process_build_id;
+
+        trace->tool.ordered_samples = true;
+        trace->tool.ordering_requires_timestamps = true;
+
+        /* add tid to output */
+        trace->multiple_threads = true;
+
+        if (symbol__init() < 0)
+                return -1;
+
+        session = perf_session__new(input_name, O_RDONLY, 0, false,
+                                    &trace->tool);
+        if (session == NULL)
+                return -ENOMEM;
+
+        err = perf_session__set_tracepoints_handlers(session, handlers);
+        if (err)
+                goto out;
+
+        if (!perf_session__has_tp(session, "raw_syscalls:sys_enter")) {
+                pr_err("Data file does not have raw_syscalls:sys_enter events\n");
+                goto out;
+        }
+
+        if (!perf_session__has_tp(session, "raw_syscalls:sys_exit")) {
+                pr_err("Data file does not have raw_syscalls:sys_exit events\n");
+                goto out;
+        }
+
+        err = parse_target_str(trace);
+        if (err != 0)
+                goto out;
+
+        setup_pager();
+
+        err = perf_session__process_events(session, &trace->tool);
+        if (err)
+                pr_err("Failed to process events, error %d", err);
+
+out:
+        perf_session__delete(session);
+
+        return err;
+}
+
 static size_t trace__fprintf_threads_header(FILE *fp)
 {
         size_t printed;
@@ -593,7 +1144,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
                         color = PERF_COLOR_YELLOW;
 
                 printed += color_fprintf(fp, color, "%20s", thread->comm);
-                printed += fprintf(fp, " - %-5d :%11lu   [", thread->pid, ttrace->nr_events);
+                printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
                 printed += color_fprintf(fp, color, "%5.1f%%", ratio);
                 printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
         }
@@ -610,6 +1161,23 @@ static int trace__set_duration(const struct option *opt, const char *str,
         return 0;
 }
 
+static int trace__open_output(struct trace *trace, const char *filename)
+{
+        struct stat st;
+
+        if (!stat(filename, &st) && st.st_size) {
+                char oldname[PATH_MAX];
+
+                scnprintf(oldname, sizeof(oldname), "%s.old", filename);
+                unlink(oldname);
+                rename(filename, oldname);
+        }
+
+        trace->output = fopen(filename, "w");
+
+        return trace->output == NULL ? -errno : 0;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         const char * const trace_usage[] = {
@@ -632,26 +1200,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                         .no_delay      = true,
                         .mmap_pages    = 1024,
                 },
+                .output = stdout,
         };
+        const char *output_name = NULL;
+        const char *ev_qualifier_str = NULL;
         const struct option trace_options[] = {
+        OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
+                    "list of events to trace"),
+        OPT_STRING('o', "output", &output_name, "file", "output file name"),
+        OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
         OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
                     "trace events on existing process id"),
-        OPT_STRING(0, "tid", &trace.opts.target.tid, "tid",
+        OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
                     "trace events on existing thread id"),
-        OPT_BOOLEAN(0, "all-cpus", &trace.opts.target.system_wide,
+        OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
                     "system-wide collection from all CPUs"),
-        OPT_STRING(0, "cpu", &trace.opts.target.cpu_list, "cpu",
+        OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
                     "list of cpus to monitor"),
         OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
                     "child tasks do not inherit counters"),
-        OPT_UINTEGER(0, "mmap-pages", &trace.opts.mmap_pages,
+        OPT_UINTEGER('m', "mmap-pages", &trace.opts.mmap_pages,
                      "number of mmap data pages"),
-        OPT_STRING(0, "uid", &trace.opts.target.uid_str, "user",
+        OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
                    "user to profile"),
         OPT_CALLBACK(0, "duration", &trace, "float",
                      "show only events with duration > N.M ms",
                      trace__set_duration),
         OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
+        OPT_INCR('v', "verbose", &verbose, "be more verbose"),
         OPT_END()
         };
         int err;
@@ -659,27 +1235,57 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 
         argc = parse_options(argc, argv, trace_options, trace_usage, 0);
 
+        if (output_name != NULL) {
+                err = trace__open_output(&trace, output_name);
+                if (err < 0) {
+                        perror("failed to create output file");
+                        goto out;
+                }
+        }
+
+        if (ev_qualifier_str != NULL) {
+                const char *s = ev_qualifier_str;
+
+                trace.not_ev_qualifier = *s == '!';
+                if (trace.not_ev_qualifier)
+                        ++s;
+                trace.ev_qualifier = strlist__new(true, s);
+                if (trace.ev_qualifier == NULL) {
+                        fputs("Not enough memory to parse event qualifier",
+                              trace.output);
+                        err = -ENOMEM;
+                        goto out_close;
+                }
+        }
+
         err = perf_target__validate(&trace.opts.target);
         if (err) {
                 perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
-                printf("%s", bf);
-                return err;
+                fprintf(trace.output, "%s", bf);
+                goto out_close;
         }
 
         err = perf_target__parse_uid(&trace.opts.target);
         if (err) {
                 perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
-                printf("%s", bf);
-                return err;
+                fprintf(trace.output, "%s", bf);
+                goto out_close;
         }
 
         if (!argc && perf_target__none(&trace.opts.target))
                 trace.opts.target.system_wide = true;
 
-        err = trace__run(&trace, argc, argv);
+        if (input_name)
+                err = trace__replay(&trace);
+        else
+                err = trace__run(&trace, argc, argv);
 
         if (trace.sched && !err)
-                trace__fprintf_thread_summary(&trace, stdout);
+                trace__fprintf_thread_summary(&trace, trace.output);
 
+out_close:
+        if (output_name != NULL)
+                fclose(trace.output);
+out:
         return err;
 }
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index b5d9238cb181..5f6f9b3271bb 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -46,6 +46,8 @@ ifneq ($(obj-perf),)
 obj-perf := $(abspath $(obj-perf))/
 endif
 
+LIB_INCLUDE := $(srctree)/tools/lib/
+
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -85,7 +87,7 @@ CFLAGS += -Wall
 CFLAGS += -Wextra
 CFLAGS += -std=gnu99
 
-EXTLIBS = -lelf -lpthread -lrt -lm
+EXTLIBS = -lelf -lpthread -lrt -lm -ldl
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
   CFLAGS += -fstack-protector-all
@@ -121,8 +123,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util
 CFLAGS += -I$(src-perf)
-CFLAGS += -I$(TRACE_EVENT_DIR)
-CFLAGS += -I$(srctree)/tools/lib/
+CFLAGS += -I$(LIB_INCLUDE)
 
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 
@@ -179,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS)
 ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
   CFLAGS += -DLIBELF_MMAP
 endif
+ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y)
+  CFLAGS += -DHAVE_ELF_GETPHDRNUM
+endif
 
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 708fb8e9822a..d5a8dd44945f 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -61,6 +61,15 @@ int main(void)
 }
 endef
 
+define SOURCE_ELF_GETPHDRNUM
+#include <libelf.h>
+int main(void)
+{
+        size_t dst;
+        return elf_getphdrnum(0, &dst);
+}
+endef
+
 ifndef NO_SLANG
 define SOURCE_SLANG
 #include <slang.h>
@@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
+        printf(\"error message: %s\n\", audit_errno_to_name(0));
         return audit_open();
 }
 endef
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 32bd102c32b6..cf20187eee0a 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -125,6 +125,9 @@
 #ifndef NSEC_PER_SEC
 # define NSEC_PER_SEC                   1000000000ULL
 #endif
+#ifndef NSEC_PER_USEC
+# define NSEC_PER_USEC                  1000ULL
+#endif
 
 static inline unsigned long long rdclock(void)
 {
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
index b11cca584238..2225162ee1fc 100755
--- a/tools/perf/python/twatch.py
+++ b/tools/perf/python/twatch.py
@@ -21,7 +21,7 @@ def main():
         evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
                            wakeup_events = 1, watermark = 1,
                            sample_id_all = 1,
-                           sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID)
+                           sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU)
         evsel.open(cpus = cpus, threads = threads);
         evlist = perf.evlist(cpus, threads)
         evlist.add(evsel)
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
new file mode 100644
index 000000000000..658f5d60c873
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -0,0 +1,36 @@
+[config]
+command = record
+args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=343
+read_format=12
+inherit=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+
+# cache-misses
+type=0
+config=3
+
+# default | PERF_SAMPLE_READ
+sample_type=343
+
+# PERF_FORMAT_ID | PERF_FORMAT_GROUP
+read_format=12
+
+mmap=0
+comm=0
+enable_on_exec=0
+disabled=0
+
+# inherit is disabled for group sampling
+inherit=0
+
+# sampling disabled
+sample_freq=0
+sample_period=0
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 35b45f1466b5..1e67437fb4ca 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -93,6 +93,28 @@ static struct test {
                 .desc = "Test software clock events have valid period values",
                 .func = test__sw_clock_freq,
         },
+#if defined(__x86_64__) || defined(__i386__)
+        {
+                .desc = "Test converting perf time to TSC",
+                .func = test__perf_time_to_tsc,
+        },
+#endif
+        {
+                .desc = "Test object code reading",
+                .func = test__code_reading,
+        },
+        {
+                .desc = "Test sample parsing",
+                .func = test__sample_parsing,
+        },
+        {
+                .desc = "Test using a dummy software event to keep tracking",
+                .func = test__keep_tracking,
+        },
+        {
+                .desc = "Test parsing with no sample_id_all bit set",
+                .func = test__parse_no_sample_id_all,
+        },
         {
                 .func = NULL,
         },
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
new file mode 100644
index 000000000000..6fb781d5586c
--- /dev/null
+++ b/tools/perf/tests/code-reading.c
@@ -0,0 +1,572 @@
+#include <sys/types.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <inttypes.h>
+#include <ctype.h>
+#include <string.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "machine.h"
+#include "event.h"
+#include "thread.h"
+
+#include "tests.h"
+
+#define BUFSZ   1024
+#define READLEN 128
+
+struct state {
+        u64 done[1024];
+        size_t done_cnt;
+};
+
+static unsigned int hex(char c)
+{
+        if (c >= '0' && c <= '9')
+                return c - '0';
+        if (c >= 'a' && c <= 'f')
+                return c - 'a' + 10;
+        return c - 'A' + 10;
+}
+
+static void read_objdump_line(const char *line, size_t line_len, void **buf,
+                              size_t *len)
+{
+        const char *p;
+        size_t i;
+
+        /* Skip to a colon */
+        p = strchr(line, ':');
+        if (!p)
+                return;
+        i = p + 1 - line;
+
+        /* Read bytes */
+        while (*len) {
+                char c1, c2;
+
+                /* Skip spaces */
+                for (; i < line_len; i++) {
+                        if (!isspace(line[i]))
+                                break;
+                }
+                /* Get 2 hex digits */
+                if (i >= line_len || !isxdigit(line[i]))
+                        break;
+                c1 = line[i++];
+                if (i >= line_len || !isxdigit(line[i]))
+                        break;
+                c2 = line[i++];
+                /* Followed by a space */
+                if (i < line_len && line[i] && !isspace(line[i]))
+                        break;
+                /* Store byte */
+                *(unsigned char *)*buf = (hex(c1) << 4) | hex(c2);
+                *buf += 1;
+                *len -= 1;
+        }
+}
+
+static int read_objdump_output(FILE *f, void **buf, size_t *len)
+{
+        char *line = NULL;
+        size_t line_len;
+        ssize_t ret;
+        int err = 0;
+
+        while (1) {
+                ret = getline(&line, &line_len, f);
+                if (feof(f))
+                        break;
+                if (ret < 0) {
+                        pr_debug("getline failed\n");
+                        err = -1;
+                        break;
+                }
+                read_objdump_line(line, ret, buf, len);
+        }
+
+        free(line);
+
+        return err;
+}
+
+static int read_via_objdump(const char *filename, u64 addr, void *buf,
+                            size_t len)
+{
+        char cmd[PATH_MAX * 2];
+        const char *fmt;
+        FILE *f;
+        int ret;
+
+        fmt = "%s -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s";
+        ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len,
+                       filename);
+        if (ret <= 0 || (size_t)ret >= sizeof(cmd))
+                return -1;
+
+        pr_debug("Objdump command is: %s\n", cmd);
+
+        /* Ignore objdump errors */
+        strcat(cmd, " 2>/dev/null");
+
+        f = popen(cmd, "r");
+        if (!f) {
+                pr_debug("popen failed\n");
+                return -1;
+        }
+
+        ret = read_objdump_output(f, &buf, &len);
+        if (len) {
+                pr_debug("objdump read too few bytes\n");
+                if (!ret)
+                        ret = len;
+        }
+
+        pclose(f);
+
+        return ret;
+}
+
+static int read_object_code(u64 addr, size_t len, u8 cpumode,
+                            struct thread *thread, struct machine *machine,
+                            struct state *state)
+{
+        struct addr_location al;
+        unsigned char buf1[BUFSZ];
+        unsigned char buf2[BUFSZ];
+        size_t ret_len;
+        u64 objdump_addr;
+        int ret;
+
+        pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
+
+        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
+                              &al);
+        if (!al.map || !al.map->dso) {
+                pr_debug("thread__find_addr_map failed\n");
+                return -1;
+        }
+
+        pr_debug("File is: %s\n", al.map->dso->long_name);
+
+        if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+            !dso__is_kcore(al.map->dso)) {
+                pr_debug("Unexpected kernel address - skipping\n");
+                return 0;
+        }
+
+        pr_debug("On file address is: %#"PRIx64"\n", al.addr);
+
+        if (len > BUFSZ)
+                len = BUFSZ;
+
+        /* Do not go off the map */
+        if (addr + len > al.map->end)
+                len = al.map->end - addr;
+
+        /* Read the object code using perf */
+        ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
+                                        len);
+        if (ret_len != len) {
+                pr_debug("dso__data_read_offset failed\n");
+                return -1;
+        }
+
+        /*
+         * Converting addresses for use by objdump requires more information.
+         * map__load() does that.  See map__rip_2objdump() for details.
+         */
+        if (map__load(al.map, NULL))
+                return -1;
+
+        /* objdump struggles with kcore - try each map only once */
+        if (dso__is_kcore(al.map->dso)) {
+                size_t d;
+
+                for (d = 0; d < state->done_cnt; d++) {
+                        if (state->done[d] == al.map->start) {
+                                pr_debug("kcore map tested already");
+                                pr_debug(" - skipping\n");
+                                return 0;
+                        }
+                }
+                if (state->done_cnt >= ARRAY_SIZE(state->done)) {
+                        pr_debug("Too many kcore maps - skipping\n");
+                        return 0;
+                }
+                state->done[state->done_cnt++] = al.map->start;
+        }
+
+        /* Read the object code using objdump */
+        objdump_addr = map__rip_2objdump(al.map, al.addr);
+        ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+        if (ret > 0) {
+                /*
+                 * The kernel maps are inaccurate - assume objdump is right in
+                 * that case.
+                 */
+                if (cpumode == PERF_RECORD_MISC_KERNEL ||
+                    cpumode == PERF_RECORD_MISC_GUEST_KERNEL) {
+                        len -= ret;
+                        if (len) {
+                                pr_debug("Reducing len to %zu\n", len);
+                        } else if (dso__is_kcore(al.map->dso)) {
+                                /*
+                                 * objdump cannot handle very large segments
+                                 * that may be found in kcore.
+                                 */
+                                pr_debug("objdump failed for kcore");
+                                pr_debug(" - skipping\n");
+                                return 0;
+                        } else {
+                                return -1;
+                        }
+                }
+        }
+        if (ret < 0) {
+                pr_debug("read_via_objdump failed\n");
+                return -1;
+        }
+
+        /* The results should be identical */
+        if (memcmp(buf1, buf2, len)) {
+                pr_debug("Bytes read differ from those read by objdump\n");
+                return -1;
+        }
+        pr_debug("Bytes read match those read by objdump\n");
+
+        return 0;
+}
+
+static int process_sample_event(struct machine *machine,
+                                struct perf_evlist *evlist,
+                                union perf_event *event, struct state *state)
+{
+        struct perf_sample sample;
+        struct thread *thread;
+        u8 cpumode;
+
+        if (perf_evlist__parse_sample(evlist, event, &sample)) {
+                pr_debug("perf_evlist__parse_sample failed\n");
+                return -1;
+        }
+
+        thread = machine__findnew_thread(machine, sample.pid, sample.pid);
+        if (!thread) {
+                pr_debug("machine__findnew_thread failed\n");
+                return -1;
+        }
+
+        cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+        return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
+                                state);
+}
+
+static int process_event(struct machine *machine, struct perf_evlist *evlist,
+                         union perf_event *event, struct state *state)
+{
+        if (event->header.type == PERF_RECORD_SAMPLE)
+                return process_sample_event(machine, evlist, event, state);
+
+        if (event->header.type < PERF_RECORD_MAX)
+                return machine__process_event(machine, event);
+
+        return 0;
+}
+
+static int process_events(struct machine *machine, struct perf_evlist *evlist,
+                          struct state *state)
+{
+        union perf_event *event;
+        int i, ret;
+
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+                        ret = process_event(machine, evlist, event, state);
+                        if (ret < 0)
+                                return ret;
+                }
+        }
+        return 0;
+}
+
+static int comp(const void *a, const void *b)
+{
+        return *(int *)a - *(int *)b;
+}
+
+static void do_sort_something(void)
+{
+        int buf[40960], i;
+
+        for (i = 0; i < (int)ARRAY_SIZE(buf); i++)
+                buf[i] = ARRAY_SIZE(buf) - i - 1;
+
+        qsort(buf, ARRAY_SIZE(buf), sizeof(int), comp);
+
+        for (i = 0; i < (int)ARRAY_SIZE(buf); i++) {
+                if (buf[i] != i) {
+                        pr_debug("qsort failed\n");
+                        break;
+                }
+        }
+}
+
+static void sort_something(void)
+{
+        int i;
+
+        for (i = 0; i < 10; i++)
+                do_sort_something();
+}
+
+static void syscall_something(void)
+{
+        int pipefd[2];
+        int i;
+
+        for (i = 0; i < 1000; i++) {
+                if (pipe(pipefd) < 0) {
+                        pr_debug("pipe failed\n");
+                        break;
+                }
+                close(pipefd[1]);
+                close(pipefd[0]);
+        }
+}
+
+static void fs_something(void)
+{
+        const char *test_file_name = "temp-perf-code-reading-test-file--";
+        FILE *f;
+        int i;
+
+        for (i = 0; i < 1000; i++) {
+                f = fopen(test_file_name, "w+");
+                if (f) {
+                        fclose(f);
+                        unlink(test_file_name);
+                }
+        }
+}
+
+static void do_something(void)
+{
+        fs_something();
+
+        sort_something();
+
+        syscall_something();
+}
+
+enum {
+        TEST_CODE_READING_OK,
+        TEST_CODE_READING_NO_VMLINUX,
+        TEST_CODE_READING_NO_KCORE,
+        TEST_CODE_READING_NO_ACCESS,
+        TEST_CODE_READING_NO_KERNEL_OBJ,
+};
+
+static int do_test_code_reading(bool try_kcore)
+{
+        struct machines machines;
+        struct machine *machine;
+        struct thread *thread;
+        struct perf_record_opts opts = {
+                .mmap_pages          = UINT_MAX,
+                .user_freq           = UINT_MAX,
+                .user_interval       = ULLONG_MAX,
+                .freq                = 4000,
+                .target              = {
+                        .uses_mmap   = true,
+                },
+        };
+        struct state state = {
+                .done_cnt = 0,
+        };
+        struct thread_map *threads = NULL;
+        struct cpu_map *cpus = NULL;
+        struct perf_evlist *evlist = NULL;
+        struct perf_evsel *evsel = NULL;
+        int err = -1, ret;
+        pid_t pid;
+        struct map *map;
+        bool have_vmlinux, have_kcore, excl_kernel = false;
+
+        pid = getpid();
+
+        machines__init(&machines);
+        machine = &machines.host;
+
+        ret = machine__create_kernel_maps(machine);
+        if (ret < 0) {
+                pr_debug("machine__create_kernel_maps failed\n");
+                goto out_err;
+        }
+
+        /* Force the use of kallsyms instead of vmlinux to try kcore */
+        if (try_kcore)
+                symbol_conf.kallsyms_name = "/proc/kallsyms";
+
+        /* Load kernel map */
+        map = machine->vmlinux_maps[MAP__FUNCTION];
+        ret = map__load(map, NULL);
+        if (ret < 0) {
+                pr_debug("map__load failed\n");
+                goto out_err;
+        }
+        have_vmlinux = dso__is_vmlinux(map->dso);
+        have_kcore = dso__is_kcore(map->dso);
+
+        /* 2nd time through we just try kcore */
+        if (try_kcore && !have_kcore)
+                return TEST_CODE_READING_NO_KCORE;
+
+        /* No point getting kernel events if there is no kernel object */
+        if (!have_vmlinux && !have_kcore)
+                excl_kernel = true;
+
+        threads = thread_map__new_by_tid(pid);
+        if (!threads) {
+                pr_debug("thread_map__new_by_tid failed\n");
+                goto out_err;
+        }
+
+        ret = perf_event__synthesize_thread_map(NULL, threads,
+                                                perf_event__process, machine);
+        if (ret < 0) {
+                pr_debug("perf_event__synthesize_thread_map failed\n");
+                goto out_err;
+        }
+
+        thread = machine__findnew_thread(machine, pid, pid);
+        if (!thread) {
+                pr_debug("machine__findnew_thread failed\n");
+                goto out_err;
+        }
+
+        cpus = cpu_map__new(NULL);
+        if (!cpus) {
+                pr_debug("cpu_map__new failed\n");
+                goto out_err;
+        }
+
+        while (1) {
+                const char *str;
+
+                evlist = perf_evlist__new();
+                if (!evlist) {
+                        pr_debug("perf_evlist__new failed\n");
+                        goto out_err;
+                }
+
+                perf_evlist__set_maps(evlist, cpus, threads);
+
+                if (excl_kernel)
+                        str = "cycles:u";
+                else
+                        str = "cycles";
+                pr_debug("Parsing event '%s'\n", str);
+                ret = parse_events(evlist, str);
+                if (ret < 0) {
+                        pr_debug("parse_events failed\n");
+                        goto out_err;
+                }
+
+                perf_evlist__config(evlist, &opts);
+
+                evsel = perf_evlist__first(evlist);
+
+                evsel->attr.comm = 1;
+                evsel->attr.disabled = 1;
+                evsel->attr.enable_on_exec = 0;
+
+                ret = perf_evlist__open(evlist);
+                if (ret < 0) {
+                        if (!excl_kernel) {
+                                excl_kernel = true;
+                                perf_evlist__delete(evlist);
+                                evlist = NULL;
+                                continue;
+                        }
+                        pr_debug("perf_evlist__open failed\n");
+                        goto out_err;
+                }
+                break;
+        }
+
+        ret = perf_evlist__mmap(evlist, UINT_MAX, false);
+        if (ret < 0) {
+                pr_debug("perf_evlist__mmap failed\n");
+                goto out_err;
+        }
+
+        perf_evlist__enable(evlist);
+
+        do_something();
+
+        perf_evlist__disable(evlist);
+
+        ret = process_events(machine, evlist, &state);
+        if (ret < 0)
+                goto out_err;
+
+        if (!have_vmlinux && !have_kcore && !try_kcore)
+                err = TEST_CODE_READING_NO_KERNEL_OBJ;
+        else if (!have_vmlinux && !try_kcore)
+                err = TEST_CODE_READING_NO_VMLINUX;
+        else if (excl_kernel)
+                err = TEST_CODE_READING_NO_ACCESS;
+        else
+                err = TEST_CODE_READING_OK;
+out_err:
+        if (evlist) {
+                perf_evlist__munmap(evlist);
+                perf_evlist__close(evlist);
+                perf_evlist__delete(evlist);
+        }
+        if (cpus)
+                cpu_map__delete(cpus);
+        if (threads)
+                thread_map__delete(threads);
+        machines__destroy_kernel_maps(&machines);
+        machine__delete_threads(machine);
+        machines__exit(&machines);
+
+        return err;
+}
+
+int test__code_reading(void)
+{
+        int ret;
+
+        ret = do_test_code_reading(false);
+        if (!ret)
+                ret = do_test_code_reading(true);
+
+        switch (ret) {
+        case TEST_CODE_READING_OK:
+                return 0;
+        case TEST_CODE_READING_NO_VMLINUX:
+                fprintf(stderr, " (no vmlinux)");
+                return 0;
+        case TEST_CODE_READING_NO_KCORE:
+                fprintf(stderr, " (no kcore)");
+                return 0;
+        case TEST_CODE_READING_NO_ACCESS:
+                fprintf(stderr, " (no access)");
+                return 0;
+        case TEST_CODE_READING_NO_KERNEL_OBJ:
+                fprintf(stderr, " (no kernel obj)");
+                return 0;
+        default:
+                return -1;
+        };
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 5eaffa2de9c5..dffe0551acaa 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -10,14 +10,6 @@
 #include "symbol.h"
 #include "tests.h"
 
-#define TEST_ASSERT_VAL(text, cond) \
-do { \
-        if (!(cond)) { \
-                pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
-                return -1; \
-        } \
-} while (0)
-
 static char *test_file(int size)
 {
         static char buf_templ[] = "/tmp/test-XXXXXX";
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index a5d2fcc5ae35..9b98c1554833 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,6 +1,6 @@
+#include <traceevent/event-parse.h>
 #include "evsel.h"
 #include "tests.h"
-#include "event-parse.h"
 
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
                                   int size, bool should_be_signed)
@@ -49,7 +49,7 @@ int test__perf_evsel__tp_sched_test(void)
         if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
                 ret = -1;
 
-        if (perf_evsel__test_field(evsel, "prev_state", 8, true))
+        if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
                 ret = -1;
 
         if (perf_evsel__test_field(evsel, "next_comm", 16, true))
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 89085a9615e2..4228ffc0d968 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -88,7 +88,8 @@ static struct machine *setup_fake_machine(struct machines *machines)
         for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
                 struct thread *thread;
 
-                thread = machine__findnew_thread(machine, fake_threads[i].pid);
+                thread = machine__findnew_thread(machine, fake_threads[i].pid,
+                                                 fake_threads[i].pid);
                 if (thread == NULL)
                         goto out;
 
@@ -210,17 +211,15 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
         list_for_each_entry(evsel, &evlist->entries, node) {
                 for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
                         const union perf_event event = {
-                                .ip = {
-                                        .header = {
-                                                .misc = PERF_RECORD_MISC_USER,
-                                        },
-                                        .pid = fake_common_samples[k].pid,
-                                        .ip  = fake_common_samples[k].ip,
+                                .header = {
+                                        .misc = PERF_RECORD_MISC_USER,
                                 },
                         };
 
+                        sample.pid = fake_common_samples[k].pid;
+                        sample.ip = fake_common_samples[k].ip;
                         if (perf_event__preprocess_sample(&event, machine, &al,
-                                                          &sample, 0) < 0)
+                                                          &sample) < 0)
                                 goto out;
 
                         he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
@@ -234,17 +233,15 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
                 for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
                         const union perf_event event = {
-                                .ip = {
-                                        .header = {
-                                                .misc = PERF_RECORD_MISC_USER,
-                                        },
-                                        .pid = fake_samples[i][k].pid,
-                                        .ip  = fake_samples[i][k].ip,
+                                .header = {
+                                        .misc = PERF_RECORD_MISC_USER,
                                 },
                         };
 
+                        sample.pid = fake_samples[i][k].pid;
+                        sample.ip = fake_samples[i][k].ip;
                         if (perf_event__preprocess_sample(&event, machine, &al,
-                                                          &sample, 0) < 0)
+                                                          &sample) < 0)
                                 goto out;
 
                         he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
new file mode 100644
index 000000000000..d444ea2c47d9
--- /dev/null
+++ b/tools/perf/tests/keep-tracking.c
@@ -0,0 +1,154 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#define CHECK__(x) {                            \
+        while ((x) < 0) {                       \
+                pr_debug(#x " failed!\n");      \
+                goto out_err;                   \
+        }                                       \
+}
+
+#define CHECK_NOT_NULL__(x) {                   \
+        while ((x) == NULL) {                   \
+                pr_debug(#x " failed!\n");      \
+                goto out_err;                   \
+        }                                       \
+}
+
+static int find_comm(struct perf_evlist *evlist, const char *comm)
+{
+        union perf_event *event;
+        int i, found;
+
+        found = 0;
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+                        if (event->header.type == PERF_RECORD_COMM &&
+                            (pid_t)event->comm.pid == getpid() &&
+                            (pid_t)event->comm.tid == getpid() &&
+                            strcmp(event->comm.comm, comm) == 0)
+                                found += 1;
+                }
+        }
+        return found;
+}
+
+/**
+ * test__keep_tracking - test using a dummy software event to keep tracking.
+ *
+ * This function implements a test that checks that tracking events continue
+ * when an event is disabled but a dummy software event is not disabled.  If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ */
+int test__keep_tracking(void)
+{
+        struct perf_record_opts opts = {
+                .mmap_pages          = UINT_MAX,
+                .user_freq           = UINT_MAX,
+                .user_interval       = ULLONG_MAX,
+                .freq                = 4000,
+                .target              = {
+                        .uses_mmap   = true,
+                },
+        };
+        struct thread_map *threads = NULL;
+        struct cpu_map *cpus = NULL;
+        struct perf_evlist *evlist = NULL;
+        struct perf_evsel *evsel = NULL;
+        int found, err = -1;
+        const char *comm;
+
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
+        CHECK_NOT_NULL__(threads);
+
+        cpus = cpu_map__new(NULL);
+        CHECK_NOT_NULL__(cpus);
+
+        evlist = perf_evlist__new();
+        CHECK_NOT_NULL__(evlist);
+
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        CHECK__(parse_events(evlist, "dummy:u"));
+        CHECK__(parse_events(evlist, "cycles:u"));
+
+        perf_evlist__config(evlist, &opts);
+
+        evsel = perf_evlist__first(evlist);
+
+        evsel->attr.comm = 1;
+        evsel->attr.disabled = 1;
+        evsel->attr.enable_on_exec = 0;
+
+        if (perf_evlist__open(evlist) < 0) {
+                fprintf(stderr, " (not supported)");
+                err = 0;
+                goto out_err;
+        }
+
+        CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+        /*
+         * First, test that a 'comm' event can be found when the event is
+         * enabled.
+         */
+
+        perf_evlist__enable(evlist);
+
+        comm = "Test COMM 1";
+        CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+        perf_evlist__disable(evlist);
+
+        found = find_comm(evlist, comm);
+        if (found != 1) {
+                pr_debug("First time, failed to find tracking event.\n");
+                goto out_err;
+        }
+
+        /*
+         * Secondly, test that a 'comm' event can be found when the event is
+         * disabled with the dummy event still enabled.
+         */
+
+        perf_evlist__enable(evlist);
+
+        evsel = perf_evlist__last(evlist);
+
+        CHECK__(perf_evlist__disable_event(evlist, evsel));
+
+        comm = "Test COMM 2";
+        CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0));
+
+        perf_evlist__disable(evlist);
+
+        found = find_comm(evlist, comm);
+        if (found != 1) {
+                pr_debug("Seconf time, failed to find tracking event.\n");
+                goto out_err;
+        }
+
+        err = 0;
+
+out_err:
+        if (evlist) {
+                perf_evlist__disable(evlist);
+                perf_evlist__munmap(evlist);
+                perf_evlist__close(evlist);
+                perf_evlist__delete(evlist);
+        }
+        if (cpus)
+                cpu_map__delete(cpus);
+        if (threads)
+                thread_map__delete(threads);
+
+        return err;
+}
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index c441a2875128..2ca0abf1b2b6 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,6 +1,8 @@
 PERF := .
 MK   := Makefile
 
+has = $(shell which $1 2>/dev/null)
+
 # standard single make variable specified
 make_clean_all      := clean all
 make_python_perf_so := python/perf.so
@@ -25,6 +27,13 @@ make_help           := help
 make_doc            := doc
 make_perf_o         := perf.o
 make_util_map_o     := util/map.o
+make_install        := install
+make_install_bin    := install-bin
+make_install_doc    := install-doc
+make_install_man    := install-man
+make_install_html   := install-html
+make_install_info   := install-info
+make_install_pdf    := install-pdf
 
 # all the NO_* variable combined
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
@@ -50,14 +59,27 @@ run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
 run += make_no_libbionic
-run += make_tags
-run += make_cscope
 run += make_help
 run += make_doc
 run += make_perf_o
 run += make_util_map_o
+run += make_install
+run += make_install_bin
+# FIXME 'install-*' commented out till they're fixed
+# run += make_install_doc
+# run += make_install_man
+# run += make_install_html
+# run += make_install_info
+# run += make_install_pdf
 run += make_minimal
 
+ifneq ($(call has,ctags),)
+run += make_tags
+endif
+ifneq ($(call has,cscope),)
+run += make_cscope
+endif
+
 # $(run_O) contains same portion of $(run) tests with '_O' attached
 # to distinguish O=... tests
 run_O := $(addsuffix _O,$(run))
@@ -84,6 +106,31 @@ test_make_python_perf_so := test -f $(PERF)/python/perf.so
 test_make_perf_o     := test -f $(PERF)/perf.o
 test_make_util_map_o := test -f $(PERF)/util/map.o
 
+test_make_install       := test -x $$TMP_DEST/bin/perf
+test_make_install_O     := $(test_make_install)
+test_make_install_bin   := $(test_make_install)
+test_make_install_bin_O := $(test_make_install)
+
+# FIXME nothing gets installed
+test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
+test_make_install_man_O  := $(test_make_install_man)
+
+# FIXME nothing gets installed
+test_make_install_doc    := $(test_ok)
+test_make_install_doc_O  := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_html   := $(test_ok)
+test_make_install_html_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_info   := $(test_ok)
+test_make_install_info_O := $(test_ok)
+
+# FIXME nothing gets installed
+test_make_install_pdf    := $(test_ok)
+test_make_install_pdf_O  := $(test_ok)
+
 # Kbuild tests only
 #test_make_python_perf_so_O := test -f $$TMP/tools/perf/python/perf.so
 #test_make_perf_o_O         := test -f $$TMP/tools/perf/perf.o
@@ -95,7 +142,7 @@ test_make_util_map_o_O := true
 test_default = test -x $(PERF)/perf
 test = $(if $(test_$1),$(test_$1),$(test_default))
 
-test_default_O = test -x $$TMP/perf
+test_default_O = test -x $$TMP_O/perf
 test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
 
 all:
@@ -111,23 +158,27 @@ clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null)
 
 $(run):
         $(call clean)
-        @cmd="cd $(PERF) && make -f $(MK) $($@)"; \
+        @TMP_DEST=$$(mktemp -d); \
+        cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1; \
         echo "  test: $(call test,$@)"; \
         $(call test,$@) && \
-        rm -f $@
+        rm -f $@ \
+        rm -rf $$TMP_DEST
 
 $(run_O):
         $(call clean)
-        @TMP=$$(mktemp -d); \
-        cmd="cd $(PERF) && make -f $(MK) $($(patsubst %_O,%,$@)) O=$$TMP"; \
+        @TMP_O=$$(mktemp -d); \
+        TMP_DEST=$$(mktemp -d); \
+        cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
         echo "- $@: $$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1 && \
         echo "  test: $(call test_O,$@)"; \
         $(call test_O,$@) && \
         rm -f $@ && \
-        rm -rf $$TMP
+        rm -rf $$TMP_O \
+        rm -rf $$TMP_DEST
 
 all: $(run) $(run_O)
         @echo OK
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5b1b5aba722b..c4185b9aeb80 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -72,7 +72,7 @@ int test__basic_mmap(void)
                 }
 
                 evsels[i]->attr.wakeup_events = 1;
-                perf_evsel__set_sample_id(evsels[i]);
+                perf_evsel__set_sample_id(evsels[i], false);
 
                 perf_evlist__add(evlist, evsels[i]);
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 0275bab4ea9e..48114d164e9f 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -7,14 +7,6 @@
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
-#define TEST_ASSERT_VAL(text, cond) \
-do { \
-        if (!(cond)) { \
-                pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
-                return -1; \
-        } \
-} while (0)
-
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
                              PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
 
@@ -460,6 +452,7 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist)
                         evsel->attr.exclude_kernel);
         TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
 
         return 0;
 }
@@ -528,6 +521,7 @@ static int test__group1(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* cycles:upp */
         evsel = perf_evsel__next(evsel);
@@ -543,6 +537,7 @@ static int test__group1(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         return 0;
 }
@@ -568,6 +563,7 @@ static int test__group2(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* cache-references + :u modifier */
         evsel = perf_evsel__next(evsel);
@@ -582,6 +578,7 @@ static int test__group2(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* cycles:k */
         evsel = perf_evsel__next(evsel);
@@ -595,6 +592,7 @@ static int test__group2(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         return 0;
 }
@@ -623,6 +621,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
                 !strcmp(leader->group_name, "group1"));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* group1 cycles:kppp */
         evsel = perf_evsel__next(evsel);
@@ -639,6 +638,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* group2 cycles + G modifier */
         evsel = leader = perf_evsel__next(evsel);
@@ -656,6 +656,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
                 !strcmp(leader->group_name, "group2"));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* group2 1:3 + G modifier */
         evsel = perf_evsel__next(evsel);
@@ -669,6 +670,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* instructions:u */
         evsel = perf_evsel__next(evsel);
@@ -682,6 +684,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         return 0;
 }
@@ -709,6 +712,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* instructions:kp + p */
         evsel = perf_evsel__next(evsel);
@@ -724,6 +728,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         return 0;
 }
@@ -750,6 +755,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* instructions + G */
         evsel = perf_evsel__next(evsel);
@@ -764,6 +770,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
         TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* cycles:G */
         evsel = leader = perf_evsel__next(evsel);
@@ -780,6 +787,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)
         TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
         TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
         TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+        TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
 
         /* instructions:G */
         evsel = perf_evsel__next(evsel);
@@ -971,6 +979,142 @@ static int test__group_gh4(struct perf_evlist *evlist)
         return 0;
 }
 
+static int test__leader_sample1(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel, *leader;
+
+        TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+        /* cycles - sampling group leader */
+        evsel = leader = perf_evlist__first(evlist);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+        TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+        /* cache-misses - not sampling */
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+        TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+        /* branch-misses - not sampling */
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+        TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+        return 0;
+}
+
+static int test__leader_sample2(struct perf_evlist *evlist __maybe_unused)
+{
+        struct perf_evsel *evsel, *leader;
+
+        TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+
+        /* instructions - sampling group leader */
+        evsel = leader = perf_evlist__first(evlist);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+        TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+        /* branch-misses - not sampling */
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+        TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+        TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong sample_read", evsel->sample_read);
+
+        return 0;
+}
+
+static int test__checkevent_pinned_modifier(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+        TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+        TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+        TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
+        TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+        return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__pinned_group(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel, *leader;
+
+        TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+        /* cycles - group leader */
+        evsel = leader = perf_evlist__first(evlist);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+        TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+        TEST_ASSERT_VAL("wrong pinned", evsel->attr.pinned);
+
+        /* cache-misses - can not be pinned, but will go on with the leader */
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+        /* branch-misses - ditto */
+        evsel = perf_evsel__next(evsel);
+        TEST_ASSERT_VAL("wrong config",
+                        PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config);
+        TEST_ASSERT_VAL("wrong pinned", !evsel->attr.pinned);
+
+        return 0;
+}
+
 static int count_tracepoints(void)
 {
         char events_path[PATH_MAX];
@@ -1187,6 +1331,22 @@ static struct evlist_test test__events[] = {
                 .name  = "{cycles:G,cache-misses:H}:uG",
                 .check = test__group_gh4,
         },
+        [38] = {
+                .name  = "{cycles,cache-misses,branch-misses}:S",
+                .check = test__leader_sample1,
+        },
+        [39] = {
+                .name  = "{instructions,branch-misses}:Su",
+                .check = test__leader_sample2,
+        },
+        [40] = {
+                .name  = "instructions:uDp",
+                .check = test__checkevent_pinned_modifier,
+        },
+        [41] = {
+                .name  = "{cycles,cache-misses,branch-misses}:D",
+                .check = test__pinned_group,
+        },
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1254,24 +1414,20 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 
 static int test_term(struct terms_test *t)
 {
-        struct list_head *terms;
+        struct list_head terms;
         int ret;
 
-        terms = malloc(sizeof(*terms));
-        if (!terms)
-                return -ENOMEM;
-
-        INIT_LIST_HEAD(terms);
+        INIT_LIST_HEAD(&terms);
 
-        ret = parse_events_terms(terms, t->str);
+        ret = parse_events_terms(&terms, t->str);
         if (ret) {
                 pr_debug("failed to parse terms '%s', err %d\n",
                          t->str , ret);
                 return ret;
         }
 
-        ret = t->check(terms);
-        parse_events__free_terms(terms);
+        ret = t->check(&terms);
+        parse_events__free_terms(&terms);
 
         return ret;
 }
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
new file mode 100644
index 000000000000..e117b6c6a248
--- /dev/null
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -0,0 +1,108 @@
+#include <sys/types.h>
+#include <stddef.h>
+
+#include "tests.h"
+
+#include "event.h"
+#include "evlist.h"
+#include "header.h"
+#include "util.h"
+
+static int process_event(struct perf_evlist **pevlist, union perf_event *event)
+{
+        struct perf_sample sample;
+
+        if (event->header.type == PERF_RECORD_HEADER_ATTR) {
+                if (perf_event__process_attr(NULL, event, pevlist)) {
+                        pr_debug("perf_event__process_attr failed\n");
+                        return -1;
+                }
+                return 0;
+        }
+
+        if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+                return -1;
+
+        if (!*pevlist)
+                return -1;
+
+        if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
+                pr_debug("perf_evlist__parse_sample failed\n");
+                return -1;
+        }
+
+        return 0;
+}
+
+static int process_events(union perf_event **events, size_t count)
+{
+        struct perf_evlist *evlist = NULL;
+        int err = 0;
+        size_t i;
+
+        for (i = 0; i < count && !err; i++)
+                err = process_event(&evlist, events[i]);
+
+        if (evlist)
+                perf_evlist__delete(evlist);
+
+        return err;
+}
+
+struct test_attr_event {
+        struct attr_event attr;
+        u64 id;
+};
+
+/**
+ * test__parse_no_sample_id_all - test parsing with no sample_id_all bit set.
+ *
+ * This function tests parsing data produced on kernel's that do not support the
+ * sample_id_all bit.  Without the sample_id_all bit, non-sample events (such as
+ * mmap events) do not have an id sample appended, and consequently logic
+ * designed to determine the id will not work.  That case happens when there is
+ * more than one selected event, so this test processes three events: 2
+ * attributes representing the selected events and one mmap event.
+ *
+ * Return: %0 on success, %-1 if the test fails.
+ */
+int test__parse_no_sample_id_all(void)
+{
+        int err;
+
+        struct test_attr_event event1 = {
+                .attr = {
+                        .header = {
+                                .type = PERF_RECORD_HEADER_ATTR,
+                                .size = sizeof(struct test_attr_event),
+                        },
+                },
+                .id = 1,
+        };
+        struct test_attr_event event2 = {
+                .attr = {
+                        .header = {
+                                .type = PERF_RECORD_HEADER_ATTR,
+                                .size = sizeof(struct test_attr_event),
+                        },
+                },
+                .id = 2,
+        };
+        struct mmap_event event3 = {
+                .header = {
+                        .type = PERF_RECORD_MMAP,
+                        .size = sizeof(struct mmap_event),
+                },
+        };
+        union perf_event *events[] = {
+                (union perf_event *)&event1,
+                (union perf_event *)&event2,
+                (union perf_event *)&event3,
+        };
+
+        err = process_events(events, ARRAY_SIZE(events));
+        if (err)
+                return -1;
+
+        return 0;
+}
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 72d8881873b0..b8a7056519ac 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -50,7 +50,7 @@ int test__PERF_RECORD(void)
         struct perf_sample sample;
         const char *cmd = "sleep";
         const char *argv[] = { cmd, "1", NULL, };
-        char *bname;
+        char *bname, *mmap_filename;
         u64 prev_time = 0;
         bool found_cmd_mmap = false,
              found_libc_mmap = false,
@@ -212,6 +212,7 @@ int test__PERF_RECORD(void)
 
                                 if ((type == PERF_RECORD_COMM ||
                                      type == PERF_RECORD_MMAP ||
+                                     type == PERF_RECORD_MMAP2 ||
                                      type == PERF_RECORD_FORK ||
                                      type == PERF_RECORD_EXIT) &&
                                      (pid_t)event->comm.pid != evlist->workload.pid) {
@@ -220,7 +221,8 @@ int test__PERF_RECORD(void)
                                 }
 
                                 if ((type == PERF_RECORD_COMM ||
-                                     type == PERF_RECORD_MMAP) &&
+                                     type == PERF_RECORD_MMAP ||
+                                     type == PERF_RECORD_MMAP2) &&
                                      event->comm.pid != event->comm.tid) {
                                         pr_debug("%s with different pid/tid!\n", name);
                                         ++errs;
@@ -236,7 +238,12 @@ int test__PERF_RECORD(void)
                                 case PERF_RECORD_EXIT:
                                         goto found_exit;
                                 case PERF_RECORD_MMAP:
-                                        bname = strrchr(event->mmap.filename, '/');
+                                        mmap_filename = event->mmap.filename;
+                                        goto check_bname;
+                                case PERF_RECORD_MMAP2:
+                                        mmap_filename = event->mmap2.filename;
+                                check_bname:
+                                        bname = strrchr(mmap_filename, '/');
                                         if (bname != NULL) {
                                                 if (!found_cmd_mmap)
                                                         found_cmd_mmap = !strcmp(bname + 1, cmd);
@@ -245,7 +252,7 @@ int test__PERF_RECORD(void)
                                                 if (!found_ld_mmap)
                                                         found_ld_mmap = !strncmp(bname + 1, "ld", 2);
                                         } else if (!found_vdso_mmap)
-                                                found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+                                                found_vdso_mmap = !strcmp(mmap_filename, "[vdso]");
                                         break;
 
                                 case PERF_RECORD_SAMPLE:
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
new file mode 100644
index 000000000000..0ab61b1f408e
--- /dev/null
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -0,0 +1,177 @@
+#include <stdio.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <sys/prctl.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+#include "../arch/x86/util/tsc.h"
+
+#define CHECK__(x) {                            \
+        while ((x) < 0) {                       \
+                pr_debug(#x " failed!\n");      \
+                goto out_err;                   \
+        }                                       \
+}
+
+#define CHECK_NOT_NULL__(x) {                   \
+        while ((x) == NULL) {                   \
+                pr_debug(#x " failed!\n");      \
+                goto out_err;                   \
+        }                                       \
+}
+
+static u64 rdtsc(void)
+{
+        unsigned int low, high;
+
+        asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+        return low | ((u64)high) << 32;
+}
+
+/**
+ * test__perf_time_to_tsc - test converting perf time to TSC.
+ *
+ * This function implements a test that checks that the conversion of perf time
+ * to and from TSC is consistent with the order of events.  If the test passes
+ * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
+ * supported then then the test passes but " (not supported)" is printed.
+ */
+int test__perf_time_to_tsc(void)
+{
+        struct perf_record_opts opts = {
+                .mmap_pages          = UINT_MAX,
+                .user_freq           = UINT_MAX,
+                .user_interval       = ULLONG_MAX,
+                .freq                = 4000,
+                .target              = {
+                        .uses_mmap   = true,
+                },
+                .sample_time         = true,
+        };
+        struct thread_map *threads = NULL;
+        struct cpu_map *cpus = NULL;
+        struct perf_evlist *evlist = NULL;
+        struct perf_evsel *evsel = NULL;
+        int err = -1, ret, i;
+        const char *comm1, *comm2;
+        struct perf_tsc_conversion tc;
+        struct perf_event_mmap_page *pc;
+        union perf_event *event;
+        u64 test_tsc, comm1_tsc, comm2_tsc;
+        u64 test_time, comm1_time = 0, comm2_time = 0;
+
+        threads = thread_map__new(-1, getpid(), UINT_MAX);
+        CHECK_NOT_NULL__(threads);
+
+        cpus = cpu_map__new(NULL);
+        CHECK_NOT_NULL__(cpus);
+
+        evlist = perf_evlist__new();
+        CHECK_NOT_NULL__(evlist);
+
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        CHECK__(parse_events(evlist, "cycles:u"));
+
+        perf_evlist__config(evlist, &opts);
+
+        evsel = perf_evlist__first(evlist);
+
+        evsel->attr.comm = 1;
+        evsel->attr.disabled = 1;
+        evsel->attr.enable_on_exec = 0;
+
+        CHECK__(perf_evlist__open(evlist));
+
+        CHECK__(perf_evlist__mmap(evlist, UINT_MAX, false));
+
+        pc = evlist->mmap[0].base;
+        ret = perf_read_tsc_conversion(pc, &tc);
+        if (ret) {
+                if (ret == -EOPNOTSUPP) {
+                        fprintf(stderr, " (not supported)");
+                        return 0;
+                }
+                goto out_err;
+        }
+
+        perf_evlist__enable(evlist);
+
+        comm1 = "Test COMM 1";
+        CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0));
+
+        test_tsc = rdtsc();
+
+        comm2 = "Test COMM 2";
+        CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0));
+
+        perf_evlist__disable(evlist);
+
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+                        struct perf_sample sample;
+
+                        if (event->header.type != PERF_RECORD_COMM ||
+                            (pid_t)event->comm.pid != getpid() ||
+                            (pid_t)event->comm.tid != getpid())
+                                continue;
+
+                        if (strcmp(event->comm.comm, comm1) == 0) {
+                                CHECK__(perf_evsel__parse_sample(evsel, event,
+                                                                 &sample));
+                                comm1_time = sample.time;
+                        }
+                        if (strcmp(event->comm.comm, comm2) == 0) {
+                                CHECK__(perf_evsel__parse_sample(evsel, event,
+                                                                 &sample));
+                                comm2_time = sample.time;
+                        }
+                }
+        }
+
+        if (!comm1_time || !comm2_time)
+                goto out_err;
+
+        test_time = tsc_to_perf_time(test_tsc, &tc);
+        comm1_tsc = perf_time_to_tsc(comm1_time, &tc);
+        comm2_tsc = perf_time_to_tsc(comm2_time, &tc);
+
+        pr_debug("1st event perf time %"PRIu64" tsc %"PRIu64"\n",
+                 comm1_time, comm1_tsc);
+        pr_debug("rdtsc          time %"PRIu64" tsc %"PRIu64"\n",
+                 test_time, test_tsc);
+        pr_debug("2nd event perf time %"PRIu64" tsc %"PRIu64"\n",
+                 comm2_time, comm2_tsc);
+
+        if (test_time <= comm1_time ||
+            test_time >= comm2_time)
+                goto out_err;
+
+        if (test_tsc <= comm1_tsc ||
+            test_tsc >= comm2_tsc)
+                goto out_err;
+
+        err = 0;
+
+out_err:
+        if (evlist) {
+                perf_evlist__disable(evlist);
+                perf_evlist__munmap(evlist);
+                perf_evlist__close(evlist);
+                perf_evlist__delete(evlist);
+        }
+        if (cpus)
+                cpu_map__delete(cpus);
+        if (threads)
+                thread_map__delete(threads);
+
+        return err;
+}
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
new file mode 100644
index 000000000000..77f598dbd97a
--- /dev/null
+++ b/tools/perf/tests/sample-parsing.c
@@ -0,0 +1,316 @@
+#include <stdbool.h>
+#include <inttypes.h>
+
+#include "util.h"
+#include "event.h"
+#include "evsel.h"
+
+#include "tests.h"
+
+#define COMP(m) do {                                    \
+        if (s1->m != s2->m) {                           \
+                pr_debug("Samples differ at '"#m"'\n"); \
+                return false;                           \
+        }                                               \
+} while (0)
+
+#define MCOMP(m) do {                                   \
+        if (memcmp(&s1->m, &s2->m, sizeof(s1->m))) {    \
+                pr_debug("Samples differ at '"#m"'\n"); \
+                return false;                           \
+        }                                               \
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+                         const struct perf_sample *s2, u64 type, u64 regs_user,
+                         u64 read_format)
+{
+        size_t i;
+
+        if (type & PERF_SAMPLE_IDENTIFIER)
+                COMP(id);
+
+        if (type & PERF_SAMPLE_IP)
+                COMP(ip);
+
+        if (type & PERF_SAMPLE_TID) {
+                COMP(pid);
+                COMP(tid);
+        }
+
+        if (type & PERF_SAMPLE_TIME)
+                COMP(time);
+
+        if (type & PERF_SAMPLE_ADDR)
+                COMP(addr);
+
+        if (type & PERF_SAMPLE_ID)
+                COMP(id);
+
+        if (type & PERF_SAMPLE_STREAM_ID)
+                COMP(stream_id);
+
+        if (type & PERF_SAMPLE_CPU)
+                COMP(cpu);
+
+        if (type & PERF_SAMPLE_PERIOD)
+                COMP(period);
+
+        if (type & PERF_SAMPLE_READ) {
+                if (read_format & PERF_FORMAT_GROUP)
+                        COMP(read.group.nr);
+                else
+                        COMP(read.one.value);
+                if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                        COMP(read.time_enabled);
+                if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                        COMP(read.time_running);
+                /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+                if (read_format & PERF_FORMAT_GROUP) {
+                        for (i = 0; i < s1->read.group.nr; i++)
+                                MCOMP(read.group.values[i]);
+                } else {
+                        COMP(read.one.id);
+                }
+        }
+
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                COMP(callchain->nr);
+                for (i = 0; i < s1->callchain->nr; i++)
+                        COMP(callchain->ips[i]);
+        }
+
+        if (type & PERF_SAMPLE_RAW) {
+                COMP(raw_size);
+                if (memcmp(s1->raw_data, s2->raw_data, s1->raw_size)) {
+                        pr_debug("Samples differ at 'raw_data'\n");
+                        return false;
+                }
+        }
+
+        if (type & PERF_SAMPLE_BRANCH_STACK) {
+                COMP(branch_stack->nr);
+                for (i = 0; i < s1->branch_stack->nr; i++)
+                        MCOMP(branch_stack->entries[i]);
+        }
+
+        if (type & PERF_SAMPLE_REGS_USER) {
+                size_t sz = hweight_long(regs_user) * sizeof(u64);
+
+                COMP(user_regs.abi);
+                if (s1->user_regs.abi &&
+                    (!s1->user_regs.regs || !s2->user_regs.regs ||
+                     memcmp(s1->user_regs.regs, s2->user_regs.regs, sz))) {
+                        pr_debug("Samples differ at 'user_regs'\n");
+                        return false;
+                }
+        }
+
+        if (type & PERF_SAMPLE_STACK_USER) {
+                COMP(user_stack.size);
+                if (memcmp(s1->user_stack.data, s1->user_stack.data,
+                           s1->user_stack.size)) {
+                        pr_debug("Samples differ at 'user_stack'\n");
+                        return false;
+                }
+        }
+
+        if (type & PERF_SAMPLE_WEIGHT)
+                COMP(weight);
+
+        if (type & PERF_SAMPLE_DATA_SRC)
+                COMP(data_src);
+
+        return true;
+}
+
+static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+{
+        struct perf_evsel evsel = {
+                .needs_swap = false,
+                .attr = {
+                        .sample_type = sample_type,
+                        .sample_regs_user = sample_regs_user,
+                        .read_format = read_format,
+                },
+        };
+        union perf_event *event;
+        union {
+                struct ip_callchain callchain;
+                u64 data[64];
+        } callchain = {
+                /* 3 ips */
+                .data = {3, 201, 202, 203},
+        };
+        union {
+                struct branch_stack branch_stack;
+                u64 data[64];
+        } branch_stack = {
+                /* 1 branch_entry */
+                .data = {1, 211, 212, 213},
+        };
+        u64 user_regs[64];
+        const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
+        const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
+        struct perf_sample sample = {
+                .ip             = 101,
+                .pid            = 102,
+                .tid            = 103,
+                .time           = 104,
+                .addr           = 105,
+                .id             = 106,
+                .stream_id      = 107,
+                .period         = 108,
+                .weight         = 109,
+                .cpu            = 110,
+                .raw_size       = sizeof(raw_data),
+                .data_src       = 111,
+                .raw_data       = (void *)raw_data,
+                .callchain      = &callchain.callchain,
+                .branch_stack   = &branch_stack.branch_stack,
+                .user_regs      = {
+                        .abi    = PERF_SAMPLE_REGS_ABI_64,
+                        .regs   = user_regs,
+                },
+                .user_stack     = {
+                        .size   = sizeof(data),
+                        .data   = (void *)data,
+                },
+                .read           = {
+                        .time_enabled = 0x030a59d664fca7deULL,
+                        .time_running = 0x011b6ae553eb98edULL,
+                },
+        };
+        struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
+        struct perf_sample sample_out;
+        size_t i, sz, bufsz;
+        int err, ret = -1;
+
+        for (i = 0; i < sizeof(user_regs); i++)
+                *(i + (u8 *)user_regs) = i & 0xfe;
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                sample.read.group.nr     = 4;
+                sample.read.group.values = values;
+        } else {
+                sample.read.one.value = 0x08789faeb786aa87ULL;
+                sample.read.one.id    = 99;
+        }
+
+        sz = perf_event__sample_event_size(&sample, sample_type,
+                                           sample_regs_user, read_format);
+        bufsz = sz + 4096; /* Add a bit for overrun checking */
+        event = malloc(bufsz);
+        if (!event) {
+                pr_debug("malloc failed\n");
+                return -1;
+        }
+
+        memset(event, 0xff, bufsz);
+        event->header.type = PERF_RECORD_SAMPLE;
+        event->header.misc = 0;
+        event->header.size = sz;
+
+        err = perf_event__synthesize_sample(event, sample_type,
+                                            sample_regs_user, read_format,
+                                            &sample, false);
+        if (err) {
+                pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+                         "perf_event__synthesize_sample", sample_type, err);
+                goto out_free;
+        }
+
+        /* The data does not contain 0xff so we use that to check the size */
+        for (i = bufsz; i > 0; i--) {
+                if (*(i - 1 + (u8 *)event) != 0xff)
+                        break;
+        }
+        if (i != sz) {
+                pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+                         i, sz);
+                goto out_free;
+        }
+
+        evsel.sample_size = __perf_evsel__sample_size(sample_type);
+
+        err = perf_evsel__parse_sample(&evsel, event, &sample_out);
+        if (err) {
+                pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+                         "perf_evsel__parse_sample", sample_type, err);
+                goto out_free;
+        }
+
+        if (!samples_same(&sample, &sample_out, sample_type,
+                          sample_regs_user, read_format)) {
+                pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+                         sample_type);
+                goto out_free;
+        }
+
+        ret = 0;
+out_free:
+        free(event);
+        if (ret && read_format)
+                pr_debug("read_format %#"PRIx64"\n", read_format);
+        return ret;
+}
+
+/**
+ * test__sample_parsing - test sample parsing.
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample.  The test
+ * checks sample format bits separately and together.  If the test passes %0 is
+ * returned, otherwise %-1 is returned.
+ */
+int test__sample_parsing(void)
+{
+        const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
+        u64 sample_type;
+        u64 sample_regs_user;
+        size_t i;
+        int err;
+
+        /*
+         * Fail the test if it has not been updated when new sample format bits
+         * were added.
+         */
+        if (PERF_SAMPLE_MAX > PERF_SAMPLE_IDENTIFIER << 1) {
+                pr_debug("sample format has changed - test needs updating\n");
+                return -1;
+        }
+
+        /* Test each sample format bit separately */
+        for (sample_type = 1; sample_type != PERF_SAMPLE_MAX;
+             sample_type <<= 1) {
+                /* Test read_format variations */
+                if (sample_type == PERF_SAMPLE_READ) {
+                        for (i = 0; i < ARRAY_SIZE(rf); i++) {
+                                err = do_test(sample_type, 0, rf[i]);
+                                if (err)
+                                        return err;
+                        }
+                        continue;
+                }
+
+                if (sample_type == PERF_SAMPLE_REGS_USER)
+                        sample_regs_user = 0x3fff;
+                else
+                        sample_regs_user = 0;
+
+                err = do_test(sample_type, sample_regs_user, 0);
+                if (err)
+                        return err;
+        }
+
+        /* Test all sample format bits together */
+        sample_type = PERF_SAMPLE_MAX - 1;
+        sample_regs_user = 0x3fff;
+        for (i = 0; i < ARRAY_SIZE(rf); i++) {
+                err = do_test(sample_type, sample_regs_user, rf[i]);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index dd7feae2d37b..e0ac713857ba 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,6 +1,14 @@
 #ifndef TESTS_H
 #define TESTS_H
 
+#define TEST_ASSERT_VAL(text, cond)                                      \
+do {                                                                     \
+        if (!(cond)) {                                                   \
+                pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+                return -1;                                               \
+        }                                                                \
+} while (0)
+
 enum {
         TEST_OK   =  0,
         TEST_FAIL = -1,
@@ -27,5 +35,10 @@ int test__bp_signal(void);
 int test__bp_signal_overflow(void);
 int test__task_exit(void);
 int test__sw_clock_freq(void);
+int test__perf_time_to_tsc(void);
+int test__code_reading(void);
+int test__sample_parsing(void);
+int test__keep_tracking(void);
+int test__parse_no_sample_id_all(void);
 
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 7b4c4d26d1ba..2bd13edcbc17 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -16,6 +16,8 @@ static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
         return 0;
 }
 
+#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
+
 int test__vmlinux_matches_kallsyms(void)
 {
         int err = -1;
@@ -25,6 +27,7 @@ int test__vmlinux_matches_kallsyms(void)
         struct machine kallsyms, vmlinux;
         enum map_type type = MAP__FUNCTION;
         struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
+        u64 mem_start, mem_end;
 
         /*
          * Step 1:
@@ -73,7 +76,7 @@ int test__vmlinux_matches_kallsyms(void)
                 goto out;
         }
 
-        ref_reloc_sym.addr = sym->start;
+        ref_reloc_sym.addr = UM(sym->start);
 
         /*
          * Step 5:
@@ -123,10 +126,14 @@ int test__vmlinux_matches_kallsyms(void)
                 if (sym->start == sym->end)
                         continue;
 
-                first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
+                mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
+                mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
+
+                first_pair = machine__find_kernel_symbol(&kallsyms, type,
+                                                         mem_start, NULL, NULL);
                 pair = first_pair;
 
-                if (pair && pair->start == sym->start) {
+                if (pair && UM(pair->start) == mem_start) {
 next_pair:
                         if (strcmp(sym->name, pair->name) == 0) {
                                 /*
@@ -138,12 +145,20 @@ next_pair:
                                  * off the real size. More than that and we
                                  * _really_ have a problem.
                                  */
-                                s64 skew = sym->end - pair->end;
-                                if (llabs(skew) < page_size)
-                                        continue;
+                                s64 skew = mem_end - UM(pair->end);
+                                if (llabs(skew) >= page_size)
+                                        pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+                                                 mem_start, sym->name, mem_end,
+                                                 UM(pair->end));
+
+                                /*
+                                 * Do not count this as a failure, because we
+                                 * could really find a case where it's not
+                                 * possible to get proper function end from
+                                 * kallsyms.
+                                 */
+                                continue;
 
-                                pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
-                                         sym->start, sym->name, sym->end, pair->end);
                         } else {
                                 struct rb_node *nnd;
 detour:
@@ -152,7 +167,7 @@ detour:
                                 if (nnd) {
                                         struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
 
-                                        if (next->start == sym->start) {
+                                        if (UM(next->start) == mem_start) {
                                                 pair = next;
                                                 goto next_pair;
                                         }
@@ -165,10 +180,11 @@ detour:
                                 }
 
                                 pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
-                                         sym->start, sym->name, pair->name);
+                                         mem_start, sym->name, pair->name);
                         }
                 } else
-                        pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name);
+                        pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
+                                 mem_start, sym->name);
 
                 err = -1;
         }
@@ -201,16 +217,19 @@ detour:
         for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
                 struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
 
-                pair = map_groups__find(&kallsyms.kmaps, type, pos->start);
+                mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
+                mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+
+                pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
                 if (pair == NULL || pair->priv)
                         continue;
 
-                if (pair->start == pos->start) {
+                if (pair->start == mem_start) {
                         pair->priv = 1;
                         pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
                                 pos->start, pos->end, pos->pgoff, pos->dso->name);
-                        if (pos->pgoff != pair->pgoff || pos->end != pair->end)
-                                pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "",
+                        if (mem_end != pair->end)
+                                pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
                                         pair->start, pair->end, pair->pgoff);
                         pr_info(" %s\n", pair->dso->name);
                         pair->priv = 1;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index cc64d3f7fc36..08545ae46992 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -428,6 +428,14 @@ static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
         browser->b.nr_entries = browser->nr_asm_entries;
 }
 
+#define SYM_TITLE_MAX_SIZE (PATH_MAX + 64)
+
+static int sym_title(struct symbol *sym, struct map *map, char *title,
+                     size_t sz)
+{
+        return snprintf(title, sz, "%s  %s", sym->name, map->dso->long_name);
+}
+
 static bool annotate_browser__callq(struct annotate_browser *browser,
                                     struct perf_evsel *evsel,
                                     struct hist_browser_timer *hbt)
@@ -438,6 +446,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
         struct annotation *notes;
         struct symbol *target;
         u64 ip;
+        char title[SYM_TITLE_MAX_SIZE];
 
         if (!ins__is_call(dl->ins))
                 return false;
@@ -461,7 +470,8 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 
         pthread_mutex_unlock(&notes->lock);
         symbol__tui_annotate(target, ms->map, evsel, hbt);
-        ui_browser__show_title(&browser->b, sym->name);
+        sym_title(sym, ms->map, title, sizeof(title));
+        ui_browser__show_title(&browser->b, title);
         return true;
 }
 
@@ -495,7 +505,7 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
 
         dl = annotate_browser__find_offset(browser, dl->ops.target.offset, &idx);
         if (dl == NULL) {
-                ui_helpline__puts("Invallid jump offset");
+                ui_helpline__puts("Invalid jump offset");
                 return true;
         }
 
@@ -653,8 +663,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
         const char *help = "Press 'h' for help on key bindings";
         int delay_secs = hbt ? hbt->refresh : 0;
         int key;
+        char title[SYM_TITLE_MAX_SIZE];
 
-        if (ui_browser__show(&browser->b, sym->name, help) < 0)
+        sym_title(sym, ms->map, title, sizeof(title));
+        if (ui_browser__show(&browser->b, title, help) < 0)
                 return -1;
 
         annotate_browser__calc_percent(browser, evsel);
@@ -720,7 +732,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
                 "s             Toggle source code view\n"
                 "/             Search string\n"
                 "r             Run available scripts\n"
-                "?             Search previous string\n");
+                "?             Search string backwards\n");
                         continue;
                 case 'r':
                         {
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fc0bd3843d34..7ef36c360471 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -685,8 +685,10 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
         return he->stat._field;                                         \
 }                                                                       \
                                                                         \
-static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp,        \
-                                           struct hist_entry *he)       \
+static int                                                              \
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+                                struct perf_hpp *hpp,                   \
+                                struct hist_entry *he)                  \
 {                                                                       \
         return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb);      \
 }
@@ -701,8 +703,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL)
 
 void hist_browser__init_hpp(void)
 {
-        perf_hpp__column_enable(PERF_HPP__OVERHEAD);
-
         perf_hpp__init();
 
         perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -762,9 +762,9 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         first = false;
 
                         if (fmt->color) {
-                                width -= fmt->color(&hpp, entry);
+                                width -= fmt->color(fmt, &hpp, entry);
                         } else {
-                                width -= fmt->entry(&hpp, entry);
+                                width -= fmt->entry(fmt, &hpp, entry);
                                 slsmg_printf("%s", s);
                         }
                 }
@@ -1256,7 +1256,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
                 printed += scnprintf(bf + printed, size - printed,
                                     ", Thread: %s(%d)",
                                     (thread->comm_set ? thread->comm : ""),
-                                    thread->pid);
+                                    thread->tid);
         if (dso)
                 printed += scnprintf(bf + printed, size - printed,
                                     ", DSO: %s", dso->short_name);
@@ -1579,7 +1579,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                     asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
                              (browser->hists->thread_filter ? "out of" : "into"),
                              (thread->comm_set ? thread->comm : ""),
-                             thread->pid) > 0)
+                             thread->tid) > 0)
                         zoom_thread = nr_options++;
 
                 if (dso != NULL &&
@@ -1702,7 +1702,7 @@ zoom_out_thread:
                         } else {
                                 ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
                                                    thread->comm_set ? thread->comm : "",
-                                                   thread->pid);
+                                                   thread->tid);
                                 browser->hists->thread_filter = thread;
                                 sort_thread.elide = true;
                                 pstack__push(fstack, &browser->hists->thread_filter);
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 9708dd5fb8f3..2ca66cc1160f 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -91,7 +91,8 @@ static u64 he_get_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp,                    \
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+                                       struct perf_hpp *hpp,                    \
                                        struct hist_entry *he)                   \
 {                                                                               \
         return __hpp__color_fmt(hpp, he, he_get_##_field);                      \
@@ -108,8 +109,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
 
 void perf_gtk__init_hpp(void)
 {
-        perf_hpp__column_enable(PERF_HPP__OVERHEAD);
-
         perf_hpp__init();
 
         perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -124,6 +123,81 @@ void perf_gtk__init_hpp(void)
                                 perf_gtk__hpp_color_overhead_guest_us;
 }
 
+static void callchain_list__sym_name(struct callchain_list *cl,
+                                     char *bf, size_t bfsize)
+{
+        if (cl->ms.sym)
+                scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+        else
+                scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+}
+
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+                                    GtkTreeIter *parent, int col, u64 total)
+{
+        struct rb_node *nd;
+        bool has_single_node = (rb_first(root) == rb_last(root));
+
+        for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+                struct callchain_node *node;
+                struct callchain_list *chain;
+                GtkTreeIter iter, new_parent;
+                bool need_new_parent;
+                double percent;
+                u64 hits, child_total;
+
+                node = rb_entry(nd, struct callchain_node, rb_node);
+
+                hits = callchain_cumul_hits(node);
+                percent = 100.0 * hits / total;
+
+                new_parent = *parent;
+                need_new_parent = !has_single_node && (node->val_nr > 1);
+
+                list_for_each_entry(chain, &node->val, list) {
+                        char buf[128];
+
+                        gtk_tree_store_append(store, &iter, &new_parent);
+
+                        scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+                        gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+                        callchain_list__sym_name(chain, buf, sizeof(buf));
+                        gtk_tree_store_set(store, &iter, col, buf, -1);
+
+                        if (need_new_parent) {
+                                /*
+                                 * Only show the top-most symbol in a callchain
+                                 * if it's not the only callchain.
+                                 */
+                                new_parent = iter;
+                                need_new_parent = false;
+                        }
+                }
+
+                if (callchain_param.mode == CHAIN_GRAPH_REL)
+                        child_total = node->children_hit;
+                else
+                        child_total = total;
+
+                /* Now 'iter' contains info of the last callchain_list */
+                perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
+                                        child_total);
+        }
+}
+
+static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
+                             GtkTreeViewColumn *col __maybe_unused,
+                             gpointer user_data __maybe_unused)
+{
+        bool expanded = gtk_tree_view_row_expanded(view, path);
+
+        if (expanded)
+                gtk_tree_view_collapse_row(view, path);
+        else
+                gtk_tree_view_expand_row(view, path, FALSE);
+}
+
 static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                                  float min_pcnt)
 {
@@ -131,10 +205,11 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
         GType col_types[MAX_COLUMNS];
         GtkCellRenderer *renderer;
         struct sort_entry *se;
-        GtkListStore *store;
+        GtkTreeStore *store;
         struct rb_node *nd;
         GtkWidget *view;
         int col_idx;
+        int sym_col = -1;
         int nr_cols;
         char s[512];
 
@@ -153,10 +228,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                 if (se->elide)
                         continue;
 
+                if (se == &sort_sym)
+                        sym_col = nr_cols;
+
                 col_types[nr_cols++] = G_TYPE_STRING;
         }
 
-        store = gtk_list_store_newv(nr_cols, col_types);
+        store = gtk_tree_store_newv(nr_cols, col_types);
 
         view = gtk_tree_view_new();
 
@@ -165,7 +243,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
         col_idx = 0;
 
         perf_hpp__for_each_format(fmt) {
-                fmt->header(&hpp);
+                fmt->header(fmt, &hpp);
 
                 gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
                                                             -1, ltrim(s),
@@ -183,6 +261,18 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                                                             col_idx++, NULL);
         }
 
+        for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+                GtkTreeViewColumn *column;
+
+                column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+                gtk_tree_view_column_set_resizable(column, TRUE);
+
+                if (col_idx == sym_col) {
+                        gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+                                                          column);
+                }
+        }
+
         gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
 
         g_object_unref(GTK_TREE_MODEL(store));
@@ -199,17 +289,17 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                 if (percent < min_pcnt)
                         continue;
 
-                gtk_list_store_append(store, &iter);
+                gtk_tree_store_append(store, &iter, NULL);
 
                 col_idx = 0;
 
                 perf_hpp__for_each_format(fmt) {
                         if (fmt->color)
-                                fmt->color(&hpp, h);
+                                fmt->color(fmt, &hpp, h);
                         else
-                                fmt->entry(&hpp, h);
+                                fmt->entry(fmt, &hpp, h);
 
-                        gtk_list_store_set(store, &iter, col_idx++, s, -1);
+                        gtk_tree_store_set(store, &iter, col_idx++, s, -1);
                 }
 
                 list_for_each_entry(se, &hist_entry__sort_list, list) {
@@ -219,10 +309,26 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
                         se->se_snprintf(h, s, ARRAY_SIZE(s),
                                         hists__col_len(hists, se->se_width_idx));
 
-                        gtk_list_store_set(store, &iter, col_idx++, s, -1);
+                        gtk_tree_store_set(store, &iter, col_idx++, s, -1);
+                }
+
+                if (symbol_conf.use_callchain && sort__has_sym) {
+                        u64 total;
+
+                        if (callchain_param.mode == CHAIN_GRAPH_REL)
+                                total = h->stat.period;
+                        else
+                                total = hists->stats.total_period;
+
+                        perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
+                                                sym_col, total);
                 }
         }
 
+        gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+        g_signal_connect(view, "row-activated",
+                         G_CALLBACK(on_row_activated), NULL);
         gtk_container_add(GTK_CONTAINER(window), view);
 }
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4bf91b09d62d..0a193281eba8 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -1,4 +1,5 @@
 #include <math.h>
+#include <linux/compiler.h>
 
 #include "../util/hist.h"
 #include "../util/util.h"
@@ -79,7 +80,8 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 }
 
 #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width)           \
-static int hpp__header_##_type(struct perf_hpp *hpp)                    \
+static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+                               struct perf_hpp *hpp)                    \
 {                                                                       \
         int len = _min_width;                                           \
                                                                         \
@@ -92,7 +94,8 @@ static int hpp__header_##_type(struct perf_hpp *hpp)			\
 }
 
 #define __HPP_WIDTH_FN(_type, _min_width, _unit_width)                  \
-static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused)      \
+static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,  \
+                              struct perf_hpp *hpp __maybe_unused)      \
 {                                                                       \
         int len = _min_width;                                           \
                                                                         \
@@ -110,14 +113,16 @@ static u64 he_get_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he)      \
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,          \
+                              struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
         return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",                 \
                           (hpp_snprint_fn)percent_color_snprintf, true);        \
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)                                   \
-static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he)      \
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,         \
+                              struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
         const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";         \
         return __hpp__fmt(hpp, he, he_get_##_field, fmt,                        \
@@ -130,7 +135,8 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
         return he->stat._field;                                                 \
 }                                                                               \
                                                                                 \
-static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he)      \
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,         \
+                              struct perf_hpp *hpp, struct hist_entry *he)      \
 {                                                                               \
         const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;    \
         return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \
@@ -157,196 +163,6 @@ HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
 HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
 HPP_RAW_FNS(period, "Period", period, 12, 12)
 
-
-static int hpp__header_baseline(struct perf_hpp *hpp)
-{
-        return scnprintf(hpp->buf, hpp->size, "Baseline");
-}
-
-static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused)
-{
-        return 8;
-}
-
-static double baseline_percent(struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        struct hists *pair_hists = pair ? pair->hists : NULL;
-        double percent = 0.0;
-
-        if (pair) {
-                u64 total_period = pair_hists->stats.total_period;
-                u64 base_period  = pair->stat.period;
-
-                percent = 100.0 * base_period / total_period;
-        }
-
-        return percent;
-}
-
-static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        double percent = baseline_percent(he);
-
-        if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
-                return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
-        else
-                return scnprintf(hpp->buf, hpp->size, "        ");
-}
-
-static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        double percent = baseline_percent(he);
-        const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
-
-        if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
-                return scnprintf(hpp->buf, hpp->size, fmt, percent);
-        else
-                return scnprintf(hpp->buf, hpp->size, "            ");
-}
-
-static int hpp__header_period_baseline(struct perf_hpp *hpp)
-{
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
-
-        return scnprintf(hpp->buf, hpp->size, fmt, "Period Base");
-}
-
-static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused)
-{
-        return 12;
-}
-
-static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        u64 period = pair ? pair->stat.period : 0;
-        const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
-
-        return scnprintf(hpp->buf, hpp->size, fmt, period);
-}
-
-static int hpp__header_delta(struct perf_hpp *hpp)
-{
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
-
-        return scnprintf(hpp->buf, hpp->size, fmt, "Delta");
-}
-
-static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused)
-{
-        return 7;
-}
-
-static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s";
-        char buf[32] = " ";
-        double diff = 0.0;
-
-        if (pair) {
-                if (he->diff.computed)
-                        diff = he->diff.period_ratio_delta;
-                else
-                        diff = perf_diff__compute_delta(he, pair);
-        } else
-                diff = perf_diff__period_percent(he, he->stat.period);
-
-        if (fabs(diff) >= 0.01)
-                scnprintf(buf, sizeof(buf), "%+4.2F%%", diff);
-
-        return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_ratio(struct perf_hpp *hpp)
-{
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-
-        return scnprintf(hpp->buf, hpp->size, fmt, "Ratio");
-}
-
-static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused)
-{
-        return 14;
-}
-
-static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-        char buf[32] = " ";
-        double ratio = 0.0;
-
-        if (pair) {
-                if (he->diff.computed)
-                        ratio = he->diff.period_ratio;
-                else
-                        ratio = perf_diff__compute_ratio(he, pair);
-        }
-
-        if (ratio > 0.0)
-                scnprintf(buf, sizeof(buf), "%+14.6F", ratio);
-
-        return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_wdiff(struct perf_hpp *hpp)
-{
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-
-        return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff");
-}
-
-static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused)
-{
-        return 14;
-}
-
-static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-        char buf[32] = " ";
-        s64 wdiff = 0;
-
-        if (pair) {
-                if (he->diff.computed)
-                        wdiff = he->diff.wdiff;
-                else
-                        wdiff = perf_diff__compute_wdiff(he, pair);
-        }
-
-        if (wdiff != 0)
-                scnprintf(buf, sizeof(buf), "%14ld", wdiff);
-
-        return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_formula(struct perf_hpp *hpp)
-{
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%70s";
-
-        return scnprintf(hpp->buf, hpp->size, fmt, "Formula");
-}
-
-static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused)
-{
-        return 70;
-}
-
-static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
-{
-        struct hist_entry *pair = hist_entry__next_pair(he);
-        const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s";
-        char buf[96] = " ";
-
-        if (pair)
-                perf_diff__formula(he, pair, buf, sizeof(buf));
-
-        return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
 #define HPP__COLOR_PRINT_FNS(_name)                     \
         {                                               \
                 .header = hpp__header_ ## _name,        \
@@ -363,19 +179,13 @@ static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
         }
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-        HPP__COLOR_PRINT_FNS(baseline),
         HPP__COLOR_PRINT_FNS(overhead),
         HPP__COLOR_PRINT_FNS(overhead_sys),
         HPP__COLOR_PRINT_FNS(overhead_us),
         HPP__COLOR_PRINT_FNS(overhead_guest_sys),
         HPP__COLOR_PRINT_FNS(overhead_guest_us),
         HPP__PRINT_FNS(samples),
-        HPP__PRINT_FNS(period),
-        HPP__PRINT_FNS(period_baseline),
-        HPP__PRINT_FNS(delta),
-        HPP__PRINT_FNS(ratio),
-        HPP__PRINT_FNS(wdiff),
-        HPP__PRINT_FNS(formula)
+        HPP__PRINT_FNS(period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -396,6 +206,8 @@ LIST_HEAD(perf_hpp__list);
 
 void perf_hpp__init(void)
 {
+        perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
         if (symbol_conf.show_cpu_utilization) {
                 perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS);
                 perf_hpp__column_enable(PERF_HPP__OVERHEAD_US);
@@ -424,46 +236,6 @@ void perf_hpp__column_enable(unsigned col)
         perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
-static inline void advance_hpp(struct perf_hpp *hpp, int inc)
-{
-        hpp->buf  += inc;
-        hpp->size -= inc;
-}
-
-int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
-                                bool color)
-{
-        const char *sep = symbol_conf.field_sep;
-        struct perf_hpp_fmt *fmt;
-        char *start = hpp->buf;
-        int ret;
-        bool first = true;
-
-        if (symbol_conf.exclude_other && !he->parent)
-                return 0;
-
-        perf_hpp__for_each_format(fmt) {
-                /*
-                 * If there's no field_sep, we still need
-                 * to display initial '  '.
-                 */
-                if (!sep || !first) {
-                        ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
-                        advance_hpp(hpp, ret);
-                } else
-                        first = false;
-
-                if (color && fmt->color)
-                        ret = fmt->color(hpp, he);
-                else
-                        ret = fmt->entry(hpp, he);
-
-                advance_hpp(hpp, ret);
-        }
-
-        return hpp->buf - start;
-}
-
 int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size,
                               struct hists *hists)
 {
@@ -499,7 +271,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
                 if (i)
                         ret += 2;
 
-                ret += fmt->width(&dummy_hpp);
+                ret += fmt->width(fmt, &dummy_hpp);
         }
 
         list_for_each_entry(se, &hist_entry__sort_list, list)
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ae6a789cb0f6..47d9a571f261 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -30,7 +30,6 @@ void setup_browser(bool fallback_to_pager)
                 if (fallback_to_pager)
                         setup_pager();
 
-                perf_hpp__column_enable(PERF_HPP__OVERHEAD);
                 perf_hpp__init();
                 break;
         }
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index ae7a75432249..194e2f42ff5d 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -308,10 +308,51 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
         return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
 }
 
+static inline void advance_hpp(struct perf_hpp *hpp, int inc)
+{
+        hpp->buf  += inc;
+        hpp->size -= inc;
+}
+
+static int hist_entry__period_snprintf(struct perf_hpp *hpp,
+                                       struct hist_entry *he,
+                                       bool color)
+{
+        const char *sep = symbol_conf.field_sep;
+        struct perf_hpp_fmt *fmt;
+        char *start = hpp->buf;
+        int ret;
+        bool first = true;
+
+        if (symbol_conf.exclude_other && !he->parent)
+                return 0;
+
+        perf_hpp__for_each_format(fmt) {
+                /*
+                 * If there's no field_sep, we still need
+                 * to display initial '  '.
+                 */
+                if (!sep || !first) {
+                        ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+                        advance_hpp(hpp, ret);
+                } else
+                        first = false;
+
+                if (color && fmt->color)
+                        ret = fmt->color(fmt, hpp, he);
+                else
+                        ret = fmt->entry(fmt, hpp, he);
+
+                advance_hpp(hpp, ret);
+        }
+
+        return hpp->buf - start;
+}
+
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
-                               struct hists *hists, FILE *fp)
+                               struct hists *hists,
+                               char *bf, size_t bfsz, FILE *fp)
 {
-        char bf[512];
         int ret;
         struct perf_hpp hpp = {
                 .buf            = bf,
@@ -319,8 +360,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
         };
         bool color = !symbol_conf.field_sep;
 
-        if (size == 0 || size > sizeof(bf))
-                size = hpp.size = sizeof(bf);
+        if (size == 0 || size > bfsz)
+                size = hpp.size = bfsz;
 
         ret = hist_entry__period_snprintf(&hpp, he, color);
         hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
@@ -351,6 +392,8 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 .ptr    = hists_to_evsel(hists),
         };
         bool first = true;
+        size_t linesz;
+        char *line = NULL;
 
         init_rem_hits();
 
@@ -365,7 +408,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 else
                         first = false;
 
-                fmt->header(&dummy_hpp);
+                fmt->header(fmt, &dummy_hpp);
                 fprintf(fp, "%s", bf);
         }
 
@@ -410,7 +453,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 else
                         first = false;
 
-                width = fmt->width(&dummy_hpp);
+                width = fmt->width(fmt, &dummy_hpp);
                 for (i = 0; i < width; i++)
                         fprintf(fp, ".");
         }
@@ -438,6 +481,13 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 goto out;
 
 print_entries:
+        linesz = hists__sort_list_width(hists) + 3 + 1;
+        line = malloc(linesz);
+        if (line == NULL) {
+                ret = -1;
+                goto out;
+        }
+
         for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
                 float percent = h->stat.period * 100.0 /
@@ -449,10 +499,10 @@ print_entries:
                 if (percent < min_pcnt)
                         continue;
 
-                ret += hist_entry__fprintf(h, max_cols, hists, fp);
+                ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
 
                 if (max_rows && ++nr_rows >= max_rows)
-                        goto out;
+                        break;
 
                 if (h->ms.map == NULL && verbose > 1) {
                         __map_groups__fprintf_maps(&h->thread->mg,
@@ -460,6 +510,8 @@ print_entries:
                         fprintf(fp, "%.10s end\n", graph_dotted_line);
                 }
         }
+
+        free(line);
 out:
         free(rem_sq_bracket);
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index d102716c43a1..7eae5488ecea 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -110,10 +110,10 @@ static int jump__parse(struct ins_operands *ops)
 {
         const char *s = strchr(ops->raw, '+');
 
-        ops->target.addr = strtoll(ops->raw, NULL, 16);
+        ops->target.addr = strtoull(ops->raw, NULL, 16);
 
         if (s++ != NULL)
-                ops->target.offset = strtoll(s, NULL, 16);
+                ops->target.offset = strtoull(s, NULL, 16);
         else
                 ops->target.offset = UINT64_MAX;
 
@@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
                     end = map__rip_2objdump(map, sym->end);
 
                 offset = line_ip - start;
-                if (offset < 0 || (u64)line_ip > end)
+                if ((u64)line_ip < start || (u64)line_ip > end)
                         offset = -1;
                 else
                         parsed_line = tmp2 + 1;
@@ -821,11 +821,55 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
         if (dl == NULL)
                 return -1;
 
+        if (dl->ops.target.offset == UINT64_MAX)
+                dl->ops.target.offset = dl->ops.target.addr -
+                                        map__rip_2objdump(map, sym->start);
+
+        /*
+         * kcore has no symbols, so add the call target name if it is on the
+         * same map.
+         */
+        if (dl->ins && ins__is_call(dl->ins) && !dl->ops.target.name) {
+                struct symbol *s;
+                u64 ip = dl->ops.target.addr;
+
+                if (ip >= map->start && ip <= map->end) {
+                        ip = map->map_ip(map, ip);
+                        s = map__find_symbol(map, ip, NULL);
+                        if (s && s->start == ip)
+                                dl->ops.target.name = strdup(s->name);
+                }
+        }
+
         disasm__add(&notes->src->source, dl);
 
         return 0;
 }
 
+static void delete_last_nop(struct symbol *sym)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct list_head *list = &notes->src->source;
+        struct disasm_line *dl;
+
+        while (!list_empty(list)) {
+                dl = list_entry(list->prev, struct disasm_line, node);
+
+                if (dl->ins && dl->ins->ops) {
+                        if (dl->ins->ops != &nop_ops)
+                                return;
+                } else {
+                        if (!strstr(dl->line, " nop ") &&
+                            !strstr(dl->line, " nopl ") &&
+                            !strstr(dl->line, " nopw "))
+                                return;
+                }
+
+                list_del(&dl->node);
+                disasm_line__free(dl);
+        }
+}
+
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 {
         struct dso *dso = map->dso;
@@ -864,7 +908,8 @@ fallback:
                 free_filename = false;
         }
 
-        if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+        if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+            !dso__is_kcore(dso)) {
                 char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
                 char *build_id_msg = NULL;
 
@@ -898,7 +943,7 @@ fallback:
         snprintf(command, sizeof(command),
                  "%s %s%s --start-address=0x%016" PRIx64
                  " --stop-address=0x%016" PRIx64
-                 " -d %s %s -C %s|grep -v %s|expand",
+                 " -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
                  objdump_path ? objdump_path : "objdump",
                  disassembler_style ? "-M " : "",
                  disassembler_style ? disassembler_style : "",
@@ -918,6 +963,13 @@ fallback:
                 if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
                         break;
 
+        /*
+         * kallsyms does not have symbol sizes so there may a nop at the end.
+         * Remove it.
+         */
+        if (dso__is_kcore(dso))
+                delete_last_nop(sym);
+
         pclose(file);
 out_free_filename:
         if (free_filename)
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 5295625c0c00..7ded71d19d75 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -18,13 +18,14 @@
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
                            union perf_event *event,
-                           struct perf_sample *sample __maybe_unused,
+                           struct perf_sample *sample,
                            struct perf_evsel *evsel __maybe_unused,
                            struct machine *machine)
 {
         struct addr_location al;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+        struct thread *thread = machine__findnew_thread(machine, sample->pid,
+                                                        sample->pid);
 
         if (thread == NULL) {
                 pr_err("problem processing %d event, skipping it.\n",
@@ -33,7 +34,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
         }
 
         thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              event->ip.ip, &al);
+                              sample->ip, &al);
 
         if (al.map != NULL)
                 al.map->dso->hit = 1;
@@ -47,7 +48,9 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
                                        __maybe_unused,
                                        struct machine *machine)
 {
-        struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+        struct thread *thread = machine__findnew_thread(machine,
+                                                        event->fork.pid,
+                                                        event->fork.tid);
 
         dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
                     event->fork.ppid, event->fork.ptid);
@@ -64,6 +67,7 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 struct perf_tool build_id__mark_dso_hit_ops = {
         .sample = build_id__mark_dso_hit,
         .mmap   = perf_event__process_mmap,
+        .mmap2  = perf_event__process_mmap2,
         .fork   = perf_event__process_fork,
         .exit   = perf_event__exit_del_thread,
         .attr            = perf_event__process_attr,
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42b6a632fe7b..482f68081cd8 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -15,19 +15,12 @@
 #include <errno.h>
 #include <math.h>
 
+#include "hist.h"
 #include "util.h"
 #include "callchain.h"
 
 __thread struct callchain_cursor callchain_cursor;
 
-bool ip_callchain__valid(struct ip_callchain *chain,
-                         const union perf_event *event)
-{
-        unsigned int chain_size = event->header.size;
-        chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-        return chain->nr * sizeof(u64) <= chain_size;
-}
-
 #define chain_for_each_child(child, parent)     \
         list_for_each_entry(child, &parent->children, siblings)
 
@@ -327,7 +320,8 @@ append_chain(struct callchain_node *root,
         /*
          * Lookup in the current node
          * If we have a symbol, then compare the start to match
-         * anywhere inside a function.
+         * anywhere inside a function, unless function
+         * mode is disabled.
          */
         list_for_each_entry(cnode, &root->val, list) {
                 struct callchain_cursor_node *node;
@@ -339,7 +333,8 @@ append_chain(struct callchain_node *root,
 
                 sym = node->sym;
 
-                if (cnode->ms.sym && sym) {
+                if (cnode->ms.sym && sym &&
+                    callchain_param.key == CCKEY_FUNCTION) {
                         if (cnode->ms.sym->start != sym->start)
                                 break;
                 } else if (cnode->ip != node->ip)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 3ee9f67d5af0..2b585bc308cf 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -41,12 +41,18 @@ struct callchain_param;
 typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
                                  u64, struct callchain_param *);
 
+enum chain_key {
+        CCKEY_FUNCTION,
+        CCKEY_ADDRESS
+};
+
 struct callchain_param {
         enum chain_mode         mode;
         u32                     print_limit;
         double                  min_percent;
         sort_chain_func_t       sort;
         enum chain_order        order;
+        enum chain_key          key;
 };
 
 struct callchain_list {
@@ -103,11 +109,6 @@ int callchain_append(struct callchain_root *root,
 int callchain_merge(struct callchain_cursor *cursor,
                     struct callchain_root *dst, struct callchain_root *src);
 
-struct ip_callchain;
-union perf_event;
-
-bool ip_callchain__valid(struct ip_callchain *chain,
-                         const union perf_event *event);
 /*
  * Initialize a cursor before adding entries inside, but keep
  * the previously allocated entries as a cache.
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 9bed02e5fb3d..b123bb9d6f55 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -41,7 +41,7 @@ static inline int cpu_map__nr(const struct cpu_map *map)
         return map ? map->nr : 1;
 }
 
-static inline bool cpu_map__all(const struct cpu_map *map)
+static inline bool cpu_map__empty(const struct cpu_map *map)
 {
         return map ? map->map[0] == -1 : true;
 }
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index c4374f07603c..e3c1ff8512c8 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -78,6 +78,8 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
                          symbol_conf.symfs, build_id_hex, build_id_hex + 2);
                 break;
 
+        case DSO_BINARY_TYPE__VMLINUX:
+        case DSO_BINARY_TYPE__GUEST_VMLINUX:
         case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
                 snprintf(file, size, "%s%s",
                          symbol_conf.symfs, dso->long_name);
@@ -93,11 +95,14 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
                          dso->long_name);
                 break;
 
+        case DSO_BINARY_TYPE__KCORE:
+        case DSO_BINARY_TYPE__GUEST_KCORE:
+                snprintf(file, size, "%s", dso->long_name);
+                break;
+
         default:
         case DSO_BINARY_TYPE__KALLSYMS:
-        case DSO_BINARY_TYPE__VMLINUX:
         case DSO_BINARY_TYPE__GUEST_KALLSYMS:
-        case DSO_BINARY_TYPE__GUEST_VMLINUX:
         case DSO_BINARY_TYPE__JAVA_JIT:
         case DSO_BINARY_TYPE__NOT_FOUND:
                 ret = -1;
@@ -419,6 +424,7 @@ struct dso *dso__new(const char *name)
                 dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
                 dso->loaded = 0;
+                dso->rel = 0;
                 dso->sorted_by_name = 0;
                 dso->has_build_id = 0;
                 dso->kernel = DSO_TYPE_USER;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index d51aaf272c68..b793053335d6 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/rbtree.h>
+#include <stdbool.h>
 #include "types.h"
 #include "map.h"
 
@@ -20,6 +21,8 @@ enum dso_binary_type {
         DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
         DSO_BINARY_TYPE__GUEST_KMODULE,
         DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+        DSO_BINARY_TYPE__KCORE,
+        DSO_BINARY_TYPE__GUEST_KCORE,
         DSO_BINARY_TYPE__NOT_FOUND,
 };
 
@@ -84,6 +87,7 @@ struct dso {
         u8               lname_alloc:1;
         u8               sorted_by_name;
         u8               loaded;
+        u8               rel;
         u8               build_id[BUILD_ID_SIZE];
         const char       *short_name;
         char             *long_name;
@@ -146,4 +150,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
 size_t dso__fprintf_symbols_by_name(struct dso *dso,
                                     enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+
+static inline bool dso__is_vmlinux(struct dso *dso)
+{
+        return dso->data_type == DSO_BINARY_TYPE__VMLINUX ||
+               dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+}
+
+static inline bool dso__is_kcore(struct dso *dso)
+{
+        return dso->data_type == DSO_BINARY_TYPE__KCORE ||
+               dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE;
+}
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 3e5f5430a28a..e23bde19d590 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
 }
 
 /**
+ * die_is_func_def - Ensure that this DIE is a subprogram and definition
+ * @dw_die: a DIE
+ *
+ * Ensure that this DIE is a subprogram and NOT a declaration. This
+ * returns true if @dw_die is a function definition.
+ **/
+bool die_is_func_def(Dwarf_Die *dw_die)
+{
+        Dwarf_Attribute attr;
+
+        return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
+                dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+}
+
+/**
  * die_get_data_member_location - Get the data-member offset
  * @mb_die: a DIE of a member of a data structure
  * @offs: The offset of the member in the data structure
@@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
         struct __addr_die_search_param *ad = data;
 
+        /*
+         * Since a declaration entry doesn't has given pc, this always returns
+         * function definition entry.
+         */
         if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
             dwarf_haspc(fn_die, ad->addr)) {
                 memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 6ce1717784b7..8658d41697d2 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
 extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
                         int (*callback)(Dwarf_Die *, void *), void *data);
 
+/* Ensure that this DIE is a subprogram and definition (not declaration) */
+extern bool die_is_func_def(Dwarf_Die *dw_die);
+
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 5cd13d768cec..9b393e7dca6f 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -11,6 +11,7 @@
 static const char *perf_event__names[] = {
         [0]                                     = "TOTAL",
         [PERF_RECORD_MMAP]                      = "MMAP",
+        [PERF_RECORD_MMAP2]                     = "MMAP2",
         [PERF_RECORD_LOST]                      = "LOST",
         [PERF_RECORD_COMM]                      = "COMM",
         [PERF_RECORD_EXIT]                      = "EXIT",
@@ -186,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 return -1;
         }
 
-        event->header.type = PERF_RECORD_MMAP;
+        event->header.type = PERF_RECORD_MMAP2;
         /*
          * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
          */
@@ -197,7 +198,9 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 char prot[5];
                 char execname[PATH_MAX];
                 char anonstr[] = "//anon";
+                unsigned int ino;
                 size_t size;
+                ssize_t n;
 
                 if (fgets(bf, sizeof(bf), fp) == NULL)
                         break;
@@ -206,9 +209,16 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 strcpy(execname, "");
 
                 /* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-                sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-                       &event->mmap.start, &event->mmap.len, prot,
-                       &event->mmap.pgoff, execname);
+                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+                       &event->mmap2.start, &event->mmap2.len, prot,
+                       &event->mmap2.pgoff, &event->mmap2.maj,
+                       &event->mmap2.min,
+                       &ino, execname);
+
+                event->mmap2.ino = (u64)ino;
+
+                if (n != 8)
+                        continue;
 
                 if (prot[2] != 'x')
                         continue;
@@ -217,15 +227,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                         strcpy(execname, anonstr);
 
                 size = strlen(execname) + 1;
-                memcpy(event->mmap.filename, execname, size);
+                memcpy(event->mmap2.filename, execname, size);
                 size = PERF_ALIGN(size, sizeof(u64));
-                event->mmap.len -= event->mmap.start;
-                event->mmap.header.size = (sizeof(event->mmap) -
-                                           (sizeof(event->mmap.filename) - size));
-                memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-                event->mmap.header.size += machine->id_hdr_size;
-                event->mmap.pid = tgid;
-                event->mmap.tid = pid;
+                event->mmap2.len -= event->mmap.start;
+                event->mmap2.header.size = (sizeof(event->mmap2) -
+                                        (sizeof(event->mmap2.filename) - size));
+                memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+                event->mmap2.header.size += machine->id_hdr_size;
+                event->mmap2.pid = tgid;
+                event->mmap2.tid = pid;
 
                 if (process(tool, event, &synth_sample, machine) != 0) {
                         rc = -1;
@@ -527,6 +537,17 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
                        event->mmap.len, event->mmap.pgoff, event->mmap.filename);
 }
 
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
+{
+        return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
+                           " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n",
+                       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+                       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
+                       event->mmap2.min, event->mmap2.ino,
+                       event->mmap2.ino_generation,
+                       event->mmap2.filename);
+}
+
 int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
                              union perf_event *event,
                              struct perf_sample *sample __maybe_unused,
@@ -535,6 +556,14 @@ int perf_event__process_mmap(struct perf_tool *tool __maybe_unused,
         return machine__process_mmap_event(machine, event);
 }
 
+int perf_event__process_mmap2(struct perf_tool *tool __maybe_unused,
+                             union perf_event *event,
+                             struct perf_sample *sample __maybe_unused,
+                             struct machine *machine)
+{
+        return machine__process_mmap2_event(machine, event);
+}
+
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
 {
         return fprintf(fp, "(%d:%d):(%d:%d)\n",
@@ -574,6 +603,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
         case PERF_RECORD_MMAP:
                 ret += perf_event__fprintf_mmap(event, fp);
                 break;
+        case PERF_RECORD_MMAP2:
+                ret += perf_event__fprintf_mmap2(event, fp);
+                break;
         default:
                 ret += fprintf(fp, "\n");
         }
@@ -595,6 +627,7 @@ void thread__find_addr_map(struct thread *self,
                            struct addr_location *al)
 {
         struct map_groups *mg = &self->mg;
+        bool load_map = false;
 
         al->thread = self;
         al->addr = addr;
@@ -609,11 +642,13 @@ void thread__find_addr_map(struct thread *self,
         if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
                 al->level = 'k';
                 mg = &machine->kmaps;
+                load_map = true;
         } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
                 al->level = '.';
         } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
                 al->level = 'g';
                 mg = &machine->kmaps;
+                load_map = true;
         } else {
                 /*
                  * 'u' means guest os user space.
@@ -654,18 +689,25 @@ try_again:
                         mg = &machine->kmaps;
                         goto try_again;
                 }
-        } else
+        } else {
+                /*
+                 * Kernel maps might be changed when loading symbols so loading
+                 * must be done prior to using kernel maps.
+                 */
+                if (load_map)
+                        map__load(al->map, machine->symbol_filter);
                 al->addr = al->map->map_ip(al->map, al->addr);
+        }
 }
 
 void thread__find_addr_location(struct thread *thread, struct machine *machine,
                                 u8 cpumode, enum map_type type, u64 addr,
-                                struct addr_location *al,
-                                symbol_filter_t filter)
+                                struct addr_location *al)
 {
         thread__find_addr_map(thread, machine, cpumode, type, addr, al);
         if (al->map != NULL)
-                al->sym = map__find_symbol(al->map, al->addr, filter);
+                al->sym = map__find_symbol(al->map, al->addr,
+                                           machine->symbol_filter);
         else
                 al->sym = NULL;
 }
@@ -673,11 +715,11 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine,
 int perf_event__preprocess_sample(const union perf_event *event,
                                   struct machine *machine,
                                   struct addr_location *al,
-                                  struct perf_sample *sample,
-                                  symbol_filter_t filter)
+                                  struct perf_sample *sample)
 {
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+        struct thread *thread = machine__findnew_thread(machine, sample->pid,
+                                                        sample->pid);
 
         if (thread == NULL)
                 return -1;
@@ -686,7 +728,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
             !strlist__has_entry(symbol_conf.comm_list, thread->comm))
                 goto out_filtered;
 
-        dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+        dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
         /*
          * Have we already created the kernel maps for this machine?
          *
@@ -699,7 +741,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
                 machine__create_kernel_maps(machine);
 
         thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              event->ip.ip, al);
+                              sample->ip, al);
         dump_printf(" ...... dso: %s\n",
                     al->map ? al->map->dso->long_name :
                         al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -717,7 +759,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
                                                    dso->long_name)))))
                         goto out_filtered;
 
-                al->sym = map__find_symbol(al->map, al->addr, filter);
+                al->sym = map__find_symbol(al->map, al->addr,
+                                           machine->symbol_filter);
         }
 
         if (symbol_conf.sym_list &&
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 181389535c0c..c67ecc457d29 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,22 +8,25 @@
 #include "map.h"
 #include "build-id.h"
 
-/*
- * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
- */
-struct ip_event {
+struct mmap_event {
         struct perf_event_header header;
-        u64 ip;
         u32 pid, tid;
-        unsigned char __more_data[];
+        u64 start;
+        u64 len;
+        u64 pgoff;
+        char filename[PATH_MAX];
 };
 
-struct mmap_event {
+struct mmap2_event {
         struct perf_event_header header;
         u32 pid, tid;
         u64 start;
         u64 len;
         u64 pgoff;
+        u32 maj;
+        u32 min;
+        u64 ino;
+        u64 ino_generation;
         char filename[PATH_MAX];
 };
 
@@ -63,7 +66,8 @@ struct read_event {
         (PERF_SAMPLE_IP | PERF_SAMPLE_TID |             \
          PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
         PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |        \
-         PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+         PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |         \
+         PERF_SAMPLE_IDENTIFIER)
 
 struct sample_event {
         struct perf_event_header        header;
@@ -71,6 +75,7 @@ struct sample_event {
 };
 
 struct regs_dump {
+        u64 abi;
         u64 *regs;
 };
 
@@ -80,6 +85,23 @@ struct stack_dump {
         char *data;
 };
 
+struct sample_read_value {
+        u64 value;
+        u64 id;
+};
+
+struct sample_read {
+        u64 time_enabled;
+        u64 time_running;
+        union {
+                struct {
+                        u64 nr;
+                        struct sample_read_value *values;
+                } group;
+                struct sample_read_value one;
+        };
+};
+
 struct perf_sample {
         u64 ip;
         u32 pid, tid;
@@ -97,6 +119,7 @@ struct perf_sample {
         struct branch_stack *branch_stack;
         struct regs_dump  user_regs;
         struct stack_dump user_stack;
+        struct sample_read read;
 };
 
 #define PERF_MEM_DATA_SRC_NONE \
@@ -116,7 +139,7 @@ struct build_id_event {
 enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_USER_TYPE_START             = 64,
         PERF_RECORD_HEADER_ATTR                 = 64,
-        PERF_RECORD_HEADER_EVENT_TYPE           = 65,
+        PERF_RECORD_HEADER_EVENT_TYPE           = 65, /* depreceated */
         PERF_RECORD_HEADER_TRACING_DATA         = 66,
         PERF_RECORD_HEADER_BUILD_ID             = 67,
         PERF_RECORD_FINISHED_ROUND              = 68,
@@ -148,8 +171,8 @@ struct tracing_data_event {
 
 union perf_event {
         struct perf_event_header        header;
-        struct ip_event                 ip;
         struct mmap_event               mmap;
+        struct mmap2_event              mmap2;
         struct comm_event               comm;
         struct fork_event               fork;
         struct lost_event               lost;
@@ -199,6 +222,10 @@ int perf_event__process_mmap(struct perf_tool *tool,
                              union perf_event *event,
                              struct perf_sample *sample,
                              struct machine *machine);
+int perf_event__process_mmap2(struct perf_tool *tool,
+                             union perf_event *event,
+                             struct perf_sample *sample,
+                             struct machine *machine);
 int perf_event__process_fork(struct perf_tool *tool,
                              union perf_event *event,
                              struct perf_sample *sample,
@@ -216,17 +243,20 @@ struct addr_location;
 int perf_event__preprocess_sample(const union perf_event *self,
                                   struct machine *machine,
                                   struct addr_location *al,
-                                  struct perf_sample *sample,
-                                  symbol_filter_t filter);
+                                  struct perf_sample *sample);
 
 const char *perf_event__name(unsigned int id);
 
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+                                     u64 sample_regs_user, u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
+                                  u64 sample_regs_user, u64 read_format,
                                   const struct perf_sample *sample,
                                   bool swapped);
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8065ce8fa9a5..f9f77bee0b1b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -14,6 +14,7 @@
 #include "target.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "debug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -48,26 +49,29 @@ struct perf_evlist *perf_evlist__new(void)
         return evlist;
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-                        struct perf_record_opts *opts)
+/**
+ * perf_evlist__set_id_pos - set the positions of event ids.
+ * @evlist: selected event list
+ *
+ * Events with compatible sample types all have the same id_pos
+ * and is_pos.  For convenience, put a copy on evlist.
+ */
+void perf_evlist__set_id_pos(struct perf_evlist *evlist)
 {
-        struct perf_evsel *evsel;
-        /*
-         * Set the evsel leader links before we configure attributes,
-         * since some might depend on this info.
-         */
-        if (opts->group)
-                perf_evlist__set_leader(evlist);
+        struct perf_evsel *first = perf_evlist__first(evlist);
 
-        if (evlist->cpus->map[0] < 0)
-                opts->no_inherit = true;
+        evlist->id_pos = first->id_pos;
+        evlist->is_pos = first->is_pos;
+}
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
-                perf_evsel__config(evsel, opts);
+static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
 
-                if (evlist->nr_entries > 1)
-                        perf_evsel__set_sample_id(evsel);
-        }
+        list_for_each_entry(evsel, &evlist->entries, node)
+                perf_evsel__calc_id_pos(evsel);
+
+        perf_evlist__set_id_pos(evlist);
 }
 
 static void perf_evlist__purge(struct perf_evlist *evlist)
@@ -100,15 +104,20 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
         list_add_tail(&entry->node, &evlist->entries);
-        ++evlist->nr_entries;
+        if (!evlist->nr_entries++)
+                perf_evlist__set_id_pos(evlist);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
                                    struct list_head *list,
                                    int nr_entries)
 {
+        bool set_id_pos = !evlist->nr_entries;
+
         list_splice_tail(list, &evlist->entries);
         evlist->nr_entries += nr_entries;
+        if (set_id_pos)
+                perf_evlist__set_id_pos(evlist);
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -209,6 +218,21 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
         return NULL;
 }
 
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+                                     const char *name)
+{
+        struct perf_evsel *evsel;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
+                    (strcmp(evsel->name, name) == 0))
+                        return evsel;
+        }
+
+        return NULL;
+}
+
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
                            const char *sys, const char *name, void *handler)
 {
@@ -232,7 +256,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 list_for_each_entry(pos, &evlist->entries, node) {
-                        if (!perf_evsel__is_group_leader(pos))
+                        if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
                                 ioctl(FD(pos, cpu, thread),
@@ -250,7 +274,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 list_for_each_entry(pos, &evlist->entries, node) {
-                        if (!perf_evsel__is_group_leader(pos))
+                        if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
                                 ioctl(FD(pos, cpu, thread),
@@ -259,6 +283,44 @@ void perf_evlist__enable(struct perf_evlist *evlist)
         }
 }
 
+int perf_evlist__disable_event(struct perf_evlist *evlist,
+                               struct perf_evsel *evsel)
+{
+        int cpu, thread, err;
+
+        if (!evsel->fd)
+                return 0;
+
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                for (thread = 0; thread < evlist->threads->nr; thread++) {
+                        err = ioctl(FD(evsel, cpu, thread),
+                                    PERF_EVENT_IOC_DISABLE, 0);
+                        if (err)
+                                return err;
+                }
+        }
+        return 0;
+}
+
+int perf_evlist__enable_event(struct perf_evlist *evlist,
+                              struct perf_evsel *evsel)
+{
+        int cpu, thread, err;
+
+        if (!evsel->fd)
+                return -EINVAL;
+
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                for (thread = 0; thread < evlist->threads->nr; thread++) {
+                        err = ioctl(FD(evsel, cpu, thread),
+                                    PERF_EVENT_IOC_ENABLE, 0);
+                        if (err)
+                                return err;
+                }
+        }
+        return 0;
+}
+
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
         int nr_cpus = cpu_map__nr(evlist->cpus);
@@ -302,6 +364,24 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 {
         u64 read_data[4] = { 0, };
         int id_idx = 1; /* The first entry is the counter value */
+        u64 id;
+        int ret;
+
+        ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
+        if (!ret)
+                goto add;
+
+        if (errno != ENOTTY)
+                return -1;
+
+        /* Legacy way to get event id.. All hail to old kernels! */
+
+        /*
+         * This way does not work with group format read, so bail
+         * out in that case.
+         */
+        if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP)
+                return -1;
 
         if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
             read(fd, &read_data, sizeof(read_data)) == -1)
@@ -312,25 +392,39 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
         if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
                 ++id_idx;
 
-        perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
+        id = read_data[id_idx];
+
+ add:
+        perf_evlist__id_add(evlist, evsel, cpu, thread, id);
         return 0;
 }
 
-struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
 {
         struct hlist_head *head;
         struct perf_sample_id *sid;
         int hash;
 
-        if (evlist->nr_entries == 1)
-                return perf_evlist__first(evlist);
-
         hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
         head = &evlist->heads[hash];
 
         hlist_for_each_entry(sid, head, node)
                 if (sid->id == id)
-                        return sid->evsel;
+                        return sid;
+
+        return NULL;
+}
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+{
+        struct perf_sample_id *sid;
+
+        if (evlist->nr_entries == 1)
+                return perf_evlist__first(evlist);
+
+        sid = perf_evlist__id2sid(evlist, id);
+        if (sid)
+                return sid->evsel;
 
         if (!perf_evlist__sample_id_all(evlist))
                 return perf_evlist__first(evlist);
@@ -338,6 +432,60 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
         return NULL;
 }
 
+static int perf_evlist__event2id(struct perf_evlist *evlist,
+                                 union perf_event *event, u64 *id)
+{
+        const u64 *array = event->sample.array;
+        ssize_t n;
+
+        n = (event->header.size - sizeof(event->header)) >> 3;
+
+        if (event->header.type == PERF_RECORD_SAMPLE) {
+                if (evlist->id_pos >= n)
+                        return -1;
+                *id = array[evlist->id_pos];
+        } else {
+                if (evlist->is_pos > n)
+                        return -1;
+                n -= evlist->is_pos;
+                *id = array[n];
+        }
+        return 0;
+}
+
+static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+                                                   union perf_event *event)
+{
+        struct perf_evsel *first = perf_evlist__first(evlist);
+        struct hlist_head *head;
+        struct perf_sample_id *sid;
+        int hash;
+        u64 id;
+
+        if (evlist->nr_entries == 1)
+                return first;
+
+        if (!first->attr.sample_id_all &&
+            event->header.type != PERF_RECORD_SAMPLE)
+                return first;
+
+        if (perf_evlist__event2id(evlist, event, &id))
+                return NULL;
+
+        /* Synthesized events have an id of zero */
+        if (!id)
+                return first;
+
+        hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+        head = &evlist->heads[hash];
+
+        hlist_for_each_entry(sid, head, node) {
+                if (sid->id == id)
+                        return sid->evsel;
+        }
+        return NULL;
+}
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
         struct perf_mmap *md = &evlist->mmap[idx];
@@ -403,16 +551,20 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
         return event;
 }
 
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+{
+        if (evlist->mmap[idx].base != NULL) {
+                munmap(evlist->mmap[idx].base, evlist->mmap_len);
+                evlist->mmap[idx].base = NULL;
+        }
+}
+
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
         int i;
 
-        for (i = 0; i < evlist->nr_mmaps; i++) {
-                if (evlist->mmap[i].base != NULL) {
-                        munmap(evlist->mmap[i].base, evlist->mmap_len);
-                        evlist->mmap[i].base = NULL;
-                }
-        }
+        for (i = 0; i < evlist->nr_mmaps; i++)
+                __perf_evlist__munmap(evlist, i);
 
         free(evlist->mmap);
         evlist->mmap = NULL;
@@ -421,7 +573,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
         evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
-        if (cpu_map__all(evlist->cpus))
+        if (cpu_map__empty(evlist->cpus))
                 evlist->nr_mmaps = thread_map__nr(evlist->threads);
         evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
         return evlist->mmap != NULL ? 0 : -ENOMEM;
@@ -450,6 +602,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
         int nr_cpus = cpu_map__nr(evlist->cpus);
         int nr_threads = thread_map__nr(evlist->threads);
 
+        pr_debug2("perf event ring buffer mmapped per cpu\n");
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 int output = -1;
 
@@ -477,12 +630,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
         return 0;
 
 out_unmap:
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                if (evlist->mmap[cpu].base != NULL) {
-                        munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-                        evlist->mmap[cpu].base = NULL;
-                }
-        }
+        for (cpu = 0; cpu < nr_cpus; cpu++)
+                __perf_evlist__munmap(evlist, cpu);
         return -1;
 }
 
@@ -492,6 +641,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
         int thread;
         int nr_threads = thread_map__nr(evlist->threads);
 
+        pr_debug2("perf event ring buffer mmapped per thread\n");
         for (thread = 0; thread < nr_threads; thread++) {
                 int output = -1;
 
@@ -517,12 +667,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
         return 0;
 
 out_unmap:
-        for (thread = 0; thread < nr_threads; thread++) {
-                if (evlist->mmap[thread].base != NULL) {
-                        munmap(evlist->mmap[thread].base, evlist->mmap_len);
-                        evlist->mmap[thread].base = NULL;
-                }
-        }
+        for (thread = 0; thread < nr_threads; thread++)
+                __perf_evlist__munmap(evlist, thread);
         return -1;
 }
 
@@ -573,7 +719,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
                         return -ENOMEM;
         }
 
-        if (cpu_map__all(cpus))
+        if (cpu_map__empty(cpus))
                 return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
         return perf_evlist__mmap_per_cpu(evlist, prot, mask);
@@ -650,20 +796,66 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 {
+        struct perf_evsel *pos;
+
+        if (evlist->nr_entries == 1)
+                return true;
+
+        if (evlist->id_pos < 0 || evlist->is_pos < 0)
+                return false;
+
+        list_for_each_entry(pos, &evlist->entries, node) {
+                if (pos->id_pos != evlist->id_pos ||
+                    pos->is_pos != evlist->is_pos)
+                        return false;
+        }
+
+        return true;
+}
+
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+
+        if (evlist->combined_sample_type)
+                return evlist->combined_sample_type;
+
+        list_for_each_entry(evsel, &evlist->entries, node)
+                evlist->combined_sample_type |= evsel->attr.sample_type;
+
+        return evlist->combined_sample_type;
+}
+
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+        evlist->combined_sample_type = 0;
+        return __perf_evlist__combined_sample_type(evlist);
+}
+
+bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
+{
         struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+        u64 read_format = first->attr.read_format;
+        u64 sample_type = first->attr.sample_type;
 
         list_for_each_entry_continue(pos, &evlist->entries, node) {
-                if (first->attr.sample_type != pos->attr.sample_type)
+                if (read_format != pos->attr.read_format)
                         return false;
         }
 
+        /* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */
+        if ((sample_type & PERF_SAMPLE_READ) &&
+            !(read_format & PERF_FORMAT_ID)) {
+                return false;
+        }
+
         return true;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+u64 perf_evlist__read_format(struct perf_evlist *evlist)
 {
         struct perf_evsel *first = perf_evlist__first(evlist);
-        return first->attr.sample_type;
+        return first->attr.read_format;
 }
 
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
@@ -692,6 +884,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
 
         if (sample_type & PERF_SAMPLE_CPU)
                 size += sizeof(data->cpu) * 2;
+
+        if (sample_type & PERF_SAMPLE_IDENTIFIER)
+                size += sizeof(data->id);
 out:
         return size;
 }
@@ -735,6 +930,8 @@ int perf_evlist__open(struct perf_evlist *evlist)
         struct perf_evsel *evsel;
         int err;
 
+        perf_evlist__update_id_pos(evlist);
+
         list_for_each_entry(evsel, &evlist->entries, node) {
                 err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
                 if (err < 0)
@@ -783,13 +980,6 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                 fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
 
                 /*
-                 * Do a dummy execvp to get the PLT entry resolved,
-                 * so we avoid the resolver overhead on the real
-                 * execvp call.
-                 */
-                execvp("", (char **)argv);
-
-                /*
                  * Tell the parent we're ready to go
                  */
                 close(child_ready_pipe[1]);
@@ -838,7 +1028,7 @@ out_close_ready_pipe:
 int perf_evlist__start_workload(struct perf_evlist *evlist)
 {
         if (evlist->workload.cork_fd > 0) {
-                char bf;
+                char bf = 0;
                 int ret;
                 /*
                  * Remove the cork, let it rip!
@@ -857,7 +1047,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
                               struct perf_sample *sample)
 {
-        struct perf_evsel *evsel = perf_evlist__first(evlist);
+        struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+        if (!evsel)
+                return -EFAULT;
         return perf_evsel__parse_sample(evsel, event, sample);
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0583d36252be..880d7139d2fb 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -32,6 +32,9 @@ struct perf_evlist {
         int              nr_fds;
         int              nr_mmaps;
         int              mmap_len;
+        int              id_pos;
+        int              is_pos;
+        u64              combined_sample_type;
         struct {
                 int     cork_fd;
                 pid_t   pid;
@@ -71,6 +74,10 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter);
 struct perf_evsel *
 perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id);
 
+struct perf_evsel *
+perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
+                                     const char *name);
+
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
                          int cpu, int thread, u64 id);
 
@@ -78,11 +85,15 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
+struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+void perf_evlist__set_id_pos(struct perf_evlist *evlist);
+bool perf_can_sample_identifier(void);
 void perf_evlist__config(struct perf_evlist *evlist,
                          struct perf_record_opts *opts);
 
@@ -99,6 +110,11 @@ void perf_evlist__munmap(struct perf_evlist *evlist);
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 
+int perf_evlist__disable_event(struct perf_evlist *evlist,
+                               struct perf_evsel *evsel);
+int perf_evlist__enable_event(struct perf_evlist *evlist,
+                              struct perf_evsel *evsel);
+
 void perf_evlist__set_selected(struct perf_evlist *evlist,
                                struct perf_evsel *evsel);
 
@@ -118,7 +134,9 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist);
 void __perf_evlist__set_leader(struct list_head *list);
 void perf_evlist__set_leader(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__read_format(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 
@@ -127,6 +145,7 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *even
 
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
+bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
                                    struct list_head *list,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c9c7494506a1..0ce9febf1ba0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -9,27 +9,30 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include "asm/bug.h"
 #include <lk/debugfs.h>
-#include "event-parse.h"
+#include <traceevent/event-parse.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
+#include <sys/resource.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
-#include <linux/hw_breakpoint.h>
-#include <linux/perf_event.h>
 #include "perf_regs.h"
+#include "debug.h"
 
 static struct {
         bool sample_id_all;
         bool exclude_guest;
+        bool mmap2;
 } perf_missing_features;
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
-static int __perf_evsel__sample_size(u64 sample_type)
+int __perf_evsel__sample_size(u64 sample_type)
 {
         u64 mask = sample_type & PERF_SAMPLE_MASK;
         int size = 0;
@@ -45,6 +48,72 @@ static int __perf_evsel__sample_size(u64 sample_type)
         return size;
 }
 
+/**
+ * __perf_evsel__calc_id_pos - calculate id_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position of the event id (PERF_SAMPLE_ID or
+ * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
+ * sample_event.
+ */
+static int __perf_evsel__calc_id_pos(u64 sample_type)
+{
+        int idx = 0;
+
+        if (sample_type & PERF_SAMPLE_IDENTIFIER)
+                return 0;
+
+        if (!(sample_type & PERF_SAMPLE_ID))
+                return -1;
+
+        if (sample_type & PERF_SAMPLE_IP)
+                idx += 1;
+
+        if (sample_type & PERF_SAMPLE_TID)
+                idx += 1;
+
+        if (sample_type & PERF_SAMPLE_TIME)
+                idx += 1;
+
+        if (sample_type & PERF_SAMPLE_ADDR)
+                idx += 1;
+
+        return idx;
+}
+
+/**
+ * __perf_evsel__calc_is_pos - calculate is_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position (counting backwards) of the event id
+ * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
+ * sample_id_all is used there is an id sample appended to non-sample events.
+ */
+static int __perf_evsel__calc_is_pos(u64 sample_type)
+{
+        int idx = 1;
+
+        if (sample_type & PERF_SAMPLE_IDENTIFIER)
+                return 1;
+
+        if (!(sample_type & PERF_SAMPLE_ID))
+                return -1;
+
+        if (sample_type & PERF_SAMPLE_CPU)
+                idx += 1;
+
+        if (sample_type & PERF_SAMPLE_STREAM_ID)
+                idx += 1;
+
+        return idx;
+}
+
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
+{
+        evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
+        evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
+}
+
 void hists__init(struct hists *hists)
 {
         memset(hists, 0, sizeof(*hists));
@@ -61,6 +130,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
         if (!(evsel->attr.sample_type & bit)) {
                 evsel->attr.sample_type |= bit;
                 evsel->sample_size += sizeof(u64);
+                perf_evsel__calc_id_pos(evsel);
         }
 }
 
@@ -70,12 +140,19 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
         if (evsel->attr.sample_type & bit) {
                 evsel->attr.sample_type &= ~bit;
                 evsel->sample_size -= sizeof(u64);
+                perf_evsel__calc_id_pos(evsel);
         }
 }
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel)
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+                               bool can_sample_identifier)
 {
-        perf_evsel__set_sample_bit(evsel, ID);
+        if (can_sample_identifier) {
+                perf_evsel__reset_sample_bit(evsel, ID);
+                perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+        } else {
+                perf_evsel__set_sample_bit(evsel, ID);
+        }
         evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
@@ -88,6 +165,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
         INIT_LIST_HEAD(&evsel->node);
         hists__init(&evsel->hists);
         evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
+        perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
@@ -246,6 +324,7 @@ const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
         "major-faults",
         "alignment-faults",
         "emulation-faults",
+        "dummy",
 };
 
 static const char *__perf_evsel__sw_name(u64 config)
@@ -490,6 +569,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 void perf_evsel__config(struct perf_evsel *evsel,
                         struct perf_record_opts *opts)
 {
+        struct perf_evsel *leader = evsel->leader;
         struct perf_event_attr *attr = &evsel->attr;
         int track = !evsel->idx; /* only the first counter needs these */
 
@@ -499,6 +579,25 @@ void perf_evsel__config(struct perf_evsel *evsel,
         perf_evsel__set_sample_bit(evsel, IP);
         perf_evsel__set_sample_bit(evsel, TID);
 
+        if (evsel->sample_read) {
+                perf_evsel__set_sample_bit(evsel, READ);
+
+                /*
+                 * We need ID even in case of single event, because
+                 * PERF_SAMPLE_READ process ID specific data.
+                 */
+                perf_evsel__set_sample_id(evsel, false);
+
+                /*
+                 * Apply group format only if we belong to group
+                 * with more than one members.
+                 */
+                if (leader->nr_members > 1) {
+                        attr->read_format |= PERF_FORMAT_GROUP;
+                        attr->inherit = 0;
+                }
+        }
+
         /*
          * We default some events to a 1 default interval. But keep
          * it a weak assumption overridable by the user.
@@ -514,6 +613,15 @@ void perf_evsel__config(struct perf_evsel *evsel,
                 }
         }
 
+        /*
+         * Disable sampling for all group members other
+         * than leader in case leader 'leads' the sampling.
+         */
+        if ((leader != evsel) && leader->sample_read) {
+                attr->sample_freq   = 0;
+                attr->sample_period = 0;
+        }
+
         if (opts->no_samples)
                 attr->sample_freq = 0;
 
@@ -569,8 +677,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
         if (opts->sample_weight)
                 attr->sample_type       |= PERF_SAMPLE_WEIGHT;
 
-        attr->mmap = track;
-        attr->comm = track;
+        attr->mmap  = track;
+        attr->mmap2 = track && !perf_missing_features.mmap2;
+        attr->comm  = track;
 
         /*
          * XXX see the function comment above
@@ -605,15 +714,15 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
         return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
-int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
-                           const char *filter)
+static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads,
+                          int ioc,  void *arg)
 {
         int cpu, thread;
 
         for (cpu = 0; cpu < ncpus; cpu++) {
                 for (thread = 0; thread < nthreads; thread++) {
                         int fd = FD(evsel, cpu, thread),
-                            err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+                            err = ioctl(fd, ioc, arg);
 
                         if (err)
                                 return err;
@@ -623,6 +732,21 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
         return 0;
 }
 
+int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
+                           const char *filter)
+{
+        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+                                     PERF_EVENT_IOC_SET_FILTER,
+                                     (void *)filter);
+}
+
+int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+                                     PERF_EVENT_IOC_ENABLE,
+                                     0);
+}
+
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
         evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
@@ -817,12 +941,72 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
         return fd;
 }
 
+#define __PRINT_ATTR(fmt, cast, field)  \
+        fprintf(fp, "  %-19s "fmt"\n", #field, cast attr->field)
+
+#define PRINT_ATTR_U32(field)  __PRINT_ATTR("%u" , , field)
+#define PRINT_ATTR_X32(field)  __PRINT_ATTR("%#x", , field)
+#define PRINT_ATTR_U64(field)  __PRINT_ATTR("%" PRIu64, (uint64_t), field)
+#define PRINT_ATTR_X64(field)  __PRINT_ATTR("%#"PRIx64, (uint64_t), field)
+
+#define PRINT_ATTR2N(name1, field1, name2, field2)      \
+        fprintf(fp, "  %-19s %u    %-19s %u\n",         \
+        name1, attr->field1, name2, attr->field2)
+
+#define PRINT_ATTR2(field1, field2) \
+        PRINT_ATTR2N(#field1, field1, #field2, field2)
+
+static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
+{
+        size_t ret = 0;
+
+        ret += fprintf(fp, "%.60s\n", graph_dotted_line);
+        ret += fprintf(fp, "perf_event_attr:\n");
+
+        ret += PRINT_ATTR_U32(type);
+        ret += PRINT_ATTR_U32(size);
+        ret += PRINT_ATTR_X64(config);
+        ret += PRINT_ATTR_U64(sample_period);
+        ret += PRINT_ATTR_U64(sample_freq);
+        ret += PRINT_ATTR_X64(sample_type);
+        ret += PRINT_ATTR_X64(read_format);
+
+        ret += PRINT_ATTR2(disabled, inherit);
+        ret += PRINT_ATTR2(pinned, exclusive);
+        ret += PRINT_ATTR2(exclude_user, exclude_kernel);
+        ret += PRINT_ATTR2(exclude_hv, exclude_idle);
+        ret += PRINT_ATTR2(mmap, comm);
+        ret += PRINT_ATTR2(freq, inherit_stat);
+        ret += PRINT_ATTR2(enable_on_exec, task);
+        ret += PRINT_ATTR2(watermark, precise_ip);
+        ret += PRINT_ATTR2(mmap_data, sample_id_all);
+        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(wakeup_events);
+        ret += PRINT_ATTR_U32(wakeup_watermark);
+        ret += PRINT_ATTR_X32(bp_type);
+        ret += PRINT_ATTR_X64(bp_addr);
+        ret += PRINT_ATTR_X64(config1);
+        ret += PRINT_ATTR_U64(bp_len);
+        ret += PRINT_ATTR_X64(config2);
+        ret += PRINT_ATTR_X64(branch_sample_type);
+        ret += PRINT_ATTR_X64(sample_regs_user);
+        ret += PRINT_ATTR_U32(sample_stack_user);
+
+        ret += fprintf(fp, "%.60s\n", graph_dotted_line);
+
+        return ret;
+}
+
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
                               struct thread_map *threads)
 {
         int cpu, thread;
         unsigned long flags = 0;
         int pid = -1, err;
+        enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
         if (evsel->fd == NULL &&
             perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
@@ -834,12 +1018,17 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
         }
 
 fallback_missing_features:
+        if (perf_missing_features.mmap2)
+                evsel->attr.mmap2 = 0;
         if (perf_missing_features.exclude_guest)
                 evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
 
+        if (verbose >= 2)
+                perf_event_attr__fprintf(&evsel->attr, stderr);
+
         for (cpu = 0; cpu < cpus->nr; cpu++) {
 
                 for (thread = 0; thread < threads->nr; thread++) {
@@ -849,6 +1038,9 @@ retry_sample_id:
                                 pid = threads->map[thread];
 
                         group_fd = get_group_fd(evsel, cpu, thread);
+retry_open:
+                        pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+                                  pid, cpus->map[cpu], group_fd, flags);
 
                         FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
                                                                      pid,
@@ -858,17 +1050,45 @@ retry_sample_id:
                                 err = -errno;
                                 goto try_fallback;
                         }
+                        set_rlimit = NO_CHANGE;
                 }
         }
 
         return 0;
 
 try_fallback:
+        /*
+         * perf stat needs between 5 and 22 fds per CPU. When we run out
+         * of them try to increase the limits.
+         */
+        if (err == -EMFILE && set_rlimit < INCREASED_MAX) {
+                struct rlimit l;
+                int old_errno = errno;
+
+                if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+                        if (set_rlimit == NO_CHANGE)
+                                l.rlim_cur = l.rlim_max;
+                        else {
+                                l.rlim_cur = l.rlim_max + 1000;
+                                l.rlim_max = l.rlim_cur;
+                        }
+                        if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
+                                set_rlimit++;
+                                errno = old_errno;
+                                goto retry_open;
+                        }
+                }
+                errno = old_errno;
+        }
+
         if (err != -EINVAL || cpu > 0 || thread > 0)
                 goto out_close;
 
-        if (!perf_missing_features.exclude_guest &&
-            (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+        if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+                perf_missing_features.mmap2 = true;
+                goto fallback_missing_features;
+        } else if (!perf_missing_features.exclude_guest &&
+                   (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
                 perf_missing_features.exclude_guest = true;
                 goto fallback_missing_features;
         } else if (!perf_missing_features.sample_id_all) {
@@ -951,6 +1171,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
         array += ((event->header.size -
                    sizeof(event->header)) / sizeof(u64)) - 1;
 
+        if (type & PERF_SAMPLE_IDENTIFIER) {
+                sample->id = *array;
+                array--;
+        }
+
         if (type & PERF_SAMPLE_CPU) {
                 u.val64 = *array;
                 if (swapped) {
@@ -994,24 +1219,30 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
         return 0;
 }
 
-static bool sample_overlap(const union perf_event *event,
-                           const void *offset, u64 size)
+static inline bool overflow(const void *endp, u16 max_size, const void *offset,
+                            u64 size)
 {
-        const void *base = event;
+        return size > max_size || offset + size > endp;
+}
 
-        if (offset + size > base + event->header.size)
-                return true;
+#define OVERFLOW_CHECK(offset, size, max_size)                          \
+        do {                                                            \
+                if (overflow(endp, (max_size), (offset), (size)))       \
+                        return -EFAULT;                                 \
+        } while (0)
 
-        return false;
-}
+#define OVERFLOW_CHECK_u64(offset) \
+        OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
 
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                              struct perf_sample *data)
 {
         u64 type = evsel->attr.sample_type;
-        u64 regs_user = evsel->attr.sample_regs_user;
         bool swapped = evsel->needs_swap;
         const u64 *array;
+        u16 max_size = event->header.size;
+        const void *endp = (void *)event + max_size;
+        u64 sz;
 
         /*
          * used for cross-endian analysis. See git commit 65014ab3
@@ -1033,11 +1264,22 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
         array = event->sample.array;
 
+        /*
+         * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
+         * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
+         * check the format does not go past the end of the event.
+         */
         if (evsel->sample_size + sizeof(event->header) > event->header.size)
                 return -EFAULT;
 
+        data->id = -1ULL;
+        if (type & PERF_SAMPLE_IDENTIFIER) {
+                data->id = *array;
+                array++;
+        }
+
         if (type & PERF_SAMPLE_IP) {
-                data->ip = event->ip.ip;
+                data->ip = *array;
                 array++;
         }
 
@@ -1066,7 +1308,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
         }
 
-        data->id = -1ULL;
         if (type & PERF_SAMPLE_ID) {
                 data->id = *array;
                 array++;
@@ -1096,25 +1337,62 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         }
 
         if (type & PERF_SAMPLE_READ) {
-                fprintf(stderr, "PERF_SAMPLE_READ is unsupported for now\n");
-                return -1;
+                u64 read_format = evsel->attr.read_format;
+
+                OVERFLOW_CHECK_u64(array);
+                if (read_format & PERF_FORMAT_GROUP)
+                        data->read.group.nr = *array;
+                else
+                        data->read.one.value = *array;
+
+                array++;
+
+                if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+                        OVERFLOW_CHECK_u64(array);
+                        data->read.time_enabled = *array;
+                        array++;
+                }
+
+                if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+                        OVERFLOW_CHECK_u64(array);
+                        data->read.time_running = *array;
+                        array++;
+                }
+
+                /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+                if (read_format & PERF_FORMAT_GROUP) {
+                        const u64 max_group_nr = UINT64_MAX /
+                                        sizeof(struct sample_read_value);
+
+                        if (data->read.group.nr > max_group_nr)
+                                return -EFAULT;
+                        sz = data->read.group.nr *
+                             sizeof(struct sample_read_value);
+                        OVERFLOW_CHECK(array, sz, max_size);
+                        data->read.group.values =
+                                        (struct sample_read_value *)array;
+                        array = (void *)array + sz;
+                } else {
+                        OVERFLOW_CHECK_u64(array);
+                        data->read.one.id = *array;
+                        array++;
+                }
         }
 
         if (type & PERF_SAMPLE_CALLCHAIN) {
-                if (sample_overlap(event, array, sizeof(data->callchain->nr)))
-                        return -EFAULT;
-
-                data->callchain = (struct ip_callchain *)array;
+                const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
-                if (sample_overlap(event, array, data->callchain->nr))
+                OVERFLOW_CHECK_u64(array);
+                data->callchain = (struct ip_callchain *)array++;
+                if (data->callchain->nr > max_callchain_nr)
                         return -EFAULT;
-
-                array += 1 + data->callchain->nr;
+                sz = data->callchain->nr * sizeof(u64);
+                OVERFLOW_CHECK(array, sz, max_size);
+                array = (void *)array + sz;
         }
 
         if (type & PERF_SAMPLE_RAW) {
-                const u64 *pdata;
-
+                OVERFLOW_CHECK_u64(array);
                 u.val64 = *array;
                 if (WARN_ONCE(swapped,
                               "Endianness of raw data not corrected!\n")) {
@@ -1123,65 +1401,71 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                         u.val32[0] = bswap_32(u.val32[0]);
                         u.val32[1] = bswap_32(u.val32[1]);
                 }
-
-                if (sample_overlap(event, array, sizeof(u32)))
-                        return -EFAULT;
-
                 data->raw_size = u.val32[0];
-                pdata = (void *) array + sizeof(u32);
+                array = (void *)array + sizeof(u32);
 
-                if (sample_overlap(event, pdata, data->raw_size))
-                        return -EFAULT;
-
-                data->raw_data = (void *) pdata;
-
-                array = (void *)array + data->raw_size + sizeof(u32);
+                OVERFLOW_CHECK(array, data->raw_size, max_size);
+                data->raw_data = (void *)array;
+                array = (void *)array + data->raw_size;
         }
 
         if (type & PERF_SAMPLE_BRANCH_STACK) {
-                u64 sz;
+                const u64 max_branch_nr = UINT64_MAX /
+                                          sizeof(struct branch_entry);
 
-                data->branch_stack = (struct branch_stack *)array;
-                array++; /* nr */
+                OVERFLOW_CHECK_u64(array);
+                data->branch_stack = (struct branch_stack *)array++;
 
+                if (data->branch_stack->nr > max_branch_nr)
+                        return -EFAULT;
                 sz = data->branch_stack->nr * sizeof(struct branch_entry);
-                sz /= sizeof(u64);
-                array += sz;
+                OVERFLOW_CHECK(array, sz, max_size);
+                array = (void *)array + sz;
         }
 
         if (type & PERF_SAMPLE_REGS_USER) {
-                /* First u64 tells us if we have any regs in sample. */
-                u64 avail = *array++;
+                OVERFLOW_CHECK_u64(array);
+                data->user_regs.abi = *array;
+                array++;
+
+                if (data->user_regs.abi) {
+                        u64 regs_user = evsel->attr.sample_regs_user;
 
-                if (avail) {
+                        sz = hweight_long(regs_user) * sizeof(u64);
+                        OVERFLOW_CHECK(array, sz, max_size);
                         data->user_regs.regs = (u64 *)array;
-                        array += hweight_long(regs_user);
+                        array = (void *)array + sz;
                 }
         }
 
         if (type & PERF_SAMPLE_STACK_USER) {
-                u64 size = *array++;
+                OVERFLOW_CHECK_u64(array);
+                sz = *array++;
 
                 data->user_stack.offset = ((char *)(array - 1)
                                           - (char *) event);
 
-                if (!size) {
+                if (!sz) {
                         data->user_stack.size = 0;
                 } else {
+                        OVERFLOW_CHECK(array, sz, max_size);
                         data->user_stack.data = (char *)array;
-                        array += size / sizeof(*array);
+                        array = (void *)array + sz;
+                        OVERFLOW_CHECK_u64(array);
                         data->user_stack.size = *array++;
                 }
         }
 
         data->weight = 0;
         if (type & PERF_SAMPLE_WEIGHT) {
+                OVERFLOW_CHECK_u64(array);
                 data->weight = *array;
                 array++;
         }
 
         data->data_src = PERF_MEM_DATA_SRC_NONE;
         if (type & PERF_SAMPLE_DATA_SRC) {
+                OVERFLOW_CHECK_u64(array);
                 data->data_src = *array;
                 array++;
         }
@@ -1189,12 +1473,105 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
         return 0;
 }
 
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+                                     u64 sample_regs_user, u64 read_format)
+{
+        size_t sz, result = sizeof(struct sample_event);
+
+        if (type & PERF_SAMPLE_IDENTIFIER)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_IP)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_TID)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_TIME)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_ADDR)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_ID)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_STREAM_ID)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_CPU)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_PERIOD)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_READ) {
+                result += sizeof(u64);
+                if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                        result += sizeof(u64);
+                if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                        result += sizeof(u64);
+                /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+                if (read_format & PERF_FORMAT_GROUP) {
+                        sz = sample->read.group.nr *
+                             sizeof(struct sample_read_value);
+                        result += sz;
+                } else {
+                        result += sizeof(u64);
+                }
+        }
+
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                sz = (sample->callchain->nr + 1) * sizeof(u64);
+                result += sz;
+        }
+
+        if (type & PERF_SAMPLE_RAW) {
+                result += sizeof(u32);
+                result += sample->raw_size;
+        }
+
+        if (type & PERF_SAMPLE_BRANCH_STACK) {
+                sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+                sz += sizeof(u64);
+                result += sz;
+        }
+
+        if (type & PERF_SAMPLE_REGS_USER) {
+                if (sample->user_regs.abi) {
+                        result += sizeof(u64);
+                        sz = hweight_long(sample_regs_user) * sizeof(u64);
+                        result += sz;
+                } else {
+                        result += sizeof(u64);
+                }
+        }
+
+        if (type & PERF_SAMPLE_STACK_USER) {
+                sz = sample->user_stack.size;
+                result += sizeof(u64);
+                if (sz) {
+                        result += sz;
+                        result += sizeof(u64);
+                }
+        }
+
+        if (type & PERF_SAMPLE_WEIGHT)
+                result += sizeof(u64);
+
+        if (type & PERF_SAMPLE_DATA_SRC)
+                result += sizeof(u64);
+
+        return result;
+}
+
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
+                                  u64 sample_regs_user, u64 read_format,
                                   const struct perf_sample *sample,
                                   bool swapped)
 {
         u64 *array;
-
+        size_t sz;
         /*
          * used for cross-endian analysis. See git commit 65014ab3
          * for why this goofiness is needed.
@@ -1203,8 +1580,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
         array = event->sample.array;
 
+        if (type & PERF_SAMPLE_IDENTIFIER) {
+                *array = sample->id;
+                array++;
+        }
+
         if (type & PERF_SAMPLE_IP) {
-                event->ip.ip = sample->ip;
+                *array = sample->ip;
                 array++;
         }
 
@@ -1262,6 +1644,97 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 array++;
         }
 
+        if (type & PERF_SAMPLE_READ) {
+                if (read_format & PERF_FORMAT_GROUP)
+                        *array = sample->read.group.nr;
+                else
+                        *array = sample->read.one.value;
+                array++;
+
+                if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+                        *array = sample->read.time_enabled;
+                        array++;
+                }
+
+                if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+                        *array = sample->read.time_running;
+                        array++;
+                }
+
+                /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
+                if (read_format & PERF_FORMAT_GROUP) {
+                        sz = sample->read.group.nr *
+                             sizeof(struct sample_read_value);
+                        memcpy(array, sample->read.group.values, sz);
+                        array = (void *)array + sz;
+                } else {
+                        *array = sample->read.one.id;
+                        array++;
+                }
+        }
+
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                sz = (sample->callchain->nr + 1) * sizeof(u64);
+                memcpy(array, sample->callchain, sz);
+                array = (void *)array + sz;
+        }
+
+        if (type & PERF_SAMPLE_RAW) {
+                u.val32[0] = sample->raw_size;
+                if (WARN_ONCE(swapped,
+                              "Endianness of raw data not corrected!\n")) {
+                        /*
+                         * Inverse of what is done in perf_evsel__parse_sample
+                         */
+                        u.val32[0] = bswap_32(u.val32[0]);
+                        u.val32[1] = bswap_32(u.val32[1]);
+                        u.val64 = bswap_64(u.val64);
+                }
+                *array = u.val64;
+                array = (void *)array + sizeof(u32);
+
+                memcpy(array, sample->raw_data, sample->raw_size);
+                array = (void *)array + sample->raw_size;
+        }
+
+        if (type & PERF_SAMPLE_BRANCH_STACK) {
+                sz = sample->branch_stack->nr * sizeof(struct branch_entry);
+                sz += sizeof(u64);
+                memcpy(array, sample->branch_stack, sz);
+                array = (void *)array + sz;
+        }
+
+        if (type & PERF_SAMPLE_REGS_USER) {
+                if (sample->user_regs.abi) {
+                        *array++ = sample->user_regs.abi;
+                        sz = hweight_long(sample_regs_user) * sizeof(u64);
+                        memcpy(array, sample->user_regs.regs, sz);
+                        array = (void *)array + sz;
+                } else {
+                        *array++ = 0;
+                }
+        }
+
+        if (type & PERF_SAMPLE_STACK_USER) {
+                sz = sample->user_stack.size;
+                *array++ = sz;
+                if (sz) {
+                        memcpy(array, sample->user_stack.data, sz);
+                        array = (void *)array + sz;
+                        *array++ = sz;
+                }
+        }
+
+        if (type & PERF_SAMPLE_WEIGHT) {
+                *array = sample->weight;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_DATA_SRC) {
+                *array = sample->data_src;
+                array++;
+        }
+
         return 0;
 }
 
@@ -1391,6 +1864,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
                 bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+                bit_name(IDENTIFIER),
                 { .name = NULL, }
         };
 #undef bit_name
@@ -1458,6 +1932,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
                 if_print(exclude_hv);
                 if_print(exclude_idle);
                 if_print(mmap);
+                if_print(mmap2);
                 if_print(comm);
                 if_print(freq);
                 if_print(inherit_stat);
@@ -1482,7 +1957,7 @@ out:
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
                           char *msg, size_t msgsize)
 {
-        if ((err == ENOENT || err == ENXIO) &&
+        if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
             evsel->attr.type   == PERF_TYPE_HARDWARE &&
             evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
                 /*
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3f156ccc1acb..4a7bdc713bab 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -38,6 +38,9 @@ struct perf_sample_id {
         struct hlist_node       node;
         u64                     id;
         struct perf_evsel       *evsel;
+
+        /* Holds total ID period value for PERF_SAMPLE_READ processing. */
+        u64                     period;
 };
 
 /** struct perf_evsel - event selector
@@ -45,6 +48,12 @@ struct perf_sample_id {
  * @name - Can be set to retain the original event name passed by the user,
  *         so that when showing results in tools such as 'perf stat', we
  *         show the name used, not some alias.
+ * @id_pos: the position of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of
+ *          struct sample_event
+ * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
+ *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
+ *          is used there is an id sample appended to non-sample events
  */
 struct perf_evsel {
         struct list_head        node;
@@ -71,11 +80,14 @@ struct perf_evsel {
         } handler;
         struct cpu_map          *cpus;
         unsigned int            sample_size;
+        int                     id_pos;
+        int                     is_pos;
         bool                    supported;
         bool                    needs_swap;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
+        int                     sample_read;
         struct perf_evsel       *leader;
         char                    *group_name;
 };
@@ -100,6 +112,9 @@ void perf_evsel__delete(struct perf_evsel *evsel);
 void perf_evsel__config(struct perf_evsel *evsel,
                         struct perf_record_opts *opts);
 
+int __perf_evsel__sample_size(u64 sample_type);
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
 #define PERF_EVSEL__MAX_ALIASES 8
@@ -138,10 +153,12 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 #define perf_evsel__reset_sample_bit(evsel, bit) \
         __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+                               bool use_sample_identifier);
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
                            const char *filter);
+int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
                              struct cpu_map *cpus);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a4dafbee2511..ce69901176d8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -25,41 +25,9 @@
 
 static bool no_buildid_cache = false;
 
-static int trace_event_count;
-static struct perf_trace_event_type *trace_events;
-
 static u32 header_argc;
 static const char **header_argv;
 
-int perf_header__push_event(u64 id, const char *name)
-{
-        struct perf_trace_event_type *nevents;
-
-        if (strlen(name) > MAX_EVENT_NAME)
-                pr_warning("Event %s will be truncated\n", name);
-
-        nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events));
-        if (nevents == NULL)
-                return -ENOMEM;
-        trace_events = nevents;
-
-        memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type));
-        trace_events[trace_event_count].event_id = id;
-        strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1);
-        trace_event_count++;
-        return 0;
-}
-
-char *perf_header__find_event(u64 id)
-{
-        int i;
-        for (i = 0 ; i < trace_event_count; i++) {
-                if (trace_events[i].event_id == id)
-                        return trace_events[i].name;
-        }
-        return NULL;
-}
-
 /*
  * magic2 = "PERFILE2"
  * must be a numerical value to let the endianness
@@ -231,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id,
         return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
-                                u16 misc, int fd)
+static int __dsos__write_buildid_table(struct list_head *head,
+                                       struct machine *machine,
+                                       pid_t pid, u16 misc, int fd)
 {
+        char nm[PATH_MAX];
         struct dso *pos;
 
         dsos__for_each_with_build_id(pos, head) {
@@ -247,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
                 if (is_vdso_map(pos->short_name)) {
                         name = (char *) VDSO__MAP_NAME;
                         name_len = sizeof(VDSO__MAP_NAME) + 1;
+                } else if (dso__is_kcore(pos)) {
+                        machine__mmap_name(machine, nm, sizeof(nm));
+                        name = nm;
+                        name_len = strlen(nm) + 1;
                 } else {
                         name = pos->long_name;
                         name_len = pos->long_name_len + 1;
@@ -272,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
                 umisc = PERF_RECORD_MISC_GUEST_USER;
         }
 
-        err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
-                                          kmisc, fd);
+        err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+                                          machine->pid, kmisc, fd);
         if (err == 0)
-                err = __dsos__write_buildid_table(&machine->user_dsos,
+                err = __dsos__write_buildid_table(&machine->user_dsos, machine,
                                                   machine->pid, umisc, fd);
         return err;
 }
@@ -407,23 +381,31 @@ out_free:
         return err;
 }
 
-static int dso__cache_build_id(struct dso *dso, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+                               const char *debugdir)
 {
         bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
         bool is_vdso = is_vdso_map(dso->short_name);
+        char *name = dso->long_name;
+        char nm[PATH_MAX];
 
-        return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
-                                     dso->long_name, debugdir,
-                                     is_kallsyms, is_vdso);
+        if (dso__is_kcore(dso)) {
+                is_kallsyms = true;
+                machine__mmap_name(machine, nm, sizeof(nm));
+                name = nm;
+        }
+        return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+                                     debugdir, is_kallsyms, is_vdso);
 }
 
-static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+static int __dsos__cache_build_ids(struct list_head *head,
+                                   struct machine *machine, const char *debugdir)
 {
         struct dso *pos;
         int err = 0;
 
         dsos__for_each_with_build_id(pos, head)
-                if (dso__cache_build_id(pos, debugdir))
+                if (dso__cache_build_id(pos, machine, debugdir))
                         err = -1;
 
         return err;
@@ -431,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
 
 static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-        int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
-        ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
+        int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+                                          debugdir);
+        ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
         return ret;
 }
 
@@ -748,18 +731,19 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu)
         char filename[MAXPATHLEN];
         char *buf = NULL, *p;
         size_t len = 0;
+        ssize_t sret;
         u32 i = 0;
         int ret = -1;
 
         sprintf(filename, CORE_SIB_FMT, cpu);
         fp = fopen(filename, "r");
         if (!fp)
-                return -1;
-
-        if (getline(&buf, &len, fp) <= 0)
-                goto done;
+                goto try_threads;
 
+        sret = getline(&buf, &len, fp);
         fclose(fp);
+        if (sret <= 0)
+                goto try_threads;
 
         p = strchr(buf, '\n');
         if (p)
@@ -775,7 +759,9 @@ static int build_cpu_topo(struct cpu_topo *tp, int cpu)
                 buf = NULL;
                 len = 0;
         }
+        ret = 0;
 
+try_threads:
         sprintf(filename, THRD_SIB_FMT, cpu);
         fp = fopen(filename, "r");
         if (!fp)
@@ -1380,6 +1366,9 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
 
                 fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
 
+                fprintf(fp, ", attr_mmap2 = %d", evsel->attr.mmap2);
+                fprintf(fp, ", attr_mmap  = %d", evsel->attr.mmap);
+                fprintf(fp, ", attr_mmap_data = %d", evsel->attr.mmap_data);
                 if (evsel->ids) {
                         fprintf(fp, ", id = {");
                         for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
@@ -2257,7 +2246,7 @@ static int perf_header__adds_write(struct perf_header *header,
 
         sec_size = sizeof(*feat_sec) * nr_sections;
 
-        sec_start = header->data_offset + header->data_size;
+        sec_start = header->feat_offset;
         lseek(fd, sec_start + sec_size, SEEK_SET);
 
         for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
@@ -2304,6 +2293,7 @@ int perf_session__write_header(struct perf_session *session,
         struct perf_file_attr   f_attr;
         struct perf_header *header = &session->header;
         struct perf_evsel *evsel;
+        u64 attr_offset;
         int err;
 
         lseek(fd, sizeof(f_header), SEEK_SET);
@@ -2317,7 +2307,7 @@ int perf_session__write_header(struct perf_session *session,
                 }
         }
 
-        header->attr_offset = lseek(fd, 0, SEEK_CUR);
+        attr_offset = lseek(fd, 0, SEEK_CUR);
 
         list_for_each_entry(evsel, &evlist->entries, node) {
                 f_attr = (struct perf_file_attr){
@@ -2334,17 +2324,8 @@ int perf_session__write_header(struct perf_session *session,
                 }
         }
 
-        header->event_offset = lseek(fd, 0, SEEK_CUR);
-        header->event_size = trace_event_count * sizeof(struct perf_trace_event_type);
-        if (trace_events) {
-                err = do_write(fd, trace_events, header->event_size);
-                if (err < 0) {
-                        pr_debug("failed to write perf header events\n");
-                        return err;
-                }
-        }
-
         header->data_offset = lseek(fd, 0, SEEK_CUR);
+        header->feat_offset = header->data_offset + header->data_size;
 
         if (at_exit) {
                 err = perf_header__adds_write(header, evlist, fd);
@@ -2357,17 +2338,14 @@ int perf_session__write_header(struct perf_session *session,
                 .size      = sizeof(f_header),
                 .attr_size = sizeof(f_attr),
                 .attrs = {
-                        .offset = header->attr_offset,
+                        .offset = attr_offset,
                         .size   = evlist->nr_entries * sizeof(f_attr),
                 },
                 .data = {
                         .offset = header->data_offset,
                         .size   = header->data_size,
                 },
-                .event_types = {
-                        .offset = header->event_offset,
-                        .size   = header->event_size,
-                },
+                /* event_types is ignored, store zeros */
         };
 
         memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
@@ -2417,7 +2395,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
         sec_size = sizeof(*feat_sec) * nr_sections;
 
-        lseek(fd, header->data_offset + header->data_size, SEEK_SET);
+        lseek(fd, header->feat_offset, SEEK_SET);
 
         err = perf_header__getbuffer64(header, fd, feat_sec, sec_size);
         if (err < 0)
@@ -2523,6 +2501,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
         /* check for legacy format */
         ret = memcmp(&magic, __perf_magic1, sizeof(magic));
         if (ret == 0) {
+                ph->version = PERF_HEADER_VERSION_1;
                 pr_debug("legacy perf.data format\n");
                 if (is_pipe)
                         return try_all_pipe_abis(hdr_sz, ph);
@@ -2544,6 +2523,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
                 return -1;
 
         ph->needs_swap = true;
+        ph->version = PERF_HEADER_VERSION_2;
 
         return 0;
 }
@@ -2614,10 +2594,9 @@ int perf_file_header__read(struct perf_file_header *header,
         memcpy(&ph->adds_features, &header->adds_features,
                sizeof(ph->adds_features));
 
-        ph->event_offset = header->event_types.offset;
-        ph->event_size   = header->event_types.size;
         ph->data_offset  = header->data.offset;
         ph->data_size    = header->data.size;
+        ph->feat_offset  = header->data.offset + header->data.size;
         return 0;
 }
 
@@ -2666,19 +2645,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
         return 0;
 }
 
-static int perf_header__read_pipe(struct perf_session *session, int fd)
+static int perf_header__read_pipe(struct perf_session *session)
 {
         struct perf_header *header = &session->header;
         struct perf_pipe_file_header f_header;
 
-        if (perf_file_header__read_pipe(&f_header, header, fd,
+        if (perf_file_header__read_pipe(&f_header, header, session->fd,
                                         session->repipe) < 0) {
                 pr_debug("incompatible file format\n");
                 return -EINVAL;
         }
 
-        session->fd = fd;
-
         return 0;
 }
 
@@ -2772,20 +2749,21 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
         return 0;
 }
 
-int perf_session__read_header(struct perf_session *session, int fd)
+int perf_session__read_header(struct perf_session *session)
 {
         struct perf_header *header = &session->header;
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         u64                     f_id;
         int nr_attrs, nr_ids, i, j;
+        int fd = session->fd;
 
         session->evlist = perf_evlist__new();
         if (session->evlist == NULL)
                 return -ENOMEM;
 
         if (session->fd_pipe)
-                return perf_header__read_pipe(session, fd);
+                return perf_header__read_pipe(session);
 
         if (perf_file_header__read(&f_header, header, fd) < 0)
                 return -EINVAL;
@@ -2839,22 +2817,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
         symbol_conf.nr_events = nr_attrs;
 
-        if (f_header.event_types.size) {
-                lseek(fd, f_header.event_types.offset, SEEK_SET);
-                trace_events = malloc(f_header.event_types.size);
-                if (trace_events == NULL)
-                        return -ENOMEM;
-                if (perf_header__getbuffer64(header, fd, trace_events,
-                                             f_header.event_types.size))
-                        goto out_errno;
-                trace_event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
-        }
-
         perf_header__process_sections(header, fd, &session->pevent,
                                       perf_file_section__process);
 
-        lseek(fd, header->data_offset, SEEK_SET);
-
         if (perf_evlist__prepare_tracepoint_events(session->evlist,
                                                    session->pevent))
                 goto out_delete_evlist;
@@ -2922,7 +2887,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
         return err;
 }
 
-int perf_event__process_attr(union perf_event *event,
+int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
+                             union perf_event *event,
                              struct perf_evlist **pevlist)
 {
         u32 i, ids, n_ids;
@@ -2961,64 +2927,6 @@ int perf_event__process_attr(union perf_event *event,
         return 0;
 }
 
-int perf_event__synthesize_event_type(struct perf_tool *tool,
-                                      u64 event_id, char *name,
-                                      perf_event__handler_t process,
-                                      struct machine *machine)
-{
-        union perf_event ev;
-        size_t size = 0;
-        int err = 0;
-
-        memset(&ev, 0, sizeof(ev));
-
-        ev.event_type.event_type.event_id = event_id;
-        memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
-        strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
-
-        ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
-        size = strlen(ev.event_type.event_type.name);
-        size = PERF_ALIGN(size, sizeof(u64));
-        ev.event_type.header.size = sizeof(ev.event_type) -
-                (sizeof(ev.event_type.event_type.name) - size);
-
-        err = process(tool, &ev, NULL, machine);
-
-        return err;
-}
-
-int perf_event__synthesize_event_types(struct perf_tool *tool,
-                                       perf_event__handler_t process,
-                                       struct machine *machine)
-{
-        struct perf_trace_event_type *type;
-        int i, err = 0;
-
-        for (i = 0; i < trace_event_count; i++) {
-                type = &trace_events[i];
-
-                err = perf_event__synthesize_event_type(tool, type->event_id,
-                                                        type->name, process,
-                                                        machine);
-                if (err) {
-                        pr_debug("failed to create perf header event type\n");
-                        return err;
-                }
-        }
-
-        return err;
-}
-
-int perf_event__process_event_type(struct perf_tool *tool __maybe_unused,
-                                   union perf_event *event)
-{
-        if (perf_header__push_event(event->event_type.event_type.event_id,
-                                    event->event_type.event_type.name) < 0)
-                return -ENOMEM;
-
-        return 0;
-}
-
 int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
                                         struct perf_evlist *evlist,
                                         perf_event__handler_t process)
@@ -3065,7 +2973,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
         return aligned_size;
 }
 
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event,
                                      struct perf_session *session)
 {
         ssize_t size_read, padding, size = event->tracing_data.size;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 16a3e83c584e..307c9aed972e 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -34,6 +34,11 @@ enum {
         HEADER_FEAT_BITS        = 256,
 };
 
+enum perf_header_version {
+        PERF_HEADER_VERSION_1,
+        PERF_HEADER_VERSION_2,
+};
+
 struct perf_file_section {
         u64 offset;
         u64 size;
@@ -45,6 +50,7 @@ struct perf_file_header {
         u64                             attr_size;
         struct perf_file_section        attrs;
         struct perf_file_section        data;
+        /* event_types is ignored */
         struct perf_file_section        event_types;
         DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
@@ -84,28 +90,24 @@ struct perf_session_env {
 };
 
 struct perf_header {
-        bool                    needs_swap;
-        s64                     attr_offset;
-        u64                     data_offset;
-        u64                     data_size;
-        u64                     event_offset;
-        u64                     event_size;
+        enum perf_header_version        version;
+        bool                            needs_swap;
+        u64                             data_offset;
+        u64                             data_size;
+        u64                             feat_offset;
         DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
-        struct perf_session_env env;
+        struct perf_session_env         env;
 };
 
 struct perf_evlist;
 struct perf_session;
 
-int perf_session__read_header(struct perf_session *session, int fd);
+int perf_session__read_header(struct perf_session *session);
 int perf_session__write_header(struct perf_session *session,
                                struct perf_evlist *evlist,
                                int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
-int perf_header__push_event(u64 id, const char *name);
-char *perf_header__find_event(u64 id);
-
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
@@ -130,22 +132,14 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
                                  struct perf_session *session,
                                  perf_event__handler_t process);
-int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist);
-
-int perf_event__synthesize_event_type(struct perf_tool *tool,
-                                      u64 event_id, char *name,
-                                      perf_event__handler_t process,
-                                      struct machine *machine);
-int perf_event__synthesize_event_types(struct perf_tool *tool,
-                                       perf_event__handler_t process,
-                                       struct machine *machine);
-int perf_event__process_event_type(struct perf_tool *tool,
-                                   union perf_event *event);
+int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
+                             struct perf_evlist **pevlist);
 
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
                                         int fd, struct perf_evlist *evlist,
                                         perf_event__handler_t process);
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool,
+                                     union perf_event *event,
                                      struct perf_session *session);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b11a6cfdb414..9ff6cf3e9a99 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -24,7 +24,8 @@ enum hist_filter {
 struct callchain_param  callchain_param = {
         .mode   = CHAIN_GRAPH_REL,
         .min_percent = 0.5,
-        .order  = ORDER_CALLEE
+        .order  = ORDER_CALLEE,
+        .key    = CCKEY_FUNCTION
 };
 
 u16 hists__col_len(struct hists *hists, enum hist_column col)
@@ -610,6 +611,8 @@ void hists__collapse_resort(struct hists *hists)
         next = rb_first(root);
 
         while (next) {
+                if (session_done())
+                        break;
                 n = rb_entry(next, struct hist_entry, rb_node_in);
                 next = rb_next(&n->rb_node_in);
 
@@ -912,6 +915,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
                 rb_link_node(&he->rb_node_in, parent, p);
                 rb_insert_color(&he->rb_node_in, root);
                 hists__inc_nr_entries(hists, he);
+                he->dummy = true;
         }
 out:
         return he;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 2d3790fd99bb..1329b6b6ffe6 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -141,10 +141,12 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
-        int (*header)(struct perf_hpp *hpp);
-        int (*width)(struct perf_hpp *hpp);
-        int (*color)(struct perf_hpp *hpp, struct hist_entry *he);
-        int (*entry)(struct perf_hpp *hpp, struct hist_entry *he);
+        int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+        int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+        int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                     struct hist_entry *he);
+        int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                     struct hist_entry *he);
 
         struct list_head list;
 };
@@ -157,7 +159,7 @@ extern struct list_head perf_hpp__list;
 extern struct perf_hpp_fmt perf_hpp__format[];
 
 enum {
-        PERF_HPP__BASELINE,
+        /* Matches perf_hpp__format array. */
         PERF_HPP__OVERHEAD,
         PERF_HPP__OVERHEAD_SYS,
         PERF_HPP__OVERHEAD_US,
@@ -165,11 +167,6 @@ enum {
         PERF_HPP__OVERHEAD_GUEST_US,
         PERF_HPP__SAMPLES,
         PERF_HPP__PERIOD,
-        PERF_HPP__PERIOD_BASELINE,
-        PERF_HPP__DELTA,
-        PERF_HPP__RATIO,
-        PERF_HPP__WEIGHTED_DIFF,
-        PERF_HPP__FORMULA,
 
         PERF_HPP__MAX_INDEX
 };
@@ -177,8 +174,6 @@ enum {
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
-int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
-                                bool color);
 
 struct perf_evlist;
 
@@ -245,11 +240,4 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
 #endif
 
 unsigned int hists__sort_list_width(struct hists *self);
-
-double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair);
-double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair);
-s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair);
-int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
-                       char *buf, size_t size);
-double perf_diff__period_percent(struct hist_entry *he, u64 period);
 #endif  /* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 6f19c548ecc0..97a800738226 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,3 +1,4 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
+int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b2ecad6ec46b..6188d2876a71 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -25,12 +25,15 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         machine->kmaps.machine = machine;
         machine->pid = pid;
 
+        machine->symbol_filter = NULL;
+
         machine->root_dir = strdup(root_dir);
         if (machine->root_dir == NULL)
                 return -ENOMEM;
 
         if (pid != HOST_KERNEL_ID) {
-                struct thread *thread = machine__findnew_thread(machine, pid);
+                struct thread *thread = machine__findnew_thread(machine, 0,
+                                                                pid);
                 char comm[64];
 
                 if (thread == NULL)
@@ -95,6 +98,7 @@ void machines__init(struct machines *machines)
 {
         machine__init(&machines->host, "", HOST_KERNEL_ID);
         machines->guests = RB_ROOT;
+        machines->symbol_filter = NULL;
 }
 
 void machines__exit(struct machines *machines)
@@ -118,6 +122,8 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
                 return NULL;
         }
 
+        machine->symbol_filter = machines->symbol_filter;
+
         while (*p != NULL) {
                 parent = *p;
                 pos = rb_entry(parent, struct machine, rb_node);
@@ -133,6 +139,21 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
         return machine;
 }
 
+void machines__set_symbol_filter(struct machines *machines,
+                                 symbol_filter_t symbol_filter)
+{
+        struct rb_node *nd;
+
+        machines->symbol_filter = symbol_filter;
+        machines->host.symbol_filter = symbol_filter;
+
+        for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+                struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+                machine->symbol_filter = symbol_filter;
+        }
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
         struct rb_node **p = &machines->guests.rb_node;
@@ -233,7 +254,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
         return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
+static struct thread *__machine__findnew_thread(struct machine *machine,
+                                                pid_t pid, pid_t tid,
                                                 bool create)
 {
         struct rb_node **p = &machine->threads.rb_node;
@@ -241,23 +263,28 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
         struct thread *th;
 
         /*
-         * Font-end cache - PID lookups come in blocks,
+         * Front-end cache - TID lookups come in blocks,
          * so most of the time we dont have to look up
          * the full rbtree:
          */
-        if (machine->last_match && machine->last_match->pid == pid)
+        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;
+        }
 
         while (*p != NULL) {
                 parent = *p;
                 th = rb_entry(parent, struct thread, rb_node);
 
-                if (th->pid == pid) {
+                if (th->tid == tid) {
                         machine->last_match = th;
+                        if (pid && pid != th->pid_)
+                                th->pid_ = pid;
                         return th;
                 }
 
-                if (pid < th->pid)
+                if (tid < th->tid)
                         p = &(*p)->rb_left;
                 else
                         p = &(*p)->rb_right;
@@ -266,7 +293,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
         if (!create)
                 return NULL;
 
-        th = thread__new(pid);
+        th = thread__new(pid, tid);
         if (th != NULL) {
                 rb_link_node(&th->rb_node, parent, p);
                 rb_insert_color(&th->rb_node, &machine->threads);
@@ -276,19 +303,22 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
         return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+                                       pid_t tid)
 {
-        return __machine__findnew_thread(machine, pid, true);
+        return __machine__findnew_thread(machine, pid, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid)
+struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-        return __machine__findnew_thread(machine, pid, false);
+        return __machine__findnew_thread(machine, 0, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
 {
-        struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+        struct thread *thread = machine__findnew_thread(machine,
+                                                        event->comm.pid,
+                                                        event->comm.tid);
 
         if (dump_trace)
                 perf_event__fprintf_comm(event, stdout);
@@ -628,10 +658,8 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
         struct map *map = machine->vmlinux_maps[type];
         int ret = dso__load_vmlinux_path(map->dso, map, filter);
 
-        if (ret > 0) {
+        if (ret > 0)
                 dso__set_loaded(map->dso, type);
-                map__reloc_vmlinux(map);
-        }
 
         return ret;
 }
@@ -764,7 +792,7 @@ static int machine__create_modules(struct machine *machine)
                 modules = path;
         }
 
-        if (symbol__restricted_filename(path, "/proc/modules"))
+        if (symbol__restricted_filename(modules, "/proc/modules"))
                 return -1;
 
         file = fopen(modules, "r");
@@ -808,7 +836,10 @@ static int machine__create_modules(struct machine *machine)
         free(line);
         fclose(file);
 
-        return machine__set_modules_path(machine);
+        if (machine__set_modules_path(machine) < 0) {
+                pr_debug("Problems setting modules path maps, continuing anyway...\n");
+        }
+        return 0;
 
 out_delete_line:
         free(line);
@@ -858,6 +889,18 @@ static void machine__set_kernel_mmap_len(struct machine *machine,
         }
 }
 
+static bool machine__uses_kcore(struct machine *machine)
+{
+        struct dso *dso;
+
+        list_for_each_entry(dso, &machine->kernel_dsos, node) {
+                if (dso__is_kcore(dso))
+                        return true;
+        }
+
+        return false;
+}
+
 static int machine__process_kernel_mmap_event(struct machine *machine,
                                               union perf_event *event)
 {
@@ -866,6 +909,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
         enum dso_kernel_type kernel_type;
         bool is_kernel_mmap;
 
+        /* If we have maps from kcore then we do not need or want any others */
+        if (machine__uses_kcore(machine))
+                return 0;
+
         machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
         if (machine__is_host(machine))
                 kernel_type = DSO_TYPE_KERNEL;
@@ -950,6 +997,54 @@ out_problem:
         return -1;
 }
 
+int machine__process_mmap2_event(struct machine *machine,
+                                 union perf_event *event)
+{
+        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        struct thread *thread;
+        struct map *map;
+        enum map_type type;
+        int ret = 0;
+
+        if (dump_trace)
+                perf_event__fprintf_mmap2(event, stdout);
+
+        if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+            cpumode == PERF_RECORD_MISC_KERNEL) {
+                ret = machine__process_kernel_mmap_event(machine, event);
+                if (ret < 0)
+                        goto out_problem;
+                return 0;
+        }
+
+        thread = machine__findnew_thread(machine, event->mmap2.pid,
+                                        event->mmap2.pid);
+        if (thread == NULL)
+                goto out_problem;
+
+        if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+                type = MAP__VARIABLE;
+        else
+                type = MAP__FUNCTION;
+
+        map = map__new(&machine->user_dsos, event->mmap2.start,
+                        event->mmap2.len, event->mmap2.pgoff,
+                        event->mmap2.pid, event->mmap2.maj,
+                        event->mmap2.min, event->mmap2.ino,
+                        event->mmap2.ino_generation,
+                        event->mmap2.filename, type);
+
+        if (map == NULL)
+                goto out_problem;
+
+        thread__insert_map(thread, map);
+        return 0;
+
+out_problem:
+        dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
+        return 0;
+}
+
 int machine__process_mmap_event(struct machine *machine, union perf_event *event)
 {
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -969,7 +1064,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
                 return 0;
         }
 
-        thread = machine__findnew_thread(machine, event->mmap.pid);
+        thread = machine__findnew_thread(machine, event->mmap.pid,
+                                         event->mmap.pid);
         if (thread == NULL)
                 goto out_problem;
 
@@ -980,7 +1076,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
         map = map__new(&machine->user_dsos, event->mmap.start,
                         event->mmap.len, event->mmap.pgoff,
-                        event->mmap.pid, event->mmap.filename,
+                        event->mmap.pid, 0, 0, 0, 0,
+                        event->mmap.filename,
                         type);
 
         if (map == NULL)
@@ -994,11 +1091,30 @@ out_problem:
         return 0;
 }
 
+static void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+        machine->last_match = NULL;
+        rb_erase(&th->rb_node, &machine->threads);
+        /*
+         * We may have references to this thread, for instance in some hist_entry
+         * instances, so just move them to a separate list.
+         */
+        list_add_tail(&th->node, &machine->dead_threads);
+}
+
 int machine__process_fork_event(struct machine *machine, union perf_event *event)
 {
-        struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
-        struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+        struct thread *thread = machine__find_thread(machine, event->fork.tid);
+        struct thread *parent = machine__findnew_thread(machine,
+                                                        event->fork.ppid,
+                                                        event->fork.ptid);
 
+        /* if a thread currently exists for the thread id remove it */
+        if (thread != NULL)
+                machine__remove_thread(machine, thread);
+
+        thread = machine__findnew_thread(machine, event->fork.pid,
+                                         event->fork.tid);
         if (dump_trace)
                 perf_event__fprintf_task(event, stdout);
 
@@ -1011,18 +1127,8 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
         return 0;
 }
 
-static void machine__remove_thread(struct machine *machine, struct thread *th)
-{
-        machine->last_match = NULL;
-        rb_erase(&th->rb_node, &machine->threads);
-        /*
-         * We may have references to this thread, for instance in some hist_entry
-         * instances, so just move them to a separate list.
-         */
-        list_add_tail(&th->node, &machine->dead_threads);
-}
-
-int machine__process_exit_event(struct machine *machine, union perf_event *event)
+int machine__process_exit_event(struct machine *machine __maybe_unused,
+                                union perf_event *event)
 {
         struct thread *thread = machine__find_thread(machine, event->fork.tid);
 
@@ -1030,7 +1136,7 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
                 perf_event__fprintf_task(event, stdout);
 
         if (thread != NULL)
-                machine__remove_thread(machine, thread);
+                thread__exited(thread);
 
         return 0;
 }
@@ -1044,6 +1150,8 @@ int machine__process_event(struct machine *machine, union perf_event *event)
                 ret = machine__process_comm_event(machine, event); break;
         case PERF_RECORD_MMAP:
                 ret = machine__process_mmap_event(machine, event); break;
+        case PERF_RECORD_MMAP2:
+                ret = machine__process_mmap2_event(machine, event); break;
         case PERF_RECORD_FORK:
                 ret = machine__process_fork_event(machine, event); break;
         case PERF_RECORD_EXIT:
@@ -1058,11 +1166,10 @@ int machine__process_event(struct machine *machine, union perf_event *event)
         return ret;
 }
 
-static bool symbol__match_parent_regex(struct symbol *sym)
+static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-        if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+        if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
                 return 1;
-
         return 0;
 }
 
@@ -1094,7 +1201,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
                  * or else, the symbol is unknown
                  */
                 thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
-                                ip, &al, NULL);
+                                ip, &al);
                 if (al.sym)
                         goto found;
         }
@@ -1112,8 +1219,8 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
 
         memset(&al, 0, sizeof(al));
 
-        thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al,
-                                   NULL);
+        thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
+                                   &al);
         ams->addr = addr;
         ams->al_addr = al.addr;
         ams->sym = al.sym;
@@ -1159,8 +1266,8 @@ struct branch_info *machine__resolve_bstack(struct machine *machine,
 static int machine__resolve_callchain_sample(struct machine *machine,
                                              struct thread *thread,
                                              struct ip_callchain *chain,
-                                             struct symbol **parent)
-
+                                             struct symbol **parent,
+                                             struct addr_location *root_al)
 {
         u8 cpumode = PERF_RECORD_MISC_USER;
         unsigned int i;
@@ -1208,11 +1315,18 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 
                 al.filtered = false;
                 thread__find_addr_location(thread, machine, cpumode,
-                                           MAP__FUNCTION, ip, &al, NULL);
+                                           MAP__FUNCTION, ip, &al);
                 if (al.sym != NULL) {
                         if (sort__has_parent && !*parent &&
-                            symbol__match_parent_regex(al.sym))
+                            symbol__match_regex(al.sym, &parent_regex))
                                 *parent = al.sym;
+                        else if (have_ignore_callees && root_al &&
+                          symbol__match_regex(al.sym, &ignore_callees_regex)) {
+                                /* Treat this symbol as the root,
+                                   forgetting its callees. */
+                                *root_al = al;
+                                callchain_cursor_reset(&callchain_cursor);
+                        }
                         if (!symbol_conf.use_callchain)
                                 break;
                 }
@@ -1237,15 +1351,13 @@ int machine__resolve_callchain(struct machine *machine,
                                struct perf_evsel *evsel,
                                struct thread *thread,
                                struct perf_sample *sample,
-                               struct symbol **parent)
-
+                               struct symbol **parent,
+                               struct addr_location *root_al)
 {
         int ret;
 
-        callchain_cursor_reset(&callchain_cursor);
-
         ret = machine__resolve_callchain_sample(machine, thread,
-                                                sample->callchain, parent);
+                                                sample->callchain, parent, root_al);
         if (ret)
                 return ret;
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 77940680f1fc..58a6be1fc739 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -5,6 +5,7 @@
 #include <linux/rbtree.h>
 #include "map.h"
 
+struct addr_location;
 struct branch_stack;
 struct perf_evsel;
 struct perf_sample;
@@ -28,6 +29,7 @@ struct machine {
         struct list_head  kernel_dsos;
         struct map_groups kmaps;
         struct map        *vmlinux_maps[MAP__NR_TYPES];
+        symbol_filter_t   symbol_filter;
 };
 
 static inline
@@ -36,13 +38,14 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
         return machine->vmlinux_maps[type];
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid);
+struct thread *machine__find_thread(struct machine *machine, pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event);
 int machine__process_exit_event(struct machine *machine, union perf_event *event);
 int machine__process_fork_event(struct machine *machine, union perf_event *event);
 int machine__process_lost_event(struct machine *machine, union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event);
+int machine__process_mmap2_event(struct machine *machine, union perf_event *event);
 int machine__process_event(struct machine *machine, union perf_event *event);
 
 typedef void (*machine__process_t)(struct machine *machine, void *data);
@@ -50,6 +53,7 @@ typedef void (*machine__process_t)(struct machine *machine, void *data);
 struct machines {
         struct machine host;
         struct rb_root guests;
+        symbol_filter_t symbol_filter;
 };
 
 void machines__init(struct machines *machines);
@@ -67,6 +71,9 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid);
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
+void machines__set_symbol_filter(struct machines *machines,
+                                 symbol_filter_t symbol_filter);
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_dead_threads(struct machine *machine);
@@ -83,7 +90,8 @@ int machine__resolve_callchain(struct machine *machine,
                                struct perf_evsel *evsel,
                                struct thread *thread,
                                struct perf_sample *sample,
-                               struct symbol **parent);
+                               struct symbol **parent,
+                               struct addr_location *root_al);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
@@ -99,7 +107,8 @@ static inline bool machine__is_host(struct machine *machine)
         return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
+                                       pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8bcdf9e54089..4f6680d2043b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -48,7 +48,8 @@ void map__init(struct map *map, enum map_type type,
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-                     u64 pgoff, u32 pid, char *filename,
+                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 ino_gen, char *filename,
                      enum map_type type)
 {
         struct map *map = malloc(sizeof(*map));
@@ -62,6 +63,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
                 vdso = is_vdso_map(filename);
                 no_dso = is_no_dso_memory(filename);
 
+                map->maj = d_maj;
+                map->min = d_min;
+                map->ino = ino;
+                map->ino_generation = ino_gen;
+
                 if (anon) {
                         snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
                         filename = newfilename;
@@ -182,12 +188,6 @@ int map__load(struct map *map, symbol_filter_t filter)
 #endif
                 return -1;
         }
-        /*
-         * Only applies to the kernel, as its symtabs aren't relative like the
-         * module ones.
-         */
-        if (map->dso->kernel)
-                map__reloc_vmlinux(map);
 
         return 0;
 }
@@ -254,14 +254,18 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 
 /*
  * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
- * map->dso->adjust_symbols==1 for ET_EXEC-like cases.
+ * map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is
+ * relative to section start.
  */
 u64 map__rip_2objdump(struct map *map, u64 rip)
 {
-        u64 addr = map->dso->adjust_symbols ?
-                        map->unmap_ip(map, rip) :       /* RIP -> IP */
-                        rip;
-        return addr;
+        if (!map->dso->adjust_symbols)
+                return rip;
+
+        if (map->dso->rel)
+                return rip - map->pgoff;
+
+        return map->unmap_ip(map, rip);
 }
 
 void map_groups__init(struct map_groups *mg)
@@ -513,35 +517,6 @@ int map_groups__clone(struct map_groups *mg,
         return 0;
 }
 
-static u64 map__reloc_map_ip(struct map *map, u64 ip)
-{
-        return ip + (s64)map->pgoff;
-}
-
-static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
-{
-        return ip - (s64)map->pgoff;
-}
-
-void map__reloc_vmlinux(struct map *map)
-{
-        struct kmap *kmap = map__kmap(map);
-        s64 reloc;
-
-        if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
-                return;
-
-        reloc = (kmap->ref_reloc_sym->unrelocated_addr -
-                 kmap->ref_reloc_sym->addr);
-
-        if (!reloc)
-                return;
-
-        map->map_ip   = map__reloc_map_ip;
-        map->unmap_ip = map__reloc_unmap_ip;
-        map->pgoff    = reloc;
-}
-
 void maps__insert(struct rb_root *maps, struct map *map)
 {
         struct rb_node **p = &maps->rb_node;
@@ -586,3 +561,21 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 
         return NULL;
 }
+
+struct map *maps__first(struct rb_root *maps)
+{
+        struct rb_node *first = rb_first(maps);
+
+        if (first)
+                return rb_entry(first, struct map, rb_node);
+        return NULL;
+}
+
+struct map *maps__next(struct map *map)
+{
+        struct rb_node *next = rb_next(&map->rb_node);
+
+        if (next)
+                return rb_entry(next, struct map, rb_node);
+        return NULL;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index a887f2c9dfbb..4886ca280536 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,9 @@ struct map {
         bool                    erange_warned;
         u32                     priv;
         u64                     pgoff;
+        u32                     maj, min; /* only valid for MMAP2 record */
+        u64                     ino;      /* only valid for MMAP2 record */
+        u64                     ino_generation;/* only valid for MMAP2 record */
 
         /* ip -> dso rip */
         u64                     (*map_ip)(struct map *, u64);
@@ -88,8 +91,9 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 void map__init(struct map *map, enum map_type type,
                u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
-                     u64 pgoff, u32 pid, char *filename,
-                     enum map_type type);
+                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 ino_gen,
+                     char *filename, enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
@@ -112,6 +116,8 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg,
 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);
+struct map *maps__first(struct rb_root *maps);
+struct map *maps__next(struct map *map);
 void map_groups__init(struct map_groups *mg);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
@@ -139,6 +145,17 @@ static inline struct map *map_groups__find(struct map_groups *mg,
         return maps__find(&mg->maps[type], addr);
 }
 
+static inline struct map *map_groups__first(struct map_groups *mg,
+                                            enum map_type type)
+{
+        return maps__first(&mg->maps[type]);
+}
+
+static inline struct map *map_groups__next(struct map *map)
+{
+        return maps__next(map);
+}
+
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
                                        enum map_type type, u64 addr,
                                        struct map **mapp,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 995fc25db8c6..98125319b158 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,7 +6,7 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "string.h"
+#include "linux/string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -15,6 +15,7 @@
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
 #include "pmu.h"
+#include "thread_map.h"
 
 #define MAX_NAME_LEN 100
 
@@ -108,6 +109,10 @@ static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
                 .symbol = "emulation-faults",
                 .alias  = "",
         },
+        [PERF_COUNT_SW_DUMMY] = {
+                .symbol = "dummy",
+                .alias  = "",
+        },
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -217,6 +222,29 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
         return NULL;
 }
 
+struct tracepoint_path *tracepoint_name_to_path(const char *name)
+{
+        struct tracepoint_path *path = zalloc(sizeof(*path));
+        char *str = strchr(name, ':');
+
+        if (path == NULL || str == NULL) {
+                free(path);
+                return NULL;
+        }
+
+        path->system = strndup(name, str - name);
+        path->name = strdup(str+1);
+
+        if (path->system == NULL || path->name == NULL) {
+                free(path->system);
+                free(path->name);
+                free(path);
+                path = NULL;
+        }
+
+        return path;
+}
+
 const char *event_type(int type)
 {
         switch (type) {
@@ -241,40 +269,29 @@ const char *event_type(int type)
 
 
 
-static int __add_event(struct list_head **_list, int *idx,
+static int __add_event(struct list_head *list, int *idx,
                        struct perf_event_attr *attr,
                        char *name, struct cpu_map *cpus)
 {
         struct perf_evsel *evsel;
-        struct list_head *list = *_list;
-
-        if (!list) {
-                list = malloc(sizeof(*list));
-                if (!list)
-                        return -ENOMEM;
-                INIT_LIST_HEAD(list);
-        }
 
         event_attr_init(attr);
 
         evsel = perf_evsel__new(attr, (*idx)++);
-        if (!evsel) {
-                free(list);
+        if (!evsel)
                 return -ENOMEM;
-        }
 
         evsel->cpus = cpus;
         if (name)
                 evsel->name = strdup(name);
         list_add_tail(&evsel->node, list);
-        *_list = list;
         return 0;
 }
 
-static int add_event(struct list_head **_list, int *idx,
+static int add_event(struct list_head *list, int *idx,
                      struct perf_event_attr *attr, char *name)
 {
-        return __add_event(_list, idx, attr, name, NULL);
+        return __add_event(list, idx, attr, name, NULL);
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -295,7 +312,7 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
         return -1;
 }
 
-int parse_events_add_cache(struct list_head **list, int *idx,
+int parse_events_add_cache(struct list_head *list, int *idx,
                            char *type, char *op_result1, char *op_result2)
 {
         struct perf_event_attr attr;
@@ -356,31 +373,21 @@ int parse_events_add_cache(struct list_head **list, int *idx,
         return add_event(list, idx, &attr, name);
 }
 
-static int add_tracepoint(struct list_head **listp, int *idx,
+static int add_tracepoint(struct list_head *list, int *idx,
                           char *sys_name, char *evt_name)
 {
         struct perf_evsel *evsel;
-        struct list_head *list = *listp;
-
-        if (!list) {
-                list = malloc(sizeof(*list));
-                if (!list)
-                        return -ENOMEM;
-                INIT_LIST_HEAD(list);
-        }
 
         evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++);
-        if (!evsel) {
-                free(list);
+        if (!evsel)
                 return -ENOMEM;
-        }
 
         list_add_tail(&evsel->node, list);
-        *listp = list;
+
         return 0;
 }
 
-static int add_tracepoint_multi_event(struct list_head **list, int *idx,
+static int add_tracepoint_multi_event(struct list_head *list, int *idx,
                                       char *sys_name, char *evt_name)
 {
         char evt_path[MAXPATHLEN];
@@ -412,7 +419,7 @@ static int add_tracepoint_multi_event(struct list_head **list, int *idx,
         return ret;
 }
 
-static int add_tracepoint_event(struct list_head **list, int *idx,
+static int add_tracepoint_event(struct list_head *list, int *idx,
                                 char *sys_name, char *evt_name)
 {
         return strpbrk(evt_name, "*?") ?
@@ -420,7 +427,7 @@ static int add_tracepoint_event(struct list_head **list, int *idx,
                add_tracepoint(list, idx, sys_name, evt_name);
 }
 
-static int add_tracepoint_multi_sys(struct list_head **list, int *idx,
+static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
                                     char *sys_name, char *evt_name)
 {
         struct dirent *events_ent;
@@ -452,7 +459,7 @@ static int add_tracepoint_multi_sys(struct list_head **list, int *idx,
         return ret;
 }
 
-int parse_events_add_tracepoint(struct list_head **list, int *idx,
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                 char *sys, char *event)
 {
         int ret;
@@ -507,7 +514,7 @@ do {					\
         return 0;
 }
 
-int parse_events_add_breakpoint(struct list_head **list, int *idx,
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type)
 {
         struct perf_event_attr attr;
@@ -588,7 +595,7 @@ static int config_attr(struct perf_event_attr *attr,
         return 0;
 }
 
-int parse_events_add_numeric(struct list_head **list, int *idx,
+int parse_events_add_numeric(struct list_head *list, int *idx,
                              u32 type, u64 config,
                              struct list_head *head_config)
 {
@@ -621,7 +628,7 @@ static char *pmu_event_name(struct list_head *head_terms)
         return NULL;
 }
 
-int parse_events_add_pmu(struct list_head **list, int *idx,
+int parse_events_add_pmu(struct list_head *list, int *idx,
                          char *name, struct list_head *head_config)
 {
         struct perf_event_attr attr;
@@ -664,6 +671,7 @@ void parse_events__set_leader(char *name, struct list_head *list)
         leader->group_name = name ? strdup(name) : NULL;
 }
 
+/* list_event is assumed to point to malloc'ed memory */
 void parse_events_update_lists(struct list_head *list_event,
                                struct list_head *list_all)
 {
@@ -684,6 +692,8 @@ struct event_modifier {
         int eG;
         int precise;
         int exclude_GH;
+        int sample_read;
+        int pinned;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -695,6 +705,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         int eH = evsel ? evsel->attr.exclude_host : 0;
         int eG = evsel ? evsel->attr.exclude_guest : 0;
         int precise = evsel ? evsel->attr.precise_ip : 0;
+        int sample_read = 0;
+        int pinned = evsel ? evsel->attr.pinned : 0;
 
         int exclude = eu | ek | eh;
         int exclude_GH = evsel ? evsel->exclude_GH : 0;
@@ -727,6 +739,10 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
                         /* use of precise requires exclude_guest */
                         if (!exclude_GH)
                                 eG = 1;
+                } else if (*str == 'S') {
+                        sample_read = 1;
+                } else if (*str == 'D') {
+                        pinned = 1;
                 } else
                         break;
 
@@ -753,6 +769,9 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         mod->eG = eG;
         mod->precise = precise;
         mod->exclude_GH = exclude_GH;
+        mod->sample_read = sample_read;
+        mod->pinned = pinned;
+
         return 0;
 }
 
@@ -765,7 +784,7 @@ static int check_modifier(char *str)
         char *p = str;
 
         /* The sizeof includes 0 byte as well. */
-        if (strlen(str) > (sizeof("ukhGHppp") - 1))
+        if (strlen(str) > (sizeof("ukhGHpppSD") - 1))
                 return -1;
 
         while (*p) {
@@ -803,6 +822,10 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
                 evsel->attr.exclude_host   = mod.eH;
                 evsel->attr.exclude_guest  = mod.eG;
                 evsel->exclude_GH          = mod.exclude_GH;
+                evsel->sample_read         = mod.sample_read;
+
+                if (perf_evsel__is_group_leader(evsel))
+                        evsel->attr.pinned = mod.pinned;
         }
 
         return 0;
@@ -820,6 +843,32 @@ int parse_events_name(struct list_head *list, char *name)
         return 0;
 }
 
+static int parse_events__scanner(const char *str, void *data, int start_token);
+
+static int parse_events_fixup(int ret, const char *str, void *data,
+                              int start_token)
+{
+        char *o = strdup(str);
+        char *s = NULL;
+        char *t = o;
+        char *p;
+        int len = 0;
+
+        if (!o)
+                return ret;
+        while ((p = strsep(&t, ",")) != NULL) {
+                if (s)
+                        str_append(&s, &len, ",");
+                str_append(&s, &len, "cpu/");
+                str_append(&s, &len, p);
+                str_append(&s, &len, "/");
+        }
+        free(o);
+        if (!s)
+                return -ENOMEM;
+        return parse_events__scanner(s, data, start_token);
+}
+
 static int parse_events__scanner(const char *str, void *data, int start_token)
 {
         YY_BUFFER_STATE buffer;
@@ -840,6 +889,8 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
         parse_events__flush_buffer(buffer, scanner);
         parse_events__delete_buffer(buffer, scanner);
         parse_events_lex_destroy(scanner);
+        if (ret && !strchr(str, '/'))
+                ret = parse_events_fixup(ret, str, data, start_token);
         return ret;
 }
 
@@ -1026,6 +1077,33 @@ int is_valid_tracepoint(const char *event_string)
         return 0;
 }
 
+static bool is_event_supported(u8 type, unsigned config)
+{
+        bool ret = true;
+        struct perf_evsel *evsel;
+        struct perf_event_attr attr = {
+                .type = type,
+                .config = config,
+                .disabled = 1,
+                .exclude_kernel = 1,
+        };
+        struct {
+                struct thread_map map;
+                int threads[1];
+        } tmap = {
+                .map.nr  = 1,
+                .threads = { 0 },
+        };
+
+        evsel = perf_evsel__new(&attr, 0);
+        if (evsel) {
+                ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+                perf_evsel__delete(evsel);
+        }
+
+        return ret;
+}
+
 static void __print_events_type(u8 type, struct event_symbol *syms,
                                 unsigned max)
 {
@@ -1033,14 +1111,16 @@ static void __print_events_type(u8 type, struct event_symbol *syms,
         unsigned i;
 
         for (i = 0; i < max ; i++, syms++) {
+                if (!is_event_supported(type, i))
+                        continue;
+
                 if (strlen(syms->alias))
                         snprintf(name, sizeof(name),  "%s OR %s",
                                  syms->symbol, syms->alias);
                 else
                         snprintf(name, sizeof(name), "%s", syms->symbol);
 
-                printf("  %-50s [%s]\n", name,
-                        event_type_descriptors[type]);
+                printf("  %-50s [%s]\n", name, event_type_descriptors[type]);
         }
 }
 
@@ -1069,6 +1149,10 @@ int print_hwcache_events(const char *event_glob, bool name_only)
                                 if (event_glob != NULL && !strglobmatch(name, event_glob))
                                         continue;
 
+                                if (!is_event_supported(PERF_TYPE_HW_CACHE,
+                                                        type | (op << 8) | (i << 16)))
+                                        continue;
+
                                 if (name_only)
                                         printf("%s ", name);
                                 else
@@ -1079,6 +1163,8 @@ int print_hwcache_events(const char *event_glob, bool name_only)
                 }
         }
 
+        if (printed)
+                printf("\n");
         return printed;
 }
 
@@ -1096,6 +1182,9 @@ static void print_symbol_events(const char *event_glob, unsigned type,
                       (syms->alias && strglobmatch(syms->alias, event_glob))))
                         continue;
 
+                if (!is_event_supported(type, i))
+                        continue;
+
                 if (name_only) {
                         printf("%s ", syms->symbol);
                         continue;
@@ -1133,11 +1222,12 @@ void print_events(const char *event_glob, bool name_only)
 
         print_hwcache_events(event_glob, name_only);
 
+        print_pmu_events(event_glob, name_only);
+
         if (event_glob != NULL)
                 return;
 
         if (!name_only) {
-                printf("\n");
                 printf("  %-50s [%s]\n",
                        "rNNN",
                        event_type_descriptors[PERF_TYPE_RAW]);
@@ -1237,6 +1327,4 @@ void parse_events__free_terms(struct list_head *terms)
 
         list_for_each_entry_safe(term, h, terms, list)
                 free(term);
-
-        free(terms);
 }
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 8a4859315fd9..f1cb4c4b3c70 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -23,6 +23,7 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
+extern struct tracepoint_path *tracepoint_name_to_path(const char *name);
 extern bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
@@ -84,16 +85,16 @@ void parse_events__free_terms(struct list_head *terms);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
-int parse_events_add_tracepoint(struct list_head **list, int *idx,
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                 char *sys, char *event);
-int parse_events_add_numeric(struct list_head **list, int *idx,
+int parse_events_add_numeric(struct list_head *list, int *idx,
                              u32 type, u64 config,
                              struct list_head *head_config);
-int parse_events_add_cache(struct list_head **list, int *idx,
+int parse_events_add_cache(struct list_head *list, int *idx,
                            char *type, char *op_result1, char *op_result2);
-int parse_events_add_breakpoint(struct list_head **list, int *idx,
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type);
-int parse_events_add_pmu(struct list_head **list, int *idx,
+int parse_events_add_pmu(struct list_head *list, int *idx,
                          char *pmu , struct list_head *head_config);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index e9d1134c2c68..91346b753960 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -82,7 +82,8 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex     [a-fA-F0-9]+
 name            [a-zA-Z_*?][a-zA-Z0-9_*?]*
 name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?]*
-modifier_event  [ukhpGH]+
+/* If you add a modifier you need to update check_modifier() */
+modifier_event  [ukhpGHSD]+
 modifier_bp     [rwx]{1,3}
 
 %%
@@ -144,6 +145,7 @@ context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW
 cpu-migrations|migrations                       { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
 alignment-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
+dummy                                           { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
 
 L1-dcache|l1-d|l1d|L1-data              |
 L1-icache|l1-i|l1i|L1-instruction       |
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index afc44c18dfe1..4eb67ec333f1 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -22,6 +22,13 @@ do { \
                 YYABORT; \
 } while (0)
 
+#define ALLOC_LIST(list) \
+do { \
+        list = malloc(sizeof(*list)); \
+        ABORT_ON(!list);              \
+        INIT_LIST_HEAD(list);         \
+} while (0)
+
 static inc_group_count(struct list_head *list,
                        struct parse_events_evlist *data)
 {
@@ -196,9 +203,10 @@ event_pmu:
 PE_NAME '/' event_config '/'
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
         parse_events__free_terms($3);
         $$ = list;
 }
@@ -212,11 +220,12 @@ event_legacy_symbol:
 value_sym '/' event_config '/'
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
-        ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_numeric(list, &data->idx,
                                           type, config, $3));
         parse_events__free_terms($3);
         $$ = list;
@@ -225,11 +234,12 @@ value_sym '/' event_config '/'
 value_sym sep_slash_dc
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
-        ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_numeric(list, &data->idx,
                                           type, config, NULL));
         $$ = list;
 }
@@ -238,27 +248,30 @@ event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
         $$ = list;
 }
 
@@ -266,9 +279,10 @@ event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
                                              (void *) $2, $4));
         $$ = list;
 }
@@ -276,9 +290,10 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
                                              (void *) $2, NULL));
         $$ = list;
 }
@@ -287,9 +302,10 @@ event_legacy_tracepoint:
 PE_NAME ':' PE_NAME
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
         $$ = list;
 }
 
@@ -297,9 +313,10 @@ event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL));
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
         $$ = list;
 }
 
@@ -307,9 +324,10 @@ event_legacy_raw:
 PE_RAW
 {
         struct parse_events_evlist *data = _data;
-        struct list_head *list = NULL;
+        struct list_head *list;
 
-        ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_numeric(list, &data->idx,
                                           PERF_TYPE_RAW, $1, NULL));
         $$ = list;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 4c6f9c490a8d..bc9d8069d376 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -73,7 +73,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(char *name, struct list_head *format)
+static int pmu_format(const char *name, struct list_head *format)
 {
         struct stat st;
         char path[PATH_MAX];
@@ -162,7 +162,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases(char *name, struct list_head *head)
+static int pmu_aliases(const char *name, struct list_head *head)
 {
         struct stat st;
         char path[PATH_MAX];
@@ -208,7 +208,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
  * located at:
  * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
  */
-static int pmu_type(char *name, __u32 *type)
+static int pmu_type(const char *name, __u32 *type)
 {
         struct stat st;
         char path[PATH_MAX];
@@ -266,7 +266,7 @@ static void pmu_read_sysfs(void)
         closedir(dir);
 }
 
-static struct cpu_map *pmu_cpumask(char *name)
+static struct cpu_map *pmu_cpumask(const char *name)
 {
         struct stat st;
         char path[PATH_MAX];
@@ -293,7 +293,7 @@ static struct cpu_map *pmu_cpumask(char *name)
         return cpus;
 }
 
-static struct perf_pmu *pmu_lookup(char *name)
+static struct perf_pmu *pmu_lookup(const char *name)
 {
         struct perf_pmu *pmu;
         LIST_HEAD(format);
@@ -330,7 +330,7 @@ static struct perf_pmu *pmu_lookup(char *name)
         return pmu;
 }
 
-static struct perf_pmu *pmu_find(char *name)
+static struct perf_pmu *pmu_find(const char *name)
 {
         struct perf_pmu *pmu;
 
@@ -356,7 +356,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
         return NULL;
 }
 
-struct perf_pmu *perf_pmu__find(char *name)
+struct perf_pmu *perf_pmu__find(const char *name)
 {
         struct perf_pmu *pmu;
 
@@ -564,3 +564,76 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
         for (b = from; b <= to; b++)
                 set_bit(b, bits);
 }
+
+static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
+                          struct perf_pmu_alias *alias)
+{
+        snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+        return buf;
+}
+
+static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu,
+                             struct perf_pmu_alias *alias)
+{
+        snprintf(buf, len, "%s OR %s/%s/", alias->name, pmu->name, alias->name);
+        return buf;
+}
+
+static int cmp_string(const void *a, const void *b)
+{
+        const char * const *as = a;
+        const char * const *bs = b;
+        return strcmp(*as, *bs);
+}
+
+void print_pmu_events(const char *event_glob, bool name_only)
+{
+        struct perf_pmu *pmu;
+        struct perf_pmu_alias *alias;
+        char buf[1024];
+        int printed = 0;
+        int len, j;
+        char **aliases;
+
+        pmu = NULL;
+        len = 0;
+        while ((pmu = perf_pmu__scan(pmu)) != NULL)
+                list_for_each_entry(alias, &pmu->aliases, list)
+                        len++;
+        aliases = malloc(sizeof(char *) * len);
+        if (!aliases)
+                return;
+        pmu = NULL;
+        j = 0;
+        while ((pmu = perf_pmu__scan(pmu)) != NULL)
+                list_for_each_entry(alias, &pmu->aliases, list) {
+                        char *name = format_alias(buf, sizeof(buf), pmu, alias);
+                        bool is_cpu = !strcmp(pmu->name, "cpu");
+
+                        if (event_glob != NULL &&
+                            !(strglobmatch(name, event_glob) ||
+                              (!is_cpu && strglobmatch(alias->name,
+                                                       event_glob))))
+                                continue;
+                        aliases[j] = name;
+                        if (is_cpu && !name_only)
+                                aliases[j] = format_alias_or(buf, sizeof(buf),
+                                                              pmu, alias);
+                        aliases[j] = strdup(aliases[j]);
+                        j++;
+                }
+        len = j;
+        qsort(aliases, len, sizeof(char *), cmp_string);
+        for (j = 0; j < len; j++) {
+                if (name_only) {
+                        printf("%s ", aliases[j]);
+                        continue;
+                }
+                printf("  %-50s [Kernel PMU event]\n", aliases[j]);
+                free(aliases[j]);
+                printed++;
+        }
+        if (printed)
+                printf("\n");
+        free(aliases);
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 32fe55b659fa..6b2cbe2d4cc3 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -3,6 +3,7 @@
 
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
+#include <stdbool.h>
 
 enum {
         PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -21,7 +22,7 @@ struct perf_pmu {
         struct list_head list;
 };
 
-struct perf_pmu *perf_pmu__find(char *name);
+struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
                      struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
@@ -40,5 +41,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
+void print_pmu_events(const char *event_glob, bool name_only);
+
 int perf_pmu__test(void);
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index be0329394d56..371476cb8ddc 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -118,7 +118,6 @@ static const Dwfl_Callbacks offline_callbacks = {
 static int debuginfo__init_offline_dwarf(struct debuginfo *self,
                                          const char *path)
 {
-        Dwfl_Module *mod;
         int fd;
 
         fd = open(path, O_RDONLY);
@@ -129,11 +128,11 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *self,
         if (!self->dwfl)
                 goto error;
 
-        mod = dwfl_report_offline(self->dwfl, "", "", fd);
-        if (!mod)
+        self->mod = dwfl_report_offline(self->dwfl, "", "", fd);
+        if (!self->mod)
                 goto error;
 
-        self->dbg = dwfl_module_getdwarf(mod, &self->bias);
+        self->dbg = dwfl_module_getdwarf(self->mod, &self->bias);
         if (!self->dbg)
                 goto error;
 
@@ -676,37 +675,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 }
 
 /* Convert subprogram DIE to trace point */
-static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
-                                  bool retprobe, struct probe_trace_point *tp)
+static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
+                                  Dwarf_Addr paddr, bool retprobe,
+                                  struct probe_trace_point *tp)
 {
         Dwarf_Addr eaddr, highaddr;
-        const char *name;
-
-        /* Copy the name of probe point */
-        name = dwarf_diename(sp_die);
-        if (name) {
-                if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-                        pr_warning("Failed to get entry address of %s\n",
-                                   dwarf_diename(sp_die));
-                        return -ENOENT;
-                }
-                if (dwarf_highpc(sp_die, &highaddr) != 0) {
-                        pr_warning("Failed to get end address of %s\n",
-                                   dwarf_diename(sp_die));
-                        return -ENOENT;
-                }
-                if (paddr > highaddr) {
-                        pr_warning("Offset specified is greater than size of %s\n",
-                                   dwarf_diename(sp_die));
-                        return -EINVAL;
-                }
-                tp->symbol = strdup(name);
-                if (tp->symbol == NULL)
-                        return -ENOMEM;
-                tp->offset = (unsigned long)(paddr - eaddr);
-        } else
-                /* This function has no name. */
-                tp->offset = (unsigned long)paddr;
+        GElf_Sym sym;
+        const char *symbol;
+
+        /* Verify the address is correct */
+        if (dwarf_entrypc(sp_die, &eaddr) != 0) {
+                pr_warning("Failed to get entry address of %s\n",
+                           dwarf_diename(sp_die));
+                return -ENOENT;
+        }
+        if (dwarf_highpc(sp_die, &highaddr) != 0) {
+                pr_warning("Failed to get end address of %s\n",
+                           dwarf_diename(sp_die));
+                return -ENOENT;
+        }
+        if (paddr > highaddr) {
+                pr_warning("Offset specified is greater than size of %s\n",
+                           dwarf_diename(sp_die));
+                return -EINVAL;
+        }
+
+        /* Get an appropriate symbol from symtab */
+        symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+        if (!symbol) {
+                pr_warning("Failed to find symbol at 0x%lx\n",
+                           (unsigned long)paddr);
+                return -ENOENT;
+        }
+        tp->offset = (unsigned long)(paddr - sym.st_value);
+        tp->symbol = strdup(symbol);
+        if (!tp->symbol)
+                return -ENOMEM;
 
         /* Return probe must be on the head of a subprogram */
         if (retprobe) {
@@ -734,7 +738,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
         }
 
         /* If not a real subprogram, find a real one */
-        if (dwarf_tag(sc_die) != DW_TAG_subprogram) {
+        if (!die_is_func_def(sc_die)) {
                 if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
                         pr_warning("Failed to find probe point in any "
                                    "functions.\n");
@@ -980,12 +984,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
         struct dwarf_callback_param *param = data;
         struct probe_finder *pf = param->data;
         struct perf_probe_point *pp = &pf->pev->point;
-        Dwarf_Attribute attr;
 
         /* Check tag and diename */
-        if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
-            !die_compare_name(sp_die, pp->function) ||
-            dwarf_attr(sp_die, DW_AT_declaration, &attr))
+        if (!die_is_func_def(sp_die) ||
+            !die_compare_name(sp_die, pp->function))
                 return DWARF_CB_OK;
 
         /* Check declared file */
@@ -1151,7 +1153,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
         tev = &tf->tevs[tf->ntevs++];
 
         /* Trace point should be converted from subprogram DIE */
-        ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+        ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr,
                                      pf->pev->point.retprobe, &tev->point);
         if (ret < 0)
                 return ret;
@@ -1183,7 +1185,7 @@ int debuginfo__find_trace_events(struct debuginfo *self,
 {
         struct trace_event_finder tf = {
                         .pf = {.pev = pev, .callback = add_probe_trace_event},
-                        .max_tevs = max_tevs};
+                        .mod = self->mod, .max_tevs = max_tevs};
         int ret;
 
         /* Allocate result tevs array */
@@ -1252,7 +1254,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
         vl = &af->vls[af->nvls++];
 
         /* Trace point should be converted from subprogram DIE */
-        ret = convert_to_trace_point(&pf->sp_die, pf->addr,
+        ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr,
                                      pf->pev->point.retprobe, &vl->point);
         if (ret < 0)
                 return ret;
@@ -1291,6 +1293,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self,
 {
         struct available_var_finder af = {
                         .pf = {.pev = pev, .callback = add_available_vars},
+                        .mod = self->mod,
                         .max_vls = max_vls, .externs = externs};
         int ret;
 
@@ -1474,7 +1477,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
         return 0;
 }
 
-/* Search function from function name */
+/* Search function definition from function name */
 static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 {
         struct dwarf_callback_param *param = data;
@@ -1485,7 +1488,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
         if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
                 return DWARF_CB_OK;
 
-        if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
+        if (die_is_func_def(sp_die) &&
             die_compare_name(sp_die, lr->function)) {
                 lf->fname = dwarf_decl_file(sp_die);
                 dwarf_decl_line(sp_die, &lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 17e94d0c36f9..3b7d63018960 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -23,6 +23,7 @@ static inline int is_c_varname(const char *name)
 /* debug information structure */
 struct debuginfo {
         Dwarf           *dbg;
+        Dwfl_Module     *mod;
         Dwfl            *dwfl;
         Dwarf_Addr      bias;
 };
@@ -77,6 +78,7 @@ struct probe_finder {
 
 struct trace_event_finder {
         struct probe_finder     pf;
+        Dwfl_Module             *mod;           /* For solving symbols */
         struct probe_trace_event *tevs;         /* Found trace events */
         int                     ntevs;          /* Number of trace events */
         int                     max_tevs;       /* Max number of trace events */
@@ -84,6 +86,7 @@ struct trace_event_finder {
 
 struct available_var_finder {
         struct probe_finder     pf;
+        Dwfl_Module             *mod;           /* For solving symbols */
         struct variable_list    *vls;           /* Found variable lists */
         int                     nvls;           /* Number of variable lists */
         int                     max_vls;        /* Max no. of variable lists */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 925e0c3e6d91..71b5412bbbb9 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -8,6 +8,26 @@
 #include "cpumap.h"
 #include "thread_map.h"
 
+/*
+ * Support debug printing even though util/debug.c is not linked.  That means
+ * implementing 'verbose' and 'eprintf'.
+ */
+int verbose;
+
+int eprintf(int level, const char *fmt, ...)
+{
+        va_list args;
+        int ret = 0;
+
+        if (verbose >= level) {
+                va_start(args, fmt);
+                ret = vfprintf(stderr, fmt, args);
+                va_end(args);
+        }
+
+        return ret;
+}
+
 /* Define PyVarObject_HEAD_INIT for python 2.5 */
 #ifndef PyVarObject_HEAD_INIT
 # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
@@ -967,6 +987,7 @@ static struct {
         { "COUNT_SW_PAGE_FAULTS_MAJ",  PERF_COUNT_SW_PAGE_FAULTS_MAJ },
         { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS },
         { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS },
+        { "COUNT_SW_DUMMY",            PERF_COUNT_SW_DUMMY },
 
         { "SAMPLE_IP",        PERF_SAMPLE_IP },
         { "SAMPLE_TID",       PERF_SAMPLE_TID },
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
new file mode 100644
index 000000000000..18d73aa2f0f8
--- /dev/null
+++ b/tools/perf/util/record.c
@@ -0,0 +1,108 @@
+#include "evlist.h"
+#include "evsel.h"
+#include "cpumap.h"
+#include "parse-events.h"
+
+typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+        struct perf_evlist *evlist;
+        struct perf_evsel *evsel;
+        int err = -EAGAIN, fd;
+
+        evlist = perf_evlist__new();
+        if (!evlist)
+                return -ENOMEM;
+
+        if (parse_events(evlist, str))
+                goto out_delete;
+
+        evsel = perf_evlist__first(evlist);
+
+        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+        if (fd < 0)
+                goto out_delete;
+        close(fd);
+
+        fn(evsel);
+
+        fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+        if (fd < 0) {
+                if (errno == EINVAL)
+                        err = -EINVAL;
+                goto out_delete;
+        }
+        close(fd);
+        err = 0;
+
+out_delete:
+        perf_evlist__delete(evlist);
+        return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+        const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+        struct cpu_map *cpus;
+        int cpu, ret, i = 0;
+
+        cpus = cpu_map__new(NULL);
+        if (!cpus)
+                return false;
+        cpu = cpus->map[0];
+        cpu_map__delete(cpus);
+
+        do {
+                ret = perf_do_probe_api(fn, cpu, try[i++]);
+                if (!ret)
+                        return true;
+        } while (ret == -EAGAIN && try[i]);
+
+        return false;
+}
+
+static void perf_probe_sample_identifier(struct perf_evsel *evsel)
+{
+        evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+bool perf_can_sample_identifier(void)
+{
+        return perf_probe_api(perf_probe_sample_identifier);
+}
+
+void perf_evlist__config(struct perf_evlist *evlist,
+                        struct perf_record_opts *opts)
+{
+        struct perf_evsel *evsel;
+        bool use_sample_identifier = false;
+
+        /*
+         * Set the evsel leader links before we configure attributes,
+         * since some might depend on this info.
+         */
+        if (opts->group)
+                perf_evlist__set_leader(evlist);
+
+        if (evlist->cpus->map[0] < 0)
+                opts->no_inherit = true;
+
+        list_for_each_entry(evsel, &evlist->entries, node)
+                perf_evsel__config(evsel, opts);
+
+        if (evlist->nr_entries > 1) {
+                struct perf_evsel *first = perf_evlist__first(evlist);
+
+                list_for_each_entry(evsel, &evlist->entries, node) {
+                        if (evsel->attr.sample_type == first->attr.sample_type)
+                                continue;
+                        use_sample_identifier = perf_can_sample_identifier();
+                        break;
+                }
+                list_for_each_entry(evsel, &evlist->entries, node)
+                        perf_evsel__set_sample_id(evsel, use_sample_identifier);
+        }
+
+        perf_evlist__set_id_pos(evlist);
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index eacec859f299..a85e4ae5f3ac 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -261,7 +261,8 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
                                     struct perf_sample *sample,
                                     struct perf_evsel *evsel,
                                     struct machine *machine __maybe_unused,
-                                    struct addr_location *al)
+                                    struct thread *thread,
+                                        struct addr_location *al)
 {
         struct format_field *field;
         static char handler[256];
@@ -272,7 +273,6 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
         int cpu = sample->cpu;
         void *data = sample->raw_data;
         unsigned long long nsecs = sample->time;
-        struct thread *thread = al->thread;
         char *comm = thread->comm;
 
         dSP;
@@ -351,7 +351,8 @@ static void perl_process_event_generic(union perf_event *event,
                                        struct perf_sample *sample,
                                        struct perf_evsel *evsel,
                                        struct machine *machine __maybe_unused,
-                                       struct addr_location *al __maybe_unused)
+                                       struct thread *thread __maybe_unused,
+                                           struct addr_location *al __maybe_unused)
 {
         dSP;
 
@@ -377,10 +378,11 @@ static void perl_process_event(union perf_event *event,
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
                                struct machine *machine,
-                               struct addr_location *al)
+                               struct thread *thread,
+                                   struct addr_location *al)
 {
-        perl_process_tracepoint(event, sample, evsel, machine, al);
-        perl_process_event_generic(event, sample, evsel, machine, al);
+        perl_process_tracepoint(event, sample, evsel, machine, thread, al);
+        perl_process_event_generic(event, sample, evsel, machine, thread, al);
 }
 
 static void run_start_sub(void)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index e87aa5d9696b..cc75a3cef388 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -225,6 +225,7 @@ static void python_process_tracepoint(union perf_event *perf_event
                                  struct perf_sample *sample,
                                  struct perf_evsel *evsel,
                                  struct machine *machine __maybe_unused,
+                                 struct thread *thread,
                                  struct addr_location *al)
 {
         PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
@@ -238,7 +239,6 @@ static void python_process_tracepoint(union perf_event *perf_event
         int cpu = sample->cpu;
         void *data = sample->raw_data;
         unsigned long long nsecs = sample->time;
-        struct thread *thread = al->thread;
         char *comm = thread->comm;
 
         t = PyTuple_New(MAX_FIELDS);
@@ -345,12 +345,12 @@ static void python_process_general_event(union perf_event *perf_event
                                          struct perf_sample *sample,
                                          struct perf_evsel *evsel,
                                          struct machine *machine __maybe_unused,
+                                         struct thread *thread,
                                          struct addr_location *al)
 {
         PyObject *handler, *retval, *t, *dict;
         static char handler_name[64];
         unsigned n = 0;
-        struct thread *thread = al->thread;
 
         /*
          * Use the MAX_FIELDS to make the function expandable, though
@@ -404,17 +404,18 @@ static void python_process_event(union perf_event *perf_event,
                                  struct perf_sample *sample,
                                  struct perf_evsel *evsel,
                                  struct machine *machine,
+                                 struct thread *thread,
                                  struct addr_location *al)
 {
         switch (evsel->attr.type) {
         case PERF_TYPE_TRACEPOINT:
                 python_process_tracepoint(perf_event, sample, evsel,
-                                          machine, al);
+                                          machine, thread, al);
                 break;
         /* Reserve for future process_hw/sw/raw APIs */
         default:
                 python_process_general_event(perf_event, sample, evsel,
-                                             machine, al);
+                                             machine, thread, al);
         }
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cf1fe01b7e89..70ffa41518f3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <traceevent/event-parse.h>
 
 #include <byteswap.h>
 #include <unistd.h>
@@ -12,7 +13,6 @@
 #include "sort.h"
 #include "util.h"
 #include "cpumap.h"
-#include "event-parse.h"
 #include "perf_regs.h"
 #include "vdso.h"
 
@@ -24,7 +24,7 @@ static int perf_session__open(struct perf_session *self, bool force)
                 self->fd_pipe = true;
                 self->fd = STDIN_FILENO;
 
-                if (perf_session__read_header(self, self->fd) < 0)
+                if (perf_session__read_header(self) < 0)
                         pr_err("incompatible file format (rerun with -v to learn more)");
 
                 return 0;
@@ -56,7 +56,7 @@ static int perf_session__open(struct perf_session *self, bool force)
                 goto out_close;
         }
 
-        if (perf_session__read_header(self, self->fd) < 0) {
+        if (perf_session__read_header(self) < 0) {
                 pr_err("incompatible file format (rerun with -v to learn more)");
                 goto out_close;
         }
@@ -71,6 +71,11 @@ static int perf_session__open(struct perf_session *self, bool force)
                 goto out_close;
         }
 
+        if (!perf_evlist__valid_read_format(self->evlist)) {
+                pr_err("non matching read_format");
+                goto out_close;
+        }
+
         self->size = input_stat.st_size;
         return 0;
 
@@ -193,7 +198,9 @@ void perf_session__delete(struct perf_session *self)
         vdso__exit();
 }
 
-static int process_event_synth_tracing_data_stub(union perf_event *event
+static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+                                                 __maybe_unused,
+                                                 union perf_event *event
                                                  __maybe_unused,
                                                  struct perf_session *session
                                                 __maybe_unused)
@@ -202,7 +209,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event
         return 0;
 }
 
-static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
+static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
+                                         union perf_event *event __maybe_unused,
                                          struct perf_evlist **pevlist
                                          __maybe_unused)
 {
@@ -238,18 +246,11 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-static int process_event_type_stub(struct perf_tool *tool __maybe_unused,
-                                   union perf_event *event __maybe_unused)
-{
-        dump_printf(": unhandled!\n");
-        return 0;
-}
-
 static int process_finished_round(struct perf_tool *tool,
                                   union perf_event *event,
                                   struct perf_session *session);
 
-static void perf_tool__fill_defaults(struct perf_tool *tool)
+void perf_tool__fill_defaults(struct perf_tool *tool)
 {
         if (tool->sample == NULL)
                 tool->sample = process_event_sample_stub;
@@ -271,8 +272,6 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->unthrottle = process_event_stub;
         if (tool->attr == NULL)
                 tool->attr = process_event_synth_attr_stub;
-        if (tool->event_type == NULL)
-                tool->event_type = process_event_type_stub;
         if (tool->tracing_data == NULL)
                 tool->tracing_data = process_event_synth_tracing_data_stub;
         if (tool->build_id == NULL)
@@ -352,6 +351,25 @@ static void perf_event__mmap_swap(union perf_event *event,
         }
 }
 
+static void perf_event__mmap2_swap(union perf_event *event,
+                                  bool sample_id_all)
+{
+        event->mmap2.pid   = bswap_32(event->mmap2.pid);
+        event->mmap2.tid   = bswap_32(event->mmap2.tid);
+        event->mmap2.start = bswap_64(event->mmap2.start);
+        event->mmap2.len   = bswap_64(event->mmap2.len);
+        event->mmap2.pgoff = bswap_64(event->mmap2.pgoff);
+        event->mmap2.maj   = bswap_32(event->mmap2.maj);
+        event->mmap2.min   = bswap_32(event->mmap2.min);
+        event->mmap2.ino   = bswap_64(event->mmap2.ino);
+
+        if (sample_id_all) {
+                void *data = &event->mmap2.filename;
+
+                data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+                swap_sample_id_all(event, data);
+        }
+}
 static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
 {
         event->fork.pid  = bswap_32(event->fork.pid);
@@ -456,6 +474,7 @@ typedef void (*perf_event__swap_op)(union perf_event *event,
 
 static perf_event__swap_op perf_event__swap_ops[] = {
         [PERF_RECORD_MMAP]                = perf_event__mmap_swap,
+        [PERF_RECORD_MMAP2]               = perf_event__mmap2_swap,
         [PERF_RECORD_COMM]                = perf_event__comm_swap,
         [PERF_RECORD_FORK]                = perf_event__task_swap,
         [PERF_RECORD_EXIT]                = perf_event__task_swap,
@@ -496,7 +515,7 @@ static int perf_session_deliver_event(struct perf_session *session,
                                       u64 file_offset);
 
 static int flush_sample_queue(struct perf_session *s,
-                               struct perf_tool *tool)
+                       struct perf_tool *tool)
 {
         struct ordered_samples *os = &s->ordered_samples;
         struct list_head *head = &os->samples;
@@ -505,12 +524,16 @@ static int flush_sample_queue(struct perf_session *s,
         u64 limit = os->next_flush;
         u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
         unsigned idx = 0, progress_next = os->nr_samples / 16;
+        bool show_progress = limit == ULLONG_MAX;
         int ret;
 
         if (!tool->ordered_samples || !limit)
                 return 0;
 
         list_for_each_entry_safe(iter, tmp, head, list) {
+                if (session_done())
+                        return 0;
+
                 if (iter->timestamp > limit)
                         break;
 
@@ -527,7 +550,7 @@ static int flush_sample_queue(struct perf_session *s,
                 os->last_flush = iter->timestamp;
                 list_del(&iter->list);
                 list_add(&iter->list, &os->sample_cache);
-                if (++idx >= progress_next) {
+                if (show_progress && (++idx >= progress_next)) {
                         progress_next += os->nr_samples / 16;
                         ui_progress__update(idx, os->nr_samples,
                                             "Processing time ordered events...");
@@ -644,7 +667,7 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s)
 
 #define MAX_SAMPLE_BUFFER       (64 * 1024 / sizeof(struct sample_queue))
 
-static int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+int perf_session_queue_event(struct perf_session *s, union perf_event *event,
                                     struct perf_sample *sample, u64 file_offset)
 {
         struct ordered_samples *os = &s->ordered_samples;
@@ -740,7 +763,7 @@ static void perf_session__print_tstamp(struct perf_session *session,
                                        union perf_event *event,
                                        struct perf_sample *sample)
 {
-        u64 sample_type = perf_evlist__sample_type(session->evlist);
+        u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
 
         if (event->header.type != PERF_RECORD_SAMPLE &&
             !perf_evlist__sample_id_all(session->evlist)) {
@@ -755,6 +778,36 @@ static void perf_session__print_tstamp(struct perf_session *session,
                 printf("%" PRIu64 " ", sample->time);
 }
 
+static void sample_read__printf(struct perf_sample *sample, u64 read_format)
+{
+        printf("... sample_read:\n");
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                printf("...... time enabled %016" PRIx64 "\n",
+                       sample->read.time_enabled);
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                printf("...... time running %016" PRIx64 "\n",
+                       sample->read.time_running);
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                u64 i;
+
+                printf(".... group nr %" PRIu64 "\n", sample->read.group.nr);
+
+                for (i = 0; i < sample->read.group.nr; i++) {
+                        struct sample_read_value *value;
+
+                        value = &sample->read.group.values[i];
+                        printf("..... id %016" PRIx64
+                               ", value %016" PRIx64 "\n",
+                               value->id, value->value);
+                }
+        } else
+                printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n",
+                        sample->read.one.id, sample->read.one.value);
+}
+
 static void dump_event(struct perf_session *session, union perf_event *event,
                        u64 file_offset, struct perf_sample *sample)
 {
@@ -804,11 +857,15 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
         if (sample_type & PERF_SAMPLE_DATA_SRC)
                 printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
+
+        if (sample_type & PERF_SAMPLE_READ)
+                sample_read__printf(sample, evsel->attr.read_format);
 }
 
 static struct machine *
         perf_session__find_machine_for_cpumode(struct perf_session *session,
-                                               union perf_event *event)
+                                               union perf_event *event,
+                                               struct perf_sample *sample)
 {
         const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -817,10 +874,11 @@ static struct machine *
              (cpumode == PERF_RECORD_MISC_GUEST_USER))) {
                 u32 pid;
 
-                if (event->header.type == PERF_RECORD_MMAP)
+                if (event->header.type == PERF_RECORD_MMAP
+                    || event->header.type == PERF_RECORD_MMAP2)
                         pid = event->mmap.pid;
                 else
-                        pid = event->ip.pid;
+                        pid = sample->pid;
 
                 return perf_session__findnew_machine(session, pid);
         }
@@ -828,6 +886,75 @@ static struct machine *
         return &session->machines.host;
 }
 
+static int deliver_sample_value(struct perf_session *session,
+                                struct perf_tool *tool,
+                                union perf_event *event,
+                                struct perf_sample *sample,
+                                struct sample_read_value *v,
+                                struct machine *machine)
+{
+        struct perf_sample_id *sid;
+
+        sid = perf_evlist__id2sid(session->evlist, v->id);
+        if (sid) {
+                sample->id     = v->id;
+                sample->period = v->value - sid->period;
+                sid->period    = v->value;
+        }
+
+        if (!sid || sid->evsel == NULL) {
+                ++session->stats.nr_unknown_id;
+                return 0;
+        }
+
+        return tool->sample(tool, event, sample, sid->evsel, machine);
+}
+
+static int deliver_sample_group(struct perf_session *session,
+                                struct perf_tool *tool,
+                                union  perf_event *event,
+                                struct perf_sample *sample,
+                                struct machine *machine)
+{
+        int ret = -EINVAL;
+        u64 i;
+
+        for (i = 0; i < sample->read.group.nr; i++) {
+                ret = deliver_sample_value(session, tool, event, sample,
+                                           &sample->read.group.values[i],
+                                           machine);
+                if (ret)
+                        break;
+        }
+
+        return ret;
+}
+
+static int
+perf_session__deliver_sample(struct perf_session *session,
+                             struct perf_tool *tool,
+                             union  perf_event *event,
+                             struct perf_sample *sample,
+                             struct perf_evsel *evsel,
+                             struct machine *machine)
+{
+        /* We know evsel != NULL. */
+        u64 sample_type = evsel->attr.sample_type;
+        u64 read_format = evsel->attr.read_format;
+
+        /* Standard sample delievery. */
+        if (!(sample_type & PERF_SAMPLE_READ))
+                return tool->sample(tool, event, sample, evsel, machine);
+
+        /* For PERF_SAMPLE_READ we have either single or group mode. */
+        if (read_format & PERF_FORMAT_GROUP)
+                return deliver_sample_group(session, tool, event, sample,
+                                            machine);
+        else
+                return deliver_sample_value(session, tool, event, sample,
+                                            &sample->read.one, machine);
+}
+
 static int perf_session_deliver_event(struct perf_session *session,
                                       union perf_event *event,
                                       struct perf_sample *sample,
@@ -857,7 +984,8 @@ static int perf_session_deliver_event(struct perf_session *session,
                 hists__inc_nr_events(&evsel->hists, event->header.type);
         }
 
-        machine = perf_session__find_machine_for_cpumode(session, event);
+        machine = perf_session__find_machine_for_cpumode(session, event,
+                                                         sample);
 
         switch (event->header.type) {
         case PERF_RECORD_SAMPLE:
@@ -870,9 +998,12 @@ static int perf_session_deliver_event(struct perf_session *session,
                         ++session->stats.nr_unprocessable_samples;
                         return 0;
                 }
-                return tool->sample(tool, event, sample, evsel, machine);
+                return perf_session__deliver_sample(session, tool, event,
+                                                    sample, evsel, machine);
         case PERF_RECORD_MMAP:
                 return tool->mmap(tool, event, sample, machine);
+        case PERF_RECORD_MMAP2:
+                return tool->mmap2(tool, event, sample, machine);
         case PERF_RECORD_COMM:
                 return tool->comm(tool, event, sample, machine);
         case PERF_RECORD_FORK:
@@ -895,22 +1026,6 @@ static int perf_session_deliver_event(struct perf_session *session,
         }
 }
 
-static int perf_session__preprocess_sample(struct perf_session *session,
-                                           union perf_event *event, struct perf_sample *sample)
-{
-        if (event->header.type != PERF_RECORD_SAMPLE ||
-            !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
-                return 0;
-
-        if (!ip_callchain__valid(sample->callchain, event)) {
-                pr_debug("call-chain problem with event, skipping it.\n");
-                ++session->stats.nr_invalid_chains;
-                session->stats.total_invalid_chains += sample->period;
-                return -EINVAL;
-        }
-        return 0;
-}
-
 static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
                                             struct perf_tool *tool, u64 file_offset)
 {
@@ -921,16 +1036,14 @@ static int perf_session__process_user_event(struct perf_session *session, union
         /* These events are processed right away */
         switch (event->header.type) {
         case PERF_RECORD_HEADER_ATTR:
-                err = tool->attr(event, &session->evlist);
+                err = tool->attr(tool, event, &session->evlist);
                 if (err == 0)
                         perf_session__set_id_hdr_size(session);
                 return err;
-        case PERF_RECORD_HEADER_EVENT_TYPE:
-                return tool->event_type(tool, event);
         case PERF_RECORD_HEADER_TRACING_DATA:
                 /* setup for reading amidst mmap */
                 lseek(session->fd, file_offset, SEEK_SET);
-                return tool->tracing_data(event, session);
+                return tool->tracing_data(tool, event, session);
         case PERF_RECORD_HEADER_BUILD_ID:
                 return tool->build_id(tool, event, session);
         case PERF_RECORD_FINISHED_ROUND:
@@ -975,10 +1088,6 @@ static int perf_session__process_event(struct perf_session *session,
         if (ret)
                 return ret;
 
-        /* Preprocess sample records - precheck callchains */
-        if (perf_session__preprocess_sample(session, event, &sample))
-                return 0;
-
         if (tool->ordered_samples) {
                 ret = perf_session_queue_event(session, event, &sample,
                                                file_offset);
@@ -999,7 +1108,7 @@ void perf_event_header__bswap(struct perf_event_header *self)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-        return machine__findnew_thread(&session->machines.host, pid);
+        return machine__findnew_thread(&session->machines.host, 0, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)
@@ -1054,7 +1163,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
         }
 }
 
-#define session_done()  (*(volatile int *)(&session_done))
 volatile int session_done;
 
 static int __perf_session__process_pipe_events(struct perf_session *self,
@@ -1091,8 +1199,10 @@ more:
                 perf_event_header__bswap(&event->header);
 
         size = event->header.size;
-        if (size == 0)
-                size = 8;
+        if (size < sizeof(struct perf_event_header)) {
+                pr_err("bad event header size\n");
+                goto out_err;
+        }
 
         if (size > cur_size) {
                 void *new = realloc(buf, size);
@@ -1161,8 +1271,12 @@ fetch_mmaped_event(struct perf_session *session,
         if (session->header.needs_swap)
                 perf_event_header__bswap(&event->header);
 
-        if (head + event->header.size > mmap_size)
+        if (head + event->header.size > mmap_size) {
+                /* We're not fetching the event so swap back again */
+                if (session->header.needs_swap)
+                        perf_event_header__bswap(&event->header);
                 return NULL;
+        }
 
         return event;
 }
@@ -1242,7 +1356,7 @@ more:
 
         size = event->header.size;
 
-        if (size == 0 ||
+        if (size < sizeof(struct perf_event_header) ||
             perf_session__process_event(session, event, tool, file_pos) < 0) {
                 pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
                        file_offset + head, event->header.size,
@@ -1260,10 +1374,13 @@ more:
                                     "Processing events...");
         }
 
+        err = 0;
+        if (session_done())
+                goto out_err;
+
         if (file_pos < file_size)
                 goto more;
 
-        err = 0;
         /* do the final flush for ordered samples */
         session->ordered_samples.next_flush = ULLONG_MAX;
         err = flush_sample_queue(session, tool);
@@ -1295,12 +1412,15 @@ int perf_session__process_events(struct perf_session *self,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-        if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
-                pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
-                return false;
+        struct perf_evsel *evsel;
+
+        list_for_each_entry(evsel, &session->evlist->entries, node) {
+                if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
+                        return true;
         }
 
-        return true;
+        pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
+        return false;
 }
 
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
@@ -1383,13 +1503,18 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
                           struct perf_sample *sample, struct machine *machine,
-                          int print_sym, int print_dso, int print_symoffset)
+                          unsigned int print_opts, unsigned int stack_depth)
 {
         struct addr_location al;
         struct callchain_cursor_node *node;
-
-        if (perf_event__preprocess_sample(event, machine, &al, sample,
-                                          NULL) < 0) {
+        int print_ip = print_opts & PRINT_IP_OPT_IP;
+        int print_sym = print_opts & PRINT_IP_OPT_SYM;
+        int print_dso = print_opts & PRINT_IP_OPT_DSO;
+        int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
+        int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+        char s = print_oneline ? ' ' : '\t';
+
+        if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
                 error("problem processing %d event, skipping it.\n",
                         event->header.type);
                 return;
@@ -1397,37 +1522,50 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 
         if (symbol_conf.use_callchain && sample->callchain) {
 
-
                 if (machine__resolve_callchain(machine, evsel, al.thread,
-                                               sample, NULL) != 0) {
+                                               sample, NULL, NULL) != 0) {
                         if (verbose)
                                 error("Failed to resolve callchain. Skipping\n");
                         return;
                 }
                 callchain_cursor_commit(&callchain_cursor);
 
-                while (1) {
+                while (stack_depth) {
                         node = callchain_cursor_current(&callchain_cursor);
                         if (!node)
                                 break;
 
-                        printf("\t%16" PRIx64, node->ip);
+                        if (print_ip)
+                                printf("%c%16" PRIx64, s, node->ip);
+
                         if (print_sym) {
                                 printf(" ");
-                                symbol__fprintf_symname(node->sym, stdout);
+                                if (print_symoffset) {
+                                        al.addr = node->ip;
+                                        al.map  = node->map;
+                                        symbol__fprintf_symname_offs(node->sym, &al, stdout);
+                                } else
+                                        symbol__fprintf_symname(node->sym, stdout);
                         }
+
                         if (print_dso) {
                                 printf(" (");
                                 map__fprintf_dsoname(node->map, stdout);
                                 printf(")");
                         }
-                        printf("\n");
+
+                        if (!print_oneline)
+                                printf("\n");
 
                         callchain_cursor_advance(&callchain_cursor);
+
+                        stack_depth--;
                 }
 
         } else {
-                printf("%16" PRIx64, sample->ip);
+                if (print_ip)
+                        printf("%16" PRIx64, sample->ip);
+
                 if (print_sym) {
                         printf(" ");
                         if (print_symoffset)
@@ -1510,52 +1648,26 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
                                              const struct perf_evsel_str_handler *assocs,
                                              size_t nr_assocs)
 {
-        struct perf_evlist *evlist = session->evlist;
-        struct event_format *format;
         struct perf_evsel *evsel;
-        char *tracepoint, *name;
         size_t i;
         int err;
 
         for (i = 0; i < nr_assocs; i++) {
-                err = -ENOMEM;
-                tracepoint = strdup(assocs[i].name);
-                if (tracepoint == NULL)
-                        goto out;
-
-                err = -ENOENT;
-                name = strchr(tracepoint, ':');
-                if (name == NULL)
-                        goto out_free;
-
-                *name++ = '\0';
-                format = pevent_find_event_by_name(session->pevent,
-                                                   tracepoint, name);
-                if (format == NULL) {
-                        /*
-                         * Adding a handler for an event not in the session,
-                         * just ignore it.
-                         */
-                        goto next;
-                }
-
-                evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id);
+                /*
+                 * Adding a handler for an event not in the session,
+                 * just ignore it.
+                 */
+                evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name);
                 if (evsel == NULL)
-                        goto next;
+                        continue;
 
                 err = -EEXIST;
                 if (evsel->handler.func != NULL)
-                        goto out_free;
+                        goto out;
                 evsel->handler.func = assocs[i].handler;
-next:
-                free(tracepoint);
         }
 
         err = 0;
 out:
         return err;
-
-out_free:
-        free(tracepoint);
-        goto out;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index f3b235ec7bf4..04bf7373a7e5 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -37,11 +37,16 @@ struct perf_session {
         int                     fd;
         bool                    fd_pipe;
         bool                    repipe;
-        char                    *cwd;
         struct ordered_samples  ordered_samples;
         char                    filename[1];
 };
 
+#define PRINT_IP_OPT_IP         (1<<0)
+#define PRINT_IP_OPT_SYM                (1<<1)
+#define PRINT_IP_OPT_DSO                (1<<2)
+#define PRINT_IP_OPT_SYMOFFSET  (1<<3)
+#define PRINT_IP_OPT_ONELINE    (1<<4)
+
 struct perf_tool;
 
 struct perf_session *perf_session__new(const char *filename, int mode,
@@ -57,6 +62,11 @@ int __perf_session__process_events(struct perf_session *self,
 int perf_session__process_events(struct perf_session *self,
                                  struct perf_tool *tool);
 
+int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+                             struct perf_sample *sample, u64 file_offset);
+
+void perf_tool__fill_defaults(struct perf_tool *tool);
+
 int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel,
                                     struct thread *thread,
                                     struct ip_callchain *chain,
@@ -99,7 +109,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
                           struct perf_sample *sample, struct machine *machine,
-                          int print_sym, int print_dso, int print_symoffset);
+                          unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
                              const char *cpu_list, unsigned long *cpu_bitmap);
@@ -114,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 #define perf_session__set_tracepoints_handlers(session, array) \
         __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
+
+extern volatile int session_done;
+
+#define session_done()  (*(volatile int *)(&session_done))
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 313a5a730112..5f118a089519 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -7,6 +7,8 @@ const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char      *parent_pattern = default_parent_pattern;
 const char      default_sort_order[] = "comm,dso,symbol";
 const char      *sort_order = default_sort_order;
+regex_t         ignore_callees_regex;
+int             have_ignore_callees = 0;
 int             sort__need_collapse = 0;
 int             sort__has_parent = 0;
 int             sort__has_sym = 0;
@@ -55,14 +57,14 @@ static int64_t cmp_null(void *l, void *r)
 static int64_t
 sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        return right->thread->pid - left->thread->pid;
+        return right->thread->tid - left->thread->tid;
 }
 
 static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
                                        size_t size, unsigned int width)
 {
         return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-                              self->thread->comm ?: "", self->thread->pid);
+                              self->thread->comm ?: "", self->thread->tid);
 }
 
 struct sort_entry sort_thread = {
@@ -77,7 +79,7 @@ struct sort_entry sort_thread = {
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        return right->thread->pid - left->thread->pid;
+        return right->thread->tid - left->thread->tid;
 }
 
 static int64_t
@@ -872,6 +874,8 @@ static struct sort_dimension common_sort_dimensions[] = {
         DIM(SORT_PARENT, "parent", sort_parent),
         DIM(SORT_CPU, "cpu", sort_cpu),
         DIM(SORT_SRCLINE, "srcline", sort_srcline),
+        DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+        DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 };
 
 #undef DIM
@@ -891,8 +895,6 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 #define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
 
 static struct sort_dimension memory_sort_dimensions[] = {
-        DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
-        DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
         DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
         DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
         DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 45ac84c1e037..4e80dbd271e7 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -29,6 +29,8 @@ extern const char *sort_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
 extern const char default_sort_order[];
+extern regex_t ignore_callees_regex;
+extern int have_ignore_callees;
 extern int sort__need_collapse;
 extern int sort__has_parent;
 extern int sort__has_sym;
@@ -87,6 +89,9 @@ struct hist_entry {
 
         struct hist_entry_diff  diff;
 
+        /* We are added by hists__add_dummy_entry. */
+        bool                    dummy;
+
         /* XXX These two should move to some tree widget lib */
         u16                     row_offset;
         u16                     nr_rows;
@@ -138,6 +143,8 @@ enum sort_type {
         SORT_PARENT,
         SORT_CPU,
         SORT_SRCLINE,
+        SORT_LOCAL_WEIGHT,
+        SORT_GLOBAL_WEIGHT,
 
         /* branch stack specific sort keys */
         __SORT_BRANCH_STACK,
@@ -149,9 +156,7 @@ enum sort_type {
 
         /* memory mode specific sort keys */
         __SORT_MEMORY_MODE,
-        SORT_LOCAL_WEIGHT = __SORT_MEMORY_MODE,
-        SORT_GLOBAL_WEIGHT,
-        SORT_MEM_DADDR_SYMBOL,
+        SORT_MEM_DADDR_SYMBOL = __SORT_MEMORY_MODE,
         SORT_MEM_DADDR_DSO,
         SORT_MEM_LOCKED,
         SORT_MEM_TLB,
@@ -183,4 +188,6 @@ int setup_sorting(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
 
+int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
+
 #endif  /* __PERF_SORT_H */
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 7c59c28afcc5..6506b3dfb605 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -10,6 +10,12 @@ void update_stats(struct stats *stats, u64 val)
         delta = val - stats->mean;
         stats->mean += delta / stats->n;
         stats->M2 += delta*(val - stats->mean);
+
+        if (val > stats->max)
+                stats->max = val;
+
+        if (val < stats->min)
+                stats->min = val;
 }
 
 double avg_stats(struct stats *stats)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 588367c3c767..ae8ccd7227cf 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -6,6 +6,7 @@
 struct stats
 {
         double n, mean, M2;
+        u64 max, min;
 };
 
 void update_stats(struct stats *stats, u64 val);
@@ -13,4 +14,12 @@ double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
 double rel_stddev_stats(double stddev, double avg);
 
+static inline void init_stats(struct stats *stats)
+{
+        stats->n    = 0.0;
+        stats->mean = 0.0;
+        stats->M2   = 0.0;
+        stats->min  = (u64) -1;
+        stats->max  = 0;
+}
 #endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 29c7b2cb2521..f0b0c008c507 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -387,3 +387,27 @@ void *memdup(const void *src, size_t len)
 
         return p;
 }
+
+/**
+ * str_append - reallocate string and append another
+ * @s: pointer to string pointer
+ * @len: pointer to len (initialized)
+ * @a: string to append.
+ */
+int str_append(char **s, int *len, const char *a)
+{
+        int olen = *s ? strlen(*s) : 0;
+        int nlen = olen + strlen(a) + 1;
+        if (*len < nlen) {
+                *len = *len * 2;
+                if (*len < nlen)
+                        *len = nlen;
+                *s = realloc(*s, *len);
+                if (!*s)
+                        return -ENOMEM;
+                if (olen == 0)
+                        **s = 0;
+        }
+        strcat(*s, a);
+        return 0;
+}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4b12bf850325..a9c829be5216 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -8,6 +8,22 @@
 #include "symbol.h"
 #include "debug.h"
 
+#ifndef HAVE_ELF_GETPHDRNUM
+static int elf_getphdrnum(Elf *elf, size_t *dst)
+{
+        GElf_Ehdr gehdr;
+        GElf_Ehdr *ehdr;
+
+        ehdr = gelf_getehdr(elf, &gehdr);
+        if (!ehdr)
+                return -1;
+
+        *dst = ehdr->e_phnum;
+
+        return 0;
+}
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
@@ -599,11 +615,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
         if (dso->kernel == DSO_TYPE_USER) {
                 GElf_Shdr shdr;
                 ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+                                ehdr.e_type == ET_REL ||
                                 elf_section_by_name(elf, &ehdr, &shdr,
                                                      ".gnu.prelink_undo",
                                                      NULL) != NULL);
         } else {
-                ss->adjust_symbols = 0;
+                ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
+                                     ehdr.e_type == ET_REL;
         }
 
         ss->name   = strdup(name);
@@ -624,6 +642,37 @@ out_close:
         return err;
 }
 
+/**
+ * ref_reloc_sym_not_found - has kernel relocation symbol been found.
+ * @kmap: kernel maps and relocation reference symbol
+ *
+ * This function returns %true if we are dealing with the kernel maps and the
+ * relocation reference symbol has not yet been found.  Otherwise %false is
+ * returned.
+ */
+static bool ref_reloc_sym_not_found(struct kmap *kmap)
+{
+        return kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
+               !kmap->ref_reloc_sym->unrelocated_addr;
+}
+
+/**
+ * ref_reloc - kernel relocation offset.
+ * @kmap: kernel maps and relocation reference symbol
+ *
+ * This function returns the offset of kernel addresses as determined by using
+ * the relocation reference symbol i.e. if the kernel has not been relocated
+ * then the return value is zero.
+ */
+static u64 ref_reloc(struct kmap *kmap)
+{
+        if (kmap && kmap->ref_reloc_sym &&
+            kmap->ref_reloc_sym->unrelocated_addr)
+                return kmap->ref_reloc_sym->addr -
+                       kmap->ref_reloc_sym->unrelocated_addr;
+        return 0;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map,
                   struct symsrc *syms_ss, struct symsrc *runtime_ss,
                   symbol_filter_t filter, int kmodule)
@@ -642,8 +691,17 @@ int dso__load_sym(struct dso *dso, struct map *map,
         Elf_Scn *sec, *sec_strndx;
         Elf *elf;
         int nr = 0;
+        bool remap_kernel = false, adjust_kernel_syms = false;
 
         dso->symtab_type = syms_ss->type;
+        dso->rel = syms_ss->ehdr.e_type == ET_REL;
+
+        /*
+         * Modules may already have symbols from kallsyms, but those symbols
+         * have the wrong values for the dso maps, so remove them.
+         */
+        if (kmodule && syms_ss->symtab)
+                symbols__delete(&dso->symbols[map->type]);
 
         if (!syms_ss->symtab) {
                 syms_ss->symtab  = syms_ss->dynsym;
@@ -681,7 +739,31 @@ int dso__load_sym(struct dso *dso, struct map *map,
         nr_syms = shdr.sh_size / shdr.sh_entsize;
 
         memset(&sym, 0, sizeof(sym));
-        dso->adjust_symbols = runtime_ss->adjust_symbols;
+
+        /*
+         * The kernel relocation symbol is needed in advance in order to adjust
+         * kernel maps correctly.
+         */
+        if (ref_reloc_sym_not_found(kmap)) {
+                elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
+                        const char *elf_name = elf_sym__name(&sym, symstrs);
+
+                        if (strcmp(elf_name, kmap->ref_reloc_sym->name))
+                                continue;
+                        kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+                        break;
+                }
+        }
+
+        dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
+        /*
+         * Initial kernel and module mappings do not map to the dso.  For
+         * function mappings, flag the fixups.
+         */
+        if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
+                remap_kernel = true;
+                adjust_kernel_syms = dso->adjust_symbols;
+        }
         elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
                 struct symbol *f;
                 const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -690,10 +772,6 @@ int dso__load_sym(struct dso *dso, struct map *map,
                 const char *section_name;
                 bool used_opd = false;
 
-                if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
-                    strcmp(elf_name, kmap->ref_reloc_sym->name) == 0)
-                        kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
-
                 if (!is_label && !elf_sym__is_a(&sym, map->type))
                         continue;
 
@@ -745,20 +823,55 @@ int dso__load_sym(struct dso *dso, struct map *map,
                     (sym.st_value & 1))
                         --sym.st_value;
 
-                if (dso->kernel != DSO_TYPE_USER || kmodule) {
+                if (dso->kernel || kmodule) {
                         char dso_name[PATH_MAX];
 
+                        /* Adjust symbol to map to file offset */
+                        if (adjust_kernel_syms)
+                                sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+
                         if (strcmp(section_name,
                                    (curr_dso->short_name +
                                     dso->short_name_len)) == 0)
                                 goto new_symbol;
 
                         if (strcmp(section_name, ".text") == 0) {
+                                /*
+                                 * The initial kernel mapping is based on
+                                 * kallsyms and identity maps.  Overwrite it to
+                                 * map to the kernel dso.
+                                 */
+                                if (remap_kernel && dso->kernel) {
+                                        remap_kernel = false;
+                                        map->start = shdr.sh_addr +
+                                                     ref_reloc(kmap);
+                                        map->end = map->start + shdr.sh_size;
+                                        map->pgoff = shdr.sh_offset;
+                                        map->map_ip = map__map_ip;
+                                        map->unmap_ip = map__unmap_ip;
+                                        /* Ensure maps are correctly ordered */
+                                        map_groups__remove(kmap->kmaps, map);
+                                        map_groups__insert(kmap->kmaps, map);
+                                }
+
+                                /*
+                                 * The initial module mapping is based on
+                                 * /proc/modules mapped to offset zero.
+                                 * Overwrite it to map to the module dso.
+                                 */
+                                if (remap_kernel && kmodule) {
+                                        remap_kernel = false;
+                                        map->pgoff = shdr.sh_offset;
+                                }
+
                                 curr_map = map;
                                 curr_dso = dso;
                                 goto new_symbol;
                         }
 
+                        if (!kmap)
+                                goto new_symbol;
+
                         snprintf(dso_name, sizeof(dso_name),
                                  "%s%s", dso->short_name, section_name);
 
@@ -781,8 +894,16 @@ int dso__load_sym(struct dso *dso, struct map *map,
                                         dso__delete(curr_dso);
                                         goto out_elf_end;
                                 }
-                                curr_map->map_ip = identity__map_ip;
-                                curr_map->unmap_ip = identity__map_ip;
+                                if (adjust_kernel_syms) {
+                                        curr_map->start = shdr.sh_addr +
+                                                          ref_reloc(kmap);
+                                        curr_map->end = curr_map->start +
+                                                        shdr.sh_size;
+                                        curr_map->pgoff = shdr.sh_offset;
+                                } else {
+                                        curr_map->map_ip = identity__map_ip;
+                                        curr_map->unmap_ip = identity__map_ip;
+                                }
                                 curr_dso->symtab_type = dso->symtab_type;
                                 map_groups__insert(kmap->kmaps, curr_map);
                                 dsos__add(&dso->node, curr_dso);
@@ -846,6 +967,57 @@ out_elf_end:
         return err;
 }
 
+static int elf_read_maps(Elf *elf, bool exe, mapfn_t mapfn, void *data)
+{
+        GElf_Phdr phdr;
+        size_t i, phdrnum;
+        int err;
+        u64 sz;
+
+        if (elf_getphdrnum(elf, &phdrnum))
+                return -1;
+
+        for (i = 0; i < phdrnum; i++) {
+                if (gelf_getphdr(elf, i, &phdr) == NULL)
+                        return -1;
+                if (phdr.p_type != PT_LOAD)
+                        continue;
+                if (exe) {
+                        if (!(phdr.p_flags & PF_X))
+                                continue;
+                } else {
+                        if (!(phdr.p_flags & PF_R))
+                                continue;
+                }
+                sz = min(phdr.p_memsz, phdr.p_filesz);
+                if (!sz)
+                        continue;
+                err = mapfn(phdr.p_vaddr, sz, phdr.p_offset, data);
+                if (err)
+                        return err;
+        }
+        return 0;
+}
+
+int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
+                    bool *is_64_bit)
+{
+        int err;
+        Elf *elf;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return -1;
+
+        if (is_64_bit)
+                *is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
+        err = elf_read_maps(elf, exe, mapfn, data);
+
+        elf_end(elf);
+        return err;
+}
+
 void symbol__elf_init(void)
 {
         elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index a7390cde63bc..3a802c300fc5 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -301,6 +301,13 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
         return 0;
 }
 
+int file__read_maps(int fd __maybe_unused, bool exe __maybe_unused,
+                    mapfn_t mapfn __maybe_unused, void *data __maybe_unused,
+                    bool *is_64_bit __maybe_unused)
+{
+        return -1;
+}
+
 void symbol__elf_init(void)
 {
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index d5528e1cc03a..7eb0362f4ffd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -87,6 +87,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 {
         s64 a;
         s64 b;
+        size_t na, nb;
 
         /* Prefer a symbol with non zero length */
         a = syma->end - syma->start;
@@ -120,11 +121,21 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
         else if (a > b)
                 return SYMBOL_B;
 
-        /* If all else fails, choose the symbol with the longest name */
-        if (strlen(syma->name) >= strlen(symb->name))
+        /* Choose the symbol with the longest name */
+        na = strlen(syma->name);
+        nb = strlen(symb->name);
+        if (na > nb)
                 return SYMBOL_A;
-        else
+        else if (na < nb)
+                return SYMBOL_B;
+
+        /* Avoid "SyS" kernel syscall aliases */
+        if (na >= 3 && !strncmp(syma->name, "SyS", 3))
+                return SYMBOL_B;
+        if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
                 return SYMBOL_B;
+
+        return SYMBOL_A;
 }
 
 void symbols__fixup_duplicate(struct rb_root *symbols)
@@ -248,7 +259,10 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym,
         if (sym && sym->name) {
                 length = fprintf(fp, "%s", sym->name);
                 if (al) {
-                        offset = al->addr - sym->start;
+                        if (al->addr < sym->end)
+                                offset = al->addr - sym->start;
+                        else
+                                offset = al->addr - al->map->start - sym->start;
                         length += fprintf(fp, "+0x%lx", offset);
                 }
                 return length;
@@ -316,6 +330,16 @@ static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
         return NULL;
 }
 
+static struct symbol *symbols__first(struct rb_root *symbols)
+{
+        struct rb_node *n = rb_first(symbols);
+
+        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;
@@ -386,6 +410,11 @@ struct symbol *dso__find_symbol(struct dso *dso,
         return symbols__find(&dso->symbols[type], addr);
 }
 
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+{
+        return symbols__first(&dso->symbols[type]);
+}
+
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name)
 {
@@ -522,6 +551,53 @@ static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
         return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
+static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
+                                         symbol_filter_t filter)
+{
+        struct map_groups *kmaps = map__kmap(map)->kmaps;
+        struct map *curr_map;
+        struct symbol *pos;
+        int count = 0, moved = 0;
+        struct rb_root *root = &dso->symbols[map->type];
+        struct rb_node *next = rb_first(root);
+
+        while (next) {
+                char *module;
+
+                pos = rb_entry(next, struct symbol, rb_node);
+                next = rb_next(&pos->rb_node);
+
+                module = strchr(pos->name, '\t');
+                if (module)
+                        *module = '\0';
+
+                curr_map = map_groups__find(kmaps, map->type, pos->start);
+
+                if (!curr_map || (filter && filter(curr_map, pos))) {
+                        rb_erase(&pos->rb_node, root);
+                        symbol__delete(pos);
+                } else {
+                        pos->start -= curr_map->start - curr_map->pgoff;
+                        if (pos->end)
+                                pos->end -= curr_map->start - curr_map->pgoff;
+                        if (curr_map != map) {
+                                rb_erase(&pos->rb_node, root);
+                                symbols__insert(
+                                        &curr_map->dso->symbols[curr_map->type],
+                                        pos);
+                                ++moved;
+                        } else {
+                                ++count;
+                        }
+                }
+        }
+
+        /* Symbols have been adjusted */
+        dso->adjust_symbols = 1;
+
+        return count + moved;
+}
+
 /*
  * Split the symbols into maps, making sure there are no overlaps, i.e. the
  * kernel range is broken in several maps, named [kernel].N, as we don't have
@@ -663,6 +739,161 @@ bool symbol__restricted_filename(const char *filename,
         return restricted;
 }
 
+struct kcore_mapfn_data {
+        struct dso *dso;
+        enum map_type type;
+        struct list_head maps;
+};
+
+static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
+{
+        struct kcore_mapfn_data *md = data;
+        struct map *map;
+
+        map = map__new2(start, md->dso, md->type);
+        if (map == NULL)
+                return -ENOMEM;
+
+        map->end = map->start + len;
+        map->pgoff = pgoff;
+
+        list_add(&map->node, &md->maps);
+
+        return 0;
+}
+
+/*
+ * If kallsyms is referenced by name then we look for kcore in the same
+ * directory.
+ */
+static bool kcore_filename_from_kallsyms_filename(char *kcore_filename,
+                                                  const char *kallsyms_filename)
+{
+        char *name;
+
+        strcpy(kcore_filename, kallsyms_filename);
+        name = strrchr(kcore_filename, '/');
+        if (!name)
+                return false;
+
+        if (!strcmp(name, "/kallsyms")) {
+                strcpy(name, "/kcore");
+                return true;
+        }
+
+        return false;
+}
+
+static int dso__load_kcore(struct dso *dso, struct map *map,
+                           const char *kallsyms_filename)
+{
+        struct map_groups *kmaps = map__kmap(map)->kmaps;
+        struct machine *machine = kmaps->machine;
+        struct kcore_mapfn_data md;
+        struct map *old_map, *new_map, *replacement_map = NULL;
+        bool is_64_bit;
+        int err, fd;
+        char kcore_filename[PATH_MAX];
+        struct symbol *sym;
+
+        /* This function requires that the map is the kernel map */
+        if (map != machine->vmlinux_maps[map->type])
+                return -EINVAL;
+
+        if (!kcore_filename_from_kallsyms_filename(kcore_filename,
+                                                   kallsyms_filename))
+                return -EINVAL;
+
+        md.dso = dso;
+        md.type = map->type;
+        INIT_LIST_HEAD(&md.maps);
+
+        fd = open(kcore_filename, O_RDONLY);
+        if (fd < 0)
+                return -EINVAL;
+
+        /* Read new maps into temporary lists */
+        err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
+                              &is_64_bit);
+        if (err)
+                goto out_err;
+
+        if (list_empty(&md.maps)) {
+                err = -EINVAL;
+                goto out_err;
+        }
+
+        /* Remove old maps */
+        old_map = map_groups__first(kmaps, map->type);
+        while (old_map) {
+                struct map *next = map_groups__next(old_map);
+
+                if (old_map != map)
+                        map_groups__remove(kmaps, old_map);
+                old_map = next;
+        }
+
+        /* Find the kernel map using the first symbol */
+        sym = dso__first_symbol(dso, map->type);
+        list_for_each_entry(new_map, &md.maps, node) {
+                if (sym && sym->start >= new_map->start &&
+                    sym->start < new_map->end) {
+                        replacement_map = new_map;
+                        break;
+                }
+        }
+
+        if (!replacement_map)
+                replacement_map = list_entry(md.maps.next, struct map, node);
+
+        /* Add new maps */
+        while (!list_empty(&md.maps)) {
+                new_map = list_entry(md.maps.next, struct map, node);
+                list_del(&new_map->node);
+                if (new_map == replacement_map) {
+                        map->start      = new_map->start;
+                        map->end        = new_map->end;
+                        map->pgoff      = new_map->pgoff;
+                        map->map_ip     = new_map->map_ip;
+                        map->unmap_ip   = new_map->unmap_ip;
+                        map__delete(new_map);
+                        /* Ensure maps are correctly ordered */
+                        map_groups__remove(kmaps, map);
+                        map_groups__insert(kmaps, map);
+                } else {
+                        map_groups__insert(kmaps, new_map);
+                }
+        }
+
+        /*
+         * Set the data type and long name so that kcore can be read via
+         * dso__data_read_addr().
+         */
+        if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+                dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE;
+        else
+                dso->data_type = DSO_BINARY_TYPE__KCORE;
+        dso__set_long_name(dso, strdup(kcore_filename));
+
+        close(fd);
+
+        if (map->type == MAP__FUNCTION)
+                pr_debug("Using %s for kernel object code\n", kcore_filename);
+        else
+                pr_debug("Using %s for kernel data\n", kcore_filename);
+
+        return 0;
+
+out_err:
+        while (!list_empty(&md.maps)) {
+                map = list_entry(md.maps.next, struct map, node);
+                list_del(&map->node);
+                map__delete(map);
+        }
+        close(fd);
+        return -EINVAL;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
                        struct map *map, symbol_filter_t filter)
 {
@@ -680,7 +911,10 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
         else
                 dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
-        return dso__split_kallsyms(dso, map, filter);
+        if (!dso__load_kcore(dso, map, filename))
+                return dso__split_kallsyms_for_kcore(dso, map, filter);
+        else
+                return dso__split_kallsyms(dso, map, filter);
 }
 
 static int dso__load_perf_map(struct dso *dso, struct map *map,
@@ -843,10 +1077,15 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
         if (!runtime_ss && syms_ss)
                 runtime_ss = syms_ss;
 
-        if (syms_ss)
-                ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0);
-        else
+        if (syms_ss) {
+                int km;
+
+                km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+                     dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+                ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km);
+        } else {
                 ret = -1;
+        }
 
         if (ret > 0) {
                 int nr_plt;
@@ -888,8 +1127,11 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
         char symfs_vmlinux[PATH_MAX];
         enum dso_binary_type symtab_type;
 
-        snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
-                 symbol_conf.symfs, vmlinux);
+        if (vmlinux[0] == '/')
+                snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
+        else
+                snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
+                         symbol_conf.symfs, vmlinux);
 
         if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
                 symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
@@ -903,6 +1145,10 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
         symsrc__destroy(&ss);
 
         if (err > 0) {
+                if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+                        dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+                else
+                        dso->data_type = DSO_BINARY_TYPE__VMLINUX;
                 dso__set_long_name(dso, (char *)vmlinux);
                 dso__set_loaded(dso, map->type);
                 pr_debug("Using %s for symbols\n", symfs_vmlinux);
@@ -975,7 +1221,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
                         dso__set_long_name(dso,
                                            strdup(symbol_conf.vmlinux_name));
                         dso->lname_alloc = 1;
-                        goto out_fixup;
+                        return err;
                 }
                 return err;
         }
@@ -983,7 +1229,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
         if (vmlinux_path != NULL) {
                 err = dso__load_vmlinux_path(dso, map, filter);
                 if (err > 0)
-                        goto out_fixup;
+                        return err;
         }
 
         /* do not try local files if a symfs was given */
@@ -1042,9 +1288,8 @@ do_kallsyms:
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
         free(kallsyms_allocated_filename);
 
-        if (err > 0) {
+        if (err > 0 && !dso__is_kcore(dso)) {
                 dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
-out_fixup:
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
@@ -1075,7 +1320,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
                 if (symbol_conf.default_guest_vmlinux_name != NULL) {
                         err = dso__load_vmlinux(dso, map,
                                 symbol_conf.default_guest_vmlinux_name, filter);
-                        goto out_try_fixup;
+                        return err;
                 }
 
                 kallsyms_filename = symbol_conf.default_guest_kallsyms;
@@ -1089,13 +1334,9 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
         err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
         if (err > 0)
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
-
-out_try_fixup:
-        if (err > 0) {
-                if (kallsyms_filename != NULL) {
-                        machine__mmap_name(machine, path, sizeof(path));
-                        dso__set_long_name(dso, strdup(path));
-                }
+        if (err > 0 && !dso__is_kcore(dso)) {
+                machine__mmap_name(machine, path, sizeof(path));
+                dso__set_long_name(dso, strdup(path));
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5f720dc076da..fd5b70ea2981 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -215,6 +215,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
                                 u64 addr);
 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);
 
 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);
@@ -247,4 +248,8 @@ void symbols__fixup_duplicate(struct rb_root *symbols);
 void symbols__fixup_end(struct rb_root *symbols);
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
 
+typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
+int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
+                    bool *is_64_bit);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 40399cbcca77..e3d4a550a703 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,17 +7,18 @@
 #include "util.h"
 #include "debug.h"
 
-struct thread *thread__new(pid_t pid)
+struct thread *thread__new(pid_t pid, pid_t tid)
 {
         struct thread *self = zalloc(sizeof(*self));
 
         if (self != NULL) {
                 map_groups__init(&self->mg);
-                self->pid = pid;
+                self->pid_ = pid;
+                self->tid = tid;
                 self->ppid = -1;
                 self->comm = malloc(32);
                 if (self->comm)
-                        snprintf(self->comm, 32, ":%d", self->pid);
+                        snprintf(self->comm, 32, ":%d", self->tid);
         }
 
         return self;
@@ -57,7 +58,7 @@ int thread__comm_len(struct thread *self)
 
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-        return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) +
+        return fprintf(fp, "Thread %d %s\n", thread->tid, thread->comm) +
                map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
@@ -84,7 +85,7 @@ int thread__fork(struct thread *self, struct thread *parent)
                 if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
                         return -ENOMEM;
 
-        self->ppid = parent->pid;
+        self->ppid = parent->tid;
 
         return 0;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index eeb7ac62b9e3..4ebbb40d46d4 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -12,10 +12,12 @@ struct thread {
                 struct list_head node;
         };
         struct map_groups       mg;
-        pid_t                   pid;
+        pid_t                   pid_; /* Not all tools update this */
+        pid_t                   tid;
         pid_t                   ppid;
         char                    shortname[3];
         bool                    comm_set;
+        bool                    dead; /* if set thread has exited */
         char                    *comm;
         int                     comm_len;
 
@@ -24,8 +26,12 @@ struct thread {
 
 struct machine;
 
-struct thread *thread__new(pid_t pid);
+struct thread *thread__new(pid_t pid, pid_t tid);
 void thread__delete(struct thread *self);
+static inline void thread__exited(struct thread *thread)
+{
+        thread->dead = true;
+}
 
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
@@ -45,6 +51,15 @@ void thread__find_addr_map(struct thread *thread, struct machine *machine,
 
 void thread__find_addr_location(struct thread *thread, struct machine *machine,
                                 u8 cpumode, enum map_type type, u64 addr,
-                                struct addr_location *al,
-                                symbol_filter_t filter);
+                                struct addr_location *al);
+
+static inline void *thread__priv(struct thread *thread)
+{
+        return thread->priv;
+}
+
+static inline void thread__set_priv(struct thread *thread, void *p)
+{
+        thread->priv = p;
+}
 #endif  /* __PERF_THREAD_H */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index b0e1aadba8d5..4385816d3d49 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -18,12 +18,9 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
 typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
                         struct perf_sample *sample, struct machine *machine);
 
-typedef int (*event_attr_op)(union perf_event *event,
+typedef int (*event_attr_op)(struct perf_tool *tool,
+                             union perf_event *event,
                              struct perf_evlist **pevlist);
-typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
-
-typedef int (*event_synth_op)(union perf_event *event,
-                              struct perf_session *session);
 
 typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
                          struct perf_session *session);
@@ -32,6 +29,7 @@ struct perf_tool {
         event_sample    sample,
                         read;
         event_op        mmap,
+                        mmap2,
                         comm,
                         fork,
                         exit,
@@ -39,8 +37,7 @@ struct perf_tool {
                         throttle,
                         unthrottle;
         event_attr_op   attr;
-        event_synth_op  tracing_data;
-        event_simple_op event_type;
+        event_op2       tracing_data;
         event_op2       finished_round,
                         build_id;
         bool            ordered_samples;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index df46be93d902..b554ffc462b6 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -39,6 +39,8 @@ struct perf_top {
         float              min_percent;
 };
 
+#define CONSOLE_CLEAR ""
+
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
 void perf_top__reset_sample_counters(struct perf_top *top);
 #endif /* __PERF_TOP_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 3917eb9a8479..f3c9e551bd35 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -46,65 +46,6 @@
 static int output_fd;
 
 
-static const char *find_debugfs(void)
-{
-        const char *path = perf_debugfs_mount(NULL);
-
-        if (!path)
-                pr_debug("Your kernel does not support the debugfs filesystem");
-
-        return path;
-}
-
-/*
- * Finds the path to the debugfs/tracing
- * Allocates the string and stores it.
- */
-static const char *find_tracing_dir(void)
-{
-        static char *tracing;
-        static int tracing_found;
-        const char *debugfs;
-
-        if (tracing_found)
-                return tracing;
-
-        debugfs = find_debugfs();
-        if (!debugfs)
-                return NULL;
-
-        tracing = malloc(strlen(debugfs) + 9);
-        if (!tracing)
-                return NULL;
-
-        sprintf(tracing, "%s/tracing", debugfs);
-
-        tracing_found = 1;
-        return tracing;
-}
-
-static char *get_tracing_file(const char *name)
-{
-        const char *tracing;
-        char *file;
-
-        tracing = find_tracing_dir();
-        if (!tracing)
-                return NULL;
-
-        file = malloc(strlen(tracing) + strlen(name) + 2);
-        if (!file)
-                return NULL;
-
-        sprintf(file, "%s/%s", tracing, name);
-        return file;
-}
-
-static void put_tracing_file(char *file)
-{
-        free(file);
-}
-
 int bigendian(void)
 {
         unsigned char str[] = { 0x1, 0x2, 0x3, 0x4, 0x0, 0x0, 0x0, 0x0};
@@ -160,7 +101,7 @@ out:
         return err;
 }
 
-static int read_header_files(void)
+static int record_header_files(void)
 {
         char *path;
         struct stat st;
@@ -299,7 +240,7 @@ out:
         return err;
 }
 
-static int read_ftrace_files(struct tracepoint_path *tps)
+static int record_ftrace_files(struct tracepoint_path *tps)
 {
         char *path;
         int ret;
@@ -328,7 +269,7 @@ static bool system_in_tp_list(char *sys, struct tracepoint_path *tps)
         return false;
 }
 
-static int read_event_files(struct tracepoint_path *tps)
+static int record_event_files(struct tracepoint_path *tps)
 {
         struct dirent *dent;
         struct stat st;
@@ -403,7 +344,7 @@ out:
         return err;
 }
 
-static int read_proc_kallsyms(void)
+static int record_proc_kallsyms(void)
 {
         unsigned int size;
         const char *path = "/proc/kallsyms";
@@ -421,7 +362,7 @@ static int read_proc_kallsyms(void)
         return record_file(path, 4);
 }
 
-static int read_ftrace_printk(void)
+static int record_ftrace_printk(void)
 {
         unsigned int size;
         char *path;
@@ -473,12 +414,27 @@ get_tracepoints_path(struct list_head *pattrs)
                 if (pos->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
                 ++nr_tracepoints;
+
+                if (pos->name) {
+                        ppath->next = tracepoint_name_to_path(pos->name);
+                        if (ppath->next)
+                                goto next;
+
+                        if (strchr(pos->name, ':') == NULL)
+                                goto try_id;
+
+                        goto error;
+                }
+
+try_id:
                 ppath->next = tracepoint_id_to_path(pos->attr.config);
                 if (!ppath->next) {
+error:
                         pr_debug("No memory to alloc tracepoints list\n");
                         put_tracepoints_path(&path);
                         return NULL;
                 }
+next:
                 ppath = ppath->next;
         }
 
@@ -520,8 +476,6 @@ static int tracing_data_header(void)
         else
                 buf[0] = 0;
 
-        read_trace_init(buf[0], buf[0]);
-
         if (write(output_fd, buf, 1) != 1)
                 return -1;
 
@@ -583,19 +537,19 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
         err = tracing_data_header();
         if (err)
                 goto out;
-        err = read_header_files();
+        err = record_header_files();
         if (err)
                 goto out;
-        err = read_ftrace_files(tps);
+        err = record_ftrace_files(tps);
         if (err)
                 goto out;
-        err = read_event_files(tps);
+        err = record_event_files(tps);
         if (err)
                 goto out;
-        err = read_proc_kallsyms();
+        err = record_proc_kallsyms();
         if (err)
                 goto out;
-        err = read_ftrace_printk();
+        err = record_ftrace_printk();
 
 out:
         /*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 4454835a9ebc..e9e1c03f927d 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -28,12 +28,6 @@
 #include "util.h"
 #include "trace-event.h"
 
-int header_page_size_size;
-int header_page_ts_size;
-int header_page_data_offset;
-
-bool latency_format;
-
 struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
 {
         struct pevent *pevent = pevent_alloc();
@@ -192,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent,
         char *next = NULL;
         char *addr_str;
         char *mod;
-        char *fmt;
+        char *fmt = NULL;
 
         line = strtok_r(file, "\n", &next);
         while (line) {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index af215c0d2379..f2112270c663 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -39,10 +39,6 @@
 
 static int input_fd;
 
-int file_bigendian;
-int host_bigendian;
-static int long_size;
-
 static ssize_t trace_data_size;
 static bool repipe;
 
@@ -216,7 +212,7 @@ static int read_ftrace_printk(struct pevent *pevent)
 static int read_header_files(struct pevent *pevent)
 {
         unsigned long long size;
-        char *header_event;
+        char *header_page;
         char buf[BUFSIZ];
         int ret = 0;
 
@@ -229,13 +225,26 @@ static int read_header_files(struct pevent *pevent)
         }
 
         size = read8(pevent);
-        skip(size);
 
-        /*
-         * The size field in the page is of type long,
-         * use that instead, since it represents the kernel.
-         */
-        long_size = header_page_size_size;
+        header_page = malloc(size);
+        if (header_page == NULL)
+                return -1;
+
+        if (do_read(header_page, size) < 0) {
+                pr_debug("did not read header page");
+                free(header_page);
+                return -1;
+        }
+
+        if (!pevent_parse_header_page(pevent, header_page, size,
+                                      pevent_get_long_size(pevent))) {
+                /*
+                 * The commit field in the page is of type long,
+                 * use that instead, since it represents the kernel.
+                 */
+                pevent_set_long_size(pevent, pevent->header_page_size_size);
+        }
+        free(header_page);
 
         if (do_read(buf, 13) < 0)
                 return -1;
@@ -246,14 +255,8 @@ static int read_header_files(struct pevent *pevent)
         }
 
         size = read8(pevent);
-        header_event = malloc(size);
-        if (header_event == NULL)
-                return -1;
-
-        if (do_read(header_event, size) < 0)
-                ret = -1;
+        skip(size);
 
-        free(header_event);
         return ret;
 }
 
@@ -349,6 +352,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
         int show_funcs = 0;
         int show_printk = 0;
         ssize_t size = -1;
+        int file_bigendian;
+        int host_bigendian;
+        int file_long_size;
+        int file_page_size;
         struct pevent *pevent;
         int err;
 
@@ -391,12 +398,15 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 
         if (do_read(buf, 1) < 0)
                 goto out;
-        long_size = buf[0];
+        file_long_size = buf[0];
 
-        page_size = read4(pevent);
-        if (!page_size)
+        file_page_size = read4(pevent);
+        if (!file_page_size)
                 goto out;
 
+        pevent_set_long_size(pevent, file_long_size);
+        pevent_set_page_size(pevent, file_page_size);
+
         err = read_header_files(pevent);
         if (err)
                 goto out;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 8715a1006d00..95199e4eea97 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -39,7 +39,8 @@ static void process_event_unsupported(union perf_event *event __maybe_unused,
                                       struct perf_sample *sample __maybe_unused,
                                       struct perf_evsel *evsel __maybe_unused,
                                       struct machine *machine __maybe_unused,
-                                      struct addr_location *al __maybe_unused)
+                                      struct thread *thread __maybe_unused,
+                                          struct addr_location *al __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 1978c398ad87..fafe1a40444a 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -1,32 +1,18 @@
 #ifndef _PERF_UTIL_TRACE_EVENT_H
 #define _PERF_UTIL_TRACE_EVENT_H
 
+#include <traceevent/event-parse.h>
 #include "parse-events.h"
-#include "event-parse.h"
 #include "session.h"
 
 struct machine;
 struct perf_sample;
 union perf_event;
 struct perf_tool;
+struct thread;
 
-extern int header_page_size_size;
-extern int header_page_ts_size;
-extern int header_page_data_offset;
-
-extern bool latency_format;
 extern struct pevent *perf_pevent;
 
-enum {
-        RINGBUF_TYPE_PADDING            = 29,
-        RINGBUF_TYPE_TIME_EXTEND        = 30,
-        RINGBUF_TYPE_TIME_STAMP         = 31,
-};
-
-#ifndef TS_SHIFT
-#define TS_SHIFT                27
-#endif
-
 int bigendian(void);
 
 struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
@@ -83,7 +69,8 @@ struct scripting_ops {
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
                                struct machine *machine,
-                               struct addr_location *al);
+                               struct thread *thread,
+                                   struct addr_location *al);
         int (*generate_script) (struct pevent *pevent, const char *outfile);
 };
 
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 958723ba3d2e..2f891f7e70bf 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -473,7 +473,7 @@ static int entry(u64 ip, struct thread *thread, struct machine *machine,
 
         thread__find_addr_location(thread, machine,
                                    PERF_RECORD_MISC_USER,
-                                   MAP__FUNCTION, ip, &al, NULL);
+                                   MAP__FUNCTION, ip, &al);
 
         e.ip = ip;
         e.map = al.map;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 59d868add275..6d17b18e915d 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -269,3 +269,95 @@ void perf_debugfs_set_path(const char *mntpt)
         snprintf(debugfs_mountpoint, strlen(debugfs_mountpoint), "%s", mntpt);
         set_tracing_events_path(mntpt);
 }
+
+static const char *find_debugfs(void)
+{
+        const char *path = perf_debugfs_mount(NULL);
+
+        if (!path)
+                fprintf(stderr, "Your kernel does not support the debugfs filesystem");
+
+        return path;
+}
+
+/*
+ * Finds the path to the debugfs/tracing
+ * Allocates the string and stores it.
+ */
+const char *find_tracing_dir(void)
+{
+        static char *tracing;
+        static int tracing_found;
+        const char *debugfs;
+
+        if (tracing_found)
+                return tracing;
+
+        debugfs = find_debugfs();
+        if (!debugfs)
+                return NULL;
+
+        tracing = malloc(strlen(debugfs) + 9);
+        if (!tracing)
+                return NULL;
+
+        sprintf(tracing, "%s/tracing", debugfs);
+
+        tracing_found = 1;
+        return tracing;
+}
+
+char *get_tracing_file(const char *name)
+{
+        const char *tracing;
+        char *file;
+
+        tracing = find_tracing_dir();
+        if (!tracing)
+                return NULL;
+
+        file = malloc(strlen(tracing) + strlen(name) + 2);
+        if (!file)
+                return NULL;
+
+        sprintf(file, "%s/%s", tracing, name);
+        return file;
+}
+
+void put_tracing_file(char *file)
+{
+        free(file);
+}
+
+int parse_nsec_time(const char *str, u64 *ptime)
+{
+        u64 time_sec, time_nsec;
+        char *end;
+
+        time_sec = strtoul(str, &end, 10);
+        if (*end != '.' && *end != '\0')
+                return -1;
+
+        if (*end == '.') {
+                int i;
+                char nsec_buf[10];
+
+                if (strlen(++end) > 9)
+                        return -1;
+
+                strncpy(nsec_buf, end, 9);
+                nsec_buf[9] = '\0';
+
+                /* make it nsec precision */
+                for (i = strlen(nsec_buf); i < 9; i++)
+                        nsec_buf[i] = '0';
+
+                time_nsec = strtoul(nsec_buf, &end, 10);
+                if (*end != '\0')
+                        return -1;
+        } else
+                time_nsec = 0;
+
+        *ptime = time_sec * NSEC_PER_SEC + time_nsec;
+        return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2732fad03908..a53535949043 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -80,6 +80,9 @@ extern char buildid_dir[];
 extern char tracing_events_path[];
 extern void perf_debugfs_set_path(const char *mountpoint);
 const char *perf_debugfs_mount(const char *mountpoint);
+const char *find_tracing_dir(void);
+char *get_tracing_file(const char *name);
+void put_tracing_file(char *file);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -205,6 +208,8 @@ static inline int has_extension(const char *filename, const char *ext)
 #define NSEC_PER_MSEC   1000000L
 #endif
 
+int parse_nsec_time(const char *str, u64 *ptime);
+
 extern unsigned char sane_ctype[256];
 #define GIT_SPACE               0x01
 #define GIT_DIGIT               0x02