235 files changed, 11565 insertions, 2412 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 3d1bb802dbf4..3db3db9278be 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -30,3 +30,4 @@ config.mak.autogen
 *.pyo
 .config-detected
 util/intel-pt-decoder/inat-tables.c
+arch/*/include/generated/
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt
index 8484c3a04a6a..24a59998fc91 100644
--- a/tools/perf/Documentation/android.txt
+++ b/tools/perf/Documentation/android.txt
@@ -12,14 +12,14 @@ Set the NDK variable to point to the path where you installed the NDK:
 
 2. Set cross-compiling environment variables for NDK toolchain and sysroot.
 For arm:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.6/prebuilt/linux-x86/bin/arm-linux-androideabi-
-  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-arm
+  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.9/prebuilt/linux-x86_64/bin/arm-linux-androideabi-
+  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-arm
 For x86:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.6/prebuilt/linux-x86/bin/i686-linux-android-
-  export NDK_SYSROOT=${NDK}/platforms/android-9/arch-x86
+  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.9/prebuilt/linux-x86_64/bin/i686-linux-android-
+  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-x86
 
-This method is not working for Android NDK versions up to Revision 8b.
-perf uses some bionic enhancements that are not included in these NDK versions.
+This method is only tested for Android NDK versions Revision 11b and later.
+perf uses some bionic enhancements that are not included in prior NDK versions.
 You can use method (b) described below instead.
 
 (b). Use the Android source tree
@@ -49,9 +49,9 @@ II. Compile perf for Android
 ------------------------------------------------
 You need to run make with the NDK toolchain and sysroot defined above:
 For arm:
-  make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+  make WERROR=0 ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
 For x86:
-  make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+  make WERROR=0 ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
 
 III. Install perf
 -----------------------------------------------
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 778f54d4d0bd..8ffbd272952d 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -61,6 +61,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+        'always', 'never' or 'auto', allowing configuring color output
+        via the command line, in addition to via "color.ui" .perfconfig.
+        Use '--stdio-color always' to generate color even when redirecting
+        to a pipe or file. Using just '--stdio-color' is equivalent to
+        using 'always'.
+
 --tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
         present, as when piping to other commands, the stdio interface is
         used. This interfaces starts by centering on the line with more
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index dd07b55f58d8..058064db39d2 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -15,6 +15,9 @@ DESCRIPTION
 This command manages the build-id cache. It can add, remove, update and purge
 files to/from the cache. In the future it should as well set upper limits for
 the space used by the cache, etc.
+This also scans the target binary for SDT (Statically Defined Tracing) and
+record it along with the buildid-cache, which will be used by perf-probe.
+For more details, see linkperf:perf-probe[1].
 
 OPTIONS
 -------
diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index be8fa1a0a97e..f0796a47dfa3 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -34,6 +34,10 @@ OPTIONS for 'convert'
 --verbose::
         Be more verbose (show counter open errors, etc).
 
+--all::
+        Convert all events, including non-sample events (comm, fork, ...), to output.
+        Default is off, only convert samples.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 1d6092c460dd..73496320fca3 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -56,6 +56,9 @@ OPTIONS
 --all-user::
         Configure all used events to run in user space.
 
+--ldload::
+        Specify desired latency for loads event.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 3a8a9ba2b041..736da44596e4 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -67,7 +67,10 @@ OPTIONS
 
 -l::
 --list[=[GROUP:]EVENT]::
-        List up current probe events. This can also accept filtering patterns of event names.
+        List up current probe events. This can also accept filtering patterns of
+        event names.
+        When this is used with --cache, perf shows all cached probes instead of
+        the live probes.
 
 -L::
 --line=::
@@ -109,6 +112,12 @@ OPTIONS
         Dry run. With this option, --add and --del doesn't execute actual
         adding and removal operations.
 
+--cache::
+        (With --add) Cache the probes. Any events which successfully added
+        are also stored in the cache file.
+        (With --list) Show cached probes.
+        (With --del) Remove cached probes.
+
 --max-probes=NUM::
         Set the maximum number of probe points for an event. Default is 128.
 
@@ -134,19 +143,30 @@ PROBE SYNTAX
 Probe points are defined by following syntax.
 
     1) Define event based on function name
-     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+     [[GROUP:]EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
 
     2) Define event based on source file with line number
-     [EVENT=]SRC:ALN [ARG ...]
+     [[GROUP:]EVENT=]SRC:ALN [ARG ...]
 
     3) Define event based on source file with lazy pattern
-     [EVENT=]SRC;PTN [ARG ...]
+     [[GROUP:]EVENT=]SRC;PTN [ARG ...]
 
+    4) Pre-defined SDT events or cached event with name
+     %[sdt_PROVIDER:]SDTEVENT
+     or,
+     sdt_PROVIDER:SDTEVENT
 
-'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
+'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. You can also specify a group name by 'GROUP', if omitted, set 'probe' is used for kprobe and 'probe_<bin>' is used for uprobe.
+Note that using existing group name can conflict with other events. Especially, using the group name reserved for kernel modules can hide embedded events in the
+modules.
 'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
 It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
 'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
+'SDTEVENT' and 'PROVIDER' is the pre-defined event name which is defined by user SDT (Statically Defined Tracing) or the pre-cached probes with event name.
+Note that before using the SDT event, the target binary (on which SDT events are defined) must be scanned by linkperf:perf-buildid-cache[1] to make SDT events as cached events.
+
+For details of the SDT, see below.
+https://sourceware.org/gdb/onlinedocs/gdb/Static-Probe-Points.html
 
 PROBE ARGUMENT
 --------------
@@ -226,4 +246,4 @@ Add probes at malloc() function on libc
 
 SEE ALSO
 --------
-linkperf:perf-trace[1], linkperf:perf-record[1]
+linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8dbee832abd9..379a2bed07c0 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -192,6 +192,9 @@ OPTIONS
 --period::
         Record the sample period.
 
+--sample-cpu::
+        Record the sample cpu.
+
 -n::
 --no-samples::
         Don't sample.
@@ -360,6 +363,35 @@ particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
 
+--dry-run::
+Parse options then exit. --dry-run can be used to detect errors in cmdline
+options.
+
+'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj
+in config file is set to true.
+
+--tail-synthesize::
+Instead of collecting non-sample events (for example, fork, comm, mmap) at
+the beginning of record, collect them during finalizing an output file.
+The collected non-sample events reflects the status of the system when
+record is finished.
+
+--overwrite::
+Makes all events use an overwritable ring buffer. An overwritable ring
+buffer works like a flight recorder: when it gets full, the kernel will
+overwrite the oldest records, that thus will never make it to the
+perf.data file.
+
+When '--overwrite' and '--switch-output' are used perf records and drops
+events until it receives a signal, meaning that something unusual was
+detected that warrants taking a snapshot of the most current events,
+those fitting in the ring buffer at that moment.
+
+'overwrite' attribute can also be set or canceled for an event using
+config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'.
+
+Implies --tail-synthesize.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9cbddc290aff..2d1746295abf 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -265,6 +265,13 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
+--stdio-color::
+        'always', 'never' or 'auto', allowing configuring color output
+        via the command line, in addition to via "color.ui" .perfconfig.
+        Use '--stdio-color always' to generate color even when redirecting
+        to a pipe or file. Using just '--stdio-color' is equivalent to
+        using 'always'.
+
 --tui:: Use the TUI interface, that is integrated with annotate and allows
         zooming into DSOs or threads, among other features. Use of --tui
         requires a tty, if one is not present, as when piping to other
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4fc44c75263f..1f6c70594f0f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -119,13 +119,13 @@ OPTIONS
         srcline, period, iregs, brstack, brstacksym, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
-        e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
+        e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
 
-                perf script -f <fields>
+                perf script -F <fields>
 
         is equivalent to:
 
-                perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+                perf script -F trace:<fields> -F sw:<fields> -F hw:<fields>
 
         i.e., the specified fields apply to all event types if the type string
         is not given.
@@ -133,9 +133,9 @@ OPTIONS
         The arguments are processed in the order received. A later usage can
         reset a prior request. e.g.:
 
-                -f trace: -f comm,tid,time,ip,sym
+                -F trace: -F comm,tid,time,ip,sym
 
-        The first -f suppresses trace events (field list is ""), but then the
+        The first -F suppresses trace events (field list is ""), but then the
         second invocation sets the fields to comm,tid,time,ip,sym. In this case a
         warning is given to the user:
 
@@ -143,9 +143,9 @@ OPTIONS
 
         Alternatively, consider the order:
 
-                -f comm,tid,time,ip,sym -f trace:
+                -F comm,tid,time,ip,sym -F trace:
 
-        The first -f sets the fields for all events and the second -f
+        The first -F sets the fields for all events and the second -F
         suppresses trace events. The user is given a warning message about
         the override, and the result of the above is that only S/W and H/W
         events are displayed with the given fields.
@@ -154,14 +154,14 @@ OPTIONS
         event type, a message is displayed to the user that the option is
         ignored for that type. For example:
 
-                $ perf script -f comm,tid,trace
+                $ perf script -F comm,tid,trace
                 'trace' not valid for hardware events. Ignoring.
                 'trace' not valid for software events. Ignoring.
 
         Alternatively, if the type is given an invalid field is specified it
         is an error. For example:
 
-        perf script -v -f sw:comm,tid,trace
+        perf script -v -F sw:comm,tid,trace
         'trace' not valid for software events.
 
         At this point usage is displayed, and perf-script exits.
@@ -170,10 +170,19 @@ OPTIONS
         Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
         call, return, conditional, system, asynchronous, interrupt,
         transaction abort, trace begin, trace end, and in transaction,
-        respectively.
+        respectively. Known combinations of flags are printed more nicely e.g.
+        "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
+        "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
+        "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
+        "tr end" for "bE". However the "x" flag will be display separately in those
+        cases e.g. "jcc     (x)" for a condition branch within a transaction.
+
+        The callindent field is synthesized and may have a value when
+        Instruction Trace decoding. For calls and returns, it will display the
+        name of the symbol indented with spaces to reflect the stack depth.
 
         Finally, a user may not set fields to none for all event types.
-        i.e., -f "" is not allowed.
+        i.e., -F "" is not allowed.
 
         The brstack output includes branch related information with raw addresses using the
         /v/v/v/v/ syntax in the following order:
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04f23b404bbc..d96ccd4844df 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -204,6 +204,38 @@ Aggregate counts per physical processor for system-wide mode measurements.
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
 
+--topdown::
+Print top down level 1 metrics if supported by the CPU. This allows to
+determine bottle necks in the CPU pipeline for CPU bound workloads,
+by breaking the cycles consumed down into frontend bound, backend bound,
+bad speculation and retiring.
+
+Frontend bound means that the CPU cannot fetch and decode instructions fast
+enough. Backend bound means that computation or memory access is the bottle
+neck. Bad Speculation means that the CPU wasted cycles due to branch
+mispredictions and similar issues. Retiring means that the CPU computed without
+an apparently bottleneck. The bottleneck is only the real bottleneck
+if the workload is actually bound by the CPU and not by something else.
+
+For best results it is usually a good idea to use it with interval
+mode like -I 1000, as the bottleneck of workloads can change often.
+
+The top down metrics are collected per core instead of per
+CPU thread. Per core mode is automatically enabled
+and -a (global monitoring) is needed, requiring root rights or
+perf.perf_event_paranoid=-1.
+
+Topdown uses the full Performance Monitoring Unit, and needs
+disabling of the NMI watchdog (as root):
+echo 0 > /proc/sys/kernel/nmi_watchdog
+for best results. Otherwise the bottlenecks may be inconsistent
+on workload with changing phases.
+
+This enables --metric-only, unless overriden with --no-metric-only.
+
+To interpret the results it is usually needed to know on which
+CPUs the workload runs on. If needed the CPUs can be forced using
+taskset.
 
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 31a5c3ea7f74..b329c65d7f40 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -30,3 +30,7 @@ OPTIONS
 -v::
 --verbose::
         Be more verbose.
+
+-F::
+--dont-fork::
+        Do not fork child for each test, run all tests within single process.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
new file mode 100644
index 000000000000..fdc99fe6bbc3
--- /dev/null
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -0,0 +1,442 @@
+perf.data format
+
+Uptodate as of v4.7
+
+This document describes the on-disk perf.data format, generated by perf record
+or perf inject and consumed by the other perf tools.
+
+On a high level perf.data contains the events generated by the PMUs, plus metadata.
+
+All fields are in native-endian of the machine that generated the perf.data.
+
+When perf is writing to a pipe it uses a special version of the file
+format that does not rely on seeking to adjust data offsets.  This
+format is not described here. The pipe version can be converted to
+normal perf.data with perf inject.
+
+The file starts with a perf_header:
+
+struct perf_header {
+        char magic[8];          /* PERFILE2 */
+        uint64_t size;          /* size of the header */
+        uint64_t attr_size;     /* size of an attribute in attrs */
+        struct perf_file_section attrs;
+        struct perf_file_section data;
+        struct perf_file_section event_types;
+        uint64_t flags;
+        uint64_t flags1[3];
+};
+
+The magic number identifies the perf file and the version. Current perf versions
+use PERFILE2. Old perf versions generated a version 1 format (PERFFILE). Version 1
+is not described here. The magic number also identifies the endian. When the
+magic value is 64bit byte swapped compared the file is in non-native
+endian.
+
+A perf_file_section contains a pointer to another section of the perf file.
+The header contains three such pointers: for attributes, data and event types.
+
+struct perf_file_section {
+        uint64_t offset;        /* offset from start of file */
+        uint64_t size;          /* size of the section */
+};
+
+Flags section:
+
+The header is followed by different optional headers, described by the bits set
+in flags. Only headers for which the bit is set are included. Each header
+consists of a perf_file_section located after the initial header.
+The respective perf_file_section points to the data of the additional
+header and defines its size.
+
+Some headers consist of strings, which are defined like this:
+
+struct perf_header_string {
+       uint32_t len;
+       char string[len]; /* zero terminated */
+};
+
+Some headers consist of a sequence of strings, which start with a
+
+struct perf_header_string_list {
+     uint32_t nr;
+     struct perf_header_string strings[nr]; /* variable length records */
+};
+
+The bits are the flags bits in a 256 bit bitmap starting with
+flags. These define the valid bits:
+
+        HEADER_RESERVED         = 0,    /* always cleared */
+        HEADER_FIRST_FEATURE    = 1,
+        HEADER_TRACING_DATA     = 1,
+
+Describe me.
+
+        HEADER_BUILD_ID = 2,
+
+The header consists of an sequence of build_id_event. The size of each record
+is defined by header.size (see perf_event.h). Each event defines a ELF build id
+for a executable file name for a pid. An ELF build id is a unique identifier
+assigned by the linker to an executable.
+
+struct build_id_event {
+        struct perf_event_header header;
+        pid_t                    pid;
+        uint8_t                  build_id[24];
+        char                     filename[header.size - offsetof(struct build_id_event, filename)];
+};
+
+        HEADER_HOSTNAME = 3,
+
+A perf_header_string with the hostname where the data was collected
+(uname -n)
+
+        HEADER_OSRELEASE = 4,
+
+A perf_header_string with the os release where the data was collected
+(uname -r)
+
+        HEADER_VERSION = 5,
+
+A perf_header_string with the perf user tool version where the
+data was collected. This is the same as the version of the source tree
+the perf tool was built from.
+
+        HEADER_ARCH = 6,
+
+A perf_header_string with the CPU architecture (uname -m)
+
+        HEADER_NRCPUS = 7,
+
+A structure defining the number of CPUs.
+
+struct nr_cpus {
+       uint32_t nr_cpus_online;
+       uint32_t nr_cpus_available; /* CPUs not yet onlined */
+};
+
+        HEADER_CPUDESC = 8,
+
+A perf_header_string with description of the CPU. On x86 this is the model name
+in /proc/cpuinfo
+
+        HEADER_CPUID = 9,
+
+A perf_header_string with the exact CPU type. On x86 this is
+vendor,family,model,stepping. For example: GenuineIntel,6,69,1
+
+        HEADER_TOTAL_MEM = 10,
+
+An uint64_t with the total memory in bytes.
+
+        HEADER_CMDLINE = 11,
+
+A perf_header_string with the perf command line used to collect the data.
+
+        HEADER_EVENT_DESC = 12,
+
+Another description of the perf_event_attrs, more detailed than header.attrs
+including IDs and names. See perf_event.h or the man page for a description
+of a struct perf_event_attr.
+
+struct {
+       uint32_t nr; /* number of events */
+       uint32_t attr_size; /* size of each perf_event_attr */
+       struct {
+              struct perf_event_attr attr;  /* size of attr_size */
+              uint32_t nr_ids;
+              struct perf_header_string event_string;
+              uint64_t ids[nr_ids];
+       } events[nr]; /* Variable length records */
+};
+
+        HEADER_CPU_TOPOLOGY = 13,
+
+String lists defining the core and CPU threads topology.
+
+struct {
+       struct perf_header_string_list cores; /* Variable length */
+       struct perf_header_string_list threads; /* Variable length */
+};
+
+Example:
+        sibling cores   : 0-3
+        sibling threads : 0-1
+        sibling threads : 2-3
+
+        HEADER_NUMA_TOPOLOGY = 14,
+
+        A list of NUMA node descriptions
+
+struct {
+       uint32_t nr;
+       struct {
+              uint32_t nodenr;
+              uint64_t mem_total;
+              uint64_t mem_free;
+              struct perf_header_string cpus;
+       } nodes[nr]; /* Variable length records */
+};
+
+        HEADER_BRANCH_STACK = 15,
+
+Not implemented in perf.
+
+        HEADER_PMU_MAPPINGS = 16,
+
+        A list of PMU structures, defining the different PMUs supported by perf.
+
+struct {
+       uint32_t nr;
+       struct pmu {
+              uint32_t pmu_type;
+              struct perf_header_string pmu_name;
+       } [nr]; /* Variable length records */
+};
+
+        HEADER_GROUP_DESC = 17,
+
+        Description of counter groups ({...} in perf syntax)
+
+struct {
+         uint32_t nr;
+         struct {
+                struct perf_header_string string;
+                uint32_t leader_idx;
+                uint32_t nr_members;
+         } [nr]; /* Variable length records */
+};
+
+        HEADER_AUXTRACE = 18,
+
+Define additional auxtrace areas in the perf.data. auxtrace is used to store
+undecoded hardware tracing information, such as Intel Processor Trace data.
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+        u64                     file_offset;
+        u64                     sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+        struct list_head        list;
+        size_t                  nr;
+        struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+        other bits are reserved and should ignored for now
+        HEADER_FEAT_BITS        = 256,
+
+Attributes
+
+This is an array of perf_event_attrs, each attr_size bytes long, which defines
+each event collected. See perf_event.h or the man page for a detailed
+description.
+
+Data
+
+This section is the bulk of the file. It consist of a stream of perf_events
+describing events. This matches the format generated by the kernel.
+See perf_event.h or the manpage for a detailed description.
+
+Some notes on parsing:
+
+Ordering
+
+The events are not necessarily in time stamp order, as they can be
+collected in parallel on different CPUs. If the events should be
+processed in time order they need to be sorted first. It is possible
+to only do a partial sort using the FINISHED_ROUND event header (see
+below). perf record guarantees that there is no reordering over a
+FINISHED_ROUND.
+
+ID vs IDENTIFIER
+
+When the event stream contains multiple events each event is identified
+by an ID. This can be either through the PERF_SAMPLE_ID or the
+PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is
+at a fixed offset from the event header, which allows reliable
+parsing of the header. Relying on ID may be ambigious.
+IDENTIFIER is only supported by newer Linux kernels.
+
+Perf record specific events:
+
+In addition to the kernel generated event types perf record adds its
+own event types (in addition it also synthesizes some kernel events,
+for example MMAP events)
+
+        PERF_RECORD_USER_TYPE_START             = 64,
+        PERF_RECORD_HEADER_ATTR                 = 64,
+
+struct attr_event {
+        struct perf_event_header header;
+        struct perf_event_attr attr;
+        uint64_t id[];
+};
+
+        PERF_RECORD_HEADER_EVENT_TYPE           = 65, /* depreceated */
+
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+        uint64_t        event_id;
+        char    name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+        struct perf_event_header header;
+        struct perf_trace_event_type event_type;
+};
+
+
+        PERF_RECORD_HEADER_TRACING_DATA         = 66,
+
+Describe me
+
+struct tracing_data_event {
+        struct perf_event_header header;
+        uint32_t size;
+};
+
+        PERF_RECORD_HEADER_BUILD_ID             = 67,
+
+Define a ELF build ID for a referenced executable.
+
+       struct build_id_event;   /* See above */
+
+        PERF_RECORD_FINISHED_ROUND              = 68,
+
+No event reordering over this header. No payload.
+
+        PERF_RECORD_ID_INDEX                    = 69,
+
+Map event ids to CPUs and TIDs.
+
+struct id_index_entry {
+        uint64_t id;
+        uint64_t idx;
+        uint64_t cpu;
+        uint64_t tid;
+};
+
+struct id_index_event {
+        struct perf_event_header header;
+        uint64_t nr;
+        struct id_index_entry entries[nr];
+};
+
+        PERF_RECORD_AUXTRACE_INFO               = 70,
+
+Auxtrace type specific information. Describe me
+
+struct auxtrace_info_event {
+        struct perf_event_header header;
+        uint32_t type;
+        uint32_t reserved__; /* For alignment */
+        uint64_t priv[];
+};
+
+        PERF_RECORD_AUXTRACE                    = 71,
+
+Defines auxtrace data. Followed by the actual data. The contents of
+the auxtrace data is dependent on the event and the CPU. For example
+for Intel Processor Trace it contains Processor Trace data generated
+by the CPU.
+
+struct auxtrace_event {
+        struct perf_event_header header;
+        uint64_t size;
+        uint64_t offset;
+        uint64_t reference;
+        uint32_t idx;
+        uint32_t tid;
+        uint32_t cpu;
+        uint32_t reserved__; /* For alignment */
+};
+
+struct aux_event {
+        struct perf_event_header header;
+        uint64_t        aux_offset;
+        uint64_t        aux_size;
+        uint64_t        flags;
+};
+
+        PERF_RECORD_AUXTRACE_ERROR              = 72,
+
+Describes an error in hardware tracing
+
+enum auxtrace_error_type {
+        PERF_AUXTRACE_ERROR_ITRACE  = 1,
+        PERF_AUXTRACE_ERROR_MAX
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+        struct perf_event_header header;
+        uint32_t type;
+        uint32_t code;
+        uint32_t cpu;
+        uint32_t pid;
+        uint32_t tid;
+        uint32_t reserved__; /* For alignment */
+        uint64_t ip;
+        char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+Event types
+
+Define the event attributes with their IDs.
+
+An array bound by the perf_file_section size.
+
+        struct {
+                struct perf_event_attr attr;   /* Size defined by header.attr_size */
+                struct perf_file_section ids;
+        }
+
+ids points to a array of uint64_t defining the ids for event attr attr.
+
+References:
+
+include/uapi/linux/perf_event.h
+
+This is the canonical description of the kernel generated perf_events
+and the perf_event_attrs.
+
+perf_events manpage
+
+A manpage describing perf_event and perf_event_attr is here:
+http://web.eece.maine.edu/~vweaver/projects/perf_events/programming.html
+This tends to be slightly behind the kernel include, but has better
+descriptions.  An (typically older) version of the man page may be
+included with the standard Linux man pages, available with "man
+perf_events"
+
+pmu-tools
+
+https://github.com/andikleen/pmu-tools/tree/master/parser
+
+A definition of the perf.data format in python "construct" format is available
+in pmu-tools parser. This allows to read perf.data from python and dump it.
+
+quipper
+
+The quipper C++ parser is available at
+https://chromium.googlesource.com/chromiumos/platform/chromiumos-wide-profiling/
+Unfortunately this parser tends to be many versions behind and may not be able
+to parse data files generated by recent perf.
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8c8c6b9ce915..ad2534df4ba6 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -12,13 +12,23 @@ tools/arch/sparc/include/asm/barrier_32.h
 tools/arch/sparc/include/asm/barrier_64.h
 tools/arch/tile/include/asm/barrier.h
 tools/arch/x86/include/asm/barrier.h
+tools/arch/x86/include/asm/cpufeatures.h
+tools/arch/x86/include/asm/disabled-features.h
+tools/arch/x86/include/asm/required-features.h
+tools/arch/x86/include/uapi/asm/svm.h
+tools/arch/x86/include/uapi/asm/vmx.h
+tools/arch/x86/include/uapi/asm/kvm.h
+tools/arch/x86/include/uapi/asm/kvm_perf.h
+tools/arch/x86/lib/memcpy_64.S
+tools/arch/x86/lib/memset_64.S
+tools/arch/s390/include/uapi/asm/kvm_perf.h
+tools/arch/s390/include/uapi/asm/sie.h
 tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
 tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
-tools/lib/bpf
 tools/lib/api
 tools/lib/bpf
 tools/lib/subcmd
@@ -29,6 +39,9 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
 tools/lib/bitmap.c
+tools/lib/str_error_r.c
+tools/lib/vsprintf.c
+tools/include/asm/alternative-asm.h
 tools/include/asm/atomic.h
 tools/include/asm/barrier.h
 tools/include/asm/bug.h
@@ -52,43 +65,16 @@ tools/include/linux/hash.h
 tools/include/linux/kernel.h
 tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/uapi/linux/bpf.h
+tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/hw_breakpoint.h
+tools/include/uapi/linux/perf_event.h
 tools/include/linux/poison.h
 tools/include/linux/rbtree.h
 tools/include/linux/rbtree_augmented.h
 tools/include/linux/string.h
+tools/include/linux/stringify.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 tools/include/linux/bitmap.h
-include/asm-generic/bitops/arch_hweight.h
-include/asm-generic/bitops/const_hweight.h
-include/asm-generic/bitops/fls64.h
-include/asm-generic/bitops/__fls.h
-include/asm-generic/bitops/fls.h
-include/linux/perf_event.h
-include/linux/list.h
-include/linux/hash.h
-include/linux/stringify.h
-include/linux/swab.h
-arch/*/include/asm/unistd*.h
-arch/*/include/uapi/asm/unistd*.h
-arch/*/include/uapi/asm/perf_regs.h
-arch/*/lib/memcpy*.S
-arch/*/lib/memset*.S
-arch/*/include/asm/*features.h
-include/linux/poison.h
-include/linux/hw_breakpoint.h
-include/uapi/linux/perf_event.h
-include/uapi/linux/bpf.h
-include/uapi/linux/bpf_common.h
-include/uapi/linux/const.h
-include/uapi/linux/swab.h
-include/uapi/linux/hw_breakpoint.h
-arch/x86/include/asm/svm.h
-arch/x86/include/asm/vmx.h
-arch/x86/include/asm/kvm_host.h
-arch/x86/include/uapi/asm/svm.h
-arch/x86/include/uapi/asm/vmx.h
-arch/x86/include/uapi/asm/kvm.h
-arch/x86/include/uapi/asm/kvm_perf.h
-arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/kvm_perf.h
+tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/config/Makefile b/tools/perf/Makefile.config
index 5ad0255f8756..24803c58049a 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/Makefile.config
@@ -73,17 +73,25 @@ endif
 #
 #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
 #
+
+libunwind_arch_set_flags = $(eval $(libunwind_arch_set_flags_code))
+define libunwind_arch_set_flags_code
+  FEATURE_CHECK_CFLAGS-libunwind-$(1)  = -I$(LIBUNWIND_DIR)/include
+  FEATURE_CHECK_LDFLAGS-libunwind-$(1) = -L$(LIBUNWIND_DIR)/lib
+endef
+
 ifdef LIBUNWIND_DIR
   LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
   LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64
+  $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch)))
 endif
-LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
 
 # Set per-feature check compilation flags
 FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS) $(LIBUNWIND_LIBS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
@@ -107,7 +115,7 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
-FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
+FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -198,11 +206,11 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/uapi
 CFLAGS += -I$(srctree)/tools/include/
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
-CFLAGS += -I$(srctree)/arch/$(ARCH)/include
-CFLAGS += -I$(srctree)/include/uapi
-CFLAGS += -I$(srctree)/include
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
+CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/
 
 # $(obj-perf)      for generated common-cmds.h
 # $(obj-perf)/util for generated bison/flex headers
@@ -249,7 +257,7 @@ else
       LIBC_SUPPORT := 1
     endif
     ifeq ($(LIBC_SUPPORT),1)
-      msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install elfutils-libelf-devel/libelf-dev);
+      msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel);
 
       NO_LIBELF := 1
       NO_DWARF := 1
@@ -301,6 +309,16 @@ ifndef NO_LIBELF
     CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
   endif
 
+  ifeq ($(feature-libelf-gelf_getnote), 1)
+    CFLAGS += -DHAVE_GELF_GETNOTE_SUPPORT
+  else
+    msg := $(warning gelf_getnote() not found on libelf, SDT support disabled);
+  endif
+
+  ifeq ($(feature-libelf-getshdrstrndx), 1)
+    CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT
+  endif
+
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
       msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
@@ -337,6 +355,16 @@ ifndef NO_LIBELF
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
+ifndef NO_SDT
+  ifneq ($(feature-sdt), 1)
+    msg := $(warning No sys/sdt.h found, no SDT events are defined, please install systemtap-sdt-devel or systemtap-sdt-dev);
+    NO_SDT := 1;
+  else
+    CFLAGS += -DHAVE_SDT_EVENT
+    $(call detected,CONFIG_SDT_EVENT)
+  endif
+endif
+
 ifdef PERF_HAVE_JITDUMP
   ifndef NO_DWARF
     $(call detected,CONFIG_JITDUMP)
@@ -351,10 +379,42 @@ ifeq ($(ARCH),powerpc)
 endif
 
 ifndef NO_LIBUNWIND
+  have_libunwind :=
+
+  ifeq ($(feature-libunwind-x86), 1)
+    $(call detected,CONFIG_LIBUNWIND_X86)
+    CFLAGS += -DHAVE_LIBUNWIND_X86_SUPPORT
+    LDFLAGS += -lunwind-x86
+    EXTLIBS_LIBUNWIND += -lunwind-x86
+    have_libunwind = 1
+  endif
+
+  ifeq ($(feature-libunwind-aarch64), 1)
+    $(call detected,CONFIG_LIBUNWIND_AARCH64)
+    CFLAGS += -DHAVE_LIBUNWIND_AARCH64_SUPPORT
+    LDFLAGS += -lunwind-aarch64
+    EXTLIBS_LIBUNWIND += -lunwind-aarch64
+    have_libunwind = 1
+    $(call feature_check,libunwind-debug-frame-aarch64)
+    ifneq ($(feature-libunwind-debug-frame-aarch64), 1)
+      msg := $(warning No debug_frame support found in libunwind-aarch64);
+      CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME_AARCH64
+    endif
+  endif
+
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
+    NO_LOCAL_LIBUNWIND := 1
+  else
+    have_libunwind := 1
+    $(call detected,CONFIG_LOCAL_LIBUNWIND)
+  endif
+
+  ifneq ($(have_libunwind), 1)
     NO_LIBUNWIND := 1
   endif
+else
+  NO_LOCAL_LIBUNWIND := 1
 endif
 
 ifndef NO_LIBBPF
@@ -392,7 +452,7 @@ else
   NO_DWARF_UNWIND := 1
 endif
 
-ifndef NO_LIBUNWIND
+ifndef NO_LOCAL_LIBUNWIND
   ifeq ($(ARCH),$(filter $(ARCH),arm arm64))
     $(call feature_check,libunwind-debug-frame)
     ifneq ($(feature-libunwind-debug-frame), 1)
@@ -403,10 +463,15 @@ ifndef NO_LIBUNWIND
     # non-ARM has no dwarf_find_debug_frame() function:
     CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
   endif
-  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
   EXTLIBS += $(LIBUNWIND_LIBS)
+  LDFLAGS += $(LIBUNWIND_LIBS)
+endif
+
+ifndef NO_LIBUNWIND
+  CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
   CFLAGS  += $(LIBUNWIND_CFLAGS)
   LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  EXTLIBS += $(EXTLIBS_LIBUNWIND)
 endif
 
 ifndef NO_LIBAUDIT
@@ -437,7 +502,7 @@ endif
 
 ifndef NO_SLANG
   ifneq ($(feature-libslang), 1)
-    msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
+    msg := $(warning slang not found, disables TUI support. Please install slang-devel, libslang-dev or libslang2-dev);
     NO_SLANG := 1
   else
     # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index bde8cbae7dd9..2d9087501633 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -81,6 +81,9 @@ include ../scripts/utilities.mak
 #
 # Define NO_LIBBPF if you do not want BPF support
 #
+# Define NO_SDT if you do not want to define SDT event in perf tools,
+# note that it doesn't disable SDT scanning support.
+#
 # Define FEATURES_DUMP to provide features detection dump file
 # and bypass the feature detection
 
@@ -158,7 +161,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 BPF_DIR         = $(srctree)/tools/lib/bpf/
 SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
 
-# include config/Makefile by default and rule out
+# include Makefile.config by default and rule out
 # non-config cases
 config := 1
 
@@ -180,7 +183,7 @@ ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
 FEATURE_TESTS := all
 endif
 endif
-include config/Makefile
+include Makefile.config
 endif
 
 ifeq ($(config),0)
@@ -254,7 +257,8 @@ PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
-        $(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+        $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
+        CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
           $(PYTHON_WORD) util/setup.py \
           --quiet build_ext; \
         mkdir -p $(OUTPUT)python && \
@@ -344,6 +348,87 @@ export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 include $(srctree)/tools/build/Makefile.include
 
 $(PERF_IN): prepare FORCE
+        @(test -f ../../include/uapi/linux/perf_event.h && ( \
+        (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/linux/hash.h && ( \
+        (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
+        || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
+        (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
+        || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/asm/disabled-features.h && ( \
+        (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/asm/required-features.h && ( \
+        (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \
+        (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/lib/memcpy_64.S && ( \
+        (diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/lib/memset_64.S && ( \
+        (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \
+        || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true
+        @(test -f ../../arch/arm/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/perf_regs.h ../../arch/arm/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/arm64/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/perf_regs.h ../../arch/arm64/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/powerpc/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/perf_regs.h ../../arch/powerpc/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/uapi/asm/perf_regs.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/perf_regs.h ../../arch/x86/include/uapi/asm/perf_regs.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/perf_regs.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm.h ../../arch/x86/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/kvm_perf.h ../../arch/x86/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/uapi/asm/svm.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/svm.h ../../arch/x86/include/uapi/asm/svm.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/svm.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/x86/include/uapi/asm/vmx.h && ( \
+        (diff -B ../arch/x86/include/uapi/asm/vmx.h ../../arch/x86/include/uapi/asm/vmx.h >/dev/null) \
+        || echo "Warning: tools/arch/x86/include/uapi/asm/vmx.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/powerpc/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/powerpc/include/uapi/asm/kvm.h ../../arch/powerpc/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/powerpc/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/s390/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm.h ../../arch/s390/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/s390/include/uapi/asm/kvm_perf.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/kvm_perf.h ../../arch/s390/include/uapi/asm/kvm_perf.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/kvm_perf.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/s390/include/uapi/asm/sie.h && ( \
+        (diff -B ../arch/s390/include/uapi/asm/sie.h ../../arch/s390/include/uapi/asm/sie.h >/dev/null) \
+        || echo "Warning: tools/arch/s390/include/uapi/asm/sie.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/arm/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm/include/uapi/asm/kvm.h ../../arch/arm/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+        @(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
+        (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
+        || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/asm-generic/bitops/__fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/asm-generic/bitops/fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
+        @(test -f ../../include/asm-generic/bitops/fls64.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
         $(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
@@ -621,7 +706,7 @@ $(INSTALL_DOC_TARGETS):
 ### Cleaning rules
 
 #
-# This is here, not in config/Makefile, because config/Makefile does
+# This is here, not in Makefile.config, because Makefile.config does
 # not get included for the clean target:
 #
 config-clean:
diff --git a/tools/perf/arch/arm/util/Build b/tools/perf/arch/arm/util/Build
index d22e3d07de3d..f98da17357c0 100644
--- a/tools/perf/arch/arm/util/Build
+++ b/tools/perf/arch/arm/util/Build
@@ -1,4 +1,4 @@
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
-libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index e58123a8912b..02f41dba4f4f 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -1,2 +1,2 @@
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
-libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index a87afa91a99e..c116b713f7f7 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -1,11 +1,13 @@
 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 #include "../../util/debug.h"
+#endif
 
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
         switch (regnum) {
         case UNW_AARCH64_X0:
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index e83c8ce24303..886dd2aaff0d 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,6 +1,7 @@
 #include <stdio.h>
 #include <sys/utsname.h>
 #include "common.h"
+#include "../util/util.h"
 #include "../util/debug.h"
 
 const char *const arm_triplets[] = {
@@ -9,34 +10,44 @@ const char *const arm_triplets[] = {
         "arm-unknown-linux-",
         "arm-unknown-linux-gnu-",
         "arm-unknown-linux-gnueabi-",
+        "arm-linux-gnu-",
+        "arm-linux-gnueabihf-",
+        "arm-none-eabi-",
         NULL
 };
 
 const char *const arm64_triplets[] = {
         "aarch64-linux-android-",
+        "aarch64-linux-gnu-",
         NULL
 };
 
 const char *const powerpc_triplets[] = {
         "powerpc-unknown-linux-gnu-",
         "powerpc64-unknown-linux-gnu-",
+        "powerpc64-linux-gnu-",
+        "powerpc64le-linux-gnu-",
         NULL
 };
 
 const char *const s390_triplets[] = {
         "s390-ibm-linux-",
+        "s390x-linux-gnu-",
         NULL
 };
 
 const char *const sh_triplets[] = {
         "sh-unknown-linux-gnu-",
         "sh64-unknown-linux-gnu-",
+        "sh-linux-gnu-",
+        "sh64-linux-gnu-",
         NULL
 };
 
 const char *const sparc_triplets[] = {
         "sparc-unknown-linux-gnu-",
         "sparc64-unknown-linux-gnu-",
+        "sparc64-linux-gnu-",
         NULL
 };
 
@@ -49,12 +60,19 @@ const char *const x86_triplets[] = {
         "i386-pc-linux-gnu-",
         "i686-linux-android-",
         "i686-android-linux-",
+        "x86_64-linux-gnu-",
+        "i586-linux-gnu-",
         NULL
 };
 
 const char *const mips_triplets[] = {
         "mips-unknown-linux-gnu-",
         "mipsel-linux-android-",
+        "mips-linux-gnu-",
+        "mips64-linux-gnu-",
+        "mips64el-linux-gnuabi64-",
+        "mips64-linux-gnuabi64-",
+        "mipsel-linux-gnu-",
         NULL
 };
 
@@ -102,7 +120,7 @@ static int lookup_triplets(const char *const *triplets, const char *name)
  * Return architecture name in a normalized form.
  * The conversion logic comes from the Makefile.
  */
-static const char *normalize_arch(char *arch)
+const char *normalize_arch(char *arch)
 {
         if (!strcmp(arch, "x86_64"))
                 return "x86";
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index 7529cfb143ce..6b01c736b7d9 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -6,5 +6,6 @@
 extern const char *objdump_path;
 
 int perf_env__lookup_objdump(struct perf_env *env);
+const char *normalize_arch(char *arch);
 
 #endif /* ARCH_PERF_COMMON_H */
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 8a61372bb47a..5bd7b9260cc0 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,3 +2,5 @@ libperf-y += header.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
+
+libperf-y += machine.o
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
new file mode 100644
index 000000000000..b9a95a1a8e69
--- /dev/null
+++ b/tools/perf/arch/s390/util/machine.c
@@ -0,0 +1,19 @@
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "machine.h"
+#include "api/fs/fs.h"
+
+int arch__fix_module_text_start(u64 *start, const char *name)
+{
+        char path[PATH_MAX];
+
+        snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
+                                (int)strlen(name) - 2, name + 1);
+
+        if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
+                return -1;
+
+        return 0;
+}
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index cac6d17ce5db..555263e385c9 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,3 +374,5 @@
 543     x32     io_setup                compat_sys_io_setup
 544     x32     io_submit               compat_sys_io_submit
 545     x32     execveat                compat_sys_execveat/ptregs
+534     x32     preadv2                 compat_sys_preadv2
+535     x32     pwritev2                compat_sys_pwritev2
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
index 3b491cfe204e..0f196eec9f48 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c
@@ -6,6 +6,1016 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 81 78 56 34 12    \tbound  %eax,0x12345678(%ecx)",},
+{{0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 88 78 56 34 12    \tbound  %ecx,0x12345678(%eax)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 98 78 56 34 12    \tbound  %ebx,0x12345678(%eax)",},
+{{0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a0 78 56 34 12    \tbound  %esp,0x12345678(%eax)",},
+{{0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 a8 78 56 34 12    \tbound  %ebp,0x12345678(%eax)",},
+{{0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b0 78 56 34 12    \tbound  %esi,0x12345678(%eax)",},
+{{0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 b8 78 56 34 12    \tbound  %edi,0x12345678(%eax)",},
+{{0x62, 0x08, }, 2, 0, "", "",
+"62 08                \tbound  %ecx,(%eax)",},
+{{0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 05 78 56 34 12    \tbound  %eax,0x12345678",},
+{{0x62, 0x14, 0x01, }, 3, 0, "", "",
+"62 14 01             \tbound  %edx,(%ecx,%eax,1)",},
+{{0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 14 05 78 56 34 12 \tbound  %edx,0x12345678(,%eax,1)",},
+{{0x62, 0x14, 0x08, }, 3, 0, "", "",
+"62 14 08             \tbound  %edx,(%eax,%ecx,1)",},
+{{0x62, 0x14, 0xc8, }, 3, 0, "", "",
+"62 14 c8             \tbound  %edx,(%eax,%ecx,8)",},
+{{0x62, 0x50, 0x12, }, 3, 0, "", "",
+"62 50 12             \tbound  %edx,0x12(%eax)",},
+{{0x62, 0x55, 0x12, }, 3, 0, "", "",
+"62 55 12             \tbound  %edx,0x12(%ebp)",},
+{{0x62, 0x54, 0x01, 0x12, }, 4, 0, "", "",
+"62 54 01 12          \tbound  %edx,0x12(%ecx,%eax,1)",},
+{{0x62, 0x54, 0x05, 0x12, }, 4, 0, "", "",
+"62 54 05 12          \tbound  %edx,0x12(%ebp,%eax,1)",},
+{{0x62, 0x54, 0x08, 0x12, }, 4, 0, "", "",
+"62 54 08 12          \tbound  %edx,0x12(%eax,%ecx,1)",},
+{{0x62, 0x54, 0xc8, 0x12, }, 4, 0, "", "",
+"62 54 c8 12          \tbound  %edx,0x12(%eax,%ecx,8)",},
+{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 90 78 56 34 12    \tbound  %edx,0x12345678(%eax)",},
+{{0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "",
+"62 95 78 56 34 12    \tbound  %edx,0x12345678(%ebp)",},
+{{0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 01 78 56 34 12 \tbound  %edx,0x12345678(%ecx,%eax,1)",},
+{{0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 05 78 56 34 12 \tbound  %edx,0x12345678(%ebp,%eax,1)",},
+{{0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 08 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,1)",},
+{{0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"62 94 c8 78 56 34 12 \tbound  %edx,0x12345678(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 81 78 56 34 12 \tbound  %ax,0x12345678(%ecx)",},
+{{0x66, 0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 88 78 56 34 12 \tbound  %cx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 98 78 56 34 12 \tbound  %bx,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a0 78 56 34 12 \tbound  %sp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 a8 78 56 34 12 \tbound  %bp,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b0 78 56 34 12 \tbound  %si,0x12345678(%eax)",},
+{{0x66, 0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 b8 78 56 34 12 \tbound  %di,0x12345678(%eax)",},
+{{0x66, 0x62, 0x08, }, 3, 0, "", "",
+"66 62 08             \tbound  %cx,(%eax)",},
+{{0x66, 0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 05 78 56 34 12 \tbound  %ax,0x12345678",},
+{{0x66, 0x62, 0x14, 0x01, }, 4, 0, "", "",
+"66 62 14 01          \tbound  %dx,(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 14 05 78 56 34 12 \tbound  %dx,0x12345678(,%eax,1)",},
+{{0x66, 0x62, 0x14, 0x08, }, 4, 0, "", "",
+"66 62 14 08          \tbound  %dx,(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x14, 0xc8, }, 4, 0, "", "",
+"66 62 14 c8          \tbound  %dx,(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x50, 0x12, }, 4, 0, "", "",
+"66 62 50 12          \tbound  %dx,0x12(%eax)",},
+{{0x66, 0x62, 0x55, 0x12, }, 4, 0, "", "",
+"66 62 55 12          \tbound  %dx,0x12(%ebp)",},
+{{0x66, 0x62, 0x54, 0x01, 0x12, }, 5, 0, "", "",
+"66 62 54 01 12       \tbound  %dx,0x12(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x05, 0x12, }, 5, 0, "", "",
+"66 62 54 05 12       \tbound  %dx,0x12(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x54, 0x08, 0x12, }, 5, 0, "", "",
+"66 62 54 08 12       \tbound  %dx,0x12(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x54, 0xc8, 0x12, }, 5, 0, "", "",
+"66 62 54 c8 12       \tbound  %dx,0x12(%eax,%ecx,8)",},
+{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 90 78 56 34 12 \tbound  %dx,0x12345678(%eax)",},
+{{0x66, 0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"66 62 95 78 56 34 12 \tbound  %dx,0x12345678(%ebp)",},
+{{0x66, 0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 01 78 56 34 12 \tbound  %dx,0x12345678(%ecx,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 05 78 56 34 12 \tbound  %dx,0x12345678(%ebp,%eax,1)",},
+{{0x66, 0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 08 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,1)",},
+{{0x66, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 62 94 c8 78 56 34 12 \tbound  %dx,0x12345678(%eax,%ecx,8)",},
+{{0x0f, 0x41, 0xd8, }, 3, 0, "", "",
+"0f 41 d8             \tcmovno %eax,%ebx",},
+{{0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%cx",},
+{{0x0f, 0x44, 0xd8, }, 3, 0, "", "",
+"0f 44 d8             \tcmove  %eax,%ebx",},
+{{0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%ecx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%eax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%eax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%eax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%eax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%eax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%ecx),%k5",},
+{{0xc5, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 90 ac c8 23 01 00 00 \tkmovw  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%ecx)",},
+{{0xc5, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f8 91 ac c8 23 01 00 00 \tkmovw  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 90 ac c8 23 01 00 00 \tkmovq  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f8 91 ac c8 23 01 00 00 \tkmovq  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%ecx),%k5",},
+{{0xc5, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 90 ac c8 23 01 00 00 \tkmovb  0x123(%eax,%ecx,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%ecx)",},
+{{0xc5, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "",
+"c5 f9 91 ac c8 23 01 00 00 \tkmovb  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%ecx),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 90 ac c8 23 01 00 00 \tkmovd  0x123(%eax,%ecx,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%ecx)",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 e1 f9 91 ac c8 23 01 00 00 \tkmovd  %k5,0x123(%eax,%ecx,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 5b f5    \tvcvtqq2ps %zmm5,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 48 6f f5    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 6f f5    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 48 6f f5    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 6f f5    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 6f f5    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 48 6f f5    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 78 f5    \tvcvttps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 78 f5    \tvcvttpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 78 c6    \tvcvttsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 78 c6    \tvcvttss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 78 f5    \tvcvttps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 78 f5    \tvcvttpd2uqq %zmm5,%zmm6",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %eax,%ebx",},
+{{0x62, 0xf1, 0x7c, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7c 48 79 f5    \tvcvtps2udq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fc 4f 79 f5    \tvcvtpd2udq %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7f, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7f 08 79 c6    \tvcvtsd2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7e, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 7e 08 79 c6    \tvcvtss2usi %xmm6,%eax",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 79 f5    \tvcvtps2uqq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 79 f5    \tvcvtpd2uqq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f 7a f5    \tvcvtudq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 7a f5    \tvcvtuqq2pd %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7f 48 7a f5    \tvcvtudq2ps %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 ff 4f 7a f5    \tvcvtuqq2ps %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7a f5    \tvcvttps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7a f5    \tvcvttpd2qq %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7d, 0x4f, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 7d 4f 7b f5    \tvcvtps2qq %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 f1 fd 48 7b f5    \tvcvtpd2qq %zmm5,%zmm6",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fd 7f ee          \tvmovdqa %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7d, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7d 48 7f ee    \tvmovdqa32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfd, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fd 48 7f ee    \tvmovdqa64 %zmm5,%zmm6",},
+{{0xc5, 0xfe, 0x7f, 0xee, }, 4, 0, "", "",
+"c5 fe 7f ee          \tvmovdqu %ymm5,%ymm6",},
+{{0x62, 0xf1, 0x7e, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7e 48 7f ee    \tvmovdqu32 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xfe, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 fe 48 7f ee    \tvmovdqu64 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0x7f, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 7f 48 7f ee    \tvmovdqu8 %zmm5,%zmm6",},
+{{0x62, 0xf1, 0xff, 0x48, 0x7f, 0xee, }, 6, 0, "", "",
+"62 f1 ff 48 7f ee    \tvmovdqu16 %zmm5,%zmm6",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 db f4    \tvpandd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 db f4    \tvpandq %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 df f4    \tvpandnd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xdf, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 df f4    \tvpandnq %zmm4,%zmm5,%zmm6",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0xf1, 0x7e, 0x4f, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 7e 4f e6 f5    \tvcvtdq2pd %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xfe, 0x48, 0xe6, 0xf5, }, 6, 0, "", "",
+"62 f1 fe 48 e6 f5    \tvcvtqq2pd %zmm5,%zmm6",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 eb f4    \tvpord  %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xeb, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 eb f4    \tvporq  %zmm4,%zmm5,%zmm6",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x55, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 55 48 ef f4    \tvpxord %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0xef, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 ef f4    \tvpxorq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x10, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 10 f4    \tvpsrlvw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x10, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 10 ee    \tvpmovuswb %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x11, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 11 ee    \tvpmovusdb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x11, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 11 f4    \tvpsravw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x12, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 12 ee    \tvpmovusqb %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x12, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 12 f4    \tvpsllvw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0xf2, 0x7d, 0x4f, 0x13, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 4f 13 f5    \tvcvtph2ps %ymm5,%zmm6{%k7}",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x13, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 13 ee    \tvpmovusdw %zmm5,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x14, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 14 ee    \tvpmovusqw %zmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 14 f4    \tvprorvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x14, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 14 f4    \tvprorvq %zmm4,%zmm5,%zmm6",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x15, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 15 ee    \tvpmovusqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x55, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 15 f4    \tvprolvd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x15, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 15 f4    \tvprolvq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 16 d4    \tvpermps %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x16, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 16 d4    \tvpermpd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x19, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 19 f7    \tvbroadcastf32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1a 31    \tvbroadcastf32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1a 31    \tvbroadcastf64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 1b 31    \tvbroadcastf32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 1b 31    \tvbroadcastf64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x1f, 0xf4, }, 6, 0, "", "",
+"62 f2 fd 48 1f f4    \tvpabsq %zmm4,%zmm6",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x20, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 20 ee    \tvpmovswb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x21, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 21 ee    \tvpmovsdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x22, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 22 ee    \tvpmovsqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x23, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 23 ee    \tvpmovsdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x24, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 24 ee    \tvpmovsqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x25, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 25 ee    \tvpmovsqd %zmm5,%ymm6{%k7}",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 26 ed    \tvptestmb %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x26, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 26 ed    \tvptestmw %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 26 ec    \tvptestnmb %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x26, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 26 ec    \tvptestnmw %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0x4d, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 4d 48 27 ed    \tvptestmd %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0xcd, 0x48, 0x27, 0xed, }, 6, 0, "", "",
+"62 f2 cd 48 27 ed    \tvptestmq %zmm5,%zmm6,%k5",},
+{{0x62, 0xf2, 0x56, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 56 48 27 ec    \tvptestnmd %zmm4,%zmm5,%k5",},
+{{0x62, 0xf2, 0xd6, 0x48, 0x27, 0xec, }, 6, 0, "", "",
+"62 f2 d6 48 27 ec    \tvptestnmq %zmm4,%zmm5,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 28 f5    \tvpmovm2b %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x28, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 28 f5    \tvpmovm2w %k5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 29 ee    \tvpmovb2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x29, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 29 ee    \tvpmovw2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%ecx),%ymm4",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x2a, 0xce, }, 6, 0, "", "",
+"62 f2 fe 48 2a ce    \tvpbroadcastmb2q %k6,%zmm1",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 2c f4    \tvscalefps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x2c, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 2c f4    \tvscalefpd %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%ecx),%ymm4,%ymm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 2d f4    \tvscalefss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 2d f4    \tvscalefsd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x30, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 30 ee    \tvpmovwb %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x31, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 31 ee    \tvpmovdb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x32, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 32 ee    \tvpmovqb %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x33, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 33 ee    \tvpmovdw %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x34, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 34 ee    \tvpmovqw %zmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0xf2, 0x7e, 0x4f, 0x35, 0xee, }, 6, 0, "", "",
+"62 f2 7e 4f 35 ee    \tvpmovqd %zmm5,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x4d, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 4d 2f 36 d4    \tvpermd %ymm4,%ymm6,%ymm2{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x2f, 0x36, 0xd4, }, 6, 0, "", "",
+"62 f2 cd 2f 36 d4    \tvpermq %ymm4,%ymm6,%ymm2{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 7e 48 38 f5    \tvpmovm2d %k5,%zmm6",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x38, 0xf5, }, 6, 0, "", "",
+"62 f2 fe 48 38 f5    \tvpmovm2q %k5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 39 f4    \tvpminsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x39, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 39 f4    \tvpminsq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 7e 48 39 ee    \tvpmovd2m %zmm6,%k5",},
+{{0x62, 0xf2, 0xfe, 0x48, 0x39, 0xee, }, 6, 0, "", "",
+"62 f2 fe 48 39 ee    \tvpmovq2m %zmm6,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x7e, 0x48, 0x3a, 0xf6, }, 6, 0, "", "",
+"62 f2 7e 48 3a f6    \tvpbroadcastmw2d %k6,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3b f4    \tvpminud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3b, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3b f4    \tvpminuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3d f4    \tvpmaxsd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3d f4    \tvpmaxsq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 3f f4    \tvpmaxud %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x3f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 3f f4    \tvpmaxuq %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 40 f4    \tvpmulld %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x40, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 40 f4    \tvpmullq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 42 f5    \tvgetexpps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x42, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 42 f5    \tvgetexppd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x43, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 43 f4    \tvgetexpss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xe5, 0x0f, 0x43, 0xe2, }, 6, 0, "", "",
+"62 f2 e5 0f 43 e2    \tvgetexpsd %xmm2,%xmm3,%xmm4{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 44 f5    \tvplzcntd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x44, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 44 f5    \tvplzcntq %zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf2, 0x55, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 46 f4    \tvpsravd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x46, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 46 f4    \tvpsravq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4c f5    \tvrcp14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4c, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4c f5    \tvrcp14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4d f4    \tvrcp14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4d f4    \tvrcp14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 4e f5    \tvrsqrt14ps %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x4e, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 4e f5    \tvrsqrt14pd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 0f 4f f4    \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",},
+{{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 0f 4f f4    \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "",
+"62 f2 7d 48 59 f7    \tvbroadcasti32x2 %xmm7,%zmm6",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%ecx),%ymm4",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5a 31    \tvbroadcasti32x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5a 31    \tvbroadcasti64x2 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 5b 31    \tvbroadcasti32x8 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 5b 31    \tvbroadcasti64x4 (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 64 f4    \tvpblendmd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 64 f4    \tvpblendmq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 65 f4    \tvblendmps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x65, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 65 f4    \tvblendmpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 66 f4    \tvpblendmb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 66 f4    \tvpblendmw %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 75 f4    \tvpermi2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 75 f4    \tvpermi2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 76 f4    \tvpermi2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x76, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 76 f4    \tvpermi2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 77 f4    \tvpermi2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x77, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 77 f4    \tvpermi2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7a, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7a d8    \tvpbroadcastb %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7b, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7b d8    \tvpbroadcastw %eax,%xmm3",},
+{{0x62, 0xf2, 0x7d, 0x08, 0x7c, 0xd8, }, 6, 0, "", "",
+"62 f2 7d 08 7c d8    \tvpbroadcastd %eax,%xmm3",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7d f4    \tvpermt2b %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7d f4    \tvpermt2w %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7e f4    \tvpermt2d %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7e, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7e f4    \tvpermt2q %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x55, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 7f f4    \tvpermt2ps %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x7f, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 7f f4    \tvpermt2pd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x83, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 83 f4    \tvpmultishiftqb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 88 31    \tvexpandps (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x88, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 88 31    \tvexpandpd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 89 31    \tvpexpandd (%ecx),%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x89, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 89 31    \tvpexpandq (%ecx),%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8a 31    \tvcompressps %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8a, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8a 31    \tvcompresspd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x7d, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 7d 48 8b 31    \tvpcompressd %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0xfd, 0x48, 0x8b, 0x31, }, 6, 0, "", "",
+"62 f2 fd 48 8b 31    \tvpcompressq %zmm6,(%ecx)",},
+{{0x62, 0xf2, 0x55, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 55 48 8d f4    \tvpermb %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 8d f4    \tvpermw %zmm4,%zmm5,%zmm6",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 90 b4 fd 7b 00 00 00 \tvpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 90 b4 fd 7b 00 00 00 \tvpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%ebp,%xmm7,2),%xmm1",},
+{{0x62, 0xf2, 0x7d, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a0 b4 fd 7b 00 00 00 \tvpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a1 b4 fd 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x29, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 29 a1 b4 fd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a2 b4 fd 7b 00 00 00 \tvscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a2 b4 fd 7b 00 00 00 \tvscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b4 f4    \tvpmadd52luq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "",
+"62 f2 d5 48 b5 f4    \tvpmadd52huq %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 7d 48 c4 f5    \tvpconflictd %zmm5,%zmm6",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc4, 0xf5, }, 6, 0, "", "",
+"62 f2 fd 48 c4 f5    \tvpconflictq %zmm5,%zmm6",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 c8 fe    \tvexp2ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xc8, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 c8 fe    \tvexp2pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 ca fe    \tvrcp28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xca, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 ca fe    \tvrcp28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cb fd    \tvrcp28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cb fd    \tvrcp28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0x7d, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 7d 48 cc fe    \tvrsqrt28ps %zmm6,%zmm7",},
+{{0x62, 0xf2, 0xfd, 0x48, 0xcc, 0xfe, }, 6, 0, "", "",
+"62 f2 fd 48 cc fe    \tvrsqrt28pd %zmm6,%zmm7",},
+{{0x62, 0xf2, 0x4d, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 4d 0f cd fd    \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "",
+"62 f2 cd 0f cd fd    \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 03 fd 12 \tvalignq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x08, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 08 f5 12 \tvrndscaleps $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x09, 0xf5, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 09 f5 12 \tvrndscalepd $0x12,%zmm5,%zmm6",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0x55, 0x0f, 0x0a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 0f 0a f4 12 \tvrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0xf3, 0xd5, 0x0f, 0x0b, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 0f 0b f4 12 \tvrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 18 f4 12 \tvinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 18 f4 12 \tvinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 19 ee 12 \tvextractf32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 19 ee 12 \tvextractf64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 1a fd 12 \tvinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 1a fd 12 \tvinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 1b f7 12 \tvextractf32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 1b f7 12 \tvextractf64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1e ee 12 \tvpcmpud $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1e ee 12 \tvpcmpuq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 1f ee 12 \tvpcmpd $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 1f ee 12 \tvpcmpq $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 23 fd 12 \tvshuff32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 23 fd 12 \tvshuff64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 25 fd 12 \tvpternlogd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 25 fd 12 \tvpternlogq $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 26 fe 12 \tvgetmantps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 26 fe 12 \tvgetmantpd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 27 fd 12 \tvgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 27 fd 12 \tvgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0xf3, 0x55, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 4f 38 f4 12 \tvinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf3, 0xd5, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 d5 4f 38 f4 12 \tvinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 39 ee 12 \tvextracti32x4 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 39 ee 12 \tvextracti64x2 $0x12,%zmm5,%xmm6{%k7}",},
+{{0x62, 0xf3, 0x4d, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 4f 3a fd 12 \tvinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 4f 3a fd 12 \tvinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 7d 4f 3b f7 12 \tvextracti32x8 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0xfd, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "",
+"62 f3 fd 4f 3b f7 12 \tvextracti64x4 $0x12,%zmm6,%ymm7{%k7}",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3e ee 12 \tvpcmpub $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3e ee 12 \tvpcmpuw $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0x45, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 45 48 3f ee 12 \tvpcmpb $0x12,%zmm6,%zmm7,%k5",},
+{{0x62, 0xf3, 0xc5, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "",
+"62 f3 c5 48 3f ee 12 \tvpcmpw $0x12,%zmm6,%zmm7,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 50 fd 12 \tvrangepd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 51 fd 12 \tvrangess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 51 fd 12 \tvrangesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x4d, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 48 54 fd 12 \tvfixupimmps $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xcd, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 48 54 fd 12 \tvfixupimmpd $0x12,%zmm5,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 0f 55 fd 12 \tvfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0xcd, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 0f 55 fd 12 \tvfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 56 fe 12 \tvreduceps $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 56 fe 12 \tvreducepd $0x12,%zmm6,%zmm7",},
+{{0x62, 0xf3, 0x4d, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 4d 08 57 fd 12 \tvreducess $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0xcd, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "",
+"62 f3 cd 08 57 fd 12 \tvreducesd $0x12,%xmm5,%xmm6,%xmm7",},
+{{0x62, 0xf3, 0x7d, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 48 66 ef 12 \tvfpclassps $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 48 66 ef 12 \tvfpclasspd $0x12,%zmm7,%k5",},
+{{0x62, 0xf3, 0x7d, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",},
+{{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "",
+"62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 c5 12 \tvprorq $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 4d 48 72 cd 12 \tvprold $0x12,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 f1 cd 48 72 cd 12 \tvprolq $0x12,%zmm5,%zmm6",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0xf1, 0x6d, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 6d 48 72 e6 05 \tvpsrad $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf1, 0xed, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "",
+"62 f1 ed 48 72 e6 05 \tvpsraq $0x5,%zmm6,%zmm2",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 7d 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 f2 fd 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 48 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x4f, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 4f 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}",},
+{{0x62, 0xf1, 0xd5, 0xcf, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 cf 58 f4    \tvaddpd %zmm4,%zmm5,%zmm6{%k7}{z}",},
+{{0x62, 0xf1, 0xd5, 0x18, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 18 58 f4    \tvaddpd {rn-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 58 58 f4    \tvaddpd {ru-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x38, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 38 58 f4    \tvaddpd {rd-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x78, 0x58, 0xf4, }, 6, 0, "", "",
+"62 f1 d5 78 58 f4    \tvaddpd {rz-sae},%zmm4,%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 48 58 31    \tvaddpd (%ecx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xb4, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 f1 d5 48 58 b4 c8 23 01 00 00 \tvaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x31, }, 6, 0, "", "",
+"62 f1 d5 58 58 31    \tvaddpd (%ecx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 48 58 72 7f \tvaddpd 0x1fc0(%edx),%zmm5,%zmm6",},
+{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 f1 d5 58 58 72 7f \tvaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6",},
+{{0x62, 0xf1, 0x4c, 0x58, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 4c 58 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5",},
+{{0x62, 0xf1, 0xe7, 0x0f, 0xc2, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 f1 e7 0f c2 ac c8 23 01 00 00 01 \tvcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}",},
+{{0x62, 0xf1, 0xd7, 0x1f, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 f1 d7 1f c2 ec 02 \tvcmplesd {sae},%xmm4,%xmm5,%k5{%k7}",},
+{{0x62, 0xf3, 0x5d, 0x0f, 0x27, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 f3 5d 0f 27 ac c8 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%eax),%bnd0",},
 {{0xf3, 0x0f, 0x1b, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
@@ -309,19 +1319,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%eax,%ecx,1)",},
 {{0xf2, 0xe8, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "call", "unconditional",
-"f2 e8 fc ff ff ff    \tbnd call 3c3 <main+0x3c3>",},
+"f2 e8 fc ff ff ff    \tbnd call fce <main+0xfce>",},
 {{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect",
 "f2 ff 10             \tbnd call *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd ret ",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3ce <main+0x3ce>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fd9 <main+0xfd9>",},
 {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional",
-"f2 e9 fc ff ff ff    \tbnd jmp 3d4 <main+0x3d4>",},
+"f2 e9 fc ff ff ff    \tbnd jmp fdf <main+0xfdf>",},
 {{0xf2, 0xff, 0x21, }, 3, 0, "jmp", "indirect",
 "f2 ff 21             \tbnd jmp *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional",
-"f2 0f 85 fc ff ff ff \tbnd jne 3de <main+0x3de>",},
+"f2 0f 85 fc ff ff ff \tbnd jne fe9 <main+0xfe9>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
@@ -654,5 +1664,3 @@
 "0f c7 1d 78 56 34 12 \txrstors 0x12345678",},
 {{0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%eax,%ecx,8)",},
-{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "",
-"66 0f ae f8          \tpcommit ",},
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
index 4fe7cce179c4..af25bc8240d0 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c
@@ -6,6 +6,938 @@
 
 {{0x0f, 0x31, }, 2, 0, "", "",
 "0f 31                \trdtsc  ",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x48, 0x0f, 0x41, 0xd8, }, 4, 0, "", "",
+"48 0f 41 d8          \tcmovno %rax,%rbx",},
+{{0x48, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%cx",},
+{{0x48, 0x0f, 0x44, 0xd8, }, 4, 0, "", "",
+"48 0f 44 d8          \tcmove  %rax,%rbx",},
+{{0x48, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"48 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%rcx",},
+{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
+"66 0f 44 88 78 56 34 12 \tcmove  0x12345678(%rax),%cx",},
+{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 90 80 78 56 34 12 \tseto   0x12345678(%rax)",},
+{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 91 80 78 56 34 12 \tsetno  0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 92 80 78 56 34 12 \tsetb   0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 93 80 78 56 34 12 \tsetae  0x12345678(%rax)",},
+{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 98 80 78 56 34 12 \tsets   0x12345678(%rax)",},
+{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "",
+"0f 99 80 78 56 34 12 \tsetns  0x12345678(%rax)",},
+{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cc 41 ef          \tkandw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 41 ef       \tkandq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "",
+"c5 cd 41 ef          \tkandb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 41 ef       \tkandd  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cc 42 ef          \tkandnw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 42 ef       \tkandnq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "",
+"c5 cd 42 ef          \tkandnb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 42 ef       \tkandnd %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f8 44 f7          \tknotw  %k7,%k6",},
+{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f8 44 f7       \tknotq  %k7,%k6",},
+{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "",
+"c5 f9 44 f7          \tknotb  %k7,%k6",},
+{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "",
+"c4 e1 f9 44 f7       \tknotd  %k7,%k6",},
+{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cc 45 ef          \tkorw   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 45 ef       \tkorq   %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "",
+"c5 cd 45 ef          \tkorb   %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 45 ef       \tkord   %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cc 46 ef          \tkxnorw %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 46 ef       \tkxnorq %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "",
+"c5 cd 46 ef          \tkxnorb %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 46 ef       \tkxnord %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cc 47 ef          \tkxorw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 47 ef       \tkxorq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "",
+"c5 cd 47 ef          \tkxorb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 47 ef       \tkxord  %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cc 4a ef          \tkaddw  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4a ef       \tkaddq  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "",
+"c5 cd 4a ef          \tkaddb  %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "",
+"c4 e1 cd 4a ef       \tkaddd  %k7,%k6,%k5",},
+{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cd 4b ef          \tkunpckbw %k7,%k6,%k5",},
+{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "",
+"c5 cc 4b ef          \tkunpckwd %k7,%k6,%k5",},
+{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "",
+"c4 e1 cc 4b ef       \tkunpckdq %k7,%k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f8 90 ee          \tkmovw  %k6,%k5",},
+{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f8 90 29          \tkmovw  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x78, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 90 ac f0 23 01 00 00 \tkmovw  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f8 91 29          \tkmovw  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x78, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 78 91 ac f0 23 01 00 00 \tkmovw  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f8 92 e8          \tkmovw  %eax,%k5",},
+{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f8 92 ed          \tkmovw  %ebp,%k5",},
+{{0xc4, 0xc1, 0x78, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 78 92 ed       \tkmovw  %r13d,%k5",},
+{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f8 93 c5          \tkmovw  %k5,%eax",},
+{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f8 93 ed          \tkmovw  %k5,%ebp",},
+{{0xc5, 0x78, 0x93, 0xed, }, 4, 0, "", "",
+"c5 78 93 ed          \tkmovw  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 90 ee       \tkmovq  %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 90 29       \tkmovq  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf8, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 90 ac f0 23 01 00 00 \tkmovq  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f8 91 29       \tkmovq  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf8, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f8 91 ac f0 23 01 00 00 \tkmovq  %k5,0x123(%rax,%r14,8)",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xe8, }, 5, 0, "", "",
+"c4 e1 fb 92 e8       \tkmovq  %rax,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 92 ed       \tkmovq  %rbp,%k5",},
+{{0xc4, 0xc1, 0xfb, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 fb 92 ed       \tkmovq  %r13,%k5",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xc5, }, 5, 0, "", "",
+"c4 e1 fb 93 c5       \tkmovq  %k5,%rax",},
+{{0xc4, 0xe1, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 e1 fb 93 ed       \tkmovq  %k5,%rbp",},
+{{0xc4, 0x61, 0xfb, 0x93, 0xed, }, 5, 0, "", "",
+"c4 61 fb 93 ed       \tkmovq  %k5,%r13",},
+{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "",
+"c5 f9 90 ee          \tkmovb  %k6,%k5",},
+{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "",
+"c5 f9 90 29          \tkmovb  (%rcx),%k5",},
+{{0xc4, 0xa1, 0x79, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 90 ac f0 23 01 00 00 \tkmovb  0x123(%rax,%r14,8),%k5",},
+{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "",
+"c5 f9 91 29          \tkmovb  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0x79, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 79 91 ac f0 23 01 00 00 \tkmovb  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 f9 92 e8          \tkmovb  %eax,%k5",},
+{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "",
+"c5 f9 92 ed          \tkmovb  %ebp,%k5",},
+{{0xc4, 0xc1, 0x79, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 79 92 ed       \tkmovb  %r13d,%k5",},
+{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 f9 93 c5          \tkmovb  %k5,%eax",},
+{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "",
+"c5 f9 93 ed          \tkmovb  %k5,%ebp",},
+{{0xc5, 0x79, 0x93, 0xed, }, 4, 0, "", "",
+"c5 79 93 ed          \tkmovb  %k5,%r13d",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 90 ee       \tkmovd  %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 90 29       \tkmovd  (%rcx),%k5",},
+{{0xc4, 0xa1, 0xf9, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 90 ac f0 23 01 00 00 \tkmovd  0x123(%rax,%r14,8),%k5",},
+{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "",
+"c4 e1 f9 91 29       \tkmovd  %k5,(%rcx)",},
+{{0xc4, 0xa1, 0xf9, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "",
+"c4 a1 f9 91 ac f0 23 01 00 00 \tkmovd  %k5,0x123(%rax,%r14,8)",},
+{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "",
+"c5 fb 92 e8          \tkmovd  %eax,%k5",},
+{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "",
+"c5 fb 92 ed          \tkmovd  %ebp,%k5",},
+{{0xc4, 0xc1, 0x7b, 0x92, 0xed, }, 5, 0, "", "",
+"c4 c1 7b 92 ed       \tkmovd  %r13d,%k5",},
+{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "",
+"c5 fb 93 c5          \tkmovd  %k5,%eax",},
+{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "",
+"c5 fb 93 ed          \tkmovd  %k5,%ebp",},
+{{0xc5, 0x7b, 0x93, 0xed, }, 4, 0, "", "",
+"c5 7b 93 ed          \tkmovd  %k5,%r13d",},
+{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f8 98 ee          \tkortestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 98 ee       \tkortestq %k6,%k5",},
+{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "",
+"c5 f9 98 ee          \tkortestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 98 ee       \tkortestd %k6,%k5",},
+{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f8 99 ee          \tktestw %k6,%k5",},
+{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f8 99 ee       \tktestq %k6,%k5",},
+{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "",
+"c5 f9 99 ee          \tktestb %k6,%k5",},
+{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "",
+"c4 e1 f9 99 ee       \tktestd %k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 30 ee 12    \tkshiftrw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 31 ee 5b    \tkshiftrq $0x5b,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "",
+"c4 e3 f9 32 ee 12    \tkshiftlw $0x12,%k6,%k5",},
+{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "",
+"c4 e3 f9 33 ee 5b    \tkshiftlq $0x5b,%k6,%k5",},
+{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f8 5b f5          \tvcvtdq2ps %xmm5,%xmm6",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 5b f5    \tvcvtqq2ps %zmm29,%ymm6{%k7}",},
+{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 f9 5b f5          \tvcvtps2dq %xmm5,%xmm6",},
+{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "",
+"c5 fa 5b f5          \tvcvttps2dq %xmm5,%xmm6",},
+{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "",
+"0f 6f e0             \tmovq   %mm0,%mm4",},
+{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fd 6f f4          \tvmovdqa %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 7d 48 6f d1    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fd 48 6f d1    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "",
+"c5 fe 6f f4          \tvmovdqu %ymm4,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7e 48 6f f5    \tvmovdqu32 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xfe, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 6f d1    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 6f f5    \tvmovdqu8 %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x48, 0x6f, 0xd1, }, 6, 0, "", "",
+"62 01 ff 48 6f d1    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0x78, 0xc3, }, 3, 0, "", "",
+"0f 78 c3             \tvmread %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x78, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 78 d1    \tvcvttps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 78 f5    \tvcvttpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 78 c6    \tvcvttsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x78, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 78 c6    \tvcvttss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x78, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 78 d5    \tvcvttps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 78 f5    \tvcvttpd2uqq %zmm29,%zmm30",},
+{{0x0f, 0x79, 0xd8, }, 3, 0, "", "",
+"0f 79 d8             \tvmwrite %rax,%rbx",},
+{{0x62, 0x01, 0x7c, 0x48, 0x79, 0xd1, }, 6, 0, "", "",
+"62 01 7c 48 79 d1    \tvcvtps2udq %zmm25,%zmm26",},
+{{0x62, 0x91, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "",
+"62 91 fc 4f 79 f5    \tvcvtpd2udq %zmm29,%ymm6{%k7}",},
+{{0x62, 0xf1, 0xff, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 ff 08 79 c6    \tvcvtsd2usi %xmm6,%rax",},
+{{0x62, 0xf1, 0xfe, 0x08, 0x79, 0xc6, }, 6, 0, "", "",
+"62 f1 fe 08 79 c6    \tvcvtss2usi %xmm6,%rax",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x79, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 79 d5    \tvcvtps2uqq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 79 f5    \tvcvtpd2uqq %zmm29,%zmm30",},
+{{0x62, 0x61, 0x7e, 0x4f, 0x7a, 0xed, }, 6, 0, "", "",
+"62 61 7e 4f 7a ed    \tvcvtudq2pd %ymm5,%zmm29{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 7a d1    \tvcvtuqq2pd %zmm25,%zmm26",},
+{{0x62, 0x01, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 7f 48 7a f5    \tvcvtudq2ps %zmm29,%zmm30",},
+{{0x62, 0x01, 0xff, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 ff 4f 7a d1    \tvcvtuqq2ps %zmm25,%ymm26{%k7}",},
+{{0x62, 0x01, 0x7d, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "",
+"62 01 7d 4f 7a d1    \tvcvttps2qq %ymm25,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7a f5    \tvcvttpd2qq %zmm29,%zmm30",},
+{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 57 08 7b f0    \tvcvtusi2sd %eax,%xmm5,%xmm6",},
+{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 f1 56 08 7b f0    \tvcvtusi2ss %eax,%xmm5,%xmm6",},
+{{0x62, 0x61, 0x7d, 0x4f, 0x7b, 0xd5, }, 6, 0, "", "",
+"62 61 7d 4f 7b d5    \tvcvtps2qq %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "",
+"62 01 fd 48 7b f5    \tvcvtpd2qq %zmm29,%zmm30",},
+{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "",
+"0f 7f c4             \tmovq   %mm0,%mm4",},
+{{0xc5, 0x7d, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7d 7f c6          \tvmovdqa %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7d, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7d 48 7f ca    \tvmovdqa32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfd, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fd 48 7f ca    \tvmovdqa64 %zmm25,%zmm26",},
+{{0xc5, 0x7e, 0x7f, 0xc6, }, 4, 0, "", "",
+"c5 7e 7f c6          \tvmovdqu %ymm8,%ymm6",},
+{{0x62, 0x01, 0x7e, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 7e 48 7f ca    \tvmovdqu32 %zmm25,%zmm26",},
+{{0x62, 0x01, 0xfe, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 fe 48 7f ca    \tvmovdqu64 %zmm25,%zmm26",},
+{{0x62, 0x61, 0x7f, 0x48, 0x7f, 0x31, }, 6, 0, "", "",
+"62 61 7f 48 7f 31    \tvmovdqu8 %zmm30,(%rcx)",},
+{{0x62, 0x01, 0xff, 0x48, 0x7f, 0xca, }, 6, 0, "", "",
+"62 01 ff 48 7f ca    \tvmovdqu16 %zmm25,%zmm26",},
+{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "",
+"0f db d1             \tpand   %mm1,%mm2",},
+{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "",
+"66 0f db d1          \tpand   %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "",
+"c5 cd db d4          \tvpand  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 db d0    \tvpandd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 db d0    \tvpandq %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "",
+"0f df d1             \tpandn  %mm1,%mm2",},
+{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "",
+"66 0f df d1          \tpandn  %xmm1,%xmm2",},
+{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "",
+"c5 cd df d4          \tvpandn %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 df d0    \tvpandnd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xdf, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 df d0    \tvpandnq %zmm24,%zmm25,%zmm26",},
+{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 f9 e6 d1          \tvcvttpd2dq %xmm1,%xmm2",},
+{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "",
+"c5 fa e6 f5          \tvcvtdq2pd %xmm5,%xmm6",},
+{{0x62, 0x61, 0x7e, 0x4f, 0xe6, 0xd5, }, 6, 0, "", "",
+"62 61 7e 4f e6 d5    \tvcvtdq2pd %ymm5,%zmm26{%k7}",},
+{{0x62, 0x01, 0xfe, 0x48, 0xe6, 0xd1, }, 6, 0, "", "",
+"62 01 fe 48 e6 d1    \tvcvtqq2pd %zmm25,%zmm26",},
+{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "",
+"c5 fb e6 d1          \tvcvtpd2dq %xmm1,%xmm2",},
+{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "",
+"0f eb f4             \tpor    %mm4,%mm6",},
+{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "",
+"c5 cd eb d4          \tvpor   %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 eb d0    \tvpord  %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xeb, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 eb d0    \tvporq  %zmm24,%zmm25,%zmm26",},
+{{0x0f, 0xef, 0xf4, }, 3, 0, "", "",
+"0f ef f4             \tpxor   %mm4,%mm6",},
+{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "",
+"c5 cd ef d4          \tvpxor  %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x01, 0x35, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 35 40 ef d0    \tvpxord %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x01, 0xb5, 0x40, 0xef, 0xd0, }, 6, 0, "", "",
+"62 01 b5 40 ef d0    \tvpxorq %zmm24,%zmm25,%zmm26",},
+{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "",
+"66 0f 38 10 c1       \tpblendvb %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x02, 0x9d, 0x40, 0x10, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 10 eb    \tvpsrlvw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x10, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 10 e6    \tvpmovuswb %zmm28,%ymm6{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x11, 0xe6, }, 6, 0, "", "",
+"62 62 7e 4f 11 e6    \tvpmovusdb %zmm28,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x11, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 11 eb    \tvpsravw %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x12, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 12 de    \tvpmovusqb %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x9d, 0x40, 0x12, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 12 eb    \tvpsllvw %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "",
+"c4 e2 7d 13 eb       \tvcvtph2ps %xmm3,%ymm5",},
+{{0x62, 0x62, 0x7d, 0x4f, 0x13, 0xdd, }, 6, 0, "", "",
+"62 62 7d 4f 13 dd    \tvcvtph2ps %ymm5,%zmm27{%k7}",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x13, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 13 de    \tvpmovusdw %zmm27,%ymm6{%k7}",},
+{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "",
+"66 0f 38 14 c1       \tblendvps %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x14, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 14 de    \tvpmovusqw %zmm27,%xmm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 14 eb    \tvprorvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x14, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 14 eb    \tvprorvq %zmm27,%zmm28,%zmm29",},
+{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "",
+"66 0f 38 15 c1       \tblendvpd %xmm0,%xmm1,%xmm0",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x15, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 15 de    \tvpmovusqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x02, 0x1d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 1d 40 15 eb    \tvprolvd %zmm27,%zmm28,%zmm29",},
+{{0x62, 0x02, 0x9d, 0x40, 0x15, 0xeb, }, 6, 0, "", "",
+"62 02 9d 40 15 eb    \tvprolvq %zmm27,%zmm28,%zmm29",},
+{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 16 d4       \tvpermps %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 16 f0    \tvpermps %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x16, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 16 f0    \tvpermpd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 19 f4       \tvbroadcastsd %xmm4,%ymm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x19, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 19 d3    \tvbroadcastf32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 1a 21       \tvbroadcastf128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 1a 11    \tvbroadcastf32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1a 11    \tvbroadcastf64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x1b, 0x19, }, 6, 0, "", "",
+"62 62 7d 48 1b 19    \tvbroadcastf32x8 (%rcx),%zmm27",},
+{{0x62, 0x62, 0xfd, 0x48, 0x1b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 1b 11    \tvbroadcastf64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x1f, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 1f e3    \tvpabsq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "",
+"c4 e2 79 20 ec       \tvpmovsxbw %xmm4,%xmm5",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x20, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 20 de    \tvpmovswb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 21 f4       \tvpmovsxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x21, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 21 de    \tvpmovsdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 22 e4       \tvpmovsxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x22, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 22 de    \tvpmovsqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 23 e4       \tvpmovsxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x23, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 23 de    \tvpmovsdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 24 f4       \tvpmovsxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x24, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 24 de    \tvpmovsqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 25 e4       \tvpmovsxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x25, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 25 de    \tvpmovsqd %zmm27,%ymm6{%k7}",},
+{{0x62, 0x92, 0x1d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 26 eb    \tvptestmb %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x26, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 26 eb    \tvptestmw %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 26 40 26 ea    \tvptestnmb %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x26, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 26 ea    \tvptestnmw %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0x1d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 1d 40 27 eb    \tvptestmd %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x9d, 0x40, 0x27, 0xeb, }, 6, 0, "", "",
+"62 92 9d 40 27 eb    \tvptestmq %zmm27,%zmm28,%k5",},
+{{0x62, 0x92, 0x26, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 26 40 27 ea    \tvptestnmd %zmm26,%zmm27,%k5",},
+{{0x62, 0x92, 0xa6, 0x40, 0x27, 0xea, }, 6, 0, "", "",
+"62 92 a6 40 27 ea    \tvptestnmq %zmm26,%zmm27,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 28 d4       \tvpmuldq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 28 e5    \tvpmovm2b %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x28, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 28 e5    \tvpmovm2w %k5,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 29 d4       \tvpcmpeqq %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x92, 0x7e, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 29 ec    \tvpmovb2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x29, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 29 ec    \tvpmovw2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 2a 21       \tvmovntdqa (%rcx),%ymm4",},
+{{0x62, 0x62, 0xfe, 0x48, 0x2a, 0xf6, }, 6, 0, "", "",
+"62 62 fe 48 2a f6    \tvpbroadcastmb2q %k6,%zmm30",},
+{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2c 31       \tvmaskmovps (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 2c d0    \tvscalefps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x2c, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 2c d0    \tvscalefpd %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "",
+"c4 e2 5d 2d 31       \tvmaskmovpd (%rcx),%ymm4,%ymm6",},
+{{0x62, 0x02, 0x35, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 2d d0    \tvscalefss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x2d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 2d d0    \tvscalefsd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 30 e4       \tvpmovzxbw %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x30, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 30 de    \tvpmovwb %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 31 f4       \tvpmovzxbd %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x31, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 31 de    \tvpmovdb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 32 e4       \tvpmovzxbq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x32, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 32 de    \tvpmovqb %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 33 e4       \tvpmovzxwd %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x33, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 33 de    \tvpmovdw %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "",
+"c4 e2 7d 34 f4       \tvpmovzxwq %xmm4,%ymm6",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x34, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 34 de    \tvpmovqw %zmm27,%xmm6{%k7}",},
+{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "",
+"c4 e2 7d 35 e4       \tvpmovzxdq %xmm4,%ymm4",},
+{{0x62, 0x62, 0x7e, 0x4f, 0x35, 0xde, }, 6, 0, "", "",
+"62 62 7e 4f 35 de    \tvpmovqd %zmm27,%ymm6{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 36 d4       \tvpermd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x82, 0x2d, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 2d 27 36 f0    \tvpermd %ymm24,%ymm26,%ymm22{%k7}",},
+{{0x62, 0x82, 0xad, 0x27, 0x36, 0xf0, }, 6, 0, "", "",
+"62 82 ad 27 36 f0    \tvpermq %ymm24,%ymm26,%ymm22{%k7}",},
+{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 38 d4       \tvpminsb %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 7e 48 38 e5    \tvpmovm2d %k5,%zmm28",},
+{{0x62, 0x62, 0xfe, 0x48, 0x38, 0xe5, }, 6, 0, "", "",
+"62 62 fe 48 38 e5    \tvpmovm2q %k5,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "",
+"c4 e2 69 39 d9       \tvpminsd %xmm1,%xmm2,%xmm3",},
+{{0x62, 0x02, 0x35, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 39 d0    \tvpminsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x39, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 39 d0    \tvpminsq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x92, 0x7e, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 7e 48 39 ec    \tvpmovd2m %zmm28,%k5",},
+{{0x62, 0x92, 0xfe, 0x48, 0x39, 0xec, }, 6, 0, "", "",
+"62 92 fe 48 39 ec    \tvpmovq2m %zmm28,%k5",},
+{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3a d4       \tvpminuw %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x62, 0x7e, 0x48, 0x3a, 0xe6, }, 6, 0, "", "",
+"62 62 7e 48 3a e6    \tvpbroadcastmw2d %k6,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3b d4       \tvpminud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3b d0    \tvpminud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3b, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3b d0    \tvpminuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3d d4       \tvpmaxsd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3d d0    \tvpmaxsd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3d d0    \tvpmaxsq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 3f d4       \tvpmaxud %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 3f d0    \tvpmaxud %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x3f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 3f d0    \tvpmaxuq %zmm24,%zmm25,%zmm26",},
+{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 40 d4       \tvpmulld %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 40 d0    \tvpmulld %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x40, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 40 d0    \tvpmullq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x42, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 42 d1    \tvgetexpps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x42, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 42 e3    \tvgetexppd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x43, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 43 d0    \tvgetexpss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x95, 0x07, 0x43, 0xf4, }, 6, 0, "", "",
+"62 02 95 07 43 f4    \tvgetexpsd %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 7d 48 44 e3    \tvplzcntd %zmm27,%zmm28",},
+{{0x62, 0x02, 0xfd, 0x48, 0x44, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 44 e3    \tvplzcntq %zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "",
+"c4 e2 4d 46 d4       \tvpsravd %ymm4,%ymm6,%ymm2",},
+{{0x62, 0x02, 0x35, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 46 d0    \tvpsravd %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xb5, 0x40, 0x46, 0xd0, }, 6, 0, "", "",
+"62 02 b5 40 46 d0    \tvpsravq %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4c, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4c d1    \tvrcp14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4c, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4c e3    \tvrcp14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4d d0    \tvrcp14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4d, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4d d0    \tvrcp14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0x4e, 0xd1, }, 6, 0, "", "",
+"62 02 7d 48 4e d1    \tvrsqrt14ps %zmm25,%zmm26",},
+{{0x62, 0x02, 0xfd, 0x48, 0x4e, 0xe3, }, 6, 0, "", "",
+"62 02 fd 48 4e e3    \tvrsqrt14pd %zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 35 07 4f d0    \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",},
+{{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "",
+"62 02 b5 07 4f d0    \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "",
+"c4 e2 79 59 f4       \tvpbroadcastq %xmm4,%xmm6",},
+{{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "",
+"62 02 7d 48 59 d3    \tvbroadcasti32x2 %xmm27,%zmm26",},
+{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "",
+"c4 e2 7d 5a 21       \tvbroadcasti128 (%rcx),%ymm4",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 5a 11    \tvbroadcasti32x4 (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5a, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5a 11    \tvbroadcasti64x2 (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x5b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 5b 21    \tvbroadcasti32x8 (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 5b 11    \tvbroadcasti64x4 (%rcx),%zmm26",},
+{{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 64 e2    \tvpblendmd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 64 e2    \tvpblendmq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x65, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 65 d0    \tvblendmps %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x65, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 65 e2    \tvblendmpd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 66 e2    \tvpblendmb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 66 e2    \tvpblendmw %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "",
+"62 02 35 40 75 d0    \tvpermi2b %zmm24,%zmm25,%zmm26",},
+{{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 75 e2    \tvpermi2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 76 e2    \tvpermi2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x76, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 76 e2    \tvpermi2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 77 e2    \tvpermi2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x77, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 77 e2    \tvpermi2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7a, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7a f0    \tvpbroadcastb %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7b, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7b f0    \tvpbroadcastw %eax,%xmm30",},
+{{0x62, 0x62, 0x7d, 0x08, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 7d 08 7c f0    \tvpbroadcastd %eax,%xmm30",},
+{{0x62, 0x62, 0xfd, 0x48, 0x7c, 0xf0, }, 6, 0, "", "",
+"62 62 fd 48 7c f0    \tvpbroadcastq %rax,%zmm30",},
+{{0x62, 0x02, 0x25, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7d e2    \tvpermt2b %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7d e2    \tvpermt2w %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7e e2    \tvpermt2d %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7e, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7e e2    \tvpermt2q %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x25, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 7f e2    \tvpermt2ps %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x7f, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 7f e2    \tvpermt2pd %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x83, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 83 e2    \tvpmultishiftqb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x88, 0x11, }, 6, 0, "", "",
+"62 62 7d 48 88 11    \tvexpandps (%rcx),%zmm26",},
+{{0x62, 0x62, 0xfd, 0x48, 0x88, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 88 21    \tvexpandpd (%rcx),%zmm28",},
+{{0x62, 0x62, 0x7d, 0x48, 0x89, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 89 21    \tvpexpandd (%rcx),%zmm28",},
+{{0x62, 0x62, 0xfd, 0x48, 0x89, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 89 11    \tvpexpandq (%rcx),%zmm26",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8a 21    \tvcompressps %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8a, 0x21, }, 6, 0, "", "",
+"62 62 fd 48 8a 21    \tvcompresspd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0x7d, 0x48, 0x8b, 0x21, }, 6, 0, "", "",
+"62 62 7d 48 8b 21    \tvpcompressd %zmm28,(%rcx)",},
+{{0x62, 0x62, 0xfd, 0x48, 0x8b, 0x11, }, 6, 0, "", "",
+"62 62 fd 48 8b 11    \tvpcompressq %zmm26,(%rcx)",},
+{{0x62, 0x02, 0x25, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 25 40 8d e2    \tvpermb %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 8d e2    \tvpermw %zmm26,%zmm27,%zmm28",},
+{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "",
+"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 90 94 dd 7b 00 00 00 \tvpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 90 94 dd 7b 00 00 00 \tvpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}",},
+{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "",
+"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%rbp,%xmm7,2),%xmm1",},
+{{0x62, 0x22, 0x7d, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a0 94 dd 7b 00 00 00 \tvpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa1, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a1 b4 ed 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0xb2, 0xfd, 0x21, 0xa1, 0xb4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 fd 21 a1 b4 dd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0x22, 0x7d, 0x41, 0xa2, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 7d 41 a2 a4 ed 7b 00 00 00 \tvscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa2, 0xa4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a2 a4 dd 7b 00 00 00 \tvscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}",},
+{{0x62, 0xb2, 0x7d, 0x41, 0xa3, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b4 e2    \tvpmadd52luq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "",
+"62 02 a5 40 b5 e2    \tvpmadd52huq %zmm26,%zmm27,%zmm28",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 7d 48 c4 da    \tvpconflictd %zmm26,%zmm27",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc4, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c4 da    \tvpconflictq %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xc8, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 c8 f5    \tvexp2ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xc8, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 c8 da    \tvexp2pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x7d, 0x48, 0xca, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 ca f5    \tvrcp28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xca, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 ca da    \tvrcp28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcb, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cb f4    \tvrcp28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcb, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cb d9    \tvrcp28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x02, 0x7d, 0x48, 0xcc, 0xf5, }, 6, 0, "", "",
+"62 02 7d 48 cc f5    \tvrsqrt28ps %zmm29,%zmm30",},
+{{0x62, 0x02, 0xfd, 0x48, 0xcc, 0xda, }, 6, 0, "", "",
+"62 02 fd 48 cc da    \tvrsqrt28pd %zmm26,%zmm27",},
+{{0x62, 0x02, 0x15, 0x07, 0xcd, 0xf4, }, 6, 0, "", "",
+"62 02 15 07 cd f4    \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "",
+"62 02 ad 07 cd d9    \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 03 d9 12 \tvalignq $0x12,%zmm25,%zmm26,%zmm27",},
+{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 08 d6 05    \tvroundps $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0x7d, 0x48, 0x08, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 08 d1 12 \tvrndscaleps $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 09 d6 05    \tvroundpd $0x5,%ymm6,%ymm2",},
+{{0x62, 0x03, 0xfd, 0x48, 0x09, 0xd1, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 09 d1 12 \tvrndscalepd $0x12,%zmm25,%zmm26",},
+{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0a d4 05    \tvroundss $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0x35, 0x07, 0x0a, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 07 0a d0 12 \tvrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 49 0b d4 05    \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",},
+{{0x62, 0x03, 0xb5, 0x07, 0x0b, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 07 0b d0 12 \tvrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 18 f4 05    \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 18 d0 12 \tvinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 18 d0 12 \tvinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 19 e4 05    \tvextractf128 $0x5,%ymm4,%xmm4",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 19 ca 12 \tvextractf32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 19 ca 12 \tvextractf64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x2d, 0x47, 0x1a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 47 1a d9 12 \tvinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x47, 0x1a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 47 1a f4 12 \tvinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x1b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 1b ee 12 \tvextractf32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x1b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 1b d3 12 \tvextractf64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1e ed 12 \tvpcmpud $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1e ea 12 \tvpcmpuq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x1f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 1f ed 12 \tvpcmpd $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x1f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 1f ea 12 \tvpcmpq $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x03, 0x15, 0x40, 0x23, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 23 f4 12 \tvshuff32x4 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x23, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 23 d9 12 \tvshuff64x2 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 25 f4 12 \tvpternlogd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x95, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 25 f4 12 \tvpternlogq $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x7d, 0x48, 0x26, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 26 da 12 \tvgetmantps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x26, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 26 f5 12 \tvgetmantpd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x07, 0x27, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 07 27 d9 12 \tvgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x95, 0x07, 0x27, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 07 27 f4 12 \tvgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "",
+"c4 e3 5d 38 f4 05    \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",},
+{{0x62, 0x03, 0x35, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 35 47 38 d0 12 \tvinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0x62, 0x03, 0xb5, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "",
+"62 03 b5 47 38 d0 12 \tvinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",},
+{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "",
+"c4 e3 7d 39 e6 05    \tvextracti128 $0x5,%ymm4,%xmm6",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 39 ca 12 \tvextracti32x4 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 39 ca 12 \tvextracti64x2 $0x12,%zmm25,%xmm26{%k7}",},
+{{0x62, 0x03, 0x15, 0x47, 0x3a, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 47 3a f4 12 \tvinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x47, 0x3a, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 47 3a d9 12 \tvinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x4f, 0x3b, 0xee, 0x12, }, 7, 0, "", "",
+"62 03 7d 4f 3b ee 12 \tvextracti32x8 $0x12,%zmm29,%ymm30{%k7}",},
+{{0x62, 0x03, 0xfd, 0x4f, 0x3b, 0xd3, 0x12, }, 7, 0, "", "",
+"62 03 fd 4f 3b d3 12 \tvextracti64x4 $0x12,%zmm26,%ymm27{%k7}",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3e, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3e ed 12 \tvpcmpub $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3e, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3e ea 12 \tvpcmpuw $0x12,%zmm26,%zmm27,%k5",},
+{{0x62, 0x93, 0x0d, 0x40, 0x3f, 0xed, 0x12, }, 7, 0, "", "",
+"62 93 0d 40 3f ed 12 \tvpcmpb $0x12,%zmm29,%zmm30,%k5",},
+{{0x62, 0x93, 0xa5, 0x40, 0x3f, 0xea, 0x12, }, 7, 0, "", "",
+"62 93 a5 40 3f ea 12 \tvpcmpw $0x12,%zmm26,%zmm27,%k5",},
+{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "",
+"c4 e3 4d 42 d4 05    \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",},
+{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "",
+"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",},
+{{0x62, 0x03, 0x2d, 0x40, 0x43, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 40 50 f4 12 \tvrangepd $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x51, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 51 d9 12 \tvrangess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x51, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 51 f4 12 \tvrangesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x03, 0x15, 0x40, 0x54, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 40 54 f4 12 \tvfixupimmps $0x12,%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x03, 0xad, 0x40, 0x54, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 40 54 d9 12 \tvfixupimmpd $0x12,%zmm25,%zmm26,%zmm27",},
+{{0x62, 0x03, 0x15, 0x07, 0x55, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 15 07 55 f4 12 \tvfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}",},
+{{0x62, 0x03, 0xad, 0x07, 0x55, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 ad 07 55 d9 12 \tvfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}",},
+{{0x62, 0x03, 0x7d, 0x48, 0x56, 0xda, 0x12, }, 7, 0, "", "",
+"62 03 7d 48 56 da 12 \tvreduceps $0x12,%zmm26,%zmm27",},
+{{0x62, 0x03, 0xfd, 0x48, 0x56, 0xf5, 0x12, }, 7, 0, "", "",
+"62 03 fd 48 56 f5 12 \tvreducepd $0x12,%zmm29,%zmm30",},
+{{0x62, 0x03, 0x2d, 0x00, 0x57, 0xd9, 0x12, }, 7, 0, "", "",
+"62 03 2d 00 57 d9 12 \tvreducess $0x12,%xmm25,%xmm26,%xmm27",},
+{{0x62, 0x03, 0x95, 0x00, 0x57, 0xf4, 0x12, }, 7, 0, "", "",
+"62 03 95 00 57 f4 12 \tvreducesd $0x12,%xmm28,%xmm29,%xmm30",},
+{{0x62, 0x93, 0x7d, 0x48, 0x66, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 48 66 eb 12 \tvfpclassps $0x12,%zmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x48, 0x66, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 48 66 ee 12 \tvfpclasspd $0x12,%zmm30,%k5",},
+{{0x62, 0x93, 0x7d, 0x08, 0x67, 0xeb, 0x12, }, 7, 0, "", "",
+"62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",},
+{{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "",
+"62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",},
+{{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "",
+"62 91 ad 40 72 c1 12 \tvprorq $0x12,%zmm25,%zmm26",},
+{{0x62, 0x91, 0x0d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 0d 40 72 cd 12 \tvprold $0x12,%zmm29,%zmm30",},
+{{0x62, 0x91, 0x8d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "",
+"62 91 8d 40 72 cd 12 \tvprolq $0x12,%zmm29,%zmm30",},
+{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "",
+"0f 72 e6 02          \tpsrad  $0x2,%mm6",},
+{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "",
+"c5 ed 72 e6 05       \tvpsrad $0x5,%ymm6,%ymm2",},
+{{0x62, 0x91, 0x4d, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 4d 40 72 e2 05 \tvpsrad $0x5,%zmm26,%zmm22",},
+{{0x62, 0x91, 0xcd, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "",
+"62 91 cd 40 72 e2 05 \tvpsraq $0x5,%zmm26,%zmm22",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 7d 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "",
+"62 92 fd 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}",},
+{{0x62, 0x01, 0x95, 0x40, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 40 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x47, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 47 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}",},
+{{0x62, 0x01, 0x95, 0xc7, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 c7 58 f4    \tvaddpd %zmm28,%zmm29,%zmm30{%k7}{z}",},
+{{0x62, 0x01, 0x95, 0x10, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 10 58 f4    \tvaddpd {rn-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x50, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 50 58 f4    \tvaddpd {ru-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x30, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 30 58 f4    \tvaddpd {rd-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x01, 0x95, 0x70, 0x58, 0xf4, }, 6, 0, "", "",
+"62 01 95 70 58 f4    \tvaddpd {rz-sae},%zmm28,%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 40 58 31    \tvaddpd (%rcx),%zmm29,%zmm30",},
+{{0x62, 0x21, 0x95, 0x40, 0x58, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "",
+"62 21 95 40 58 b4 f0 23 01 00 00 \tvaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x31, }, 6, 0, "", "",
+"62 61 95 50 58 31    \tvaddpd (%rcx){1to8},%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x40, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 40 58 72 7f \tvaddpd 0x1fc0(%rdx),%zmm29,%zmm30",},
+{{0x62, 0x61, 0x95, 0x50, 0x58, 0x72, 0x7f, }, 7, 0, "", "",
+"62 61 95 50 58 72 7f \tvaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30",},
+{{0x62, 0xf1, 0x0c, 0x50, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "",
+"62 f1 0c 50 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5",},
+{{0x62, 0xb1, 0x97, 0x07, 0xc2, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "",
+"62 b1 97 07 c2 ac f0 23 01 00 00 01 \tvcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}",},
+{{0x62, 0x91, 0x97, 0x17, 0xc2, 0xec, 0x02, }, 7, 0, "", "",
+"62 91 97 17 c2 ec 02 \tvcmplesd {sae},%xmm28,%xmm29,%k5{%k7}",},
+{{0x62, 0x23, 0x15, 0x07, 0x27, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "",
+"62 23 15 07 27 b4 f0 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}",},
 {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "",
 "f3 0f 1b 00          \tbndmk  (%rax),%bnd0",},
 {{0xf3, 0x41, 0x0f, 0x1b, 0x00, }, 5, 0, "", "",
@@ -325,19 +1257,19 @@
 {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
 "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%rax,%rcx,1)",},
 {{0xf2, 0xe8, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "call", "unconditional",
-"f2 e8 00 00 00 00    \tbnd callq 3f6 <main+0x3f6>",},
+"f2 e8 00 00 00 00    \tbnd callq f22 <main+0xf22>",},
 {{0x67, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect",
 "67 f2 ff 10          \tbnd callq *(%eax)",},
 {{0xf2, 0xc3, }, 2, 0, "ret", "indirect",
 "f2 c3                \tbnd retq ",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 402 <main+0x402>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f2e <main+0xf2e>",},
 {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional",
-"f2 e9 00 00 00 00    \tbnd jmpq 408 <main+0x408>",},
+"f2 e9 00 00 00 00    \tbnd jmpq f34 <main+0xf34>",},
 {{0x67, 0xf2, 0xff, 0x21, }, 4, 0, "jmp", "indirect",
 "67 f2 ff 21          \tbnd jmpq *(%ecx)",},
 {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional",
-"f2 0f 85 00 00 00 00 \tbnd jne 413 <main+0x413>",},
+"f2 0f 85 00 00 00 00 \tbnd jne f3f <main+0xf3f>",},
 {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
 "0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
 {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
@@ -764,5 +1696,3 @@
 "0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%rax,%rcx,8)",},
 {{0x41, 0x0f, 0xc7, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
 "41 0f c7 9c c8 78 56 34 12 \txrstors 0x12345678(%r8,%rcx,8)",},
-{{0x66, 0x0f, 0xae, 0xf8, }, 4, 0, "", "",
-"66 0f ae f8          \tpcommit ",},
diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
index 41b1b1c62660..979487dae8d4 100644
--- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c
+++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c
@@ -19,8 +19,882 @@ int main(void)
         /* Following line is a marker for the awk script - do not change */
         asm volatile("rdtsc"); /* Start here */
 
+        /* Test fix for vcvtph2ps in x86-opcode-map.txt */
+
+        asm volatile("vcvtph2ps %xmm3,%ymm5");
+
 #ifdef __x86_64__
 
+        /* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+        asm volatile("cmovno %rax,%rbx");
+        asm volatile("cmovno 0x12345678(%rax),%rcx");
+        asm volatile("cmovno 0x12345678(%rax),%cx");
+
+        asm volatile("cmove  %rax,%rbx");
+        asm volatile("cmove 0x12345678(%rax),%rcx");
+        asm volatile("cmove 0x12345678(%rax),%cx");
+
+        asm volatile("seto    0x12345678(%rax)");
+        asm volatile("setno   0x12345678(%rax)");
+        asm volatile("setb    0x12345678(%rax)");
+        asm volatile("setc    0x12345678(%rax)");
+        asm volatile("setnae  0x12345678(%rax)");
+        asm volatile("setae   0x12345678(%rax)");
+        asm volatile("setnb   0x12345678(%rax)");
+        asm volatile("setnc   0x12345678(%rax)");
+        asm volatile("sets    0x12345678(%rax)");
+        asm volatile("setns   0x12345678(%rax)");
+
+        /* AVX-512: Mask Instructions */
+
+        asm volatile("kandw  %k7,%k6,%k5");
+        asm volatile("kandq  %k7,%k6,%k5");
+        asm volatile("kandb  %k7,%k6,%k5");
+        asm volatile("kandd  %k7,%k6,%k5");
+
+        asm volatile("kandnw  %k7,%k6,%k5");
+        asm volatile("kandnq  %k7,%k6,%k5");
+        asm volatile("kandnb  %k7,%k6,%k5");
+        asm volatile("kandnd  %k7,%k6,%k5");
+
+        asm volatile("knotw  %k7,%k6");
+        asm volatile("knotq  %k7,%k6");
+        asm volatile("knotb  %k7,%k6");
+        asm volatile("knotd  %k7,%k6");
+
+        asm volatile("korw  %k7,%k6,%k5");
+        asm volatile("korq  %k7,%k6,%k5");
+        asm volatile("korb  %k7,%k6,%k5");
+        asm volatile("kord  %k7,%k6,%k5");
+
+        asm volatile("kxnorw  %k7,%k6,%k5");
+        asm volatile("kxnorq  %k7,%k6,%k5");
+        asm volatile("kxnorb  %k7,%k6,%k5");
+        asm volatile("kxnord  %k7,%k6,%k5");
+
+        asm volatile("kxorw  %k7,%k6,%k5");
+        asm volatile("kxorq  %k7,%k6,%k5");
+        asm volatile("kxorb  %k7,%k6,%k5");
+        asm volatile("kxord  %k7,%k6,%k5");
+
+        asm volatile("kaddw  %k7,%k6,%k5");
+        asm volatile("kaddq  %k7,%k6,%k5");
+        asm volatile("kaddb  %k7,%k6,%k5");
+        asm volatile("kaddd  %k7,%k6,%k5");
+
+        asm volatile("kunpckbw %k7,%k6,%k5");
+        asm volatile("kunpckwd %k7,%k6,%k5");
+        asm volatile("kunpckdq %k7,%k6,%k5");
+
+        asm volatile("kmovw  %k6,%k5");
+        asm volatile("kmovw  (%rcx),%k5");
+        asm volatile("kmovw  0x123(%rax,%r14,8),%k5");
+        asm volatile("kmovw  %k5,(%rcx)");
+        asm volatile("kmovw  %k5,0x123(%rax,%r14,8)");
+        asm volatile("kmovw  %eax,%k5");
+        asm volatile("kmovw  %ebp,%k5");
+        asm volatile("kmovw  %r13d,%k5");
+        asm volatile("kmovw  %k5,%eax");
+        asm volatile("kmovw  %k5,%ebp");
+        asm volatile("kmovw  %k5,%r13d");
+
+        asm volatile("kmovq  %k6,%k5");
+        asm volatile("kmovq  (%rcx),%k5");
+        asm volatile("kmovq  0x123(%rax,%r14,8),%k5");
+        asm volatile("kmovq  %k5,(%rcx)");
+        asm volatile("kmovq  %k5,0x123(%rax,%r14,8)");
+        asm volatile("kmovq  %rax,%k5");
+        asm volatile("kmovq  %rbp,%k5");
+        asm volatile("kmovq  %r13,%k5");
+        asm volatile("kmovq  %k5,%rax");
+        asm volatile("kmovq  %k5,%rbp");
+        asm volatile("kmovq  %k5,%r13");
+
+        asm volatile("kmovb  %k6,%k5");
+        asm volatile("kmovb  (%rcx),%k5");
+        asm volatile("kmovb  0x123(%rax,%r14,8),%k5");
+        asm volatile("kmovb  %k5,(%rcx)");
+        asm volatile("kmovb  %k5,0x123(%rax,%r14,8)");
+        asm volatile("kmovb  %eax,%k5");
+        asm volatile("kmovb  %ebp,%k5");
+        asm volatile("kmovb  %r13d,%k5");
+        asm volatile("kmovb  %k5,%eax");
+        asm volatile("kmovb  %k5,%ebp");
+        asm volatile("kmovb  %k5,%r13d");
+
+        asm volatile("kmovd  %k6,%k5");
+        asm volatile("kmovd  (%rcx),%k5");
+        asm volatile("kmovd  0x123(%rax,%r14,8),%k5");
+        asm volatile("kmovd  %k5,(%rcx)");
+        asm volatile("kmovd  %k5,0x123(%rax,%r14,8)");
+        asm volatile("kmovd  %eax,%k5");
+        asm volatile("kmovd  %ebp,%k5");
+        asm volatile("kmovd  %r13d,%k5");
+        asm volatile("kmovd  %k5,%eax");
+        asm volatile("kmovd  %k5,%ebp");
+        asm volatile("kmovd %k5,%r13d");
+
+        asm volatile("kortestw %k6,%k5");
+        asm volatile("kortestq %k6,%k5");
+        asm volatile("kortestb %k6,%k5");
+        asm volatile("kortestd %k6,%k5");
+
+        asm volatile("ktestw %k6,%k5");
+        asm volatile("ktestq %k6,%k5");
+        asm volatile("ktestb %k6,%k5");
+        asm volatile("ktestd %k6,%k5");
+
+        asm volatile("kshiftrw $0x12,%k6,%k5");
+        asm volatile("kshiftrq $0x5b,%k6,%k5");
+        asm volatile("kshiftlw $0x12,%k6,%k5");
+        asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+        /* AVX-512: Op code 0f 5b */
+        asm volatile("vcvtdq2ps %xmm5,%xmm6");
+        asm volatile("vcvtqq2ps %zmm29,%ymm6{%k7}");
+        asm volatile("vcvtps2dq %xmm5,%xmm6");
+        asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+        /* AVX-512: Op code 0f 6f */
+
+        asm volatile("movq   %mm0,%mm4");
+        asm volatile("vmovdqa %ymm4,%ymm6");
+        asm volatile("vmovdqa32 %zmm25,%zmm26");
+        asm volatile("vmovdqa64 %zmm25,%zmm26");
+        asm volatile("vmovdqu %ymm4,%ymm6");
+        asm volatile("vmovdqu32 %zmm29,%zmm30");
+        asm volatile("vmovdqu64 %zmm25,%zmm26");
+        asm volatile("vmovdqu8 %zmm29,%zmm30");
+        asm volatile("vmovdqu16 %zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 78 */
+
+        asm volatile("vmread %rax,%rbx");
+        asm volatile("vcvttps2udq %zmm25,%zmm26");
+        asm volatile("vcvttpd2udq %zmm29,%ymm6{%k7}");
+        asm volatile("vcvttsd2usi %xmm6,%rax");
+        asm volatile("vcvttss2usi %xmm6,%rax");
+        asm volatile("vcvttps2uqq %ymm5,%zmm26{%k7}");
+        asm volatile("vcvttpd2uqq %zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 79 */
+
+        asm volatile("vmwrite %rax,%rbx");
+        asm volatile("vcvtps2udq %zmm25,%zmm26");
+        asm volatile("vcvtpd2udq %zmm29,%ymm6{%k7}");
+        asm volatile("vcvtsd2usi %xmm6,%rax");
+        asm volatile("vcvtss2usi %xmm6,%rax");
+        asm volatile("vcvtps2uqq %ymm5,%zmm26{%k7}");
+        asm volatile("vcvtpd2uqq %zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 7a */
+
+        asm volatile("vcvtudq2pd %ymm5,%zmm29{%k7}");
+        asm volatile("vcvtuqq2pd %zmm25,%zmm26");
+        asm volatile("vcvtudq2ps %zmm29,%zmm30");
+        asm volatile("vcvtuqq2ps %zmm25,%ymm26{%k7}");
+        asm volatile("vcvttps2qq %ymm25,%zmm26{%k7}");
+        asm volatile("vcvttpd2qq %zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 7b */
+
+        asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+        asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+        asm volatile("vcvtps2qq %ymm5,%zmm26{%k7}");
+        asm volatile("vcvtpd2qq %zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 7f */
+
+        asm volatile("movq.s  %mm0,%mm4");
+        asm volatile("vmovdqa %ymm8,%ymm6");
+        asm volatile("vmovdqa32.s %zmm25,%zmm26");
+        asm volatile("vmovdqa64.s %zmm25,%zmm26");
+        asm volatile("vmovdqu %ymm8,%ymm6");
+        asm volatile("vmovdqu32.s %zmm25,%zmm26");
+        asm volatile("vmovdqu64.s %zmm25,%zmm26");
+        asm volatile("vmovdqu8.s %zmm30,(%rcx)");
+        asm volatile("vmovdqu16.s %zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f db */
+
+        asm volatile("pand  %mm1,%mm2");
+        asm volatile("pand  %xmm1,%xmm2");
+        asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+        asm volatile("vpandd %zmm24,%zmm25,%zmm26");
+        asm volatile("vpandq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f df */
+
+        asm volatile("pandn  %mm1,%mm2");
+        asm volatile("pandn  %xmm1,%xmm2");
+        asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+        asm volatile("vpandnd %zmm24,%zmm25,%zmm26");
+        asm volatile("vpandnq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f e6 */
+
+        asm volatile("vcvttpd2dq %xmm1,%xmm2");
+        asm volatile("vcvtdq2pd %xmm5,%xmm6");
+        asm volatile("vcvtdq2pd %ymm5,%zmm26{%k7}");
+        asm volatile("vcvtqq2pd %zmm25,%zmm26");
+        asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+        /* AVX-512: Op code 0f eb */
+
+        asm volatile("por   %mm4,%mm6");
+        asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+        asm volatile("vpord  %zmm24,%zmm25,%zmm26");
+        asm volatile("vporq  %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f ef */
+
+        asm volatile("pxor   %mm4,%mm6");
+        asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+        asm volatile("vpxord %zmm24,%zmm25,%zmm26");
+        asm volatile("vpxorq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 10 */
+
+        asm volatile("pblendvb %xmm1,%xmm0");
+        asm volatile("vpsrlvw %zmm27,%zmm28,%zmm29");
+        asm volatile("vpmovuswb %zmm28,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 11 */
+
+        asm volatile("vpmovusdb %zmm28,%xmm6{%k7}");
+        asm volatile("vpsravw %zmm27,%zmm28,%zmm29");
+
+        /* AVX-512: Op code 0f 38 12 */
+
+        asm volatile("vpmovusqb %zmm27,%xmm6{%k7}");
+        asm volatile("vpsllvw %zmm27,%zmm28,%zmm29");
+
+        /* AVX-512: Op code 0f 38 13 */
+
+        asm volatile("vcvtph2ps %xmm3,%ymm5");
+        asm volatile("vcvtph2ps %ymm5,%zmm27{%k7}");
+        asm volatile("vpmovusdw %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 14 */
+
+        asm volatile("blendvps %xmm1,%xmm0");
+        asm volatile("vpmovusqw %zmm27,%xmm6{%k7}");
+        asm volatile("vprorvd %zmm27,%zmm28,%zmm29");
+        asm volatile("vprorvq %zmm27,%zmm28,%zmm29");
+
+        /* AVX-512: Op code 0f 38 15 */
+
+        asm volatile("blendvpd %xmm1,%xmm0");
+        asm volatile("vpmovusqd %zmm27,%ymm6{%k7}");
+        asm volatile("vprolvd %zmm27,%zmm28,%zmm29");
+        asm volatile("vprolvq %zmm27,%zmm28,%zmm29");
+
+        /* AVX-512: Op code 0f 38 16 */
+
+        asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+        asm volatile("vpermps %ymm24,%ymm26,%ymm22{%k7}");
+        asm volatile("vpermpd %ymm24,%ymm26,%ymm22{%k7}");
+
+        /* AVX-512: Op code 0f 38 19 */
+
+        asm volatile("vbroadcastsd %xmm4,%ymm6");
+        asm volatile("vbroadcastf32x2 %xmm27,%zmm26");
+
+        /* AVX-512: Op code 0f 38 1a */
+
+        asm volatile("vbroadcastf128 (%rcx),%ymm4");
+        asm volatile("vbroadcastf32x4 (%rcx),%zmm26");
+        asm volatile("vbroadcastf64x2 (%rcx),%zmm26");
+
+        /* AVX-512: Op code 0f 38 1b */
+
+        asm volatile("vbroadcastf32x8 (%rcx),%zmm27");
+        asm volatile("vbroadcastf64x4 (%rcx),%zmm26");
+
+        /* AVX-512: Op code 0f 38 1f */
+
+        asm volatile("vpabsq %zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 20 */
+
+        asm volatile("vpmovsxbw %xmm4,%xmm5");
+        asm volatile("vpmovswb %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 21 */
+
+        asm volatile("vpmovsxbd %xmm4,%ymm6");
+        asm volatile("vpmovsdb %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 22 */
+
+        asm volatile("vpmovsxbq %xmm4,%ymm4");
+        asm volatile("vpmovsqb %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 23 */
+
+        asm volatile("vpmovsxwd %xmm4,%ymm4");
+        asm volatile("vpmovsdw %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 24 */
+
+        asm volatile("vpmovsxwq %xmm4,%ymm6");
+        asm volatile("vpmovsqw %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 25 */
+
+        asm volatile("vpmovsxdq %xmm4,%ymm4");
+        asm volatile("vpmovsqd %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 26 */
+
+        asm volatile("vptestmb %zmm27,%zmm28,%k5");
+        asm volatile("vptestmw %zmm27,%zmm28,%k5");
+        asm volatile("vptestnmb %zmm26,%zmm27,%k5");
+        asm volatile("vptestnmw %zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 38 27 */
+
+        asm volatile("vptestmd %zmm27,%zmm28,%k5");
+        asm volatile("vptestmq %zmm27,%zmm28,%k5");
+        asm volatile("vptestnmd %zmm26,%zmm27,%k5");
+        asm volatile("vptestnmq %zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 38 28 */
+
+        asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovm2b %k5,%zmm28");
+        asm volatile("vpmovm2w %k5,%zmm28");
+
+        /* AVX-512: Op code 0f 38 29 */
+
+        asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovb2m %zmm28,%k5");
+        asm volatile("vpmovw2m %zmm28,%k5");
+
+        /* AVX-512: Op code 0f 38 2a */
+
+        asm volatile("vmovntdqa (%rcx),%ymm4");
+        asm volatile("vpbroadcastmb2q %k6,%zmm30");
+
+        /* AVX-512: Op code 0f 38 2c */
+
+        asm volatile("vmaskmovps (%rcx),%ymm4,%ymm6");
+        asm volatile("vscalefps %zmm24,%zmm25,%zmm26");
+        asm volatile("vscalefpd %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 2d */
+
+        asm volatile("vmaskmovpd (%rcx),%ymm4,%ymm6");
+        asm volatile("vscalefss %xmm24,%xmm25,%xmm26{%k7}");
+        asm volatile("vscalefsd %xmm24,%xmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 38 30 */
+
+        asm volatile("vpmovzxbw %xmm4,%ymm4");
+        asm volatile("vpmovwb %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 31 */
+
+        asm volatile("vpmovzxbd %xmm4,%ymm6");
+        asm volatile("vpmovdb %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 32 */
+
+        asm volatile("vpmovzxbq %xmm4,%ymm4");
+        asm volatile("vpmovqb %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 33 */
+
+        asm volatile("vpmovzxwd %xmm4,%ymm4");
+        asm volatile("vpmovdw %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 34 */
+
+        asm volatile("vpmovzxwq %xmm4,%ymm6");
+        asm volatile("vpmovqw %zmm27,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 35 */
+
+        asm volatile("vpmovzxdq %xmm4,%ymm4");
+        asm volatile("vpmovqd %zmm27,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 38 */
+
+        asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpermd %ymm24,%ymm26,%ymm22{%k7}");
+        asm volatile("vpermq %ymm24,%ymm26,%ymm22{%k7}");
+
+        /* AVX-512: Op code 0f 38 38 */
+
+        asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovm2d %k5,%zmm28");
+        asm volatile("vpmovm2q %k5,%zmm28");
+
+        /* AVX-512: Op code 0f 38 39 */
+
+        asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+        asm volatile("vpminsd %zmm24,%zmm25,%zmm26");
+        asm volatile("vpminsq %zmm24,%zmm25,%zmm26");
+        asm volatile("vpmovd2m %zmm28,%k5");
+        asm volatile("vpmovq2m %zmm28,%k5");
+
+        /* AVX-512: Op code 0f 38 3a */
+
+        asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+        asm volatile("vpbroadcastmw2d %k6,%zmm28");
+
+        /* AVX-512: Op code 0f 38 3b */
+
+        asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+        asm volatile("vpminud %zmm24,%zmm25,%zmm26");
+        asm volatile("vpminuq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 3d */
+
+        asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmaxsd %zmm24,%zmm25,%zmm26");
+        asm volatile("vpmaxsq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 3f */
+
+        asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmaxud %zmm24,%zmm25,%zmm26");
+        asm volatile("vpmaxuq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 42 */
+
+        asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmulld %zmm24,%zmm25,%zmm26");
+        asm volatile("vpmullq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 42 */
+
+        asm volatile("vgetexpps %zmm25,%zmm26");
+        asm volatile("vgetexppd %zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 43 */
+
+        asm volatile("vgetexpss %xmm24,%xmm25,%xmm26{%k7}");
+        asm volatile("vgetexpsd %xmm28,%xmm29,%xmm30{%k7}");
+
+        /* AVX-512: Op code 0f 38 44 */
+
+        asm volatile("vplzcntd %zmm27,%zmm28");
+        asm volatile("vplzcntq %zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 46 */
+
+        asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpsravd %zmm24,%zmm25,%zmm26");
+        asm volatile("vpsravq %zmm24,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 38 4c */
+
+        asm volatile("vrcp14ps %zmm25,%zmm26");
+        asm volatile("vrcp14pd %zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 4d */
+
+        asm volatile("vrcp14ss %xmm24,%xmm25,%xmm26{%k7}");
+        asm volatile("vrcp14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 38 4e */
+
+        asm volatile("vrsqrt14ps %zmm25,%zmm26");
+        asm volatile("vrsqrt14pd %zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 4f */
+
+        asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}");
+        asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 38 59 */
+
+        asm volatile("vpbroadcastq %xmm4,%xmm6");
+        asm volatile("vbroadcasti32x2 %xmm27,%zmm26");
+
+        /* AVX-512: Op code 0f 38 5a */
+
+        asm volatile("vbroadcasti128 (%rcx),%ymm4");
+        asm volatile("vbroadcasti32x4 (%rcx),%zmm26");
+        asm volatile("vbroadcasti64x2 (%rcx),%zmm26");
+
+        /* AVX-512: Op code 0f 38 5b */
+
+        asm volatile("vbroadcasti32x8 (%rcx),%zmm28");
+        asm volatile("vbroadcasti64x4 (%rcx),%zmm26");
+
+        /* AVX-512: Op code 0f 38 64 */
+
+        asm volatile("vpblendmd %zmm26,%zmm27,%zmm28");
+        asm volatile("vpblendmq %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 65 */
+
+        asm volatile("vblendmps %zmm24,%zmm25,%zmm26");
+        asm volatile("vblendmpd %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 66 */
+
+        asm volatile("vpblendmb %zmm26,%zmm27,%zmm28");
+        asm volatile("vpblendmw %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 75 */
+
+        asm volatile("vpermi2b %zmm24,%zmm25,%zmm26");
+        asm volatile("vpermi2w %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 76 */
+
+        asm volatile("vpermi2d %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermi2q %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 77 */
+
+        asm volatile("vpermi2ps %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermi2pd %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 7a */
+
+        asm volatile("vpbroadcastb %eax,%xmm30");
+
+        /* AVX-512: Op code 0f 38 7b */
+
+        asm volatile("vpbroadcastw %eax,%xmm30");
+
+        /* AVX-512: Op code 0f 38 7c */
+
+        asm volatile("vpbroadcastd %eax,%xmm30");
+        asm volatile("vpbroadcastq %rax,%zmm30");
+
+        /* AVX-512: Op code 0f 38 7d */
+
+        asm volatile("vpermt2b %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermt2w %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 7e */
+
+        asm volatile("vpermt2d %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermt2q %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 7f */
+
+        asm volatile("vpermt2ps %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermt2pd %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 83 */
+
+        asm volatile("vpmultishiftqb %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 88 */
+
+        asm volatile("vexpandps (%rcx),%zmm26");
+        asm volatile("vexpandpd (%rcx),%zmm28");
+
+        /* AVX-512: Op code 0f 38 89 */
+
+        asm volatile("vpexpandd (%rcx),%zmm28");
+        asm volatile("vpexpandq (%rcx),%zmm26");
+
+        /* AVX-512: Op code 0f 38 8a */
+
+        asm volatile("vcompressps %zmm28,(%rcx)");
+        asm volatile("vcompresspd %zmm28,(%rcx)");
+
+        /* AVX-512: Op code 0f 38 8b */
+
+        asm volatile("vpcompressd %zmm28,(%rcx)");
+        asm volatile("vpcompressq %zmm26,(%rcx)");
+
+        /* AVX-512: Op code 0f 38 8d */
+
+        asm volatile("vpermb %zmm26,%zmm27,%zmm28");
+        asm volatile("vpermw %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 90 */
+
+        asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherdq %xmm2,0x04(%rbp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+        asm volatile("vpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}");
+
+        /* AVX-512: Op code 0f 38 91 */
+
+        asm volatile("vpgatherqd %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherqq %xmm2,0x02(%rbp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}");
+        asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}");
+
+        /* AVX-512: Op code 0f 38 a0 */
+
+        asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+        asm volatile("vpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a1 */
+
+        asm volatile("vpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+        asm volatile("vpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a2 */
+
+        asm volatile("vscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+        asm volatile("vscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a3 */
+
+        asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}");
+        asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 b4 */
+
+        asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 b5 */
+
+        asm volatile("vpmadd52huq %zmm26,%zmm27,%zmm28");
+
+        /* AVX-512: Op code 0f 38 c4 */
+
+        asm volatile("vpconflictd %zmm26,%zmm27");
+        asm volatile("vpconflictq %zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 38 c8 */
+
+        asm volatile("vexp2ps %zmm29,%zmm30");
+        asm volatile("vexp2pd %zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 38 ca */
+
+        asm volatile("vrcp28ps %zmm29,%zmm30");
+        asm volatile("vrcp28pd %zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 38 cb */
+
+        asm volatile("vrcp28ss %xmm28,%xmm29,%xmm30{%k7}");
+        asm volatile("vrcp28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+        /* AVX-512: Op code 0f 38 cc */
+
+        asm volatile("vrsqrt28ps %zmm29,%zmm30");
+        asm volatile("vrsqrt28pd %zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 38 cd */
+
+        asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}");
+        asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}");
+
+        /* AVX-512: Op code 0f 3a 03 */
+
+        asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30");
+        asm volatile("valignq $0x12,%zmm25,%zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 3a 08 */
+
+        asm volatile("vroundps $0x5,%ymm6,%ymm2");
+        asm volatile("vrndscaleps $0x12,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 3a 09 */
+
+        asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+        asm volatile("vrndscalepd $0x12,%zmm25,%zmm26");
+
+        /* AVX-512: Op code 0f 3a 1a */
+
+        asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+        asm volatile("vrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 0b */
+
+        asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+        asm volatile("vrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 18 */
+
+        asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+        asm volatile("vinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+        asm volatile("vinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 19 */
+
+        asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+        asm volatile("vextractf32x4 $0x12,%zmm25,%xmm26{%k7}");
+        asm volatile("vextractf64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1a */
+
+        asm volatile("vinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+        asm volatile("vinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1b */
+
+        asm volatile("vextractf32x8 $0x12,%zmm29,%ymm30{%k7}");
+        asm volatile("vextractf64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1e */
+
+        asm volatile("vpcmpud $0x12,%zmm29,%zmm30,%k5");
+        asm volatile("vpcmpuq $0x12,%zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 3a 1f */
+
+        asm volatile("vpcmpd $0x12,%zmm29,%zmm30,%k5");
+        asm volatile("vpcmpq $0x12,%zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 3a 23 */
+
+        asm volatile("vshuff32x4 $0x12,%zmm28,%zmm29,%zmm30");
+        asm volatile("vshuff64x2 $0x12,%zmm25,%zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 3a 25 */
+
+        asm volatile("vpternlogd $0x12,%zmm28,%zmm29,%zmm30");
+        asm volatile("vpternlogq $0x12,%zmm28,%zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 3a 26 */
+
+        asm volatile("vgetmantps $0x12,%zmm26,%zmm27");
+        asm volatile("vgetmantpd $0x12,%zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 3a 27 */
+
+        asm volatile("vgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+        asm volatile("vgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+
+        /* AVX-512: Op code 0f 3a 38 */
+
+        asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+        asm volatile("vinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+        asm volatile("vinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 39 */
+
+        asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+        asm volatile("vextracti32x4 $0x12,%zmm25,%xmm26{%k7}");
+        asm volatile("vextracti64x2 $0x12,%zmm25,%xmm26{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3a */
+
+        asm volatile("vinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}");
+        asm volatile("vinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3b */
+
+        asm volatile("vextracti32x8 $0x12,%zmm29,%ymm30{%k7}");
+        asm volatile("vextracti64x4 $0x12,%zmm26,%ymm27{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3e */
+
+        asm volatile("vpcmpub $0x12,%zmm29,%zmm30,%k5");
+        asm volatile("vpcmpuw $0x12,%zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 3a 3f */
+
+        asm volatile("vpcmpb $0x12,%zmm29,%zmm30,%k5");
+        asm volatile("vpcmpw $0x12,%zmm26,%zmm27,%k5");
+
+        /* AVX-512: Op code 0f 3a 43 */
+
+        asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+        asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 3a 43 */
+
+        asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27");
+        asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 3a 50 */
+
+        asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27");
+        asm volatile("vrangepd $0x12,%zmm28,%zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 3a 51 */
+
+        asm volatile("vrangess $0x12,%xmm25,%xmm26,%xmm27");
+        asm volatile("vrangesd $0x12,%xmm28,%xmm29,%xmm30");
+
+        /* AVX-512: Op code 0f 3a 54 */
+
+        asm volatile("vfixupimmps $0x12,%zmm28,%zmm29,%zmm30");
+        asm volatile("vfixupimmpd $0x12,%zmm25,%zmm26,%zmm27");
+
+        /* AVX-512: Op code 0f 3a 55 */
+
+        asm volatile("vfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}");
+        asm volatile("vfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}");
+
+        /* AVX-512: Op code 0f 3a 56 */
+
+        asm volatile("vreduceps $0x12,%zmm26,%zmm27");
+        asm volatile("vreducepd $0x12,%zmm29,%zmm30");
+
+        /* AVX-512: Op code 0f 3a 57 */
+
+        asm volatile("vreducess $0x12,%xmm25,%xmm26,%xmm27");
+        asm volatile("vreducesd $0x12,%xmm28,%xmm29,%xmm30");
+
+        /* AVX-512: Op code 0f 3a 66 */
+
+        asm volatile("vfpclassps $0x12,%zmm27,%k5");
+        asm volatile("vfpclasspd $0x12,%zmm30,%k5");
+
+        /* AVX-512: Op code 0f 3a 67 */
+
+        asm volatile("vfpclassss $0x12,%xmm27,%k5");
+        asm volatile("vfpclasssd $0x12,%xmm30,%k5");
+
+        /* AVX-512: Op code 0f 72 (Grp13) */
+
+        asm volatile("vprord $0x12,%zmm25,%zmm26");
+        asm volatile("vprorq $0x12,%zmm25,%zmm26");
+        asm volatile("vprold $0x12,%zmm29,%zmm30");
+        asm volatile("vprolq $0x12,%zmm29,%zmm30");
+        asm volatile("psrad  $0x2,%mm6");
+        asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+        asm volatile("vpsrad $0x5,%zmm26,%zmm22");
+        asm volatile("vpsraq $0x5,%zmm26,%zmm22");
+
+        /* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+        asm volatile("vgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+        asm volatile("vgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+        asm volatile("vscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}");
+        asm volatile("vscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+        asm volatile("vgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}");
+        asm volatile("vscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}");
+
+        /* AVX-512: Examples */
+
+        asm volatile("vaddpd %zmm28,%zmm29,%zmm30");
+        asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}");
+        asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}{z}");
+        asm volatile("vaddpd {rn-sae},%zmm28,%zmm29,%zmm30");
+        asm volatile("vaddpd {ru-sae},%zmm28,%zmm29,%zmm30");
+        asm volatile("vaddpd {rd-sae},%zmm28,%zmm29,%zmm30");
+        asm volatile("vaddpd {rz-sae},%zmm28,%zmm29,%zmm30");
+        asm volatile("vaddpd (%rcx),%zmm29,%zmm30");
+        asm volatile("vaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30");
+        asm volatile("vaddpd (%rcx){1to8},%zmm29,%zmm30");
+        asm volatile("vaddpd 0x1fc0(%rdx),%zmm29,%zmm30");
+        asm volatile("vaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30");
+        asm volatile("vcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5");
+        asm volatile("vcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}");
+        asm volatile("vcmplesd {sae},%xmm28,%xmm29,%k5{%k7}");
+        asm volatile("vgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}");
+
         /* bndmk m64, bnd */
 
         asm volatile("bndmk (%rax), %bnd0");
@@ -471,6 +1345,921 @@ int main(void)
 
 #else  /* #ifdef __x86_64__ */
 
+        /* bound r32, mem (same op code as EVEX prefix) */
+
+        asm volatile("bound %eax, 0x12345678(%ecx)");
+        asm volatile("bound %ecx, 0x12345678(%eax)");
+        asm volatile("bound %edx, 0x12345678(%eax)");
+        asm volatile("bound %ebx, 0x12345678(%eax)");
+        asm volatile("bound %esp, 0x12345678(%eax)");
+        asm volatile("bound %ebp, 0x12345678(%eax)");
+        asm volatile("bound %esi, 0x12345678(%eax)");
+        asm volatile("bound %edi, 0x12345678(%eax)");
+        asm volatile("bound %ecx, (%eax)");
+        asm volatile("bound %eax, (0x12345678)");
+        asm volatile("bound %edx, (%ecx,%eax,1)");
+        asm volatile("bound %edx, 0x12345678(,%eax,1)");
+        asm volatile("bound %edx, (%eax,%ecx,1)");
+        asm volatile("bound %edx, (%eax,%ecx,8)");
+        asm volatile("bound %edx, 0x12(%eax)");
+        asm volatile("bound %edx, 0x12(%ebp)");
+        asm volatile("bound %edx, 0x12(%ecx,%eax,1)");
+        asm volatile("bound %edx, 0x12(%ebp,%eax,1)");
+        asm volatile("bound %edx, 0x12(%eax,%ecx,1)");
+        asm volatile("bound %edx, 0x12(%eax,%ecx,8)");
+        asm volatile("bound %edx, 0x12345678(%eax)");
+        asm volatile("bound %edx, 0x12345678(%ebp)");
+        asm volatile("bound %edx, 0x12345678(%ecx,%eax,1)");
+        asm volatile("bound %edx, 0x12345678(%ebp,%eax,1)");
+        asm volatile("bound %edx, 0x12345678(%eax,%ecx,1)");
+        asm volatile("bound %edx, 0x12345678(%eax,%ecx,8)");
+
+        /* bound r16, mem (same op code as EVEX prefix) */
+
+        asm volatile("bound %ax, 0x12345678(%ecx)");
+        asm volatile("bound %cx, 0x12345678(%eax)");
+        asm volatile("bound %dx, 0x12345678(%eax)");
+        asm volatile("bound %bx, 0x12345678(%eax)");
+        asm volatile("bound %sp, 0x12345678(%eax)");
+        asm volatile("bound %bp, 0x12345678(%eax)");
+        asm volatile("bound %si, 0x12345678(%eax)");
+        asm volatile("bound %di, 0x12345678(%eax)");
+        asm volatile("bound %cx, (%eax)");
+        asm volatile("bound %ax, (0x12345678)");
+        asm volatile("bound %dx, (%ecx,%eax,1)");
+        asm volatile("bound %dx, 0x12345678(,%eax,1)");
+        asm volatile("bound %dx, (%eax,%ecx,1)");
+        asm volatile("bound %dx, (%eax,%ecx,8)");
+        asm volatile("bound %dx, 0x12(%eax)");
+        asm volatile("bound %dx, 0x12(%ebp)");
+        asm volatile("bound %dx, 0x12(%ecx,%eax,1)");
+        asm volatile("bound %dx, 0x12(%ebp,%eax,1)");
+        asm volatile("bound %dx, 0x12(%eax,%ecx,1)");
+        asm volatile("bound %dx, 0x12(%eax,%ecx,8)");
+        asm volatile("bound %dx, 0x12345678(%eax)");
+        asm volatile("bound %dx, 0x12345678(%ebp)");
+        asm volatile("bound %dx, 0x12345678(%ecx,%eax,1)");
+        asm volatile("bound %dx, 0x12345678(%ebp,%eax,1)");
+        asm volatile("bound %dx, 0x12345678(%eax,%ecx,1)");
+        asm volatile("bound %dx, 0x12345678(%eax,%ecx,8)");
+
+        /* AVX-512: Instructions with the same op codes as Mask Instructions  */
+
+        asm volatile("cmovno %eax,%ebx");
+        asm volatile("cmovno 0x12345678(%eax),%ecx");
+        asm volatile("cmovno 0x12345678(%eax),%cx");
+
+        asm volatile("cmove  %eax,%ebx");
+        asm volatile("cmove 0x12345678(%eax),%ecx");
+        asm volatile("cmove 0x12345678(%eax),%cx");
+
+        asm volatile("seto    0x12345678(%eax)");
+        asm volatile("setno   0x12345678(%eax)");
+        asm volatile("setb    0x12345678(%eax)");
+        asm volatile("setc    0x12345678(%eax)");
+        asm volatile("setnae  0x12345678(%eax)");
+        asm volatile("setae   0x12345678(%eax)");
+        asm volatile("setnb   0x12345678(%eax)");
+        asm volatile("setnc   0x12345678(%eax)");
+        asm volatile("sets    0x12345678(%eax)");
+        asm volatile("setns   0x12345678(%eax)");
+
+        /* AVX-512: Mask Instructions */
+
+        asm volatile("kandw  %k7,%k6,%k5");
+        asm volatile("kandq  %k7,%k6,%k5");
+        asm volatile("kandb  %k7,%k6,%k5");
+        asm volatile("kandd  %k7,%k6,%k5");
+
+        asm volatile("kandnw  %k7,%k6,%k5");
+        asm volatile("kandnq  %k7,%k6,%k5");
+        asm volatile("kandnb  %k7,%k6,%k5");
+        asm volatile("kandnd  %k7,%k6,%k5");
+
+        asm volatile("knotw  %k7,%k6");
+        asm volatile("knotq  %k7,%k6");
+        asm volatile("knotb  %k7,%k6");
+        asm volatile("knotd  %k7,%k6");
+
+        asm volatile("korw  %k7,%k6,%k5");
+        asm volatile("korq  %k7,%k6,%k5");
+        asm volatile("korb  %k7,%k6,%k5");
+        asm volatile("kord  %k7,%k6,%k5");
+
+        asm volatile("kxnorw  %k7,%k6,%k5");
+        asm volatile("kxnorq  %k7,%k6,%k5");
+        asm volatile("kxnorb  %k7,%k6,%k5");
+        asm volatile("kxnord  %k7,%k6,%k5");
+
+        asm volatile("kxorw  %k7,%k6,%k5");
+        asm volatile("kxorq  %k7,%k6,%k5");
+        asm volatile("kxorb  %k7,%k6,%k5");
+        asm volatile("kxord  %k7,%k6,%k5");
+
+        asm volatile("kaddw  %k7,%k6,%k5");
+        asm volatile("kaddq  %k7,%k6,%k5");
+        asm volatile("kaddb  %k7,%k6,%k5");
+        asm volatile("kaddd  %k7,%k6,%k5");
+
+        asm volatile("kunpckbw %k7,%k6,%k5");
+        asm volatile("kunpckwd %k7,%k6,%k5");
+        asm volatile("kunpckdq %k7,%k6,%k5");
+
+        asm volatile("kmovw  %k6,%k5");
+        asm volatile("kmovw  (%ecx),%k5");
+        asm volatile("kmovw  0x123(%eax,%ecx,8),%k5");
+        asm volatile("kmovw  %k5,(%ecx)");
+        asm volatile("kmovw  %k5,0x123(%eax,%ecx,8)");
+        asm volatile("kmovw  %eax,%k5");
+        asm volatile("kmovw  %ebp,%k5");
+        asm volatile("kmovw  %k5,%eax");
+        asm volatile("kmovw  %k5,%ebp");
+
+        asm volatile("kmovq  %k6,%k5");
+        asm volatile("kmovq  (%ecx),%k5");
+        asm volatile("kmovq  0x123(%eax,%ecx,8),%k5");
+        asm volatile("kmovq  %k5,(%ecx)");
+        asm volatile("kmovq  %k5,0x123(%eax,%ecx,8)");
+
+        asm volatile("kmovb  %k6,%k5");
+        asm volatile("kmovb  (%ecx),%k5");
+        asm volatile("kmovb  0x123(%eax,%ecx,8),%k5");
+        asm volatile("kmovb  %k5,(%ecx)");
+        asm volatile("kmovb  %k5,0x123(%eax,%ecx,8)");
+        asm volatile("kmovb  %eax,%k5");
+        asm volatile("kmovb  %ebp,%k5");
+        asm volatile("kmovb  %k5,%eax");
+        asm volatile("kmovb  %k5,%ebp");
+
+        asm volatile("kmovd  %k6,%k5");
+        asm volatile("kmovd  (%ecx),%k5");
+        asm volatile("kmovd  0x123(%eax,%ecx,8),%k5");
+        asm volatile("kmovd  %k5,(%ecx)");
+        asm volatile("kmovd  %k5,0x123(%eax,%ecx,8)");
+        asm volatile("kmovd  %eax,%k5");
+        asm volatile("kmovd  %ebp,%k5");
+        asm volatile("kmovd  %k5,%eax");
+        asm volatile("kmovd  %k5,%ebp");
+
+        asm volatile("kortestw %k6,%k5");
+        asm volatile("kortestq %k6,%k5");
+        asm volatile("kortestb %k6,%k5");
+        asm volatile("kortestd %k6,%k5");
+
+        asm volatile("ktestw %k6,%k5");
+        asm volatile("ktestq %k6,%k5");
+        asm volatile("ktestb %k6,%k5");
+        asm volatile("ktestd %k6,%k5");
+
+        asm volatile("kshiftrw $0x12,%k6,%k5");
+        asm volatile("kshiftrq $0x5b,%k6,%k5");
+        asm volatile("kshiftlw $0x12,%k6,%k5");
+        asm volatile("kshiftlq $0x5b,%k6,%k5");
+
+        /* AVX-512: Op code 0f 5b */
+        asm volatile("vcvtdq2ps %xmm5,%xmm6");
+        asm volatile("vcvtqq2ps %zmm5,%ymm6{%k7}");
+        asm volatile("vcvtps2dq %xmm5,%xmm6");
+        asm volatile("vcvttps2dq %xmm5,%xmm6");
+
+        /* AVX-512: Op code 0f 6f */
+
+        asm volatile("movq   %mm0,%mm4");
+        asm volatile("vmovdqa %ymm4,%ymm6");
+        asm volatile("vmovdqa32 %zmm5,%zmm6");
+        asm volatile("vmovdqa64 %zmm5,%zmm6");
+        asm volatile("vmovdqu %ymm4,%ymm6");
+        asm volatile("vmovdqu32 %zmm5,%zmm6");
+        asm volatile("vmovdqu64 %zmm5,%zmm6");
+        asm volatile("vmovdqu8 %zmm5,%zmm6");
+        asm volatile("vmovdqu16 %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 78 */
+
+        asm volatile("vmread %eax,%ebx");
+        asm volatile("vcvttps2udq %zmm5,%zmm6");
+        asm volatile("vcvttpd2udq %zmm5,%ymm6{%k7}");
+        asm volatile("vcvttsd2usi %xmm6,%eax");
+        asm volatile("vcvttss2usi %xmm6,%eax");
+        asm volatile("vcvttps2uqq %ymm5,%zmm6{%k7}");
+        asm volatile("vcvttpd2uqq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 79 */
+
+        asm volatile("vmwrite %eax,%ebx");
+        asm volatile("vcvtps2udq %zmm5,%zmm6");
+        asm volatile("vcvtpd2udq %zmm5,%ymm6{%k7}");
+        asm volatile("vcvtsd2usi %xmm6,%eax");
+        asm volatile("vcvtss2usi %xmm6,%eax");
+        asm volatile("vcvtps2uqq %ymm5,%zmm6{%k7}");
+        asm volatile("vcvtpd2uqq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 7a */
+
+        asm volatile("vcvtudq2pd %ymm5,%zmm6{%k7}");
+        asm volatile("vcvtuqq2pd %zmm5,%zmm6");
+        asm volatile("vcvtudq2ps %zmm5,%zmm6");
+        asm volatile("vcvtuqq2ps %zmm5,%ymm6{%k7}");
+        asm volatile("vcvttps2qq %ymm5,%zmm6{%k7}");
+        asm volatile("vcvttpd2qq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 7b */
+
+        asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6");
+        asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6");
+        asm volatile("vcvtps2qq %ymm5,%zmm6{%k7}");
+        asm volatile("vcvtpd2qq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 7f */
+
+        asm volatile("movq.s  %mm0,%mm4");
+        asm volatile("vmovdqa.s %ymm5,%ymm6");
+        asm volatile("vmovdqa32.s %zmm5,%zmm6");
+        asm volatile("vmovdqa64.s %zmm5,%zmm6");
+        asm volatile("vmovdqu.s %ymm5,%ymm6");
+        asm volatile("vmovdqu32.s %zmm5,%zmm6");
+        asm volatile("vmovdqu64.s %zmm5,%zmm6");
+        asm volatile("vmovdqu8.s %zmm5,%zmm6");
+        asm volatile("vmovdqu16.s %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f db */
+
+        asm volatile("pand  %mm1,%mm2");
+        asm volatile("pand  %xmm1,%xmm2");
+        asm volatile("vpand  %ymm4,%ymm6,%ymm2");
+        asm volatile("vpandd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpandq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f df */
+
+        asm volatile("pandn  %mm1,%mm2");
+        asm volatile("pandn  %xmm1,%xmm2");
+        asm volatile("vpandn %ymm4,%ymm6,%ymm2");
+        asm volatile("vpandnd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpandnq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f e6 */
+
+        asm volatile("vcvttpd2dq %xmm1,%xmm2");
+        asm volatile("vcvtdq2pd %xmm5,%xmm6");
+        asm volatile("vcvtdq2pd %ymm5,%zmm6{%k7}");
+        asm volatile("vcvtqq2pd %zmm5,%zmm6");
+        asm volatile("vcvtpd2dq %xmm1,%xmm2");
+
+        /* AVX-512: Op code 0f eb */
+
+        asm volatile("por   %mm4,%mm6");
+        asm volatile("vpor   %ymm4,%ymm6,%ymm2");
+        asm volatile("vpord  %zmm4,%zmm5,%zmm6");
+        asm volatile("vporq  %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f ef */
+
+        asm volatile("pxor   %mm4,%mm6");
+        asm volatile("vpxor  %ymm4,%ymm6,%ymm2");
+        asm volatile("vpxord %zmm4,%zmm5,%zmm6");
+        asm volatile("vpxorq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 10 */
+
+        asm volatile("pblendvb %xmm1,%xmm0");
+        asm volatile("vpsrlvw %zmm4,%zmm5,%zmm6");
+        asm volatile("vpmovuswb %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 11 */
+
+        asm volatile("vpmovusdb %zmm5,%xmm6{%k7}");
+        asm volatile("vpsravw %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 12 */
+
+        asm volatile("vpmovusqb %zmm5,%xmm6{%k7}");
+        asm volatile("vpsllvw %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 13 */
+
+        asm volatile("vcvtph2ps %xmm3,%ymm5");
+        asm volatile("vcvtph2ps %ymm5,%zmm6{%k7}");
+        asm volatile("vpmovusdw %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 14 */
+
+        asm volatile("blendvps %xmm1,%xmm0");
+        asm volatile("vpmovusqw %zmm5,%xmm6{%k7}");
+        asm volatile("vprorvd %zmm4,%zmm5,%zmm6");
+        asm volatile("vprorvq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 15 */
+
+        asm volatile("blendvpd %xmm1,%xmm0");
+        asm volatile("vpmovusqd %zmm5,%ymm6{%k7}");
+        asm volatile("vprolvd %zmm4,%zmm5,%zmm6");
+        asm volatile("vprolvq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 16 */
+
+        asm volatile("vpermps %ymm4,%ymm6,%ymm2");
+        asm volatile("vpermps %ymm4,%ymm6,%ymm2{%k7}");
+        asm volatile("vpermpd %ymm4,%ymm6,%ymm2{%k7}");
+
+        /* AVX-512: Op code 0f 38 19 */
+
+        asm volatile("vbroadcastsd %xmm4,%ymm6");
+        asm volatile("vbroadcastf32x2 %xmm7,%zmm6");
+
+        /* AVX-512: Op code 0f 38 1a */
+
+        asm volatile("vbroadcastf128 (%ecx),%ymm4");
+        asm volatile("vbroadcastf32x4 (%ecx),%zmm6");
+        asm volatile("vbroadcastf64x2 (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 1b */
+
+        asm volatile("vbroadcastf32x8 (%ecx),%zmm6");
+        asm volatile("vbroadcastf64x4 (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 1f */
+
+        asm volatile("vpabsq %zmm4,%zmm6");
+
+        /* AVX-512: Op code 0f 38 20 */
+
+        asm volatile("vpmovsxbw %xmm4,%xmm5");
+        asm volatile("vpmovswb %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 21 */
+
+        asm volatile("vpmovsxbd %xmm4,%ymm6");
+        asm volatile("vpmovsdb %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 22 */
+
+        asm volatile("vpmovsxbq %xmm4,%ymm4");
+        asm volatile("vpmovsqb %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 23 */
+
+        asm volatile("vpmovsxwd %xmm4,%ymm4");
+        asm volatile("vpmovsdw %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 24 */
+
+        asm volatile("vpmovsxwq %xmm4,%ymm6");
+        asm volatile("vpmovsqw %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 25 */
+
+        asm volatile("vpmovsxdq %xmm4,%ymm4");
+        asm volatile("vpmovsqd %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 26 */
+
+        asm volatile("vptestmb %zmm5,%zmm6,%k5");
+        asm volatile("vptestmw %zmm5,%zmm6,%k5");
+        asm volatile("vptestnmb %zmm4,%zmm5,%k5");
+        asm volatile("vptestnmw %zmm4,%zmm5,%k5");
+
+        /* AVX-512: Op code 0f 38 27 */
+
+        asm volatile("vptestmd %zmm5,%zmm6,%k5");
+        asm volatile("vptestmq %zmm5,%zmm6,%k5");
+        asm volatile("vptestnmd %zmm4,%zmm5,%k5");
+        asm volatile("vptestnmq %zmm4,%zmm5,%k5");
+
+        /* AVX-512: Op code 0f 38 28 */
+
+        asm volatile("vpmuldq %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovm2b %k5,%zmm6");
+        asm volatile("vpmovm2w %k5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 29 */
+
+        asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovb2m %zmm6,%k5");
+        asm volatile("vpmovw2m %zmm6,%k5");
+
+        /* AVX-512: Op code 0f 38 2a */
+
+        asm volatile("vmovntdqa (%ecx),%ymm4");
+        asm volatile("vpbroadcastmb2q %k6,%zmm1");
+
+        /* AVX-512: Op code 0f 38 2c */
+
+        asm volatile("vmaskmovps (%ecx),%ymm4,%ymm6");
+        asm volatile("vscalefps %zmm4,%zmm5,%zmm6");
+        asm volatile("vscalefpd %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 2d */
+
+        asm volatile("vmaskmovpd (%ecx),%ymm4,%ymm6");
+        asm volatile("vscalefss %xmm4,%xmm5,%xmm6{%k7}");
+        asm volatile("vscalefsd %xmm4,%xmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 30 */
+
+        asm volatile("vpmovzxbw %xmm4,%ymm4");
+        asm volatile("vpmovwb %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 31 */
+
+        asm volatile("vpmovzxbd %xmm4,%ymm6");
+        asm volatile("vpmovdb %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 32 */
+
+        asm volatile("vpmovzxbq %xmm4,%ymm4");
+        asm volatile("vpmovqb %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 33 */
+
+        asm volatile("vpmovzxwd %xmm4,%ymm4");
+        asm volatile("vpmovdw %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 34 */
+
+        asm volatile("vpmovzxwq %xmm4,%ymm6");
+        asm volatile("vpmovqw %zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 35 */
+
+        asm volatile("vpmovzxdq %xmm4,%ymm4");
+        asm volatile("vpmovqd %zmm5,%ymm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 36 */
+
+        asm volatile("vpermd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpermd %ymm4,%ymm6,%ymm2{%k7}");
+        asm volatile("vpermq %ymm4,%ymm6,%ymm2{%k7}");
+
+        /* AVX-512: Op code 0f 38 38 */
+
+        asm volatile("vpminsb %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmovm2d %k5,%zmm6");
+        asm volatile("vpmovm2q %k5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 39 */
+
+        asm volatile("vpminsd %xmm1,%xmm2,%xmm3");
+        asm volatile("vpminsd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpminsq %zmm4,%zmm5,%zmm6");
+        asm volatile("vpmovd2m %zmm6,%k5");
+        asm volatile("vpmovq2m %zmm6,%k5");
+
+        /* AVX-512: Op code 0f 38 3a */
+
+        asm volatile("vpminuw %ymm4,%ymm6,%ymm2");
+        asm volatile("vpbroadcastmw2d %k6,%zmm6");
+
+        /* AVX-512: Op code 0f 38 3b */
+
+        asm volatile("vpminud %ymm4,%ymm6,%ymm2");
+        asm volatile("vpminud %zmm4,%zmm5,%zmm6");
+        asm volatile("vpminuq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 3d */
+
+        asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmaxsd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpmaxsq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 3f */
+
+        asm volatile("vpmaxud %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmaxud %zmm4,%zmm5,%zmm6");
+        asm volatile("vpmaxuq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 40 */
+
+        asm volatile("vpmulld %ymm4,%ymm6,%ymm2");
+        asm volatile("vpmulld %zmm4,%zmm5,%zmm6");
+        asm volatile("vpmullq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 42 */
+
+        asm volatile("vgetexpps %zmm5,%zmm6");
+        asm volatile("vgetexppd %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 43 */
+
+        asm volatile("vgetexpss %xmm4,%xmm5,%xmm6{%k7}");
+        asm volatile("vgetexpsd %xmm2,%xmm3,%xmm4{%k7}");
+
+        /* AVX-512: Op code 0f 38 44 */
+
+        asm volatile("vplzcntd %zmm5,%zmm6");
+        asm volatile("vplzcntq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 46 */
+
+        asm volatile("vpsravd %ymm4,%ymm6,%ymm2");
+        asm volatile("vpsravd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpsravq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 4c */
+
+        asm volatile("vrcp14ps %zmm5,%zmm6");
+        asm volatile("vrcp14pd %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 4d */
+
+        asm volatile("vrcp14ss %xmm4,%xmm5,%xmm6{%k7}");
+        asm volatile("vrcp14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 4e */
+
+        asm volatile("vrsqrt14ps %zmm5,%zmm6");
+        asm volatile("vrsqrt14pd %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 4f */
+
+        asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}");
+        asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 38 59 */
+
+        asm volatile("vpbroadcastq %xmm4,%xmm6");
+        asm volatile("vbroadcasti32x2 %xmm7,%zmm6");
+
+        /* AVX-512: Op code 0f 38 5a */
+
+        asm volatile("vbroadcasti128 (%ecx),%ymm4");
+        asm volatile("vbroadcasti32x4 (%ecx),%zmm6");
+        asm volatile("vbroadcasti64x2 (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 5b */
+
+        asm volatile("vbroadcasti32x8 (%ecx),%zmm6");
+        asm volatile("vbroadcasti64x4 (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 64 */
+
+        asm volatile("vpblendmd %zmm4,%zmm5,%zmm6");
+        asm volatile("vpblendmq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 65 */
+
+        asm volatile("vblendmps %zmm4,%zmm5,%zmm6");
+        asm volatile("vblendmpd %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 66 */
+
+        asm volatile("vpblendmb %zmm4,%zmm5,%zmm6");
+        asm volatile("vpblendmw %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 75 */
+
+        asm volatile("vpermi2b %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermi2w %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 76 */
+
+        asm volatile("vpermi2d %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermi2q %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 77 */
+
+        asm volatile("vpermi2ps %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermi2pd %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 7a */
+
+        asm volatile("vpbroadcastb %eax,%xmm3");
+
+        /* AVX-512: Op code 0f 38 7b */
+
+        asm volatile("vpbroadcastw %eax,%xmm3");
+
+        /* AVX-512: Op code 0f 38 7c */
+
+        asm volatile("vpbroadcastd %eax,%xmm3");
+
+        /* AVX-512: Op code 0f 38 7d */
+
+        asm volatile("vpermt2b %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermt2w %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 7e */
+
+        asm volatile("vpermt2d %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermt2q %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 7f */
+
+        asm volatile("vpermt2ps %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermt2pd %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 83 */
+
+        asm volatile("vpmultishiftqb %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 88 */
+
+        asm volatile("vexpandps (%ecx),%zmm6");
+        asm volatile("vexpandpd (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 89 */
+
+        asm volatile("vpexpandd (%ecx),%zmm6");
+        asm volatile("vpexpandq (%ecx),%zmm6");
+
+        /* AVX-512: Op code 0f 38 8a */
+
+        asm volatile("vcompressps %zmm6,(%ecx)");
+        asm volatile("vcompresspd %zmm6,(%ecx)");
+
+        /* AVX-512: Op code 0f 38 8b */
+
+        asm volatile("vpcompressd %zmm6,(%ecx)");
+        asm volatile("vpcompressq %zmm6,(%ecx)");
+
+        /* AVX-512: Op code 0f 38 8d */
+
+        asm volatile("vpermb %zmm4,%zmm5,%zmm6");
+        asm volatile("vpermw %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 90 */
+
+        asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherdq %xmm2,0x04(%ebp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+        asm volatile("vpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}");
+
+        /* AVX-512: Op code 0f 38 91 */
+
+        asm volatile("vpgatherqd %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherqq %xmm2,0x02(%ebp,%xmm7,2),%xmm1");
+        asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}");
+        asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}");
+
+        /* AVX-512: Op code 0f 38 a0 */
+
+        asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a1 */
+
+        asm volatile("vpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a2 */
+
+        asm volatile("vscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 a3 */
+
+        asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 b4 */
+
+        asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 b5 */
+
+        asm volatile("vpmadd52huq %zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 c4 */
+
+        asm volatile("vpconflictd %zmm5,%zmm6");
+        asm volatile("vpconflictq %zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 38 c8 */
+
+        asm volatile("vexp2ps %zmm6,%zmm7");
+        asm volatile("vexp2pd %zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 38 ca */
+
+        asm volatile("vrcp28ps %zmm6,%zmm7");
+        asm volatile("vrcp28pd %zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 38 cb */
+
+        asm volatile("vrcp28ss %xmm5,%xmm6,%xmm7{%k7}");
+        asm volatile("vrcp28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+        /* AVX-512: Op code 0f 38 cc */
+
+        asm volatile("vrsqrt28ps %zmm6,%zmm7");
+        asm volatile("vrsqrt28pd %zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 38 cd */
+
+        asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}");
+        asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 03 */
+
+        asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("valignq $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 08 */
+
+        asm volatile("vroundps $0x5,%ymm6,%ymm2");
+        asm volatile("vrndscaleps $0x12,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 3a 09 */
+
+        asm volatile("vroundpd $0x5,%ymm6,%ymm2");
+        asm volatile("vrndscalepd $0x12,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 3a 0a */
+
+        asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2");
+        asm volatile("vrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 0b */
+
+        asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2");
+        asm volatile("vrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 18 */
+
+        asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6");
+        asm volatile("vinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+        asm volatile("vinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 19 */
+
+        asm volatile("vextractf128 $0x5,%ymm4,%xmm4");
+        asm volatile("vextractf32x4 $0x12,%zmm5,%xmm6{%k7}");
+        asm volatile("vextractf64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1a */
+
+        asm volatile("vinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+        asm volatile("vinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1b */
+
+        asm volatile("vextractf32x8 $0x12,%zmm6,%ymm7{%k7}");
+        asm volatile("vextractf64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 1e */
+
+        asm volatile("vpcmpud $0x12,%zmm6,%zmm7,%k5");
+        asm volatile("vpcmpuq $0x12,%zmm6,%zmm7,%k5");
+
+        /* AVX-512: Op code 0f 3a 1f */
+
+        asm volatile("vpcmpd $0x12,%zmm6,%zmm7,%k5");
+        asm volatile("vpcmpq $0x12,%zmm6,%zmm7,%k5");
+
+        /* AVX-512: Op code 0f 3a 23 */
+
+        asm volatile("vshuff32x4 $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("vshuff64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 25 */
+
+        asm volatile("vpternlogd $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("vpternlogq $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 26 */
+
+        asm volatile("vgetmantps $0x12,%zmm6,%zmm7");
+        asm volatile("vgetmantpd $0x12,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 27 */
+
+        asm volatile("vgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+        asm volatile("vgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 38 */
+
+        asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6");
+        asm volatile("vinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+        asm volatile("vinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 39 */
+
+        asm volatile("vextracti128 $0x5,%ymm4,%xmm6");
+        asm volatile("vextracti32x4 $0x12,%zmm5,%xmm6{%k7}");
+        asm volatile("vextracti64x2 $0x12,%zmm5,%xmm6{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3a */
+
+        asm volatile("vinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+        asm volatile("vinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3b */
+
+        asm volatile("vextracti32x8 $0x12,%zmm6,%ymm7{%k7}");
+        asm volatile("vextracti64x4 $0x12,%zmm6,%ymm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 3e */
+
+        asm volatile("vpcmpub $0x12,%zmm6,%zmm7,%k5");
+        asm volatile("vpcmpuw $0x12,%zmm6,%zmm7,%k5");
+
+        /* AVX-512: Op code 0f 3a 3f */
+
+        asm volatile("vpcmpb $0x12,%zmm6,%zmm7,%k5");
+        asm volatile("vpcmpw $0x12,%zmm6,%zmm7,%k5");
+
+        /* AVX-512: Op code 0f 3a 42 */
+
+        asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2");
+        asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6");
+
+        /* AVX-512: Op code 0f 3a 43 */
+
+        asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 50 */
+
+        asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("vrangepd $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 51 */
+
+        asm volatile("vrangess $0x12,%xmm5,%xmm6,%xmm7");
+        asm volatile("vrangesd $0x12,%xmm5,%xmm6,%xmm7");
+
+        /* AVX-512: Op code 0f 3a 54 */
+
+        asm volatile("vfixupimmps $0x12,%zmm5,%zmm6,%zmm7");
+        asm volatile("vfixupimmpd $0x12,%zmm5,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 55 */
+
+        asm volatile("vfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+        asm volatile("vfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}");
+
+        /* AVX-512: Op code 0f 3a 56 */
+
+        asm volatile("vreduceps $0x12,%zmm6,%zmm7");
+        asm volatile("vreducepd $0x12,%zmm6,%zmm7");
+
+        /* AVX-512: Op code 0f 3a 57 */
+
+        asm volatile("vreducess $0x12,%xmm5,%xmm6,%xmm7");
+        asm volatile("vreducesd $0x12,%xmm5,%xmm6,%xmm7");
+
+        /* AVX-512: Op code 0f 3a 66 */
+
+        asm volatile("vfpclassps $0x12,%zmm7,%k5");
+        asm volatile("vfpclasspd $0x12,%zmm7,%k5");
+
+        /* AVX-512: Op code 0f 3a 67 */
+
+        asm volatile("vfpclassss $0x12,%xmm7,%k5");
+        asm volatile("vfpclasssd $0x12,%xmm7,%k5");
+
+        /* AVX-512: Op code 0f 72 (Grp13) */
+
+        asm volatile("vprord $0x12,%zmm5,%zmm6");
+        asm volatile("vprorq $0x12,%zmm5,%zmm6");
+        asm volatile("vprold $0x12,%zmm5,%zmm6");
+        asm volatile("vprolq $0x12,%zmm5,%zmm6");
+        asm volatile("psrad  $0x2,%mm6");
+        asm volatile("vpsrad $0x5,%ymm6,%ymm2");
+        asm volatile("vpsrad $0x5,%zmm6,%zmm2");
+        asm volatile("vpsraq $0x5,%zmm6,%zmm2");
+
+        /* AVX-512: Op code 0f 38 c6 (Grp18) */
+
+        asm volatile("vgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+        asm volatile("vgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+        asm volatile("vscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}");
+        asm volatile("vscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}");
+
+        /* AVX-512: Op code 0f 38 c7 (Grp19) */
+
+        asm volatile("vgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}");
+        asm volatile("vscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}");
+
+        /* AVX-512: Examples */
+
+        asm volatile("vaddpd %zmm4,%zmm5,%zmm6");
+        asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}");
+        asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}{z}");
+        asm volatile("vaddpd {rn-sae},%zmm4,%zmm5,%zmm6");
+        asm volatile("vaddpd {ru-sae},%zmm4,%zmm5,%zmm6");
+        asm volatile("vaddpd {rd-sae},%zmm4,%zmm5,%zmm6");
+        asm volatile("vaddpd {rz-sae},%zmm4,%zmm5,%zmm6");
+        asm volatile("vaddpd (%ecx),%zmm5,%zmm6");
+        asm volatile("vaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6");
+        asm volatile("vaddpd (%ecx){1to8},%zmm5,%zmm6");
+        asm volatile("vaddpd 0x1fc0(%edx),%zmm5,%zmm6");
+        asm volatile("vaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6");
+        asm volatile("vcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5");
+        asm volatile("vcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}");
+        asm volatile("vcmplesd {sae},%xmm4,%xmm5,%k5{%k7}");
+        asm volatile("vgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}");
+
         /* bndmk m32, bnd */
 
         asm volatile("bndmk (%eax), %bnd0");
@@ -866,10 +2655,6 @@ int main(void)
 
 #endif /* #ifndef __x86_64__ */
 
-        /* pcommit */
-
-        asm volatile("pcommit");
-
         /* Following line is a marker for the awk script - do not change */
         asm volatile("rdtsc"); /* Stop here */
 
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index d4aa567a29c4..5c76cc83186a 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -154,10 +154,6 @@ next_event:
         err = 0;
 
 out_err:
-        if (evlist) {
-                perf_evlist__disable(evlist);
-                perf_evlist__delete(evlist);
-        }
-
+        perf_evlist__delete(evlist);
         return err;
 }
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 72193f19d6d7..500cf96db979 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -1,12 +1,16 @@
+#include <errno.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/wait.h>
 #include <linux/types.h>
 #include "perf.h"
 #include "debug.h"
 #include "tests/tests.h"
 #include "cloexec.h"
+#include "util.h"
 #include "arch-tests.h"
 
 static u64 rdpmc(unsigned int counter)
@@ -111,14 +115,14 @@ static int __test__rdpmc(void)
         if (fd < 0) {
                 pr_err("Error: sys_perf_event_open() syscall returned "
                        "with %d (%s)\n", fd,
-                       strerror_r(errno, sbuf, sizeof(sbuf)));
+                       str_error_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
 
         addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
         if (addr == (void *)(-1)) {
                 pr_err("Error: mmap() syscall returned with (%s)\n",
-                       strerror_r(errno, sbuf, sizeof(sbuf)));
+                       str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_close;
         }
 
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 465970370f3e..f95e6f46ef0d 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -3,11 +3,12 @@ libperf-y += tsc.o
 libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += group.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
 
-libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 7a7805583e3f..cc1d865e31f1 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -37,7 +37,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
         intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
         if (evlist) {
-                evlist__for_each(evlist, evsel) {
+                evlist__for_each_entry(evlist, evsel) {
                         if (intel_pt_pmu &&
                             evsel->attr.type == intel_pt_pmu->type)
                                 found_pt = true;
diff --git a/tools/perf/arch/x86/util/group.c b/tools/perf/arch/x86/util/group.c
new file mode 100644
index 000000000000..37f92aa39a5d
--- /dev/null
+++ b/tools/perf/arch/x86/util/group.c
@@ -0,0 +1,27 @@
+#include <stdio.h>
+#include "api/fs/fs.h"
+#include "util/group.h"
+
+/*
+ * Check whether we can use a group for top down.
+ * Without a group may get bad results due to multiplexing.
+ */
+bool arch_topdown_check_group(bool *warn)
+{
+        int n;
+
+        if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0)
+                return false;
+        if (n > 0) {
+                *warn = true;
+                return false;
+        }
+        return true;
+}
+
+void arch_topdown_group_warn(void)
+{
+        fprintf(stderr,
+                "nmi_watchdog enabled with topdown. May give wrong results.\n"
+                "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n");
+}
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 7dc30637cf66..5132775a044f 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -124,7 +124,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
         btsr->evlist = evlist;
         btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type == intel_bts_pmu->type) {
                         if (intel_bts_evsel) {
                                 pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
@@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr)
                         container_of(itr, struct intel_bts_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(btsr->evlist, evsel) {
+        evlist__for_each_entry(btsr->evlist, evsel) {
                 if (evsel->attr.type == btsr->intel_bts_pmu->type)
                         return perf_evsel__disable(evsel);
         }
@@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
                         container_of(itr, struct intel_bts_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(btsr->evlist, evsel) {
+        evlist__for_each_entry(btsr->evlist, evsel) {
                 if (evsel->attr.type == btsr->intel_bts_pmu->type)
                         return perf_evsel__enable(evsel);
         }
@@ -422,7 +422,7 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
                         container_of(itr, struct intel_bts_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(btsr->evlist, evsel) {
+        evlist__for_each_entry(btsr->evlist, evsel) {
                 if (evsel->attr.type == btsr->intel_bts_pmu->type)
                         return perf_evlist__enable_event_idx(btsr->evlist,
                                                              evsel, idx);
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a07b9605e93b..fb51457ba338 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -131,7 +131,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str,
         if (!mask)
                 return -EINVAL;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type == intel_pt_pmu->type) {
                         *res = intel_pt_masked_bits(mask, evsel->attr.config);
                         return 0;
@@ -511,7 +511,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
         ptr->evlist = evlist;
         ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type == intel_pt_pmu->type) {
                         if (intel_pt_evsel) {
                                 pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n");
@@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr)
                         container_of(itr, struct intel_pt_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(ptr->evlist, evsel) {
+        evlist__for_each_entry(ptr->evlist, evsel) {
                 if (evsel->attr.type == ptr->intel_pt_pmu->type)
                         return perf_evsel__disable(evsel);
         }
@@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
                         container_of(itr, struct intel_pt_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(ptr->evlist, evsel) {
+        evlist__for_each_entry(ptr->evlist, evsel) {
                 if (evsel->attr.type == ptr->intel_pt_pmu->type)
                         return perf_evsel__enable(evsel);
         }
@@ -1011,7 +1011,7 @@ static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
                         container_of(itr, struct intel_pt_recording, itr);
         struct perf_evsel *evsel;
 
-        evlist__for_each(ptr->evlist, evsel) {
+        evlist__for_each_entry(ptr->evlist, evsel) {
                 if (evsel->attr.type == ptr->intel_pt_pmu->type)
                         return perf_evlist__enable_event_idx(ptr->evlist, evsel,
                                                              idx);
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 357f1b13b5ae..2e5567c94e09 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -62,6 +62,8 @@ int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
         struct perf_tsc_conversion tc;
         int err;
 
+        if (!pc)
+                return 0;
         err = perf_read_tsc_conversion(pc, &tc);
         if (err == -EOPNOTSUPP)
                 return 0;
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index db25e93d989c..4f16661cbdbb 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -1,12 +1,14 @@
 
+#ifndef REMOTE_UNWIND_LIBUNWIND
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 #include "../../util/debug.h"
+#endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
         int id;
 
@@ -70,7 +72,7 @@ int libunwind__arch_reg_id(int regnum)
         return id;
 }
 #else
-int libunwind__arch_reg_id(int regnum)
+int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
         int id;
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 0999ac536d86..8024cd5febd2 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -8,18 +8,23 @@
  * many threads and futexes as possible.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <errno.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
-#include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6952db65508a..936d89d30483 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -2,18 +2,21 @@
  * Copyright (C) 2015 Davidlohr Bueso.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct worker {
         int tid;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 718238683013..f96e22ed9f87 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -8,18 +8,21 @@
  * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static u_int32_t futex1 = 0, futex2 = 0;
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 91aaf2a1fa90..4a2ecd7438ca 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,18 +7,21 @@
  * it can be used to measure futex_wake() changes.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct thread_data {
         pthread_t worker;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index f416bd705f66..87d8f4f292d9 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -8,18 +8,21 @@
  * one or more tasks, and thus the waitqueue is never empty.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 /* all threads will block on the same futex */
 static u_int32_t futex1 = 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 5c3cce082cb8..f700369bb0f6 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,7 +6,7 @@
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
 
-#include "../../../arch/x86/lib/memcpy_64.S"
+#include "../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
  * NOT executable stack. Otherwise the final linking will assume that
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index de278784c866..58407aa24c1b 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,7 +1,7 @@
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
-#include "../../../arch/x86/lib/memset_64.S"
+#include "../../arch/x86/lib/memset_64.S"
 
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 7500d959d7eb..f7f530081aa9 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -4,6 +4,9 @@
  * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
@@ -21,7 +24,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <sys/resource.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 25c81734a950..9c1034d81b4f 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -75,7 +75,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
         sample->period = 1;
         sample->weight = 1;
 
-        he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
+        he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -236,7 +236,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 perf_session__fprintf_dsos(session, stdout);
 
         total_nr_samples = 0;
-        evlist__for_each(session->evlist, pos) {
+        evlist__for_each_entry(session->evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
                 u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
@@ -339,6 +339,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Show event group information together"),
         OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
                     "Show a column with the sum of periods"),
+        OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+                             "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+                             stdio__config_color, "always"),
         OPT_END()
         };
         int ret = hists__init();
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d75bded21fe0..30e2b2cb2421 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -209,7 +209,7 @@ static int build_id_cache__purge_path(const char *pathname)
         if (err)
                 goto out;
 
-        strlist__for_each(pos, list) {
+        strlist__for_each_entry(pos, list) {
                 err = build_id_cache__remove_s(pos->s);
                 pr_debug("Removing %s %s: %s\n", pos->s, pathname,
                          err ? "FAIL" : "Ok");
@@ -343,7 +343,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         if (add_name_list_str) {
                 list = strlist__new(add_name_list_str, NULL);
                 if (list) {
-                        strlist__for_each(pos, list)
+                        strlist__for_each_entry(pos, list)
                                 if (build_id_cache__add_file(pos->s)) {
                                         if (errno == EEXIST) {
                                                 pr_debug("%s already in the cache\n",
@@ -351,7 +351,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't add %s: %s\n",
-                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+                                                   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -361,7 +361,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         if (remove_name_list_str) {
                 list = strlist__new(remove_name_list_str, NULL);
                 if (list) {
-                        strlist__for_each(pos, list)
+                        strlist__for_each_entry(pos, list)
                                 if (build_id_cache__remove_file(pos->s)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
@@ -369,7 +369,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't remove %s: %s\n",
-                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+                                                   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -379,7 +379,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         if (purge_name_list_str) {
                 list = strlist__new(purge_name_list_str, NULL);
                 if (list) {
-                        strlist__for_each(pos, list)
+                        strlist__for_each_entry(pos, list)
                                 if (build_id_cache__purge_path(pos->s)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
@@ -387,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't remove %s: %s\n",
-                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+                                                   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -400,7 +400,7 @@ int cmd_buildid_cache(int argc, const char **argv,
         if (update_name_list_str) {
                 list = strlist__new(update_name_list_str, NULL);
                 if (list) {
-                        strlist__for_each(pos, list)
+                        strlist__for_each_entry(pos, list)
                                 if (build_id_cache__update_file(pos->s)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
@@ -408,7 +408,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                                                 continue;
                                         }
                                         pr_warning("Couldn't update %s: %s\n",
-                                                   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
+                                                   pos->s, str_error_r(errno, sbuf, sizeof(sbuf)));
                                 }
 
                         strlist__delete(list);
@@ -419,8 +419,7 @@ int cmd_buildid_cache(int argc, const char **argv,
                 pr_warning("Couldn't add %s\n", kcore_filename);
 
 out:
-        if (session)
-                perf_session__delete(session);
+        perf_session__delete(session);
 
         return ret;
 }
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index fe1b77fa21f9..e4207a23b52c 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -37,23 +37,16 @@ static int show_config(struct perf_config_set *set)
 {
         struct perf_config_section *section;
         struct perf_config_item *item;
-        struct list_head *sections;
 
         if (set == NULL)
                 return -1;
 
-        sections = &set->sections;
-        if (list_empty(sections))
-                return -1;
-
-        list_for_each_entry(section, sections, node) {
-                list_for_each_entry(item, &section->items, node) {
-                        char *value = item->value;
+        perf_config_set__for_each_entry(set, section, item) {
+                char *value = item->value;
 
-                        if (value)
-                                printf("%s.%s=%s\n", section->name,
-                                       item->name, value);
-                }
+                if (value)
+                        printf("%s.%s=%s\n", section->name,
+                               item->name, value);
         }
 
         return 0;
@@ -80,6 +73,10 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
         else if (use_user_config)
                 config_exclusive_filename = user_config;
 
+        /*
+         * At only 'config' sub-command, individually use the config set
+         * because of reinitializing with options config file location.
+         */
         set = perf_config_set__new();
         if (!set) {
                 ret = -1;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index b97bc1518b44..7ad6e17ac6b3 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -3,6 +3,7 @@
 #include "perf.h"
 #include "debug.h"
 #include <subcmd/parse-options.h>
+#include "data-convert.h"
 #include "data-convert-bt.h"
 
 typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
@@ -53,14 +54,18 @@ static int cmd_data_convert(int argc, const char **argv,
                             const char *prefix __maybe_unused)
 {
         const char *to_ctf     = NULL;
-        bool force = false;
+        struct perf_data_convert_opts opts = {
+                .force = false,
+                .all = false,
+        };
         const struct option options[] = {
                 OPT_INCR('v', "verbose", &verbose, "be more verbose"),
                 OPT_STRING('i', "input", &input_name, "file", "input file name"),
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
                 OPT_STRING(0, "to-ctf", &to_ctf, NULL, "Convert to CTF format"),
 #endif
-                OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+                OPT_BOOLEAN('f', "force", &opts.force, "don't complain, do it"),
+                OPT_BOOLEAN(0, "all", &opts.all, "Convert all events"),
                 OPT_END()
         };
 
@@ -78,7 +83,7 @@ static int cmd_data_convert(int argc, const char **argv,
 
         if (to_ctf) {
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
-                return bt_convert__perf2ctf(input_name, to_ctf, force);
+                return bt_convert__perf2ctf(input_name, to_ctf, &opts);
 #else
                 pr_err("The libbabeltrace support is not compiled in.\n");
                 return -1;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f7645a42708e..21ee753211ad 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -310,16 +310,6 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
         return -1;
 }
 
-static int hists__add_entry(struct hists *hists,
-                            struct addr_location *al,
-                            struct perf_sample *sample)
-{
-        if (__hists__add_entry(hists, al, NULL, NULL, NULL,
-                               sample, true) != NULL)
-                return 0;
-        return -ENOMEM;
-}
-
 static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
                                       union perf_event *event,
                                       struct perf_sample *sample,
@@ -336,7 +326,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
                 return -1;
         }
 
-        if (hists__add_entry(hists, &al, sample)) {
+        if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 goto out_put;
         }
@@ -373,7 +363,7 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
         struct perf_evsel *e;
 
-        evlist__for_each(evlist, e) {
+        evlist__for_each_entry(evlist, e) {
                 if (perf_evsel__match2(evsel, e))
                         return e;
         }
@@ -385,7 +375,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
@@ -666,7 +656,8 @@ static void hists__process(struct hists *hists)
         hists__precompute(hists);
         hists__output_resort(hists, NULL);
 
-        hists__fprintf(hists, true, 0, 0, 0, stdout);
+        hists__fprintf(hists, true, 0, 0, 0, stdout,
+                       symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
@@ -690,7 +681,7 @@ static void data_process(void)
         struct perf_evsel *evsel_base;
         bool first = true;
 
-        evlist__for_each(evlist_base, evsel_base) {
+        evlist__for_each_entry(evlist_base, evsel_base) {
                 struct hists *hists_base = evsel__hists(evsel_base);
                 struct data__file *d;
                 int i;
@@ -765,9 +756,7 @@ static int __cmd_diff(void)
 
  out_delete:
         data__for_each_file(i, d) {
-                if (d->session)
-                        perf_session__delete(d->session);
-
+                perf_session__delete(d->session);
                 data__free(d);
         }
 
@@ -1044,7 +1033,7 @@ static int hpp__entry_global(struct perf_hpp_fmt *_fmt, struct perf_hpp *hpp,
 }
 
 static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                       struct perf_evsel *evsel __maybe_unused)
+                       struct hists *hists __maybe_unused)
 {
         struct diff_hpp_fmt *dfmt =
                 container_of(fmt, struct diff_hpp_fmt, fmt);
@@ -1055,7 +1044,7 @@ static int hpp__header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int hpp__width(struct perf_hpp_fmt *fmt,
                       struct perf_hpp *hpp __maybe_unused,
-                      struct perf_evsel *evsel __maybe_unused)
+                      struct hists *hists __maybe_unused)
 {
         struct diff_hpp_fmt *dfmt =
                 container_of(fmt, struct diff_hpp_fmt, fmt);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 8a31f511e1a0..e09c4287fe87 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -32,7 +32,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
         if (session == NULL)
                 return -1;
 
-        evlist__for_each(session->evlist, pos) {
+        evlist__for_each_entry(session->evlist, pos) {
                 perf_evsel__fprintf(pos, details, stdout);
 
                 if (pos->attr.type == PERF_TYPE_TRACEPOINT)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index f9830c902b78..3bdb2c78a21b 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -4,7 +4,7 @@
  * Builtin help command
  */
 #include "perf.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "builtin.h"
 #include <subcmd/exec-cmd.h>
 #include "common-cmds.h"
@@ -117,7 +117,7 @@ static void exec_woman_emacs(const char *path, const char *page)
                         free(man_page);
                 }
                 warning("failed to exec '%s': %s", path,
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
         }
 }
 
@@ -150,7 +150,7 @@ static void exec_man_konqueror(const char *path, const char *page)
                         free(man_page);
                 }
                 warning("failed to exec '%s': %s", path,
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
         }
 }
 
@@ -162,7 +162,7 @@ static void exec_man_man(const char *path, const char *page)
                 path = "man";
         execlp(path, "man", page, NULL);
         warning("failed to exec '%s': %s", path,
-                strerror_r(errno, sbuf, sizeof(sbuf)));
+                str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
@@ -175,7 +175,7 @@ static void exec_man_cmd(const char *cmd, const char *page)
                 free(shell_cmd);
         }
         warning("failed to exec '%s': %s", cmd,
-                strerror_r(errno, sbuf, sizeof(sbuf)));
+                str_error_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index e5afa8fe1bf1..73c1c4cc3600 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -562,7 +562,7 @@ static void strip_init(struct perf_inject *inject)
 
         inject->tool.context_switch = perf_event__drop;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 evsel->handler = drop_sample;
 }
 
@@ -590,7 +590,7 @@ static bool ok_to_remove(struct perf_evlist *evlist,
         if (!has_tracking(evsel_to_remove))
                 return true;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->handler != drop_sample) {
                         cnt += 1;
                         if ((evsel->attr.sample_type & COMPAT_MASK) ==
@@ -608,7 +608,7 @@ static void strip_fini(struct perf_inject *inject)
         struct perf_evsel *evsel, *tmp;
 
         /* Remove non-synthesized evsels if possible */
-        evlist__for_each_safe(evlist, tmp, evsel) {
+        evlist__for_each_entry_safe(evlist, tmp, evsel) {
                 if (evsel->handler == drop_sample &&
                     ok_to_remove(evlist, evsel)) {
                         pr_debug("Deleting %s\n", perf_evsel__name(evsel));
@@ -643,7 +643,7 @@ static int __cmd_inject(struct perf_inject *inject)
         } else if (inject->sched_stat) {
                 struct perf_evsel *evsel;
 
-                evlist__for_each(session->evlist, evsel) {
+                evlist__for_each_entry(session->evlist, evsel) {
                         const char *name = perf_evsel__name(evsel);
 
                         if (!strcmp(name, "sched:sched_switch")) {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 58adfee230de..fdde1bd3e306 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -4,7 +4,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
@@ -608,6 +608,7 @@ static const struct {
         const char *compact;
 } gfp_compact_table[] = {
         { "GFP_TRANSHUGE",              "THP" },
+        { "GFP_TRANSHUGE_LIGHT",        "THL" },
         { "GFP_HIGHUSER_MOVABLE",       "HUM" },
         { "GFP_HIGHUSER",               "HU" },
         { "GFP_USER",                   "U" },
@@ -1354,7 +1355,7 @@ static int __cmd_kmem(struct perf_session *session)
                 goto out;
         }
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (!strcmp(perf_evsel__name(evsel), "kmem:mm_page_alloc") &&
                     perf_evsel__field(evsel, "pfn")) {
                         use_pfn = true;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 6487c06d2708..5e2127e04f83 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -988,7 +988,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
          * Note: exclude_{guest,host} do not apply here.
          *       This command processes KVM tracepoints from host only
          */
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 struct perf_event_attr *attr = &pos->attr;
 
                 /* make sure these *are* set */
@@ -1018,13 +1018,13 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 printf("Couldn't create the events: %s\n",
-                       strerror_r(errno, sbuf, sizeof(sbuf)));
+                       str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
 
         if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
                 ui__error("Failed to mmap the events: %s\n",
-                          strerror_r(errno, sbuf, sizeof(sbuf)));
+                          str_error_r(errno, sbuf, sizeof(sbuf)));
                 perf_evlist__close(evlist);
                 goto out;
         }
@@ -1426,11 +1426,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         err = kvm_events_live_report(kvm);
 
 out:
-        if (kvm->session)
-                perf_session__delete(kvm->session);
+        perf_session__delete(kvm->session);
         kvm->session = NULL;
-        if (kvm->evlist)
-                perf_evlist__delete(kvm->evlist);
+        perf_evlist__delete(kvm->evlist);
 
         return err;
 }
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 5e22db4684b8..88ee419e5189 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -25,7 +25,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                 OPT_END()
         };
         const char * const list_usage[] = {
-                "perf list [hw|sw|cache|tracepoint|pmu|event_glob]",
+                "perf list [hw|sw|cache|tracepoint|pmu|sdt|event_glob]",
                 NULL
         };
 
@@ -62,6 +62,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                         print_hwcache_events(NULL, raw_dump);
                 else if (strcmp(argv[i], "pmu") == 0)
                         print_pmu_events(NULL, raw_dump);
+                else if (strcmp(argv[i], "sdt") == 0)
+                        print_sdt_events(NULL, NULL, raw_dump);
                 else if ((sep = strchr(argv[i], ':')) != NULL) {
                         int sep_idx;
 
@@ -76,6 +78,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 
                         s[sep_idx] = '\0';
                         print_tracepoint_events(s, s + sep_idx + 1, raw_dump);
+                        print_sdt_events(s, s + sep_idx + 1, raw_dump);
                         free(s);
                 } else {
                         if (asprintf(&s, "*%s*", argv[i]) < 0) {
@@ -89,6 +92,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                         print_hwcache_events(s, raw_dump);
                         print_pmu_events(s, raw_dump);
                         print_tracepoint_events(NULL, s, raw_dump);
+                        print_sdt_events(NULL, s, raw_dump);
                         free(s);
                 }
         }
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 1dc140c5481d..d608a2c9e48c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -67,6 +67,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
         OPT_CALLBACK('e', "event", &mem, "event",
                      "event selector. use 'perf mem record -e list' to list available events",
                      parse_record_events),
+        OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
         OPT_INCR('v', "verbose", &verbose,
                  "be more verbose (show counter open errors, etc)"),
         OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 9af859b28b15..ee5b42173ba3 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,7 +44,7 @@
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
 #define DEFAULT_FUNC_FILTER "!_*"
-#define DEFAULT_LIST_FILTER "*:*"
+#define DEFAULT_LIST_FILTER "*"
 
 /* Session management structure */
 static struct {
@@ -308,7 +308,7 @@ static void pr_err_with_code(const char *msg, int err)
 
         pr_err("%s", msg);
         pr_debug(" Reason: %s (Code: %d)",
-                 strerror_r(-err, sbuf, sizeof(sbuf)), err);
+                 str_error_r(-err, sbuf, sizeof(sbuf)), err);
         pr_err("\n");
 }
 
@@ -363,6 +363,32 @@ out_cleanup:
         return ret;
 }
 
+static int del_perf_probe_caches(struct strfilter *filter)
+{
+        struct probe_cache *cache;
+        struct strlist *bidlist;
+        struct str_node *nd;
+        int ret;
+
+        bidlist = build_id_cache__list_all(false);
+        if (!bidlist) {
+                ret = -errno;
+                pr_debug("Failed to get buildids: %d\n", ret);
+                return ret ?: -ENOMEM;
+        }
+
+        strlist__for_each_entry(nd, bidlist) {
+                cache = probe_cache__new(nd->s);
+                if (!cache)
+                        continue;
+                if (probe_cache__filter_purge(cache, filter) < 0 ||
+                    probe_cache__commit(cache) < 0)
+                        pr_warning("Failed to remove entries for %s\n", nd->s);
+                probe_cache__delete(cache);
+        }
+        return 0;
+}
+
 static int perf_del_probe_events(struct strfilter *filter)
 {
         int ret, ret2, ufd = -1, kfd = -1;
@@ -375,6 +401,9 @@ static int perf_del_probe_events(struct strfilter *filter)
 
         pr_debug("Delete filter: \'%s\'\n", str);
 
+        if (probe_conf.cache)
+                return del_perf_probe_caches(filter);
+
         /* Get current event names */
         ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
         if (ret < 0)
@@ -389,7 +418,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
         ret = probe_file__get_events(kfd, filter, klist);
         if (ret == 0) {
-                strlist__for_each(ent, klist)
+                strlist__for_each_entry(ent, klist)
                         pr_info("Removed event: %s\n", ent->s);
 
                 ret = probe_file__del_strlist(kfd, klist);
@@ -399,7 +428,7 @@ static int perf_del_probe_events(struct strfilter *filter)
 
         ret2 = probe_file__get_events(ufd, filter, ulist);
         if (ret2 == 0) {
-                strlist__for_each(ent, ulist)
+                strlist__for_each_entry(ent, ulist)
                         pr_info("Removed event: %s\n", ent->s);
 
                 ret2 = probe_file__del_strlist(ufd, ulist);
@@ -512,6 +541,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Enable symbol demangling"),
         OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
                     "Enable kernel symbol demangling"),
+        OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
         OPT_END()
         };
         int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc3fcb597e4c..6355902fbfc8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -13,6 +13,7 @@
 #include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
+#include "util/config.h"
 
 #include "util/callchain.h"
 #include "util/cgroup.h"
@@ -118,11 +119,10 @@ backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
 }
 
 static int
-rb_find_range(struct perf_evlist *evlist,
-              void *data, int mask, u64 head, u64 old,
-              u64 *start, u64 *end)
+rb_find_range(void *data, int mask, u64 head, u64 old,
+              u64 *start, u64 *end, bool backward)
 {
-        if (!evlist->backward) {
+        if (!backward) {
                 *start = old;
                 *end = head;
                 return 0;
@@ -131,9 +131,10 @@ rb_find_range(struct perf_evlist *evlist,
         return backward_rb_find_range(data, mask, head, start, end);
 }
 
-static int record__mmap_read(struct record *rec, int idx)
+static int
+record__mmap_read(struct record *rec, struct perf_mmap *md,
+                  bool overwrite, bool backward)
 {
-        struct perf_mmap *md = &rec->evlist->mmap[idx];
         u64 head = perf_mmap__read_head(md);
         u64 old = md->prev;
         u64 end = head, start = old;
@@ -142,8 +143,8 @@ static int record__mmap_read(struct record *rec, int idx)
         void *buf;
         int rc = 0;
 
-        if (rb_find_range(rec->evlist, data, md->mask, head,
-                          old, &start, &end))
+        if (rb_find_range(data, md->mask, head,
+                          old, &start, &end, backward))
                 return -1;
 
         if (start == end)
@@ -156,7 +157,7 @@ static int record__mmap_read(struct record *rec, int idx)
                 WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
                 md->prev = head;
-                perf_evlist__mmap_consume(rec->evlist, idx);
+                perf_mmap__consume(md, overwrite || backward);
                 return 0;
         }
 
@@ -181,7 +182,7 @@ static int record__mmap_read(struct record *rec, int idx)
         }
 
         md->prev = head;
-        perf_evlist__mmap_consume(rec->evlist, idx);
+        perf_mmap__consume(md, overwrite || backward);
 out:
         return rc;
 }
@@ -341,6 +342,40 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
 
 #endif
 
+static int record__mmap_evlist(struct record *rec,
+                               struct perf_evlist *evlist)
+{
+        struct record_opts *opts = &rec->opts;
+        char msg[512];
+
+        if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+                                 opts->auxtrace_mmap_pages,
+                                 opts->auxtrace_snapshot_mode) < 0) {
+                if (errno == EPERM) {
+                        pr_err("Permission error mapping pages.\n"
+                               "Consider increasing "
+                               "/proc/sys/kernel/perf_event_mlock_kb,\n"
+                               "or try again with a smaller value of -m/--mmap_pages.\n"
+                               "(current value: %u,%u)\n",
+                               opts->mmap_pages, opts->auxtrace_mmap_pages);
+                        return -errno;
+                } else {
+                        pr_err("failed to mmap with %d (%s)\n", errno,
+                                str_error_r(errno, msg, sizeof(msg)));
+                        if (errno)
+                                return -errno;
+                        else
+                                return -EINVAL;
+                }
+        }
+        return 0;
+}
+
+static int record__mmap(struct record *rec)
+{
+        return record__mmap_evlist(rec, rec->evlist);
+}
+
 static int record__open(struct record *rec)
 {
         char msg[512];
@@ -352,7 +387,7 @@ static int record__open(struct record *rec)
 
         perf_evlist__config(evlist, opts, &callchain_param);
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
 try_again:
                 if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
                         if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
@@ -372,32 +407,14 @@ try_again:
         if (perf_evlist__apply_filters(evlist, &pos)) {
                 error("failed to set filter \"%s\" on event %s with %d (%s)\n",
                         pos->filter, perf_evsel__name(pos), errno,
-                        strerror_r(errno, msg, sizeof(msg)));
+                        str_error_r(errno, msg, sizeof(msg)));
                 rc = -1;
                 goto out;
         }
 
-        if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
-                                 opts->auxtrace_mmap_pages,
-                                 opts->auxtrace_snapshot_mode) < 0) {
-                if (errno == EPERM) {
-                        pr_err("Permission error mapping pages.\n"
-                               "Consider increasing "
-                               "/proc/sys/kernel/perf_event_mlock_kb,\n"
-                               "or try again with a smaller value of -m/--mmap_pages.\n"
-                               "(current value: %u,%u)\n",
-                               opts->mmap_pages, opts->auxtrace_mmap_pages);
-                        rc = -errno;
-                } else {
-                        pr_err("failed to mmap with %d (%s)\n", errno,
-                                strerror_r(errno, msg, sizeof(msg)));
-                        if (errno)
-                                rc = -errno;
-                        else
-                                rc = -EINVAL;
-                }
+        rc = record__mmap(rec);
+        if (rc)
                 goto out;
-        }
 
         session->evlist = evlist;
         perf_session__set_id_hdr_size(session);
@@ -481,17 +498,30 @@ static struct perf_event_header finished_round_event = {
         .type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
+                                    bool backward)
 {
         u64 bytes_written = rec->bytes_written;
         int i;
         int rc = 0;
+        struct perf_mmap *maps;
 
-        for (i = 0; i < rec->evlist->nr_mmaps; i++) {
-                struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+        if (!evlist)
+                return 0;
 
-                if (rec->evlist->mmap[i].base) {
-                        if (record__mmap_read(rec, i) != 0) {
+        maps = backward ? evlist->backward_mmap : evlist->mmap;
+        if (!maps)
+                return 0;
+
+        if (backward && evlist->bkw_mmap_state != BKW_MMAP_DATA_PENDING)
+                return 0;
+
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
+
+                if (maps[i].base) {
+                        if (record__mmap_read(rec, &maps[i],
+                                              evlist->overwrite, backward) != 0) {
                                 rc = -1;
                                 goto out;
                         }
@@ -511,10 +541,23 @@ static int record__mmap_read_all(struct record *rec)
         if (bytes_written != rec->bytes_written)
                 rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
+        if (backward)
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
         return rc;
 }
 
+static int record__mmap_read_all(struct record *rec)
+{
+        int err;
+
+        err = record__mmap_read_evlist(rec, rec->evlist, false);
+        if (err)
+                return err;
+
+        return record__mmap_read_evlist(rec, rec->evlist, true);
+}
+
 static void record__init_features(struct record *rec)
 {
         struct perf_session *session = rec->session;
@@ -561,13 +604,16 @@ record__finish_output(struct record *rec)
         return;
 }
 
-static int record__synthesize_workload(struct record *rec)
+static int record__synthesize_workload(struct record *rec, bool tail)
 {
         struct {
                 struct thread_map map;
                 struct thread_map_data map_data;
         } thread_map;
 
+        if (rec->opts.tail_synthesize != tail)
+                return 0;
+
         thread_map.map.nr = 1;
         thread_map.map.map[0].pid = rec->evlist->workload.pid;
         thread_map.map.map[0].comm = NULL;
@@ -578,7 +624,7 @@ static int record__synthesize_workload(struct record *rec)
                                                  rec->opts.proc_map_timeout);
 }
 
-static int record__synthesize(struct record *rec);
+static int record__synthesize(struct record *rec, bool tail);
 
 static int
 record__switch_output(struct record *rec, bool at_exit)
@@ -589,6 +635,10 @@ record__switch_output(struct record *rec, bool at_exit)
         /* Same Size:      "2015122520103046"*/
         char timestamp[] = "InvalidTimestamp";
 
+        record__synthesize(rec, true);
+        if (target__none(&rec->opts.target))
+                record__synthesize_workload(rec, true);
+
         rec->samples = 0;
         record__finish_output(rec);
         err = fetch_current_timestamp(timestamp, sizeof(timestamp));
@@ -611,7 +661,7 @@ record__switch_output(struct record *rec, bool at_exit)
 
         /* Output tracking events */
         if (!at_exit) {
-                record__synthesize(rec);
+                record__synthesize(rec, false);
 
                 /*
                  * In 'perf record --switch-output' without -a,
@@ -623,7 +673,7 @@ record__switch_output(struct record *rec, bool at_exit)
                  * perf_event__synthesize_thread_map() for those events.
                  */
                 if (target__none(&rec->opts.target))
-                        record__synthesize_workload(rec);
+                        record__synthesize_workload(rec, false);
         }
         return fd;
 }
@@ -655,7 +705,29 @@ perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused
         return 0;
 }
 
-static int record__synthesize(struct record *rec)
+static const struct perf_event_mmap_page *
+perf_evlist__pick_pc(struct perf_evlist *evlist)
+{
+        if (evlist) {
+                if (evlist->mmap && evlist->mmap[0].base)
+                        return evlist->mmap[0].base;
+                if (evlist->backward_mmap && evlist->backward_mmap[0].base)
+                        return evlist->backward_mmap[0].base;
+        }
+        return NULL;
+}
+
+static const struct perf_event_mmap_page *record__pick_pc(struct record *rec)
+{
+        const struct perf_event_mmap_page *pc;
+
+        pc = perf_evlist__pick_pc(rec->evlist);
+        if (pc)
+                return pc;
+        return NULL;
+}
+
+static int record__synthesize(struct record *rec, bool tail)
 {
         struct perf_session *session = rec->session;
         struct machine *machine = &session->machines.host;
@@ -665,6 +737,9 @@ static int record__synthesize(struct record *rec)
         int fd = perf_data_file__fd(file);
         int err = 0;
 
+        if (rec->opts.tail_synthesize != tail)
+                return 0;
+
         if (file->is_pipe) {
                 err = perf_event__synthesize_attrs(tool, session,
                                                    process_synthesized_event);
@@ -692,7 +767,7 @@ static int record__synthesize(struct record *rec)
                 }
         }
 
-        err = perf_event__synth_time_conv(rec->evlist->mmap[0].base, tool,
+        err = perf_event__synth_time_conv(record__pick_pc(rec), tool,
                                           process_synthesized_event, machine);
         if (err)
                 goto out;
@@ -828,7 +903,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
         machine = &session->machines.host;
 
-        err = record__synthesize(rec);
+        err = record__synthesize(rec, false);
         if (err < 0)
                 goto out_child;
 
@@ -888,6 +963,17 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         for (;;) {
                 unsigned long long hits = rec->samples;
 
+                /*
+                 * rec->evlist->bkw_mmap_state is possible to be
+                 * BKW_MMAP_EMPTY here: when done == true and
+                 * hits != rec->samples in previous round.
+                 *
+                 * perf_evlist__toggle_bkw_mmap ensure we never
+                 * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING.
+                 */
+                if (trigger_is_hit(&switch_output_trigger) || done || draining)
+                        perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
+
                 if (record__mmap_read_all(rec) < 0) {
                         trigger_error(&auxtrace_snapshot_trigger);
                         trigger_error(&switch_output_trigger);
@@ -907,8 +993,26 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 }
 
                 if (trigger_is_hit(&switch_output_trigger)) {
+                        /*
+                         * If switch_output_trigger is hit, the data in
+                         * overwritable ring buffer should have been collected,
+                         * so bkw_mmap_state should be set to BKW_MMAP_EMPTY.
+                         *
+                         * If SIGUSR2 raise after or during record__mmap_read_all(),
+                         * record__mmap_read_all() didn't collect data from
+                         * overwritable ring buffer. Read again.
+                         */
+                        if (rec->evlist->bkw_mmap_state == BKW_MMAP_RUNNING)
+                                continue;
                         trigger_ready(&switch_output_trigger);
 
+                        /*
+                         * Reenable events in overwrite ring buffer after
+                         * record__mmap_read_all(): we should have collected
+                         * data from it.
+                         */
+                        perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING);
+
                         if (!quiet)
                                 fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
                                         waking);
@@ -954,7 +1058,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
         if (forks && workload_exec_errno) {
                 char msg[STRERR_BUFSIZE];
-                const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
                 pr_err("Workload failed: %s\n", emsg);
                 err = -1;
                 goto out_child;
@@ -963,6 +1067,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         if (!quiet)
                 fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
+        if (target__none(&rec->opts.target))
+                record__synthesize_workload(rec, true);
+
 out_child:
         if (forks) {
                 int exit_status;
@@ -981,6 +1088,7 @@ out_child:
         } else
                 status = err;
 
+        record__synthesize(rec, true);
         /* this will be recalculated during process_buildids() */
         rec->samples = 0;
 
@@ -1267,6 +1375,8 @@ static struct record record = {
 const char record_callchain_help[] = CALLCHAIN_RECORD_HELP
         "\n\t\t\t\tDefault: fp";
 
+static bool dry_run;
+
 /*
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
@@ -1303,6 +1413,9 @@ struct option __record_options[] = {
         OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
                         &record.opts.no_inherit_set,
                         "child tasks do not inherit counters"),
+        OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
+                    "synthesize non-sample events at the end of output"),
+        OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
         OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
         OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
                      "number of mmap data pages and AUX area tracing mmap pages",
@@ -1321,6 +1434,7 @@ struct option __record_options[] = {
         OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
                     "per thread counts"),
         OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+        OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
         OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
                         &record.opts.sample_time_set,
                         "Record the sample timestamps"),
@@ -1386,6 +1500,8 @@ struct option __record_options[] = {
                     "append timestamp to output filename"),
         OPT_BOOLEAN(0, "switch-output", &record.switch_output,
                     "Switch output when receive SIGUSR2"),
+        OPT_BOOLEAN(0, "dry-run", &dry_run,
+                    "Parse options then exit"),
         OPT_END()
 };
 
@@ -1455,6 +1571,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (err)
                 return err;
 
+        if (dry_run)
+                return 0;
+
         err = bpf__setup_stdout(rec->evlist);
         if (err) {
                 bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
@@ -1508,6 +1627,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
                 }
         }
 
+        if (record.opts.overwrite)
+                record.opts.tail_synthesize = true;
+
         if (rec->evlist->nr_entries == 0 &&
             perf_evlist__add_default(rec->evlist) < 0) {
                 pr_err("Not enough memory for event selector list\n");
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a87cb338bdf1..949e5a15c960 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,7 +8,7 @@
 #include "builtin.h"
 
 #include "util/util.h"
-#include "util/cache.h"
+#include "util/config.h"
 
 #include "util/annotate.h"
 #include "util/color.h"
@@ -361,7 +361,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
         struct perf_evsel *pos;
 
         fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
                 const char *evname = perf_evsel__name(pos);
 
@@ -370,7 +370,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                         continue;
 
                 hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
-                hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
+                hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout,
+                               symbol_conf.use_callchain);
                 fprintf(stdout, "\n\n");
         }
 
@@ -477,7 +478,7 @@ static int report__collapse_hists(struct report *rep)
 
         ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
-        evlist__for_each(rep->session->evlist, pos) {
+        evlist__for_each_entry(rep->session->evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
 
                 if (pos->idx == 0)
@@ -510,7 +511,7 @@ static void report__output_resort(struct report *rep)
 
         ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
-        evlist__for_each(rep->session->evlist, pos)
+        evlist__for_each_entry(rep->session->evlist, pos)
                 perf_evsel__output_resort(pos, &prog);
 
         ui_progress__finish();
@@ -551,7 +552,7 @@ static int __cmd_report(struct report *rep)
 
         report__warn_kptr_restrict(rep);
 
-        evlist__for_each(session->evlist, pos)
+        evlist__for_each_entry(session->evlist, pos)
                 rep->nr_entries += evsel__hists(pos)->nr_entries;
 
         if (use_browser == 0) {
@@ -582,7 +583,7 @@ static int __cmd_report(struct report *rep)
          * might be changed during the collapse phase.
          */
         rep->nr_entries = 0;
-        evlist__for_each(session->evlist, pos)
+        evlist__for_each_entry(session->evlist, pos)
                 rep->nr_entries += evsel__hists(pos)->nr_entries;
 
         if (rep->nr_entries == 0) {
@@ -816,6 +817,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
                     "Show entries in a hierarchy"),
+        OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
+                             "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
+                             stdio__config_color, "always"),
         OPT_END()
         };
         struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index afa057666c2a..0dfe8df2ab9b 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -494,7 +494,7 @@ force_again:
                 }
                 pr_err("Error: sys_perf_event_open() syscall returned "
                        "with %d (%s)\n%s", fd,
-                       strerror_r(errno, sbuf, sizeof(sbuf)), info);
+                       str_error_r(errno, sbuf, sizeof(sbuf)), info);
                 exit(EXIT_FAILURE);
         }
         return fd;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e3ce2f34d3ad..971ff91b16cb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -21,6 +21,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/thread-stack.h"
 #include <linux/bitmap.h>
 #include <linux/stringify.h>
 #include "asm/bug.h"
@@ -63,6 +64,7 @@ enum perf_output_field {
         PERF_OUTPUT_DATA_SRC        = 1U << 17,
         PERF_OUTPUT_WEIGHT          = 1U << 18,
         PERF_OUTPUT_BPF_OUTPUT      = 1U << 19,
+        PERF_OUTPUT_CALLINDENT      = 1U << 20,
 };
 
 struct output_option {
@@ -89,6 +91,7 @@ struct output_option {
         {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
         {.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
         {.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
+        {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -339,7 +342,7 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
  */
 static int perf_session__check_output_opt(struct perf_session *session)
 {
-        int j;
+        unsigned int j;
         struct perf_evsel *evsel;
 
         for (j = 0; j < PERF_TYPE_MAX; ++j) {
@@ -369,7 +372,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
         if (!no_callchain) {
                 bool use_callchain = false;
 
-                evlist__for_each(session->evlist, evsel) {
+                evlist__for_each_entry(session->evlist, evsel) {
                         if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
                                 use_callchain = true;
                                 break;
@@ -388,17 +391,20 @@ static int perf_session__check_output_opt(struct perf_session *session)
                 struct perf_event_attr *attr;
 
                 j = PERF_TYPE_TRACEPOINT;
-                evsel = perf_session__find_first_evtype(session, j);
-                if (evsel == NULL)
-                        goto out;
 
-                attr = &evsel->attr;
+                evlist__for_each_entry(session->evlist, evsel) {
+                        if (evsel->attr.type != j)
+                                continue;
+
+                        attr = &evsel->attr;
 
-                if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
-                        output[j].fields |= PERF_OUTPUT_IP;
-                        output[j].fields |= PERF_OUTPUT_SYM;
-                        output[j].fields |= PERF_OUTPUT_DSO;
-                        set_print_ip_opts(attr);
+                        if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+                                output[j].fields |= PERF_OUTPUT_IP;
+                                output[j].fields |= PERF_OUTPUT_SYM;
+                                output[j].fields |= PERF_OUTPUT_DSO;
+                                set_print_ip_opts(attr);
+                                goto out;
+                        }
                 }
         }
 
@@ -559,6 +565,62 @@ static void print_sample_addr(struct perf_sample *sample,
         }
 }
 
+static void print_sample_callindent(struct perf_sample *sample,
+                                    struct perf_evsel *evsel,
+                                    struct thread *thread,
+                                    struct addr_location *al)
+{
+        struct perf_event_attr *attr = &evsel->attr;
+        size_t depth = thread_stack__depth(thread);
+        struct addr_location addr_al;
+        const char *name = NULL;
+        static int spacing;
+        int len = 0;
+        u64 ip = 0;
+
+        /*
+         * The 'return' has already been popped off the stack so the depth has
+         * to be adjusted to match the 'call'.
+         */
+        if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
+                depth += 1;
+
+        if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+                if (sample_addr_correlates_sym(attr)) {
+                        thread__resolve(thread, &addr_al, sample);
+                        if (addr_al.sym)
+                                name = addr_al.sym->name;
+                        else
+                                ip = sample->addr;
+                } else {
+                        ip = sample->addr;
+                }
+        } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+                if (al->sym)
+                        name = al->sym->name;
+                else
+                        ip = sample->ip;
+        }
+
+        if (name)
+                len = printf("%*s%s", (int)depth * 4, "", name);
+        else if (ip)
+                len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+
+        if (len < 0)
+                return;
+
+        /*
+         * Try to keep the output length from changing frequently so that the
+         * output lines up more nicely.
+         */
+        if (len > spacing || (len && len < spacing - 52))
+                spacing = round_up(len + 4, 32);
+
+        if (len < spacing)
+                printf("%*s", spacing - len, "");
+}
+
 static void print_sample_bts(struct perf_sample *sample,
                              struct perf_evsel *evsel,
                              struct thread *thread,
@@ -567,6 +629,9 @@ static void print_sample_bts(struct perf_sample *sample,
         struct perf_event_attr *attr = &evsel->attr;
         bool print_srcline_last = false;
 
+        if (PRINT_FIELD(CALLINDENT))
+                print_sample_callindent(sample, evsel, thread, al);
+
         /* print branch_from information */
         if (PRINT_FIELD(IP)) {
                 unsigned int print_opts = output[attr->type].print_ip_opts;
@@ -603,13 +668,42 @@ static void print_sample_bts(struct perf_sample *sample,
         printf("\n");
 }
 
+static struct {
+        u32 flags;
+        const char *name;
+} sample_flags[] = {
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "jcc"},
+        {PERF_IP_FLAG_BRANCH, "jmp"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT, "int"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT, "iret"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET, "syscall"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET, "sysret"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "async"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_INTERRUPT, "hw int"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "tx abrt"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "tr strt"},
+        {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "tr end"},
+        {0, NULL}
+};
+
 static void print_sample_flags(u32 flags)
 {
         const char *chars = PERF_IP_FLAG_CHARS;
         const int n = strlen(PERF_IP_FLAG_CHARS);
+        bool in_tx = flags & PERF_IP_FLAG_IN_TX;
+        const char *name = NULL;
         char str[33];
         int i, pos = 0;
 
+        for (i = 0; sample_flags[i].name ; i++) {
+                if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
+                        name = sample_flags[i].name;
+                        break;
+                }
+        }
+
         for (i = 0; i < n; i++, flags >>= 1) {
                 if (flags & 1)
                         str[pos++] = chars[i];
@@ -619,7 +713,11 @@ static void print_sample_flags(u32 flags)
                         str[pos++] = '?';
         }
         str[pos] = 0;
-        printf("  %-4s ", str);
+
+        if (name)
+                printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
+        else
+                printf("  %-11s ", str);
 }
 
 struct printer_data {
@@ -717,7 +815,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
         struct perf_evsel *evsel;
         int max = 0;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 int len = strlen(perf_evsel__name(evsel));
 
                 max = MAX(len, max);
@@ -942,7 +1040,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
         if (evsel->attr.type >= PERF_TYPE_MAX)
                 return 0;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (pos->attr.type == evsel->attr.type && pos != evsel)
                         return 0;
         }
@@ -1668,7 +1766,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
                         snprintf(evname, len + 1, "%s", p);
 
                         match = 0;
-                        evlist__for_each(session->evlist, pos) {
+                        evlist__for_each_entry(session->evlist, pos) {
                                 if (!strcmp(perf_evsel__name(pos), evname)) {
                                         match = 1;
                                         break;
@@ -1870,7 +1968,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         struct stat_round_event *round = &event->stat_round;
         struct perf_evsel *counter;
 
-        evlist__for_each(session->evlist, counter) {
+        evlist__for_each_entry(session->evlist, counter) {
                 perf_stat_process_counter(&stat_config, counter);
                 process_stat(counter, round->time);
         }
@@ -2017,7 +2115,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                      "comma separated output fields prepend with 'type:'. "
                      "Valid types: hw,sw,trace,raw. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-                     "addr,symoff,period,iregs,brstack,brstacksym,flags", parse_output_fields),
+                     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
+                     "callindent", parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
         OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -2256,6 +2355,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         script.session = session;
         script__setup_sample_type(&script);
 
+        if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+                itrace_synth_opts.thread_stack = true;
+
         session->itrace_synth_opts = &itrace_synth_opts;
 
         if (cpu_list) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee7ada78d86f..0c16d20d7e32 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -59,10 +59,13 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 #include "util/counts.h"
+#include "util/group.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/group.h"
 #include "asm/bug.h"
 
+#include <api/fs/fs.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
@@ -98,6 +101,15 @@ static const char * transaction_limited_attrs = {
         "}"
 };
 
+static const char * topdown_attrs[] = {
+        "topdown-total-slots",
+        "topdown-slots-retired",
+        "topdown-recovery-bubbles",
+        "topdown-fetch-bubbles",
+        "topdown-slots-issued",
+        NULL,
+};
+
 static struct perf_evlist       *evsel_list;
 
 static struct target target = {
@@ -112,6 +124,7 @@ static volatile pid_t		child_pid			= -1;
 static bool                     null_run                        =  false;
 static int                      detailed_run                    =  0;
 static bool                     transaction_run;
+static bool                     topdown_run                     = false;
 static bool                     big_num                         =  true;
 static int                      big_num_opt                     =  -1;
 static const char               *csv_sep                        = NULL;
@@ -124,6 +137,7 @@ static unsigned int		initial_delay			= 0;
 static unsigned int             unit_width                      = 4; /* strlen("unit") */
 static bool                     forever                         = false;
 static bool                     metric_only                     = false;
+static bool                     force_metric_only               = false;
 static struct timespec          ref_time;
 static struct cpu_map           *aggr_map;
 static aggr_get_id_t            aggr_get_id;
@@ -276,8 +290,12 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 static int read_counter(struct perf_evsel *counter)
 {
         int nthreads = thread_map__nr(evsel_list->threads);
-        int ncpus = perf_evsel__nr_cpus(counter);
-        int cpu, thread;
+        int ncpus, cpu, thread;
+
+        if (target__has_cpu(&target))
+                ncpus = perf_evsel__nr_cpus(counter);
+        else
+                ncpus = 1;
 
         if (!counter->supported)
                 return -ENOENT;
@@ -317,7 +335,7 @@ static void read_counters(bool close_counters)
 {
         struct perf_evsel *counter;
 
-        evlist__for_each(evsel_list, counter) {
+        evlist__for_each_entry(evsel_list, counter) {
                 if (read_counter(counter))
                         pr_debug("failed to read counter %s\n", counter->name);
 
@@ -403,7 +421,7 @@ static int perf_stat_synthesize_config(bool is_pipe)
          * Synthesize other events stuff not carried within
          * attr event - unit, scale, name
          */
-        evlist__for_each(evsel_list, counter) {
+        evlist__for_each_entry(evsel_list, counter) {
                 if (!counter->supported)
                         continue;
 
@@ -536,7 +554,7 @@ static int __run_perf_stat(int argc, const char **argv)
         if (group)
                 perf_evlist__set_leader(evsel_list);
 
-        evlist__for_each(evsel_list, counter) {
+        evlist__for_each_entry(evsel_list, counter) {
 try_again:
                 if (create_perf_stat_counter(counter) < 0) {
                         /*
@@ -582,7 +600,7 @@ try_again:
         if (perf_evlist__apply_filters(evsel_list, &counter)) {
                 error("failed to set filter \"%s\" on event %s with %d (%s)\n",
                         counter->filter, perf_evsel__name(counter), errno,
-                        strerror_r(errno, msg, sizeof(msg)));
+                        str_error_r(errno, msg, sizeof(msg)));
                 return -1;
         }
 
@@ -623,7 +641,7 @@ try_again:
                 wait(&status);
 
                 if (workload_exec_errno) {
-                        const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                        const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
                         pr_err("Workload failed: %s\n", emsg);
                         return -1;
                 }
@@ -1120,7 +1138,7 @@ static void aggr_update_shadow(void)
 
         for (s = 0; s < aggr_map->nr; s++) {
                 id = aggr_map->map[s];
-                evlist__for_each(evsel_list, counter) {
+                evlist__for_each_entry(evsel_list, counter) {
                         val = 0;
                         for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
                                 s2 = aggr_get_id(evsel_list->cpus, cpu);
@@ -1159,7 +1177,7 @@ static void print_aggr(char *prefix)
 
                 id = aggr_map->map[s];
                 first = true;
-                evlist__for_each(evsel_list, counter) {
+                evlist__for_each_entry(evsel_list, counter) {
                         val = ena = run = 0;
                         nr = 0;
                         for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1278,7 +1296,7 @@ static void print_no_aggr_metric(char *prefix)
 
                 if (prefix)
                         fputs(prefix, stat_config.output);
-                evlist__for_each(evsel_list, counter) {
+                evlist__for_each_entry(evsel_list, counter) {
                         if (first) {
                                 aggr_printout(counter, cpu, 0);
                                 first = false;
@@ -1302,7 +1320,15 @@ static int aggr_header_lens[] = {
         [AGGR_GLOBAL] = 0,
 };
 
-static void print_metric_headers(char *prefix)
+static const char *aggr_header_csv[] = {
+        [AGGR_CORE]     =       "core,cpus,",
+        [AGGR_SOCKET]   =       "socket,cpus",
+        [AGGR_NONE]     =       "cpu,",
+        [AGGR_THREAD]   =       "comm-pid,",
+        [AGGR_GLOBAL]   =       ""
+};
+
+static void print_metric_headers(const char *prefix, bool no_indent)
 {
         struct perf_stat_output_ctx out;
         struct perf_evsel *counter;
@@ -1313,12 +1339,18 @@ static void print_metric_headers(char *prefix)
         if (prefix)
                 fprintf(stat_config.output, "%s", prefix);
 
-        if (!csv_output)
+        if (!csv_output && !no_indent)
                 fprintf(stat_config.output, "%*s",
                         aggr_header_lens[stat_config.aggr_mode], "");
+        if (csv_output) {
+                if (stat_config.interval)
+                        fputs("time,", stat_config.output);
+                fputs(aggr_header_csv[stat_config.aggr_mode],
+                        stat_config.output);
+        }
 
         /* Print metrics headers only */
-        evlist__for_each(evsel_list, counter) {
+        evlist__for_each_entry(evsel_list, counter) {
                 os.evsel = counter;
                 out.ctx = &os;
                 out.print_metric = print_metric_header;
@@ -1338,28 +1370,40 @@ static void print_interval(char *prefix, struct timespec *ts)
 
         sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-        if (num_print_interval == 0 && !csv_output && !metric_only) {
+        if (num_print_interval == 0 && !csv_output) {
                 switch (stat_config.aggr_mode) {
                 case AGGR_SOCKET:
-                        fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+                        fprintf(output, "#           time socket cpus");
+                        if (!metric_only)
+                                fprintf(output, "             counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_CORE:
-                        fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+                        fprintf(output, "#           time core         cpus");
+                        if (!metric_only)
+                                fprintf(output, "             counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_NONE:
-                        fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+                        fprintf(output, "#           time CPU");
+                        if (!metric_only)
+                                fprintf(output, "                counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_THREAD:
-                        fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+                        fprintf(output, "#           time             comm-pid");
+                        if (!metric_only)
+                                fprintf(output, "                  counts %*s events\n", unit_width, "unit");
                         break;
                 case AGGR_GLOBAL:
                 default:
-                        fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+                        fprintf(output, "#           time");
+                        if (!metric_only)
+                                fprintf(output, "             counts %*s events\n", unit_width, "unit");
                 case AGGR_UNSET:
                         break;
                 }
         }
 
+        if (num_print_interval == 0 && metric_only)
+                print_metric_headers(" ", true);
         if (++num_print_interval == 25)
                 num_print_interval = 0;
 }
@@ -1428,8 +1472,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         if (metric_only) {
                 static int num_print_iv;
 
-                if (num_print_iv == 0)
-                        print_metric_headers(prefix);
+                if (num_print_iv == 0 && !interval)
+                        print_metric_headers(prefix, false);
                 if (num_print_iv++ == 25)
                         num_print_iv = 0;
                 if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
@@ -1442,11 +1486,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 print_aggr(prefix);
                 break;
         case AGGR_THREAD:
-                evlist__for_each(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter)
                         print_aggr_thread(counter, prefix);
                 break;
         case AGGR_GLOBAL:
-                evlist__for_each(evsel_list, counter)
+                evlist__for_each_entry(evsel_list, counter)
                         print_counter_aggr(counter, prefix);
                 if (metric_only)
                         fputc('\n', stat_config.output);
@@ -1455,7 +1499,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
                 if (metric_only)
                         print_no_aggr_metric(prefix);
                 else {
-                        evlist__for_each(evsel_list, counter)
+                        evlist__for_each_entry(evsel_list, counter)
                                 print_counter(counter, prefix);
                 }
                 break;
@@ -1520,6 +1564,14 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
         return 0;
 }
 
+static int enable_metric_only(const struct option *opt __maybe_unused,
+                              const char *s __maybe_unused, int unset)
+{
+        force_metric_only = true;
+        metric_only = !unset;
+        return 0;
+}
+
 static const struct option stat_options[] = {
         OPT_BOOLEAN('T', "transaction", &transaction_run,
                     "hardware transaction statistics"),
@@ -1578,8 +1630,10 @@ static const struct option stat_options[] = {
                      "aggregate counts per thread", AGGR_THREAD),
         OPT_UINTEGER('D', "delay", &initial_delay,
                      "ms to wait before starting measurement after program start"),
-        OPT_BOOLEAN(0, "metric-only", &metric_only,
-                        "Only print computed metrics. No raw values"),
+        OPT_CALLBACK_NOOPT(0, "metric-only", &metric_only, NULL,
+                        "Only print computed metrics. No raw values", enable_metric_only),
+        OPT_BOOLEAN(0, "topdown", &topdown_run,
+                        "measure topdown level 1 statistics"),
         OPT_END()
 };
 
@@ -1772,12 +1826,62 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
         return 0;
 }
 
+static int topdown_filter_events(const char **attr, char **str, bool use_group)
+{
+        int off = 0;
+        int i;
+        int len = 0;
+        char *s;
+
+        for (i = 0; attr[i]; i++) {
+                if (pmu_have_event("cpu", attr[i])) {
+                        len += strlen(attr[i]) + 1;
+                        attr[i - off] = attr[i];
+                } else
+                        off++;
+        }
+        attr[i - off] = NULL;
+
+        *str = malloc(len + 1 + 2);
+        if (!*str)
+                return -1;
+        s = *str;
+        if (i - off == 0) {
+                *s = 0;
+                return 0;
+        }
+        if (use_group)
+                *s++ = '{';
+        for (i = 0; attr[i]; i++) {
+                strcpy(s, attr[i]);
+                s += strlen(s);
+                *s++ = ',';
+        }
+        if (use_group) {
+                s[-1] = '}';
+                *s = 0;
+        } else
+                s[-1] = 0;
+        return 0;
+}
+
+__weak bool arch_topdown_check_group(bool *warn)
+{
+        *warn = false;
+        return false;
+}
+
+__weak void arch_topdown_group_warn(void)
+{
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
  */
 static int add_default_attributes(void)
 {
+        int err;
         struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK              },
@@ -1896,7 +2000,6 @@ static int add_default_attributes(void)
                 return 0;
 
         if (transaction_run) {
-                int err;
                 if (pmu_have_event("cpu", "cycles-ct") &&
                     pmu_have_event("cpu", "el-start"))
                         err = parse_events(evsel_list, transaction_attrs, NULL);
@@ -1909,6 +2012,46 @@ static int add_default_attributes(void)
                 return 0;
         }
 
+        if (topdown_run) {
+                char *str = NULL;
+                bool warn = false;
+
+                if (stat_config.aggr_mode != AGGR_GLOBAL &&
+                    stat_config.aggr_mode != AGGR_CORE) {
+                        pr_err("top down event configuration requires --per-core mode\n");
+                        return -1;
+                }
+                stat_config.aggr_mode = AGGR_CORE;
+                if (nr_cgroups || !target__has_cpu(&target)) {
+                        pr_err("top down event configuration requires system-wide mode (-a)\n");
+                        return -1;
+                }
+
+                if (!force_metric_only)
+                        metric_only = true;
+                if (topdown_filter_events(topdown_attrs, &str,
+                                arch_topdown_check_group(&warn)) < 0) {
+                        pr_err("Out of memory\n");
+                        return -1;
+                }
+                if (topdown_attrs[0] && str) {
+                        if (warn)
+                                arch_topdown_group_warn();
+                        err = parse_events(evsel_list, str, NULL);
+                        if (err) {
+                                fprintf(stderr,
+                                        "Cannot set up top down events %s: %d\n",
+                                        str, err);
+                                free(str);
+                                return -1;
+                        }
+                } else {
+                        fprintf(stderr, "System does not support topdown\n");
+                        return -1;
+                }
+                free(str);
+        }
+
         if (!evsel_list->nr_entries) {
                 if (target__has_cpu(&target))
                         default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
@@ -2010,7 +2153,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         const char **argv = session->header.env.cmdline_argv;
         int argc = session->header.env.nr_cmdline;
 
-        evlist__for_each(evsel_list, counter)
+        evlist__for_each_entry(evsel_list, counter)
                 perf_stat_process_counter(&stat_config, counter);
 
         if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2a6cc254ad0c..418ed94756d3 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -22,7 +22,7 @@
 #include "perf.h"
 
 #include "util/annotate.h"
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/color.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
@@ -128,10 +128,14 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
                 return err;
         }
 
-        err = symbol__annotate(sym, map, 0);
+        err = symbol__disassemble(sym, map, 0);
         if (err == 0) {
 out_assign:
                 top->sym_filter_entry = he;
+        } else {
+                char msg[BUFSIZ];
+                symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+                pr_err("Couldn't annotate %s: %s\n", sym->name, msg);
         }
 
         pthread_mutex_unlock(&notes->lock);
@@ -295,7 +299,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
         hists__fprintf(hists, false, top->print_entries - printed, win_width,
-                       top->min_percent, stdout);
+                       top->min_percent, stdout, symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
@@ -479,7 +483,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
                                 fprintf(stderr, "\nAvailable events:");
 
-                                evlist__for_each(top->evlist, top->sym_evsel)
+                                evlist__for_each_entry(top->evlist, top->sym_evsel)
                                         fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
                                 prompt_integer(&counter, "Enter details event counter");
@@ -490,7 +494,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                                         sleep(1);
                                         break;
                                 }
-                                evlist__for_each(top->evlist, top->sym_evsel)
+                                evlist__for_each_entry(top->evlist, top->sym_evsel)
                                         if (top->sym_evsel->idx == counter)
                                                 break;
                         } else
@@ -583,7 +587,7 @@ static void *display_thread_tui(void *arg)
          * Zooming in/out UIDs. For now juse use whatever the user passed
          * via --uid.
          */
-        evlist__for_each(top->evlist, pos) {
+        evlist__for_each_entry(top->evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
                 hists->uid_filter_str = top->record_opts.target.uid_str;
         }
@@ -888,7 +892,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
         perf_evlist__config(evlist, opts, &callchain_param);
 
-        evlist__for_each(evlist, counter) {
+        evlist__for_each_entry(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
@@ -907,7 +911,7 @@ try_again:
 
         if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
                 ui__error("Failed to mmap with %d (%s)\n",
-                            errno, strerror_r(errno, msg, sizeof(msg)));
+                            errno, str_error_r(errno, msg, sizeof(msg)));
                 goto out_err;
         }
 
@@ -1028,7 +1032,7 @@ out_delete:
 
 out_err_cpu_topo: {
         char errbuf[BUFSIZ];
-        const char *err = strerror_r(-ret, errbuf, sizeof(errbuf));
+        const char *err = str_error_r(-ret, errbuf, sizeof(errbuf));
 
         ui__error("Could not read the CPU topology map: %s\n", err);
         goto out_delete;
@@ -1295,7 +1299,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
         if (perf_evlist__create_maps(top.evlist, target) < 0) {
                 ui__error("Couldn't create thread/CPU maps: %s\n",
-                          errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf)));
+                          errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5c50fe70d6b3..b8c6766301db 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -43,7 +43,6 @@
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
-#include <sys/ptrace.h>
 #include <linux/random.h>
 #include <linux/stringify.h>
 
@@ -334,6 +333,10 @@ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
 
 #define SCA_FD syscall_arg__scnprintf_fd
 
+#ifndef AT_FDCWD
+#define AT_FDCWD        -100
+#endif
+
 static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
                                            struct syscall_arg *arg)
 {
@@ -1247,7 +1250,7 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
         i = 0;
 
-        strlist__for_each(pos, trace->ev_qualifier) {
+        strlist__for_each_entry(pos, trace->ev_qualifier) {
                 const char *sc = pos->s;
                 int id = syscalltbl__id(trace->sctbl, sc);
 
@@ -1601,7 +1604,7 @@ signed_print:
                 fprintf(trace->output, ") = %ld", ret);
         } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
                 char bf[STRERR_BUFSIZE];
-                const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
+                const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
 
                 fprintf(trace->output, ") = -1 %s %s", e, emsg);
@@ -2402,7 +2405,7 @@ out_error_apply_filters:
         fprintf(trace->output,
                 "Failed to set filter \"%s\" on event %s with %d (%s)\n",
                 evsel->filter, perf_evsel__name(evsel), errno,
-                strerror_r(errno, errbuf, sizeof(errbuf)));
+                str_error_r(errno, errbuf, sizeof(errbuf)));
         goto out_delete_evlist;
 }
 out_error_mem:
@@ -2483,7 +2486,7 @@ static int trace__replay(struct trace *trace)
                 goto out;
         }
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
                     (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
                      evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
@@ -2550,7 +2553,7 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
         printed += fprintf(fp, "                               (msec)    (msec)    (msec)    (msec)        (%%)\n");
         printed += fprintf(fp, "   --------------- -------- --------- --------- --------- ---------     ------\n");
 
-        resort_rb__for_each(nd, syscall_stats) {
+        resort_rb__for_each_entry(nd, syscall_stats) {
                 struct stats *stats = syscall_stats_entry->stats;
                 if (stats) {
                         double min = (double)(stats->min) / NSEC_PER_MSEC;
@@ -2627,7 +2630,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
                 return 0;
         }
 
-        resort_rb__for_each(nd, threads)
+        resort_rb__for_each_entry(nd, threads)
                 printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
         resort_rb__delete(threads);
@@ -2714,7 +2717,7 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 evsel->handler = handler;
 }
 
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 3573f315f955..55daefff0d54 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -59,7 +59,6 @@ static int get_e_machine(struct jitheader *hdr)
         ssize_t sret;
         char id[16];
         int fd, ret = -1;
-        int m = -1;
         struct {
                 uint16_t e_type;
                 uint16_t e_machine;
@@ -81,11 +80,7 @@ static int get_e_machine(struct jitheader *hdr)
         if (sret != sizeof(info))
                 goto error;
 
-        m = info.e_machine;
-        if (m < 0)
-                m = 0; /* ELF EM_NONE */
-
-        hdr->elf_mach = m;
+        hdr->elf_mach = info.e_machine;
         ret = 0;
 error:
         close(fd);
@@ -491,10 +486,11 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
                 if (sret != 1)
                         goto error;
         }
-        if (padding_count)
+        if (padding_count) {
                 sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
                 if (sret != 1)
                         goto error;
+        }
 
         funlockfile(fp);
         return 0;
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 83a25cef82fd..7ed72a475c57 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -5,35 +5,18 @@
 #include <sys/types.h>
 #include <sys/syscall.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <asm/barrier.h>
 
 #if defined(__i386__)
 #define cpu_relax()     asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC    {"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 336
-#endif
-#ifndef __NR_futex
-# define __NR_futex 240
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 224
-#endif
 #endif
 
 #if defined(__x86_64__)
 #define cpu_relax()     asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC    {"model name"}
-#ifndef __NR_perf_event_open
-# define __NR_perf_event_open 298
-#endif
-#ifndef __NR_futex
-# define __NR_futex 202
-#endif
-#ifndef __NR_gettid
-# define __NR_gettid 186
-#endif
 #endif
 
 #ifdef __powerpc__
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 15982cee5ef3..64c06961bfe4 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -10,7 +10,7 @@
 
 #include "util/env.h"
 #include <subcmd/exec-cmd.h>
-#include "util/cache.h"
+#include "util/config.h"
 #include "util/quote.h"
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
@@ -139,8 +139,6 @@ struct option options[] = {
         OPT_ARGUMENT("html-path", "html-path"),
         OPT_ARGUMENT("paginate", "paginate"),
         OPT_ARGUMENT("no-pager", "no-pager"),
-        OPT_ARGUMENT("perf-dir", "perf-dir"),
-        OPT_ARGUMENT("work-tree", "work-tree"),
         OPT_ARGUMENT("debugfs-dir", "debugfs-dir"),
         OPT_ARGUMENT("buildid-dir", "buildid-dir"),
         OPT_ARGUMENT("list-cmds", "list-cmds"),
@@ -200,35 +198,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                         use_pager = 0;
                         if (envchanged)
                                 *envchanged = 1;
-                } else if (!strcmp(cmd, "--perf-dir")) {
-                        if (*argc < 2) {
-                                fprintf(stderr, "No directory given for --perf-dir.\n");
-                                usage(perf_usage_string);
-                        }
-                        setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1);
-                        if (envchanged)
-                                *envchanged = 1;
-                        (*argv)++;
-                        (*argc)--;
-                        handled++;
-                } else if (!prefixcmp(cmd, CMD_PERF_DIR)) {
-                        setenv(PERF_DIR_ENVIRONMENT, cmd + strlen(CMD_PERF_DIR), 1);
-                        if (envchanged)
-                                *envchanged = 1;
-                } else if (!strcmp(cmd, "--work-tree")) {
-                        if (*argc < 2) {
-                                fprintf(stderr, "No directory given for --work-tree.\n");
-                                usage(perf_usage_string);
-                        }
-                        setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1);
-                        if (envchanged)
-                                *envchanged = 1;
-                        (*argv)++;
-                        (*argc)--;
-                } else if (!prefixcmp(cmd, CMD_WORK_TREE)) {
-                        setenv(PERF_WORK_TREE_ENVIRONMENT, cmd + strlen(CMD_WORK_TREE), 1);
-                        if (envchanged)
-                                *envchanged = 1;
                 } else if (!strcmp(cmd, "--debugfs-dir")) {
                         if (*argc < 2) {
                                 fprintf(stderr, "No directory given for --debugfs-dir.\n");
@@ -363,11 +332,6 @@ const char perf_version_string[] = PERF_VERSION;
 
 #define RUN_SETUP       (1<<0)
 #define USE_PAGER       (1<<1)
-/*
- * require working tree to be present -- anything uses this needs
- * RUN_SETUP for reading from the configuration file.
- */
-#define NEED_WORK_TREE  (1<<2)
 
 static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
@@ -391,6 +355,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 
         perf_env__set_cmdline(&perf_env, argc, argv);
         status = p->fn(argc, argv, prefix);
+        perf_config__exit();
         exit_browser(status);
         perf_env__exit(&perf_env);
         bpf__clear();
@@ -409,7 +374,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
         /* Check for ENOSPC and EIO errors.. */
         if (fflush(stdout)) {
                 fprintf(stderr, "write failure on standard output: %s",
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
         if (ferror(stdout)) {
@@ -418,7 +383,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
         }
         if (fclose(stdout)) {
                 fprintf(stderr, "close failed on standard output: %s",
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out;
         }
         status = 0;
@@ -532,6 +497,16 @@ void pthread__unblock_sigwinch(void)
         pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+        if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+                pr_debug("cannot determine cache line size");
+}
+#endif
+
 int main(int argc, const char **argv)
 {
         const char *cmd;
@@ -544,7 +519,7 @@ int main(int argc, const char **argv)
 
         /* The page_size is placed in util object. */
         page_size = sysconf(_SC_PAGE_SIZE);
-        cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+        cache_line_size(&cacheline_size);
 
         if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
                 sysctl_perf_event_max_stack = value;
@@ -558,6 +533,7 @@ int main(int argc, const char **argv)
 
         srandom(time(NULL));
 
+        perf_config__init();
         perf_config(perf_default_config, NULL);
         set_buildid_dir(NULL);
 
@@ -649,7 +625,7 @@ int main(int argc, const char **argv)
         }
 
         fprintf(stderr, "Failed to run command '%s': %s\n",
-                cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
+                cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
 out:
         return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cd8f1b150f9e..cb0f1356ff81 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -52,6 +52,7 @@ struct record_opts {
         bool         sample_weight;
         bool         sample_time;
         bool         sample_time_set;
+        bool         sample_cpu;
         bool         period;
         bool         running_time;
         bool         full_auxtrace;
@@ -59,6 +60,8 @@ struct record_opts {
         bool         record_switch_events;
         bool         all_kernel;
         bool         all_user;
+        bool         tail_synthesize;
+        bool         overwrite;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
new file mode 100755
index 000000000000..eb4dbed57de7
--- /dev/null
+++ b/tools/perf/python/tracepoint.py
@@ -0,0 +1,47 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+
+import perf
+
+class tracepoint(perf.evsel):
+    def __init__(self, sys, name):
+        config = perf.tracepoint(sys, name)
+        perf.evsel.__init__(self,
+                            type   = perf.TYPE_TRACEPOINT,
+                            config = config,
+                            freq = 0, sample_period = 1, wakeup_events = 1,
+                            sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_RAW | perf.SAMPLE_TIME)
+
+def main():
+    tp      = tracepoint("sched", "sched_switch")
+    cpus    = perf.cpu_map()
+    threads = perf.thread_map(-1)
+
+    evlist = perf.evlist(cpus, threads)
+    evlist.add(tp)
+    evlist.open()
+    evlist.mmap()
+
+    while True:
+        evlist.poll(timeout = -1)
+        for cpu in cpus:
+            event = evlist.read_on_cpu(cpu)
+            if not event:
+                continue
+
+            if not isinstance(event, perf.sample_event):
+                continue
+
+            print "time %u prev_comm=%s prev_pid=%d prev_prio=%d prev_state=0x%x ==> next_comm=%s next_pid=%d next_prio=%d" % (
+                   event.sample_time,
+                   event.prev_comm,
+                   event.prev_pid,
+                   event.prev_prio,
+                   event.prev_state,
+                   event.next_comm,
+                   event.next_pid,
+                   event.next_prio)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Build b/tools/perf/scripts/perl/Perf-Trace-Util/Build
index 928e110179cb..34faecf774ae 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Build
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Build
@@ -1,3 +1,5 @@
 libperf-y += Context.o
 
-CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs -Wno-undef -Wno-switch-default
+CFLAGS_Context.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes
+CFLAGS_Context.o += -Wno-unused-parameter -Wno-nested-externs -Wno-undef
+CFLAGS_Context.o += -Wno-switch-default -Wno-shadow
diff --git a/tools/perf/scripts/python/bin/stackcollapse-record b/tools/perf/scripts/python/bin/stackcollapse-record
new file mode 100755
index 000000000000..9d8f9f0f3a17
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-record
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+#
+# stackcollapse.py can cover all type of perf samples including
+# the tracepoints, so no special record requirements, just record what
+# you want to analyze.
+#
+perf record "$@"
diff --git a/tools/perf/scripts/python/bin/stackcollapse-report b/tools/perf/scripts/python/bin/stackcollapse-report
new file mode 100755
index 000000000000..356b9656393d
--- /dev/null
+++ b/tools/perf/scripts/python/bin/stackcollapse-report
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: produce callgraphs in short form for scripting use
+perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py -- "$@"
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
index 4d21ef2d601d..4c6f09ac7d12 100644
--- a/tools/perf/scripts/python/netdev-times.py
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -252,9 +252,10 @@ def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, i
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
         all_event_list.append(event_info)
 
-def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name):
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi,
+                    dev_name, work=None, budget=None):
         event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
-                        napi, dev_name)
+                        napi, dev_name, work, budget)
         all_event_list.append(event_info)
 
 def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
@@ -354,11 +355,13 @@ def handle_irq_softirq_exit(event_info):
         receive_hunk_list.append(rec_data)
 
 def handle_napi_poll(event_info):
-        (name, context, cpu, time, pid, comm, napi, dev_name) = event_info
+        (name, context, cpu, time, pid, comm, napi, dev_name,
+                work, budget) = event_info
         if cpu in net_rx_dic.keys():
                 event_list = net_rx_dic[cpu]['event_list']
                 rec_data = {'event_name':'napi_poll',
-                                'dev':dev_name, 'event_t':time}
+                                'dev':dev_name, 'event_t':time,
+                                'work':work, 'budget':budget}
                 event_list.append(rec_data)
 
 def handle_netif_rx(event_info):
diff --git a/tools/perf/scripts/python/stackcollapse.py b/tools/perf/scripts/python/stackcollapse.py
new file mode 100755
index 000000000000..5a605f70ef32
--- /dev/null
+++ b/tools/perf/scripts/python/stackcollapse.py
@@ -0,0 +1,125 @@
+# stackcollapse.py - format perf samples with one line per distinct call stack
+#
+# This script's output has two space-separated fields.  The first is a semicolon
+# separated stack including the program name (from the "comm" field) and the
+# function names from the call stack.  The second is a count:
+#
+#  swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2
+#
+# The file is sorted according to the first field.
+#
+# Input may be created and processed using:
+#
+#  perf record -a -g -F 99 sleep 60
+#  perf script report stackcollapse > out.stacks-folded
+#
+# (perf script record stackcollapse works too).
+#
+# Written by Paolo Bonzini <pbonzini@redhat.com>
+# Based on Brendan Gregg's stackcollapse-perf.pl script.
+
+import os
+import sys
+from collections import defaultdict
+from optparse import OptionParser, make_option
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+                '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from EventClass import *
+
+# command line parsing
+
+option_list = [
+    # formatting options for the bottom entry of the stack
+    make_option("--include-tid", dest="include_tid",
+                 action="store_true", default=False,
+                 help="include thread id in stack"),
+    make_option("--include-pid", dest="include_pid",
+                 action="store_true", default=False,
+                 help="include process id in stack"),
+    make_option("--no-comm", dest="include_comm",
+                 action="store_false", default=True,
+                 help="do not separate stacks according to comm"),
+    make_option("--tidy-java", dest="tidy_java",
+                 action="store_true", default=False,
+                 help="beautify Java signatures"),
+    make_option("--kernel", dest="annotate_kernel",
+                 action="store_true", default=False,
+                 help="annotate kernel functions with _[k]")
+]
+
+parser = OptionParser(option_list=option_list)
+(opts, args) = parser.parse_args()
+
+if len(args) != 0:
+    parser.error("unexpected command line argument")
+if opts.include_tid and not opts.include_comm:
+    parser.error("requesting tid but not comm is invalid")
+if opts.include_pid and not opts.include_comm:
+    parser.error("requesting pid but not comm is invalid")
+
+# event handlers
+
+lines = defaultdict(lambda: 0)
+
+def process_event(param_dict):
+    def tidy_function_name(sym, dso):
+        if sym is None:
+            sym = '[unknown]'
+
+        sym = sym.replace(';', ':')
+        if opts.tidy_java:
+            # the original stackcollapse-perf.pl script gives the
+            # example of converting this:
+            #    Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V
+            # to this:
+            #    org/mozilla/javascript/MemberBox:.init
+            sym = sym.replace('<', '')
+            sym = sym.replace('>', '')
+            if sym[0] == 'L' and sym.find('/'):
+                sym = sym[1:]
+            try:
+                sym = sym[:sym.index('(')]
+            except ValueError:
+                pass
+
+        if opts.annotate_kernel and dso == '[kernel.kallsyms]':
+            return sym + '_[k]'
+        else:
+            return sym
+
+    stack = list()
+    if 'callchain' in param_dict:
+        for entry in param_dict['callchain']:
+            entry.setdefault('sym', dict())
+            entry['sym'].setdefault('name', None)
+            entry.setdefault('dso', None)
+            stack.append(tidy_function_name(entry['sym']['name'],
+                                            entry['dso']))
+    else:
+        param_dict.setdefault('symbol', None)
+        param_dict.setdefault('dso', None)
+        stack.append(tidy_function_name(param_dict['symbol'],
+                                        param_dict['dso']))
+
+    if opts.include_comm:
+        comm = param_dict["comm"].replace(' ', '_')
+        sep = "-"
+        if opts.include_pid:
+            comm = comm + sep + str(param_dict['sample']['pid'])
+            sep = "/"
+        if opts.include_tid:
+            comm = comm + sep + str(param_dict['sample']['tid'])
+        stack.append(comm)
+
+    stack_string = ';'.join(reversed(stack))
+    lines[stack_string] = lines[stack_string] + 1
+
+def trace_end():
+    list = lines.keys()
+    list.sort()
+    for stack in list:
+        print "%s %d" % (stack, lines[stack])
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 66a28982547b..dc51bc570e51 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -39,6 +39,9 @@ perf-y += stat.o
 perf-y += event_update.o
 perf-y += event-times.o
 perf-y += backward-ring-buffer.o
+perf-y += sdt.o
+perf-y += is_printable_array.o
+perf-y += bitmap.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
         $(call rule_mkdir)
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index d9ba991a9a30..615780cbfe1d 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,8 +31,8 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
         for (i = 0; i < evlist->nr_mmaps; i++) {
                 union perf_event *event;
 
-                perf_evlist__mmap_read_catchup(evlist, i);
-                while ((event = perf_evlist__mmap_read_backward(evlist, i)) != NULL) {
+                perf_mmap__read_catchup(&evlist->backward_mmap[i]);
+                while ((event = perf_mmap__read_backward(&evlist->backward_mmap[i])) != NULL) {
                         const u32 type = event->header.type;
 
                         switch (type) {
@@ -60,7 +60,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
         err = perf_evlist__mmap(evlist, mmap_pages, true);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 return TEST_FAIL;
         }
 
@@ -108,7 +108,11 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
         }
 
         bzero(&parse_error, sizeof(parse_error));
-        err = parse_events(evlist, "syscalls:sys_enter_prctl", &parse_error);
+        /*
+         * Set backward bit, ring buffer should be writing from end. Record
+         * it in aux evlist
+         */
+        err = parse_events(evlist, "syscalls:sys_enter_prctl/overwrite/", &parse_error);
         if (err) {
                 pr_debug("Failed to parse tracepoint event, try use root\n");
                 ret = TEST_SKIP;
@@ -117,14 +121,10 @@ int test__backward_ring_buffer(int subtest __maybe_unused)
 
         perf_evlist__config(evlist, &opts, NULL);
 
-        /* Set backward bit, ring buffer should be writing from end */
-        evlist__for_each(evlist, evsel)
-                evsel->attr.write_backward = 1;
-
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
new file mode 100644
index 000000000000..9abe6c13090f
--- /dev/null
+++ b/tools/perf/tests/bitmap.c
@@ -0,0 +1,53 @@
+#include <linux/compiler.h>
+#include <linux/bitmap.h>
+#include "tests.h"
+#include "cpumap.h"
+#include "debug.h"
+
+#define NBITS 100
+
+static unsigned long *get_bitmap(const char *str, int nbits)
+{
+        struct cpu_map *map = cpu_map__new(str);
+        unsigned long *bm = NULL;
+        int i;
+
+        bm = bitmap_alloc(nbits);
+
+        if (map && bm) {
+                bitmap_zero(bm, nbits);
+
+                for (i = 0; i < map->nr; i++)
+                        set_bit(map->map[i], bm);
+        }
+
+        if (map)
+                cpu_map__put(map);
+        return bm;
+}
+
+static int test_bitmap(const char *str)
+{
+        unsigned long *bm = get_bitmap(str, NBITS);
+        char buf[100];
+        int ret;
+
+        bitmap_scnprintf(bm, NBITS, buf, sizeof(buf));
+        pr_debug("bitmap: %s\n", buf);
+
+        ret = !strcmp(buf, str);
+        free(bm);
+        return ret;
+}
+
+int test__bitmap_print(int subtest __maybe_unused)
+{
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3,5,7,9,11,13,15,17,19,21-40"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("2-5"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,3-6,8-10,24,35-37"));
+        TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40"));
+        return 0;
+}
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 0ec9c2c03164..268e5f8e4aa2 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -31,8 +31,8 @@ struct bpf_map_def SEC("maps") flip_table = {
         .max_entries = 1,
 };
 
-SEC("func=sys_epoll_pwait")
-int bpf_func__sys_epoll_pwait(void *ctx)
+SEC("func=SyS_epoll_wait")
+int bpf_func__SyS_epoll_wait(void *ctx)
 {
         int ind =0;
         int *flag = bpf_map_lookup_elem(&flip_table, &ind);
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index f31eed31c1a9..fc54064b9186 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -13,13 +13,13 @@
 
 #ifdef HAVE_LIBBPF_SUPPORT
 
-static int epoll_pwait_loop(void)
+static int epoll_wait_loop(void)
 {
         int i;
 
         /* Should fail NR_ITERS times */
         for (i = 0; i < NR_ITERS; i++)
-                epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+                epoll_wait(-(i + 1), NULL, 0, 0);
         return 0;
 }
 
@@ -61,7 +61,7 @@ static struct {
                 "[basic_bpf_test]",
                 "fix 'perf test LLVM' first",
                 "load bpf object failed",
-                &epoll_pwait_loop,
+                &epoll_wait_loop,
                 (NR_ITERS + 1) / 2,
         },
 #ifdef HAVE_BPF_PROLOGUE
@@ -143,14 +143,14 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 0e95c20ecf6e..778668a2a966 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -14,6 +14,8 @@
 #include <subcmd/parse-options.h>
 #include "symbol.h"
 
+static bool dont_fork;
+
 struct test __weak arch_tests[] = {
         {
                 .func = NULL,
@@ -212,6 +214,22 @@ static struct test generic_tests[] = {
                 .func = test__backward_ring_buffer,
         },
         {
+                .desc = "Test cpu map print",
+                .func = test__cpu_map_print,
+        },
+        {
+                .desc = "Test SDT event probing",
+                .func = test__sdt_event,
+        },
+        {
+                .desc = "Test is_printable_array function",
+                .func = test__is_printable_array,
+        },
+        {
+                .desc = "Test bitmap print",
+                .func = test__bitmap_print,
+        },
+        {
                 .func = NULL,
         },
 };
@@ -247,44 +265,51 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char
 
 static int run_test(struct test *test, int subtest)
 {
-        int status, err = -1, child = fork();
+        int status, err = -1, child = dont_fork ? 0 : fork();
         char sbuf[STRERR_BUFSIZE];
 
         if (child < 0) {
                 pr_err("failed to fork test: %s\n",
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
 
         if (!child) {
-                pr_debug("test child forked, pid %d\n", getpid());
-                if (!verbose) {
-                        int nullfd = open("/dev/null", O_WRONLY);
-                        if (nullfd >= 0) {
-                                close(STDERR_FILENO);
-                                close(STDOUT_FILENO);
-
-                                dup2(nullfd, STDOUT_FILENO);
-                                dup2(STDOUT_FILENO, STDERR_FILENO);
-                                close(nullfd);
+                if (!dont_fork) {
+                        pr_debug("test child forked, pid %d\n", getpid());
+
+                        if (!verbose) {
+                                int nullfd = open("/dev/null", O_WRONLY);
+
+                                if (nullfd >= 0) {
+                                        close(STDERR_FILENO);
+                                        close(STDOUT_FILENO);
+
+                                        dup2(nullfd, STDOUT_FILENO);
+                                        dup2(STDOUT_FILENO, STDERR_FILENO);
+                                        close(nullfd);
+                                }
+                        } else {
+                                signal(SIGSEGV, sighandler_dump_stack);
+                                signal(SIGFPE, sighandler_dump_stack);
                         }
-                } else {
-                        signal(SIGSEGV, sighandler_dump_stack);
-                        signal(SIGFPE, sighandler_dump_stack);
                 }
 
                 err = test->func(subtest);
-                exit(err);
+                if (!dont_fork)
+                        exit(err);
         }
 
-        wait(&status);
+        if (!dont_fork) {
+                wait(&status);
 
-        if (WIFEXITED(status)) {
-                err = (signed char)WEXITSTATUS(status);
-                pr_debug("test child finished with %d\n", err);
-        } else if (WIFSIGNALED(status)) {
-                err = -1;
-                pr_debug("test child interrupted\n");
+                if (WIFEXITED(status)) {
+                        err = (signed char)WEXITSTATUS(status);
+                        pr_debug("test child finished with %d\n", err);
+                } else if (WIFSIGNALED(status)) {
+                        err = -1;
+                        pr_debug("test child interrupted\n");
+                }
         }
 
         return err;
@@ -425,6 +450,8 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
         OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('F', "dont-fork", &dont_fork,
+                    "Do not fork for testcase"),
         OPT_END()
         };
         const char * const test_subcommands[] = { "list", NULL };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 68a69a195545..2af156a8d4e5 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -33,44 +33,86 @@ static unsigned int hex(char c)
         return c - 'A' + 10;
 }
 
-static size_t read_objdump_line(const char *line, size_t line_len, void *buf,
-                              size_t len)
+static size_t read_objdump_chunk(const char **line, unsigned char **buf,
+                                 size_t *buf_len)
 {
-        const char *p;
-        size_t i, j = 0;
-
-        /* Skip to a colon */
-        p = strchr(line, ':');
-        if (!p)
-                return 0;
-        i = p + 1 - line;
+        size_t bytes_read = 0;
+        unsigned char *chunk_start = *buf;
 
         /* Read bytes */
-        while (j < len) {
+        while (*buf_len > 0) {
                 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]))
+                c1 = *(*line)++;
+                if (!isxdigit(c1))
                         break;
-                c1 = line[i++];
-                if (i >= line_len || !isxdigit(line[i]))
+                c2 = *(*line)++;
+                if (!isxdigit(c2))
                         break;
-                c2 = line[i++];
-                /* Followed by a space */
-                if (i < line_len && line[i] && !isspace(line[i]))
+
+                /* Store byte and advance buf */
+                **buf = (hex(c1) << 4) | hex(c2);
+                (*buf)++;
+                (*buf_len)--;
+                bytes_read++;
+
+                /* End of chunk? */
+                if (isspace(**line))
                         break;
-                /* Store byte */
-                *(unsigned char *)buf = (hex(c1) << 4) | hex(c2);
-                buf += 1;
-                j++;
         }
+
+        /*
+         * objdump will display raw insn as LE if code endian
+         * is LE and bytes_per_chunk > 1. In that case reverse
+         * the chunk we just read.
+         *
+         * see disassemble_bytes() at binutils/objdump.c for details
+         * how objdump chooses display endian)
+         */
+        if (bytes_read > 1 && !bigendian()) {
+                unsigned char *chunk_end = chunk_start + bytes_read - 1;
+                unsigned char tmp;
+
+                while (chunk_start < chunk_end) {
+                        tmp = *chunk_start;
+                        *chunk_start = *chunk_end;
+                        *chunk_end = tmp;
+                        chunk_start++;
+                        chunk_end--;
+                }
+        }
+
+        return bytes_read;
+}
+
+static size_t read_objdump_line(const char *line, unsigned char *buf,
+                                size_t buf_len)
+{
+        const char *p;
+        size_t ret, bytes_read = 0;
+
+        /* Skip to a colon */
+        p = strchr(line, ':');
+        if (!p)
+                return 0;
+        p++;
+
+        /* Skip initial spaces */
+        while (*p) {
+                if (!isspace(*p))
+                        break;
+                p++;
+        }
+
+        do {
+                ret = read_objdump_chunk(&p, &buf, &buf_len);
+                bytes_read += ret;
+                p++;
+        } while (ret > 0);
+
         /* return number of successfully read bytes */
-        return j;
+        return bytes_read;
 }
 
 static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
@@ -95,7 +137,7 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
                 }
 
                 /* read objdump data into temporary buffer */
-                read_bytes = read_objdump_line(line, ret, tmp, sizeof(tmp));
+                read_bytes = read_objdump_line(line, tmp, sizeof(tmp));
                 if (!read_bytes)
                         continue;
 
@@ -152,7 +194,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 
         ret = read_objdump_output(f, buf, &len, addr);
         if (len) {
-                pr_debug("objdump read too few bytes\n");
+                pr_debug("objdump read too few bytes: %zd\n", len);
                 if (!ret)
                         ret = len;
         }
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 4cb6418a8ffc..f168a85992d0 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -1,5 +1,12 @@
 #include "tests.h"
+#include <stdio.h>
 #include "cpumap.h"
+#include "event.h"
+#include <string.h>
+#include <linux/bitops.h>
+#include "debug.h"
+
+struct machine;
 
 static int process_event_mask(struct perf_tool *tool __maybe_unused,
                          union perf_event *event,
@@ -86,3 +93,27 @@ int test__cpu_map_synthesize(int subtest __maybe_unused)
         cpu_map__put(cpus);
         return 0;
 }
+
+static int cpu_map_print(const char *str)
+{
+        struct cpu_map *map = cpu_map__new(str);
+        char buf[100];
+
+        if (!map)
+                return -1;
+
+        cpu_map__snprint(map, buf, sizeof(buf));
+        return !strcmp(buf, str);
+}
+
+int test__cpu_map_print(int subtest __maybe_unused)
+{
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3,5,7,9,11,13,15,17,19,21-40"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("2-5"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3-6,8-10,24,35-37"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,3-6,8-10,24,35-37"));
+        TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
+        return 0;
+}
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 8cf0d9e189a8..13725e09ba22 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -251,6 +251,9 @@ int test__dso_data_cache(int subtest __maybe_unused)
         long nr_end, nr = open_files_cnt();
         int dso_cnt, limit, i, fd;
 
+        /* Rest the internal dso open counter limit. */
+        reset_fd_limit();
+
         memset(&machine, 0, sizeof(machine));
 
         /* set as system limit */
@@ -312,6 +315,9 @@ int test__dso_data_reopen(int subtest __maybe_unused)
 #define dso_1 (dsos[1])
 #define dso_2 (dsos[2])
 
+        /* Rest the internal dso open counter limit. */
+        reset_fd_limit();
+
         memset(&machine, 0, sizeof(machine));
 
         /*
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 95fb744f6628..19ef77bd6eb4 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -37,7 +37,7 @@ static int attach__enable_on_exec(struct perf_evlist *evlist)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 return err;
         }
 
@@ -200,8 +200,7 @@ static int test_times(int (attach)(struct perf_evlist *),
                  count.ena, count.run);
 
 out_err:
-        if (evlist)
-                perf_evlist__delete(evlist);
+        perf_evlist__delete(evlist);
         return !err ? TEST_OK : TEST_FAIL;
 }
 
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 2de4a4f2c3ed..60926a1f6fd7 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -80,7 +80,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
         }
 
         err = 0;
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
                         --err;
                         pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index c809463edbe5..a2b5ff9bf83d 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -1,4 +1,5 @@
 #include <api/fd/array.h>
+#include <poll.h>
 #include "util/debug.h"
 #include "tests/tests.h"
 
@@ -36,7 +37,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
         }
 
         fdarray__init_revents(fda, POLLIN);
-        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
         if (nr_fds != fda->nr_alloc) {
                 pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
                          nr_fds, fda->nr_alloc);
@@ -44,7 +45,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
         }
 
         fdarray__init_revents(fda, POLLHUP);
-        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
         if (nr_fds != 0) {
                 pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
                          nr_fds, fda->nr_alloc);
@@ -57,7 +58,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 
         pr_debug("\nfiltering all but fda->entries[2]:");
         fdarray__fprintf_prefix(fda, "before", stderr);
-        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
         fdarray__fprintf_prefix(fda, " after", stderr);
         if (nr_fds != 1) {
                 pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
@@ -78,7 +79,7 @@ int test__fdarray__filter(int subtest __maybe_unused)
 
         pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
         fdarray__fprintf_prefix(fda, "before", stderr);
-        nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+        nr_fds = fdarray__filter(fda, POLLHUP, NULL, NULL);
         fdarray__fprintf_prefix(fda, " after", stderr);
         if (nr_fds != 2) {
                 pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index a9e3db3afac4..9fd54b79a788 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -216,6 +216,8 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 
                 /* check callchain entries */
                 root = &he->callchain->node.rb_root;
+
+                TEST_ASSERT_VAL("callchains expected", !RB_EMPTY_ROOT(root));
                 cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
 
                 c = 0;
@@ -666,6 +668,8 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
         perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
         setup_sorting(NULL);
+
+        callchain_param = callchain_param_default;
         callchain_register_param(&callchain_param);
 
         err = add_hist_entries(hists, machine);
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index e846f8c42013..62efb14f3a5a 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -56,7 +56,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
          * (perf [perf] main) will be collapsed to an existing entry
          * so total 9 entries will be in the tree.
          */
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
                         struct hist_entry_iter iter = {
                                 .evsel = evsel,
@@ -136,7 +136,7 @@ int test__hists_filter(int subtest __maybe_unused)
         if (err < 0)
                 goto out;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index acf5a1301c07..eddc7407ff8a 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -72,7 +72,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
          * However the second evsel also has a collapsed entry for
          * "bash [libc] malloc" so total 9 entries will be in the tree.
          */
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 struct hists *hists = evsel__hists(evsel);
 
                 for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
@@ -84,7 +84,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                         if (machine__resolve(machine, &al, &sample) < 0)
                                 goto out;
 
-                        he = __hists__add_entry(hists, &al, NULL,
+                        he = hists__add_entry(hists, &al, NULL,
                                                 NULL, NULL, &sample, true);
                         if (he == NULL) {
                                 addr_location__put(&al);
@@ -103,7 +103,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
                         if (machine__resolve(machine, &al, &sample) < 0)
                                 goto out;
 
-                        he = __hists__add_entry(hists, &al, NULL,
+                        he = hists__add_entry(hists, &al, NULL,
                                                 NULL, NULL, &sample, true);
                         if (he == NULL) {
                                 addr_location__put(&al);
@@ -301,7 +301,7 @@ int test__hists_link(int subtest __maybe_unused)
         if (err < 0)
                 goto out;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 hists = evsel__hists(evsel);
                 hists__collapse_resort(hists, NULL);
 
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
new file mode 100644
index 000000000000..42e13393e502
--- /dev/null
+++ b/tools/perf/tests/is_printable_array.c
@@ -0,0 +1,36 @@
+#include <linux/compiler.h>
+#include "tests.h"
+#include "debug.h"
+#include "util.h"
+
+int test__is_printable_array(int subtest __maybe_unused)
+{
+        char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
+        char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
+        struct {
+                char            *buf;
+                unsigned int     len;
+                int              ret;
+        } t[] = {
+                { (char *) "krava",     sizeof("krava"),        1 },
+                { (char *) "krava",     sizeof("krava") - 1,    0 },
+                { (char *) "",          sizeof(""),             1 },
+                { (char *) "",          0,                      0 },
+                { NULL,                 0,                      0 },
+                { buf1,                 sizeof(buf1),           0 },
+                { buf2,                 sizeof(buf2),           0 },
+        };
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(t); i++) {
+                int ret;
+
+                ret = is_printable_array((char *) t[i].buf, t[i].len);
+                if (ret != t[i].ret) {
+                        pr_err("failed: test %u\n", i);
+                        return TEST_FAIL;
+                }
+        }
+
+        return TEST_OK;
+}
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index d2af78193153..76f41f249944 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -1,4 +1,5 @@
 #include <stdbool.h>
+#include <stdlib.h>
 #include "tests.h"
 #include "dso.h"
 #include "debug.h"
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index cff564fb4b66..b798a4bfd238 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -5,6 +5,7 @@
 #include "llvm.h"
 #include "tests.h"
 #include "debug.h"
+#include "util.h"
 
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index cac15d93aea6..143f4d549769 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -81,6 +81,8 @@ make_no_libbionic   := NO_LIBBIONIC=1
 make_no_auxtrace    := NO_AUXTRACE=1
 make_no_libbpf      := NO_LIBBPF=1
 make_no_libcrypto   := NO_LIBCRYPTO=1
+make_with_babeltrace:= LIBBABELTRACE=1
+make_no_sdt         := NO_SDT=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -104,7 +106,7 @@ make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
-make_minimal        += NO_LIBCRYPTO=1
+make_minimal        += NO_LIBCRYPTO=1 NO_SDT=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -136,6 +138,7 @@ run += make_no_libaudit
 run += make_no_libbionic
 run += make_no_auxtrace
 run += make_no_libbpf
+run += make_with_babeltrace
 run += make_help
 run += make_doc
 run += make_perf_o
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 359e98fcd94c..634bce9caebd 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
@@ -49,7 +52,7 @@ int test__basic_mmap(int subtest __maybe_unused)
         sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
         if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
                 pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-                         cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
+                         cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_free_cpus;
         }
 
@@ -79,7 +82,7 @@ int test__basic_mmap(int subtest __maybe_unused)
                 if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
                         pr_debug("failed to open counter: %s, "
                                  "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                                 strerror_r(errno, sbuf, sizeof(sbuf)));
+                                 str_error_r(errno, sbuf, sizeof(sbuf)));
                         goto out_delete_evlist;
                 }
 
@@ -89,7 +92,7 @@ int test__basic_mmap(int subtest __maybe_unused)
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -126,7 +129,7 @@ int test__basic_mmap(int subtest __maybe_unused)
         }
 
         err = 0;
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
                         pr_debug("expected %d %s events, got %d\n",
                                  expected_nr_events[evsel->idx],
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index ad1cb63139a7..c8d9592eb142 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -1,3 +1,6 @@
+/* For the CPU_* macros */
+#include <pthread.h>
+
 #include <api/fs/fs.h>
 #include <linux/err.h>
 #include "evsel.h"
@@ -41,7 +44,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
         if (perf_evsel__open(evsel, cpus, threads) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_evsel_delete;
         }
 
@@ -62,7 +65,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
                 if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
                         pr_debug("sched_setaffinity() failed on CPU %d: %s ",
                                  cpus->map[cpu],
-                                 strerror_r(errno, sbuf, sizeof(sbuf)));
+                                 str_error_r(errno, sbuf, sizeof(sbuf)));
                         goto out_close_fd;
                 }
                 for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 4344fe482c1d..f52239fed361 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -6,6 +6,13 @@
 #include "tests.h"
 #include "debug.h"
 
+#ifndef O_DIRECTORY
+#define O_DIRECTORY    00200000
+#endif
+#ifndef AT_FDCWD
+#define AT_FDCWD       -100
+#endif
+
 int test__syscall_openat_tp_fields(int subtest __maybe_unused)
 {
         struct record_opts opts = {
@@ -51,14 +58,14 @@ int test__syscall_openat_tp_fields(int subtest __maybe_unused)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, UINT_MAX, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 1184f9ba6499..d7414128d7fe 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -29,7 +29,7 @@ int test__openat_syscall_event(int subtest __maybe_unused)
         if (perf_evsel__open_per_thread(evsel, threads) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_evsel_delete;
         }
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7865f68dc0d8..20c2e641c422 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -32,7 +32,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
         TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong type",
                         PERF_TYPE_TRACEPOINT == evsel->attr.type);
                 TEST_ASSERT_VAL("wrong sample_type",
@@ -207,7 +207,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong exclude_user",
                                 !evsel->attr.exclude_user);
                 TEST_ASSERT_VAL("wrong exclude_kernel",
@@ -1783,8 +1783,8 @@ static int test_pmu_events(void)
                 struct evlist_test e;
                 char name[MAX_NAME];
 
-                if (!strcmp(ent->d_name, ".") ||
-                    !strcmp(ent->d_name, ".."))
+                /* Names containing . are special and cannot be used directly */
+                if (strchr(ent->d_name, '.'))
                         continue;
 
                 snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 294c76b01b41..81c6eeaca0f5 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -44,8 +44,7 @@ static int process_events(union perf_event **events, size_t count)
         for (i = 0; i < count && !err; i++)
                 err = process_event(&evlist, events[i]);
 
-        if (evlist)
-                perf_evlist__delete(evlist);
+        perf_evlist__delete(evlist);
 
         return err;
 }
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b836ee6a8d9b..8f2e1de6d0ea 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -1,3 +1,6 @@
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include <sched.h>
 #include "evlist.h"
 #include "evsel.h"
@@ -104,7 +107,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
         err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
         if (err < 0) {
                 pr_debug("sched__get_first_possible_cpu: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -115,7 +118,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
          */
         if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
                 pr_debug("sched_setaffinity: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -126,7 +129,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
@@ -138,7 +141,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
         err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
new file mode 100644
index 000000000000..f59d210e1baf
--- /dev/null
+++ b/tools/perf/tests/sdt.c
@@ -0,0 +1,115 @@
+#include <stdio.h>
+#include <sys/epoll.h>
+#include <util/util.h>
+#include <util/evlist.h>
+#include <linux/filter.h>
+#include "tests.h"
+#include "debug.h"
+#include "probe-file.h"
+#include "build-id.h"
+
+/* To test SDT event, we need libelf support to scan elf binary */
+#if defined(HAVE_SDT_EVENT) && defined(HAVE_LIBELF_SUPPORT)
+
+#include <sys/sdt.h>
+
+static int target_function(void)
+{
+        DTRACE_PROBE(perf, test_target);
+        return TEST_OK;
+}
+
+/* Copied from builtin-buildid-cache.c */
+static int build_id_cache__add_file(const char *filename)
+{
+        char sbuild_id[SBUILD_ID_SIZE];
+        u8 build_id[BUILD_ID_SIZE];
+        int err;
+
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        if (err < 0) {
+                pr_debug("Failed to read build id of %s\n", filename);
+                return err;
+        }
+
+        build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+        err = build_id_cache__add_s(sbuild_id, filename, false, false);
+        if (err < 0)
+                pr_debug("Failed to add build id cache of %s\n", filename);
+        return err;
+}
+
+static char *get_self_path(void)
+{
+        char *buf = calloc(PATH_MAX, sizeof(char));
+
+        if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+                pr_debug("Failed to get correct path of perf\n");
+                free(buf);
+                return NULL;
+        }
+        return buf;
+}
+
+static int search_cached_probe(const char *target,
+                               const char *group, const char *event)
+{
+        struct probe_cache *cache = probe_cache__new(target);
+        int ret = 0;
+
+        if (!cache) {
+                pr_debug("Failed to open probe cache of %s\n", target);
+                return -EINVAL;
+        }
+
+        if (!probe_cache__find_by_name(cache, group, event)) {
+                pr_debug("Failed to find %s:%s in the cache\n", group, event);
+                ret = -ENOENT;
+        }
+        probe_cache__delete(cache);
+
+        return ret;
+}
+
+int test__sdt_event(int subtests __maybe_unused)
+{
+        int ret = TEST_FAIL;
+        char __tempdir[] = "./test-buildid-XXXXXX";
+        char *tempdir = NULL, *myself = get_self_path();
+
+        if (myself == NULL || mkdtemp(__tempdir) == NULL) {
+                pr_debug("Failed to make a tempdir for build-id cache\n");
+                goto error;
+        }
+        /* Note that buildid_dir must be an absolute path */
+        tempdir = realpath(__tempdir, NULL);
+
+        /* At first, scan itself */
+        set_buildid_dir(tempdir);
+        if (build_id_cache__add_file(myself) < 0)
+                goto error_rmdir;
+
+        /* Open a cache and make sure the SDT is stored */
+        if (search_cached_probe(myself, "sdt_perf", "test_target") < 0)
+                goto error_rmdir;
+
+        /* TBD: probing on the SDT event and collect logs */
+
+        /* Call the target and get an event */
+        ret = target_function();
+
+error_rmdir:
+        /* Cleanup temporary buildid dir */
+        rm_rf(tempdir);
+error:
+        free(tempdir);
+        free(myself);
+        return ret;
+}
+#else
+int test__sdt_event(int subtests __maybe_unused)
+{
+        pr_debug("Skip SDT event test because SDT support is not compiled\n");
+        return TEST_SKIP;
+}
+#endif
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 36e8ce1550e3..4c9fd046d57b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -70,7 +70,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
                 err = -errno;
                 pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)),
+                         str_error_r(errno, sbuf, sizeof(sbuf)),
                          knob, (u64)attr.sample_freq);
                 goto out_delete_evlist;
         }
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         err = perf_evlist__mmap(evlist, 128, true);
         if (err < 0) {
                 pr_debug("failed to mmap event: %d (%s)\n", errno,
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 39a689bf7574..7ddbe267d0ac 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -432,7 +432,7 @@ int test__switch_tracking(int subtest __maybe_unused)
         }
 
         /* Check non-tracking events are not tracking */
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel != tracking_evsel) {
                         if (evsel->attr.mmap || evsel->attr.comm) {
                                 pr_debug("Non-tracking event is tracking\n");
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 2dfff7ac8ef3..01a5ba2788c6 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -91,13 +91,13 @@ int test__task_exit(int subtest __maybe_unused)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("Couldn't open the evlist: %s\n",
-                         strerror_r(-err, sbuf, sizeof(sbuf)));
+                         str_error_r(-err, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 goto out_delete_evlist;
         }
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c57e72c826d2..7c196c585472 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -87,6 +87,10 @@ int test__synthesize_stat_round(int subtest);
 int test__event_update(int subtest);
 int test__event_times(int subtest);
 int test__backward_ring_buffer(int subtest);
+int test__cpu_map_print(int subtest);
+int test__sdt_event(int subtest);
+int test__is_printable_array(int subtest);
+int test__bitmap_print(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index fccde848fe9c..cee2a2cdc933 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -1,13 +1,20 @@
 #include <sys/types.h>
 #include <unistd.h>
+#include <sys/prctl.h>
 #include "tests.h"
 #include "thread_map.h"
 #include "debug.h"
 
+#define NAME    (const char *) "perf"
+#define NAMEUL  (unsigned long) NAME
+
 int test__thread_map(int subtest __maybe_unused)
 {
         struct thread_map *map;
 
+        TEST_ASSERT_VAL("failed to set process name",
+                        !prctl(PR_SET_NAME, NAMEUL, 0, 0, 0));
+
         /* test map on current pid */
         map = thread_map__new_by_pid(getpid());
         TEST_ASSERT_VAL("failed to alloc map", map);
@@ -19,7 +26,7 @@ int test__thread_map(int subtest __maybe_unused)
                         thread_map__pid(map, 0) == getpid());
         TEST_ASSERT_VAL("wrong comm",
                         thread_map__comm(map, 0) &&
-                        !strcmp(thread_map__comm(map, 0), "perf"));
+                        !strcmp(thread_map__comm(map, 0), NAME));
         TEST_ASSERT_VAL("wrong refcnt",
                         atomic_read(&map->refcnt) == 1);
         thread_map__put(map);
@@ -51,7 +58,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 
         TEST_ASSERT_VAL("wrong nr",   map->nr == 1);
         TEST_ASSERT_VAL("wrong pid",  map->entries[0].pid == (u64) getpid());
-        TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf"));
+        TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, NAME));
 
         threads = thread_map__new_event(&event->thread_map);
         TEST_ASSERT_VAL("failed to alloc map", threads);
@@ -61,7 +68,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
                         thread_map__pid(threads, 0) == getpid());
         TEST_ASSERT_VAL("wrong comm",
                         thread_map__comm(threads, 0) &&
-                        !strcmp(thread_map__comm(threads, 0), "perf"));
+                        !strcmp(thread_map__comm(threads, 0), NAME));
         TEST_ASSERT_VAL("wrong refcnt",
                         atomic_read(&threads->refcnt) == 1);
         thread_map__put(threads);
@@ -72,6 +79,9 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
 {
         struct thread_map *threads;
 
+        TEST_ASSERT_VAL("failed to set process name",
+                        !prctl(PR_SET_NAME, NAMEUL, 0, 0, 0));
+
         /* test map on current pid */
         threads = thread_map__new_by_pid(getpid());
         TEST_ASSERT_VAL("failed to alloc map", threads);
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index d64f4a9128a1..b08f21eb6f4d 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,5 +1,3 @@
-#include <sys/eventfd.h>
-
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE           1
 #endif
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index 021bb48c6336..74613703a14e 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,3 +1,20 @@
+#include <fcntl.h>
+
+#ifndef LOCK_MAND
+#define LOCK_MAND        32
+#endif
+
+#ifndef LOCK_READ
+#define LOCK_READ        64
+#endif
+
+#ifndef LOCK_WRITE
+#define LOCK_WRITE      128
+#endif
+
+#ifndef LOCK_RW
+#define LOCK_RW         192
+#endif
 
 static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
                                            struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index e2476211f22d..bfd3359b09b6 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,5 +1,21 @@
 #include <linux/futex.h>
 
+#ifndef FUTEX_WAIT_BITSET
+#define FUTEX_WAIT_BITSET         9
+#endif
+#ifndef FUTEX_WAKE_BITSET
+#define FUTEX_WAKE_BITSET        10
+#endif
+#ifndef FUTEX_WAIT_REQUEUE_PI
+#define FUTEX_WAIT_REQUEUE_PI    11
+#endif
+#ifndef FUTEX_CMP_REQUEUE_PI
+#define FUTEX_CMP_REQUEUE_PI     12
+#endif
+#ifndef FUTEX_CLOCK_REALTIME
+#define FUTEX_CLOCK_REALTIME    256
+#endif
+
 static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
 {
         enum syscall_futex_args {
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 3444a4d5382d..d0a3a8e402e7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,9 @@
 #include <sys/mman.h>
 
+#ifndef PROT_SEM
+#define PROT_SEM 0x8
+#endif
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
                                                struct syscall_arg *arg)
 {
@@ -16,9 +20,7 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
         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
@@ -31,10 +33,31 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+#ifndef MAP_FIXED
+#define MAP_FIXED                    0x10
+#endif
+
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS                0x20
+#endif
+
+#ifndef MAP_32BIT
+#define MAP_32BIT                    0x40
+#endif
+
 #ifndef MAP_STACK
-# define MAP_STACK              0x20000
+#define MAP_STACK                 0x20000
 #endif
 
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB               0x40000
+#endif
+
+#ifndef MAP_UNINITIALIZED
+#define MAP_UNINITIALIZED       0x4000000
+#endif
+
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
                                                 struct syscall_arg *arg)
 {
@@ -48,26 +71,20 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
         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)
@@ -78,6 +95,13 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+#ifndef MREMAP_MAYMOVE
+#define MREMAP_MAYMOVE 1
+#endif
+#ifndef MREMAP_FIXED
+#define MREMAP_FIXED 2
+#endif
+
 static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
                                                   struct syscall_arg *arg)
 {
@@ -90,9 +114,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
         }
 
         P_MREMAP_FLAG(MAYMOVE);
-#ifdef MREMAP_FIXED
         P_MREMAP_FLAG(FIXED);
-#endif
 #undef P_MREMAP_FLAG
 
         if (flags)
@@ -107,6 +129,10 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_HWPOISON           100
 #endif
 
+#ifndef MADV_SOFT_OFFLINE
+#define MADV_SOFT_OFFLINE       101
+#endif
+
 #ifndef MADV_MERGEABLE
 #define MADV_MERGEABLE           12
 #endif
@@ -115,6 +141,23 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
 #define MADV_UNMERGEABLE         13
 #endif
 
+#ifndef MADV_HUGEPAGE
+#define MADV_HUGEPAGE            14
+#endif
+
+#ifndef MADV_NOHUGEPAGE
+#define MADV_NOHUGEPAGE          15
+#endif
+
+#ifndef MADV_DONTDUMP
+#define MADV_DONTDUMP            16
+#endif
+
+#ifndef MADV_DODUMP
+#define MADV_DODUMP              17
+#endif
+
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
                                                       struct syscall_arg *arg)
 {
@@ -131,24 +174,14 @@ static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
         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
+#undef P_MADV_BHV
         default: break;
         }
 
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index 07fa8a0acad6..1106c8960cc4 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -33,7 +33,6 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
         P_MSG_FLAG(OOB);
         P_MSG_FLAG(PEEK);
         P_MSG_FLAG(DONTROUTE);
-        P_MSG_FLAG(TRYHARD);
         P_MSG_FLAG(CTRUNC);
         P_MSG_FLAG(PROBE);
         P_MSG_FLAG(TRUNC);
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 0f3679e0cdcf..f55a4597fc38 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,3 +1,18 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#ifndef O_DIRECT
+#define O_DIRECT        00040000
+#endif
+
+#ifndef O_DIRECTORY
+#define O_DIRECTORY     00200000
+#endif
+
+#ifndef O_NOATIME
+#define O_NOATIME       01000000
+#endif
 
 static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
                                                struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index c205bc608b3c..34775295b9b3 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -9,6 +9,9 @@
 #ifndef SCHED_DEADLINE
 #define SCHED_DEADLINE 6
 #endif
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
 
 static size_t syscall_arg__scnprintf_sched_policy(char *bf, size_t size,
                                                   struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index 213c5a7e3e92..356441bce27d 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,5 +1,3 @@
-#include <linux/seccomp.h>
-
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index af68a9d488bf..3eb3edb307a4 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,5 +1,5 @@
 #include "../util.h"
-#include "../cache.h"
+#include "../config.h"
 #include "../../perf.h"
 #include "libslang.h"
 #include "ui.h"
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4fc208e82c6f..2e2d10022355 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -8,6 +8,7 @@
 #include "../../util/sort.h"
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
+#include "../../util/config.h"
 #include <pthread.h>
 
 struct disasm_line_samples {
@@ -222,16 +223,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                         } else if (ins__is_call(dl->ins)) {
                                 ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
                                 SLsmg_write_char(' ');
+                        } else if (ins__is_ret(dl->ins)) {
+                                ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+                                SLsmg_write_char(' ');
                         } else {
                                 ui_browser__write_nstring(browser, " ", 2);
                         }
                 } else {
-                        if (strcmp(dl->name, "retq")) {
-                                ui_browser__write_nstring(browser, " ", 2);
-                        } else {
-                                ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-                                SLsmg_write_char(' ');
-                        }
+                        ui_browser__write_nstring(browser, " ", 2);
                 }
 
                 disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
@@ -842,14 +841,14 @@ show_help:
                                 ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
                         else if (browser->selection->offset == -1)
                                 ui_helpline__puts("Actions are only available for assembly lines.");
-                        else if (!browser->selection->ins) {
-                                if (strcmp(browser->selection->name, "retq"))
-                                        goto show_sup_ins;
+                        else if (!browser->selection->ins)
+                                goto show_sup_ins;
+                        else if (ins__is_ret(browser->selection->ins))
                                 goto out;
-                        } else if (!(annotate_browser__jump(browser) ||
+                        else if (!(annotate_browser__jump(browser) ||
                                      annotate_browser__callq(browser, evsel, hbt))) {
 show_sup_ins:
-                                ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
+                                ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
                         }
                         continue;
                 case 't':
@@ -1027,7 +1026,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
                         .use_navkeypressed = true,
                 },
         };
-        int ret = -1;
+        int ret = -1, err;
         int nr_pcnt = 1;
         size_t sizeof_bdl = sizeof(struct browser_disasm_line);
 
@@ -1051,8 +1050,11 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
                   (nr_pcnt - 1);
         }
 
-        if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
-                ui__error("%s", ui_helpline__last_msg);
+        err = symbol__disassemble(sym, map, sizeof_bdl);
+        if (err) {
+                char msg[BUFSIZ];
+                symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+                ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
                 goto out_free_offsets;
         }
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 538bae880bfe..13d414384739 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -12,35 +12,17 @@
 #include "../../util/top.h"
 #include "../../arch/common.h"
 
-#include "../browser.h"
+#include "../browsers/hists.h"
 #include "../helpline.h"
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
 #include "annotate.h"
 
-struct hist_browser {
-        struct ui_browser   b;
-        struct hists        *hists;
-        struct hist_entry   *he_selection;
-        struct map_symbol   *selection;
-        struct hist_browser_timer *hbt;
-        struct pstack       *pstack;
-        struct perf_env *env;
-        int                  print_seq;
-        bool                 show_dso;
-        bool                 show_headers;
-        float                min_pcnt;
-        u64                  nr_non_filtered_entries;
-        u64                  nr_hierarchy_entries;
-        u64                  nr_callchain_rows;
-};
-
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists,
-                                struct hist_browser_timer *hbt,
-                                char *bf, size_t size);
+static int perf_evsel_browser_title(struct hist_browser *browser,
+                                    char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -585,7 +567,12 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
                 "Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser, const char *help)
+static int hist_browser__title(struct hist_browser *browser, char *bf, size_t size)
+{
+        return browser->title ? browser->title(browser, bf, size) : 0;
+}
+
+int hist_browser__run(struct hist_browser *browser, const char *help)
 {
         int key;
         char title[160];
@@ -595,7 +582,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
         browser->b.entries = &browser->hists->entries;
         browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-        hists__browser_title(browser->hists, hbt, title, sizeof(title));
+        hist_browser__title(browser, title, sizeof(title));
 
         if (ui_browser__show(&browser->b, title, "%s", help) < 0)
                 return -1;
@@ -621,8 +608,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
                                 ui_browser__warn_lost_events(&browser->b);
                         }
 
-                        hists__browser_title(browser->hists,
-                                             hbt, title, sizeof(title));
+                        hist_browser__title(browser, title, sizeof(title));
                         ui_browser__show_title(&browser->b, title);
                         continue;
                 }
@@ -1470,7 +1456,7 @@ static int hist_browser__show_no_entry(struct hist_browser *browser,
                     column++ < browser->b.horiz_scroll)
                         continue;
 
-                ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+                ret = fmt->width(fmt, NULL, browser->hists);
 
                 if (first) {
                         /* for folded sign */
@@ -1531,7 +1517,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
                 if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
                         continue;
 
-                ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+                ret = fmt->header(fmt, &dummy_hpp, hists);
                 if (advance_hpp_check(&dummy_hpp, ret))
                         break;
 
@@ -1568,7 +1554,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
                 if (column++ < browser->b.horiz_scroll)
                         continue;
 
-                ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+                ret = fmt->header(fmt, &dummy_hpp, hists);
                 if (advance_hpp_check(&dummy_hpp, ret))
                         break;
 
@@ -1605,7 +1591,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
                         }
                         first_col = false;
 
-                        ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+                        ret = fmt->header(fmt, &dummy_hpp, hists);
                         dummy_hpp.buf[ret] = '\0';
 
                         start = trim(dummy_hpp.buf);
@@ -1622,21 +1608,38 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
         return ret;
 }
 
-static void hist_browser__show_headers(struct hist_browser *browser)
+static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 {
         char headers[1024];
 
-        if (symbol_conf.report_hierarchy)
-                hists_browser__scnprintf_hierarchy_headers(browser, headers,
-                                                           sizeof(headers));
-        else
-                hists_browser__scnprintf_headers(browser, headers,
-                                                 sizeof(headers));
+        hists_browser__scnprintf_hierarchy_headers(browser, headers,
+                                                   sizeof(headers));
+
+        ui_browser__gotorc(&browser->b, 0, 0);
+        ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+        ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+}
+
+static void hists_browser__headers(struct hist_browser *browser)
+{
+        char headers[1024];
+
+        hists_browser__scnprintf_headers(browser, headers,
+                                         sizeof(headers));
+
         ui_browser__gotorc(&browser->b, 0, 0);
         ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
         ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
 }
 
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+        if (symbol_conf.report_hierarchy)
+                hists_browser__hierarchy_headers(browser);
+        else
+                hists_browser__headers(browser);
+}
+
 static void ui_browser__hists_init_top(struct ui_browser *browser)
 {
         if (browser->top == NULL) {
@@ -2026,7 +2029,7 @@ static int hist_browser__dump(struct hist_browser *browser)
         fp = fopen(filename, "w");
         if (fp == NULL) {
                 char bf[64];
-                const char *err = strerror_r(errno, bf, sizeof(bf));
+                const char *err = str_error_r(errno, bf, sizeof(bf));
                 ui_helpline__fpush("Couldn't write to %s: %s", filename, err);
                 return -1;
         }
@@ -2039,27 +2042,50 @@ static int hist_browser__dump(struct hist_browser *browser)
         return 0;
 }
 
-static struct hist_browser *hist_browser__new(struct hists *hists,
-                                              struct hist_browser_timer *hbt,
-                                              struct perf_env *env)
+void hist_browser__init(struct hist_browser *browser,
+                        struct hists *hists)
+{
+        struct perf_hpp_fmt *fmt;
+
+        browser->hists                  = hists;
+        browser->b.refresh              = hist_browser__refresh;
+        browser->b.refresh_dimensions   = hist_browser__refresh_dimensions;
+        browser->b.seek                 = ui_browser__hists_seek;
+        browser->b.use_navkeypressed    = true;
+        browser->show_headers           = symbol_conf.show_hist_headers;
+
+        hists__for_each_format(hists, fmt) {
+                perf_hpp__reset_width(fmt, hists);
+                ++browser->b.columns;
+        }
+}
+
+struct hist_browser *hist_browser__new(struct hists *hists)
 {
         struct hist_browser *browser = zalloc(sizeof(*browser));
 
+        if (browser)
+                hist_browser__init(browser, hists);
+
+        return browser;
+}
+
+static struct hist_browser *
+perf_evsel_browser__new(struct perf_evsel *evsel,
+                        struct hist_browser_timer *hbt,
+                        struct perf_env *env)
+{
+        struct hist_browser *browser = hist_browser__new(evsel__hists(evsel));
+
         if (browser) {
-                browser->hists = hists;
-                browser->b.refresh = hist_browser__refresh;
-                browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
-                browser->b.seek = ui_browser__hists_seek;
-                browser->b.use_navkeypressed = true;
-                browser->show_headers = symbol_conf.show_hist_headers;
-                browser->hbt = hbt;
-                browser->env = env;
+                browser->hbt   = hbt;
+                browser->env   = env;
+                browser->title = perf_evsel_browser_title;
         }
-
         return browser;
 }
 
-static void hist_browser__delete(struct hist_browser *browser)
+void hist_browser__delete(struct hist_browser *browser)
 {
         free(browser);
 }
@@ -2080,10 +2106,11 @@ static inline bool is_report_browser(void *timer)
         return timer == NULL;
 }
 
-static int hists__browser_title(struct hists *hists,
-                                struct hist_browser_timer *hbt,
+static int perf_evsel_browser_title(struct hist_browser *browser,
                                 char *bf, size_t size)
 {
+        struct hist_browser_timer *hbt = browser->hbt;
+        struct hists *hists = browser->hists;
         char unit;
         int printed;
         const struct dso *dso = hists->dso_filter;
@@ -2640,7 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     struct perf_env *env)
 {
         struct hists *hists = evsel__hists(evsel);
-        struct hist_browser *browser = hist_browser__new(hists, hbt, env);
+        struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
         struct branch_info *bi;
 #define MAX_OPTIONS  16
         char *options[MAX_OPTIONS];
@@ -2649,7 +2676,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         int key = -1;
         char buf[64];
         int delay_secs = hbt ? hbt->refresh : 0;
-        struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON                                        \
         "h/?/F1        Show this window\n"                              \
@@ -2708,18 +2734,6 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         memset(options, 0, sizeof(options));
         memset(actions, 0, sizeof(actions));
 
-        hists__for_each_format(browser->hists, fmt) {
-                perf_hpp__reset_width(fmt, hists);
-                /*
-                 * This is done just once, and activates the horizontal scrolling
-                 * code in the ui_browser code, it would be better to have a the
-                 * counter in the perf_hpp code, but I couldn't find doing it here
-                 * works, FIXME by setting this in hist_browser__new, for now, be
-                 * clever 8-)
-                 */
-                ++browser->b.columns;
-        }
-
         if (symbol_conf.col_width_list_str)
                 perf_hpp__set_user_width(symbol_conf.col_width_list_str);
 
@@ -3185,7 +3199,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
         ui_helpline__push("Press ESC to exit");
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 const char *ev_name = perf_evsel__name(pos);
                 size_t line_len = strlen(ev_name) + 7;
 
@@ -3216,7 +3230,7 @@ single_entry:
                 struct perf_evsel *pos;
 
                 nr_entries = 0;
-                evlist__for_each(evlist, pos) {
+                evlist__for_each_entry(evlist, pos) {
                         if (perf_evsel__is_group_leader(pos))
                                 nr_entries++;
                 }
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
new file mode 100644
index 000000000000..39bd0f28f211
--- /dev/null
+++ b/tools/perf/ui/browsers/hists.h
@@ -0,0 +1,32 @@
+#ifndef _PERF_UI_BROWSER_HISTS_H_
+#define _PERF_UI_BROWSER_HISTS_H_ 1
+
+#include "ui/browser.h"
+
+struct hist_browser {
+        struct ui_browser   b;
+        struct hists        *hists;
+        struct hist_entry   *he_selection;
+        struct map_symbol   *selection;
+        struct hist_browser_timer *hbt;
+        struct pstack       *pstack;
+        struct perf_env     *env;
+        int                  print_seq;
+        bool                 show_dso;
+        bool                 show_headers;
+        float                min_pcnt;
+        u64                  nr_non_filtered_entries;
+        u64                  nr_hierarchy_entries;
+        u64                  nr_callchain_rows;
+
+        /* Get title string. */
+        int                  (*title)(struct hist_browser *browser,
+                             char *bf, size_t size);
+};
+
+struct hist_browser *hist_browser__new(struct hists *hists);
+void hist_browser__delete(struct hist_browser *browser);
+int hist_browser__run(struct hist_browser *browser, const char *help);
+void hist_browser__init(struct hist_browser *browser,
+                        struct hists *hists);
+#endif /* _PERF_UI_BROWSER_HISTS_H_ */
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 9c7ff8d31b27..42d319927762 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -162,12 +162,16 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
         GtkWidget *notebook;
         GtkWidget *scrolled_window;
         GtkWidget *tab_label;
+        int err;
 
         if (map->dso->annotate_warned)
                 return -1;
 
-        if (symbol__annotate(sym, map, 0) < 0) {
-                ui__error("%s", ui_helpline__current);
+        err = symbol__disassemble(sym, map, 0);
+        if (err) {
+                char msg[BUFSIZ];
+                symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
+                ui__error("Couldn't annotate %s: %s\n", sym->name, msg);
                 return -1;
         }
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 932adfaa05af..c5f3677f6679 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
                                 strcat(buf, "+");
                         first_col = false;
 
-                        fmt->header(fmt, &hpp, hists_to_evsel(hists));
+                        fmt->header(fmt, &hpp, hists);
                         strcat(buf, ltrim(rtrim(hpp.buf)));
                 }
         }
@@ -627,7 +627,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
         gtk_container_add(GTK_CONTAINER(window), vbox);
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 struct hists *hists = evsel__hists(pos);
                 const char *evname = perf_evsel__name(pos);
                 GtkWidget *scrolled_window;
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 52e7fc48af9f..00b91921edb1 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,4 +1,5 @@
 #include "../util.h"
+#include "../../util/util.h"
 #include "../../util/debug.h"
 #include "gtk.h"
 
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 700fb3cfa1c7..5b74a7eba210 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -5,6 +5,7 @@
 #include "../debug.h"
 #include "helpline.h"
 #include "ui.h"
+#include "../util.h"
 
 char ui_helpline__current[512];
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index af07ffb129ca..4274969ddc89 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -215,9 +215,10 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 
 static int hpp__width_fn(struct perf_hpp_fmt *fmt,
                          struct perf_hpp *hpp __maybe_unused,
-                         struct perf_evsel *evsel)
+                         struct hists *hists)
 {
         int len = fmt->user_len ?: fmt->len;
+        struct perf_evsel *evsel = hists_to_evsel(hists);
 
         if (symbol_conf.event_group)
                 len = max(len, evsel->nr_members * fmt->len);
@@ -229,9 +230,9 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                          struct perf_evsel *evsel)
+                          struct hists *hists)
 {
-        int len = hpp__width_fn(fmt, hpp, evsel);
+        int len = hpp__width_fn(fmt, hpp, hists);
         return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
@@ -632,7 +633,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
                 else
                         ret += 2;
 
-                ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+                ret += fmt->width(fmt, &dummy_hpp, hists);
         }
 
         if (verbose && hists__has(hists, sym)) /* Addr + origin */
@@ -657,7 +658,7 @@ unsigned int hists__overhead_width(struct hists *hists)
                 else
                         ret += 2;
 
-                ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+                ret += fmt->width(fmt, &dummy_hpp, hists);
         }
 
         return ret;
@@ -765,7 +766,7 @@ int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
         if (!symbol_conf.report_hierarchy)
                 return 0;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 hists = evsel__hists(evsel);
 
                 perf_hpp_list__for_each_sort_list(list, fmt) {
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ba51fa8a1176..1f6b0994f4f4 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -60,6 +60,13 @@ static inline int setup_gtk_browser(void) { return -1; }
 static inline void exit_gtk_browser(bool wait_for_ok __maybe_unused) {}
 #endif
 
+int stdio__config_color(const struct option *opt __maybe_unused,
+                        const char *mode, int unset __maybe_unused)
+{
+        perf_use_color_default = perf_config_colorbool("color.ui", mode, -1);
+        return 0;
+}
+
 void setup_browser(bool fallback_to_pager)
 {
         if (use_browser < 2 && (!isatty(1) || dump_trace))
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 560eb47d56f9..f04a63112079 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -492,14 +492,15 @@ out:
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
-                               struct hists *hists,
-                               char *bf, size_t bfsz, FILE *fp)
+                               char *bf, size_t bfsz, FILE *fp,
+                               bool use_callchain)
 {
         int ret;
         struct perf_hpp hpp = {
                 .buf            = bf,
                 .size           = size,
         };
+        struct hists *hists = he->hists;
         u64 total_period = hists->stats.total_period;
 
         if (size == 0 || size > bfsz)
@@ -512,7 +513,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
         ret = fprintf(fp, "%s\n", bf);
 
-        if (symbol_conf.use_callchain)
+        if (use_callchain)
                 ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
         return ret;
@@ -548,7 +549,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
                                     struct perf_hpp_list_node, list);
 
         perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-                fmt->header(fmt, hpp, hists_to_evsel(hists));
+                fmt->header(fmt, hpp, hists);
                 fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
         }
 
@@ -568,7 +569,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
                                 header_width += fprintf(fp, "+");
                         first_col = false;
 
-                        fmt->header(fmt, hpp, hists_to_evsel(hists));
+                        fmt->header(fmt, hpp, hists);
 
                         header_width += fprintf(fp, "%s", trim(hpp->buf));
                 }
@@ -589,7 +590,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
                         fprintf(fp, "%s", sep ?: "..");
                 first_col = false;
 
-                width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+                width = fmt->width(fmt, hpp, hists);
                 fprintf(fp, "%.*s", width, dots);
         }
 
@@ -606,7 +607,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
                                 width++;  /* for '+' sign between column header */
                         first_col = false;
 
-                        width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+                        width += fmt->width(fmt, hpp, hists);
                 }
 
                 if (width > header_width)
@@ -622,47 +623,31 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
         return 2;
 }
 
-size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-                      int max_cols, float min_pcnt, FILE *fp)
+static int
+hists__fprintf_hierarchy_headers(struct hists *hists,
+                                 struct perf_hpp *hpp,
+                                 FILE *fp)
 {
-        struct perf_hpp_fmt *fmt;
         struct perf_hpp_list_node *fmt_node;
-        struct rb_node *nd;
-        size_t ret = 0;
-        unsigned int width;
-        const char *sep = symbol_conf.field_sep;
-        int nr_rows = 0;
-        char bf[96];
-        struct perf_hpp dummy_hpp = {
-                .buf    = bf,
-                .size   = sizeof(bf),
-        };
-        bool first = true;
-        size_t linesz;
-        char *line = NULL;
-        unsigned indent;
-
-        init_rem_hits();
-
-        hists__for_each_format(hists, fmt)
-                perf_hpp__reset_width(fmt, hists);
-
-        if (symbol_conf.col_width_list_str)
-                perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+        struct perf_hpp_fmt *fmt;
 
-        if (!show_header)
-                goto print_entries;
+        list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+                perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+                        perf_hpp__reset_width(fmt, hists);
+        }
 
-        fprintf(fp, "# ");
+        return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
+}
 
-        if (symbol_conf.report_hierarchy) {
-                list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
-                        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
-                                perf_hpp__reset_width(fmt, hists);
-                }
-                nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
-                goto print_entries;
-        }
+static int
+hists__fprintf_standard_headers(struct hists *hists,
+                                struct perf_hpp *hpp,
+                                FILE *fp)
+{
+        struct perf_hpp_fmt *fmt;
+        unsigned int width;
+        const char *sep = symbol_conf.field_sep;
+        bool first = true;
 
         hists__for_each_format(hists, fmt) {
                 if (perf_hpp__should_skip(fmt, hists))
@@ -673,16 +658,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 else
                         first = false;
 
-                fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
-                fprintf(fp, "%s", bf);
+                fmt->header(fmt, hpp, hists);
+                fprintf(fp, "%s", hpp->buf);
         }
 
         fprintf(fp, "\n");
-        if (max_rows && ++nr_rows >= max_rows)
-                goto out;
 
         if (sep)
-                goto print_entries;
+                return 1;
 
         first = true;
 
@@ -699,20 +682,60 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                 else
                         first = false;
 
-                width = fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
+                width = fmt->width(fmt, hpp, hists);
                 for (i = 0; i < width; i++)
                         fprintf(fp, ".");
         }
 
         fprintf(fp, "\n");
-        if (max_rows && ++nr_rows >= max_rows)
-                goto out;
-
         fprintf(fp, "#\n");
-        if (max_rows && ++nr_rows >= max_rows)
+        return 3;
+}
+
+static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+{
+        char bf[96];
+        struct perf_hpp dummy_hpp = {
+                .buf    = bf,
+                .size   = sizeof(bf),
+        };
+
+        fprintf(fp, "# ");
+
+        if (symbol_conf.report_hierarchy)
+                return hists__fprintf_hierarchy_headers(hists, &dummy_hpp, fp);
+        else
+                return hists__fprintf_standard_headers(hists, &dummy_hpp, fp);
+
+}
+
+size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
+                      int max_cols, float min_pcnt, FILE *fp,
+                      bool use_callchain)
+{
+        struct perf_hpp_fmt *fmt;
+        struct rb_node *nd;
+        size_t ret = 0;
+        const char *sep = symbol_conf.field_sep;
+        int nr_rows = 0;
+        size_t linesz;
+        char *line = NULL;
+        unsigned indent;
+
+        init_rem_hits();
+
+        hists__for_each_format(hists, fmt)
+                perf_hpp__reset_width(fmt, hists);
+
+        if (symbol_conf.col_width_list_str)
+                perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
+        if (show_header)
+                nr_rows += hists__fprintf_headers(hists, fp);
+
+        if (max_rows && nr_rows >= max_rows)
                 goto out;
 
-print_entries:
         linesz = hists__sort_list_width(hists) + 3 + 1;
         linesz += perf_hpp__color_overhead();
         line = malloc(linesz);
@@ -734,7 +757,7 @@ print_entries:
                 if (percent < min_pcnt)
                         continue;
 
-                ret += hist_entry__fprintf(h, max_cols, hists, line, linesz, fp);
+                ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
 
                 if (max_rows && ++nr_rows >= max_rows)
                         break;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 7dfeba0a91f3..4ea2ba861fc2 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,3 +1,4 @@
+#include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
@@ -6,6 +7,7 @@
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
+#include "../../util/util.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index ab88383f8be8..4b6fb6c7a542 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -26,4 +26,8 @@ static inline void ui__exit(bool wait_for_ok __maybe_unused) {}
 
 void ui__refresh_dimensions(bool force);
 
+struct option;
+
+int stdio__config_color(const struct option *opt, const char *mode, int unset);
+
 #endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8c6c8a0ca642..91c5f6e1af59 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -84,6 +84,7 @@ libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
 libperf-y += mem-events.o
+libperf-y += vsprintf.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -99,7 +100,10 @@ libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
 
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+libperf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind-local.o
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
+libperf-$(CONFIG_LIBUNWIND_X86)      += libunwind/x86_32.o
+libperf-$(CONFIG_LIBUNWIND_AARCH64)  += libunwind/arm64.o
 
 libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
 
@@ -108,6 +112,7 @@ libperf-y += scripting-engines/
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 libperf-y += demangle-java.o
+libperf-y += demangle-rust.o
 
 ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
@@ -173,3 +178,7 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE
 $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index c0b43ee40d95..6455471d9cd1 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -1,4 +1,6 @@
 #include "cache.h"
+#include "util.h"
+#include "config.h"
 
 static const char *alias_key;
 static char *alias_val;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7e5a1e8874ce..4024d309bb00 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,6 +354,15 @@ static struct ins_ops nop_ops = {
         .scnprintf = nop__scnprintf,
 };
 
+static struct ins_ops ret_ops = {
+        .scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_ret(const struct ins *ins)
+{
+        return ins->ops == &ret_ops;
+}
+
 static struct ins instructions[] = {
         { .name = "add",   .ops  = &mov_ops, },
         { .name = "addl",  .ops  = &mov_ops, },
@@ -444,6 +453,7 @@ static struct ins instructions[] = {
         { .name = "xadd",  .ops  = &mov_ops, },
         { .name = "xbeginl", .ops  = &jump_ops, },
         { .name = "xbeginq", .ops  = &jump_ops, },
+        { .name = "retq",  .ops  = &ret_ops, },
 };
 
 static int ins__key_cmp(const void *name, const void *insp)
@@ -1113,7 +1123,46 @@ static void delete_last_nop(struct symbol *sym)
         }
 }
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *map,
+                              int errnum, char *buf, size_t buflen)
+{
+        struct dso *dso = map->dso;
+
+        BUG_ON(buflen == 0);
+
+        if (errnum >= 0) {
+                str_error_r(errnum, buf, buflen);
+                return 0;
+        }
+
+        switch (errnum) {
+        case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
+                char bf[SBUILD_ID_SIZE + 15] = " with build id ";
+                char *build_id_msg = NULL;
+
+                if (dso->has_build_id) {
+                        build_id__sprintf(dso->build_id,
+                                          sizeof(dso->build_id), bf + 15);
+                        build_id_msg = bf;
+                }
+                scnprintf(buf, buflen,
+                          "No vmlinux file%s\nwas found in the path.\n\n"
+                          "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
+                          "Please use:\n\n"
+                          "  perf buildid-cache -vu vmlinux\n\n"
+                          "or:\n\n"
+                          "  --vmlinux vmlinux\n", build_id_msg ?: "");
+        }
+                break;
+        default:
+                scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
+                break;
+        }
+
+        return 0;
+}
+
+int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize)
 {
         struct dso *dso = map->dso;
         char *filename = dso__build_id_filename(dso, NULL, 0);
@@ -1124,22 +1173,20 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
         char symfs_filename[PATH_MAX];
         struct kcore_extract kce;
         bool delete_extract = false;
+        int stdout_fd[2];
         int lineno = 0;
         int nline;
+        pid_t pid;
 
         if (filename)
                 symbol__join_symfs(symfs_filename, filename);
 
         if (filename == NULL) {
-                if (dso->has_build_id) {
-                        pr_err("Can't annotate %s: not enough memory\n",
-                               sym->name);
-                        return -ENOMEM;
-                }
-                goto fallback;
-        } else if (dso__is_kcore(dso)) {
+                if (dso->has_build_id)
+                        return ENOMEM;
                 goto fallback;
-        } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+        } else if (dso__is_kcore(dso) ||
+                   readlink(symfs_filename, command, sizeof(command)) < 0 ||
                    strstr(command, DSO__NAME_KALLSYMS) ||
                    access(symfs_filename, R_OK)) {
                 free(filename);
@@ -1156,27 +1203,7 @@ fallback:
 
         if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
             !dso__is_kcore(dso)) {
-                char bf[SBUILD_ID_SIZE + 15] = " with build id ";
-                char *build_id_msg = NULL;
-
-                if (dso->annotate_warned)
-                        goto out_free_filename;
-
-                if (dso->has_build_id) {
-                        build_id__sprintf(dso->build_id,
-                                          sizeof(dso->build_id), bf + 15);
-                        build_id_msg = bf;
-                }
-                err = -ENOENT;
-                dso->annotate_warned = 1;
-                pr_err("Can't annotate %s:\n\n"
-                       "No vmlinux file%s\nwas found in the path.\n\n"
-                       "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
-                       "Please use:\n\n"
-                       "  perf buildid-cache -vu vmlinux\n\n"
-                       "or:\n\n"
-                       "  --vmlinux vmlinux\n",
-                       sym->name, build_id_msg ?: "");
+                err = SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
                 goto out_free_filename;
         }
 
@@ -1248,9 +1275,32 @@ fallback:
 
         pr_debug("Executing: %s\n", command);
 
-        file = popen(command, "r");
+        err = -1;
+        if (pipe(stdout_fd) < 0) {
+                pr_err("Failure creating the pipe to run %s\n", command);
+                goto out_remove_tmp;
+        }
+
+        pid = fork();
+        if (pid < 0) {
+                pr_err("Failure forking to run %s\n", command);
+                goto out_close_stdout;
+        }
+
+        if (pid == 0) {
+                close(stdout_fd[0]);
+                dup2(stdout_fd[1], 1);
+                close(stdout_fd[1]);
+                execl("/bin/sh", "sh", "-c", command, NULL);
+                perror(command);
+                exit(-1);
+        }
+
+        close(stdout_fd[1]);
+
+        file = fdopen(stdout_fd[0], "r");
         if (!file) {
-                pr_err("Failure running %s\n", command);
+                pr_err("Failure creating FILE stream for %s\n", command);
                 /*
                  * If we were using debug info should retry with
                  * original binary.
@@ -1276,9 +1326,11 @@ fallback:
         if (dso__is_kcore(dso))
                 delete_last_nop(sym);
 
-        pclose(file);
-
+        fclose(file);
+        err = 0;
 out_remove_tmp:
+        close(stdout_fd[0]);
+
         if (dso__needs_decompress(dso))
                 unlink(symfs_filename);
 out_free_filename:
@@ -1287,6 +1339,10 @@ out_free_filename:
         if (free_filename)
                 free(filename);
         return err;
+
+out_close_stdout:
+        close(stdout_fd[1]);
+        goto out_remove_tmp;
 }
 
 static void insert_source_line(struct rb_root *root, struct source_line *src_line)
@@ -1512,13 +1568,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         const char *d_filename;
         const char *evsel_name = perf_evsel__name(evsel);
         struct annotation *notes = symbol__annotation(sym);
+        struct sym_hist *h = annotation__histogram(notes, evsel->idx);
         struct disasm_line *pos, *queue = NULL;
         u64 start = map__rip_2objdump(map, sym->start);
         int printed = 2, queue_len = 0;
         int more = 0;
         u64 len;
         int width = 8;
-        int namelen, evsel_name_len, graph_dotted_len;
+        int graph_dotted_len;
 
         filename = strdup(dso->long_name);
         if (!filename)
@@ -1530,17 +1587,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
                 d_filename = basename(filename);
 
         len = symbol__size(sym);
-        namelen = strlen(d_filename);
-        evsel_name_len = strlen(evsel_name);
 
         if (perf_evsel__is_group_event(evsel))
                 width *= evsel->nr_members;
 
-        printf(" %-*.*s|        Source code & Disassembly of %s for %s\n",
-               width, width, "Percent", d_filename, evsel_name);
+        graph_dotted_len = printf(" %-*.*s|     Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
+               width, width, "Percent", d_filename, evsel_name, h->sum);
 
-        graph_dotted_len = width + namelen + evsel_name_len;
-        printf("-%-*.*s-----------------------------------------\n",
+        printf("%-*.*s----\n",
                graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
         if (verbose)
@@ -1655,7 +1709,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
         struct rb_root source_line = RB_ROOT;
         u64 len;
 
-        if (symbol__annotate(sym, map, 0) < 0)
+        if (symbol__disassemble(sym, map, 0) < 0)
                 return -1;
 
         len = symbol__size(sym);
@@ -1676,11 +1730,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
         return 0;
 }
 
-int hist_entry__annotate(struct hist_entry *he, size_t privsize)
-{
-        return symbol__annotate(he->ms.sym, he->ms.map, privsize);
-}
-
 bool ui__has_annotation(void)
 {
         return use_browser == 1 && perf_hpp_list.sym;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 9241f8c2b7e1..f67ccb027561 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -48,6 +48,7 @@ struct ins {
 
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 
 struct annotation;
@@ -154,9 +155,27 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize);
 
-int hist_entry__annotate(struct hist_entry *he, size_t privsize);
+enum symbol_disassemble_errno {
+        SYMBOL_ANNOTATE_ERRNO__SUCCESS          = 0,
+
+        /*
+         * Choose an arbitrary negative big number not to clash with standard
+         * errno since SUS requires the errno has distinct positive values.
+         * See 'Issue 6' in the link below.
+         *
+         * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+         */
+        __SYMBOL_ANNOTATE_ERRNO__START          = -10000,
+
+        SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX       = __SYMBOL_ANNOTATE_ERRNO__START,
+
+        __SYMBOL_ANNOTATE_ERRNO__END,
+};
+
+int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
+                                 int errnum, char *buf, size_t buflen);
 
 int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 767989e0e312..ac5f0d7167e6 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -63,6 +63,7 @@ enum itrace_period_type {
  * @calls: limit branch samples to calls (can be combined with @returns)
  * @returns: limit branch samples to returns (can be combined with @calls)
  * @callchain: add callchain to 'instructions' events
+ * @thread_stack: feed branches to the thread_stack
  * @last_branch: add branch context to 'instruction' events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
@@ -82,6 +83,7 @@ struct itrace_synth_opts {
         bool                    calls;
         bool                    returns;
         bool                    callchain;
+        bool                    thread_stack;
         bool                    last_branch;
         unsigned int            callchain_sz;
         unsigned int            last_branch_sz;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 493307d1414c..1f12e4e40006 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -37,6 +37,9 @@ DEFINE_PRINT_FN(info, 1)
 DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
+        bool is_tp;
+        char *sys_name;
+        char *evt_name;
         struct perf_probe_event pev;
         bool need_prologue;
         struct bpf_insn *insns_buf;
@@ -118,6 +121,8 @@ clear_prog_priv(struct bpf_program *prog __maybe_unused,
         cleanup_perf_probe_events(&priv->pev, 1);
         zfree(&priv->insns_buf);
         zfree(&priv->type_mapping);
+        zfree(&priv->sys_name);
+        zfree(&priv->evt_name);
         free(priv);
 }
 
@@ -269,7 +274,8 @@ nextline:
 }
 
 static int
-parse_prog_config(const char *config_str, struct perf_probe_event *pev)
+parse_prog_config(const char *config_str, const char **p_main_str,
+                  bool *is_tp, struct perf_probe_event *pev)
 {
         int err;
         const char *main_str = parse_prog_config_kvpair(config_str, pev);
@@ -277,6 +283,22 @@ parse_prog_config(const char *config_str, struct perf_probe_event *pev)
         if (IS_ERR(main_str))
                 return PTR_ERR(main_str);
 
+        *p_main_str = main_str;
+        if (!strchr(main_str, '=')) {
+                /* Is a tracepoint event? */
+                const char *s = strchr(main_str, ':');
+
+                if (!s) {
+                        pr_debug("bpf: '%s' is not a valid tracepoint\n",
+                                 config_str);
+                        return -BPF_LOADER_ERRNO__CONFIG;
+                }
+
+                *is_tp = true;
+                return 0;
+        }
+
+        *is_tp = false;
         err = parse_perf_probe_command(main_str, pev);
         if (err < 0) {
                 pr_debug("bpf: '%s' is not a valid config string\n",
@@ -292,7 +314,8 @@ config_bpf_program(struct bpf_program *prog)
 {
         struct perf_probe_event *pev = NULL;
         struct bpf_prog_priv *priv = NULL;
-        const char *config_str;
+        const char *config_str, *main_str;
+        bool is_tp = false;
         int err;
 
         /* Initialize per-program probing setting */
@@ -313,10 +336,19 @@ config_bpf_program(struct bpf_program *prog)
         pev = &priv->pev;
 
         pr_debug("bpf: config program '%s'\n", config_str);
-        err = parse_prog_config(config_str, pev);
+        err = parse_prog_config(config_str, &main_str, &is_tp, pev);
         if (err)
                 goto errout;
 
+        if (is_tp) {
+                char *s = strchr(main_str, ':');
+
+                priv->is_tp = true;
+                priv->sys_name = strndup(main_str, s - main_str);
+                priv->evt_name = strdup(s + 1);
+                goto set_priv;
+        }
+
         if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
                 pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
                          config_str, PERF_BPF_PROBE_GROUP);
@@ -339,7 +371,8 @@ config_bpf_program(struct bpf_program *prog)
         }
         pr_debug("bpf: config '%s' is ok\n", config_str);
 
-        err = bpf_program__set_private(prog, priv, clear_prog_priv);
+set_priv:
+        err = bpf_program__set_priv(prog, priv, clear_prog_priv);
         if (err) {
                 pr_debug("Failed to set priv for program '%s'\n", config_str);
                 goto errout;
@@ -380,15 +413,14 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
                      struct bpf_insn *orig_insns, int orig_insns_cnt,
                      struct bpf_prog_prep_result *res)
 {
+        struct bpf_prog_priv *priv = bpf_program__priv(prog);
         struct probe_trace_event *tev;
         struct perf_probe_event *pev;
-        struct bpf_prog_priv *priv;
         struct bpf_insn *buf;
         size_t prologue_cnt = 0;
         int i, err;
 
-        err = bpf_program__get_private(prog, (void **)&priv);
-        if (err || !priv)
+        if (IS_ERR(priv) || !priv || priv->is_tp)
                 goto errout;
 
         pev = &priv->pev;
@@ -535,17 +567,21 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping,
 
 static int hook_load_preprocessor(struct bpf_program *prog)
 {
+        struct bpf_prog_priv *priv = bpf_program__priv(prog);
         struct perf_probe_event *pev;
-        struct bpf_prog_priv *priv;
         bool need_prologue = false;
         int err, i;
 
-        err = bpf_program__get_private(prog, (void **)&priv);
-        if (err || !priv) {
+        if (IS_ERR(priv) || !priv) {
                 pr_debug("Internal error when hook preprocessor\n");
                 return -BPF_LOADER_ERRNO__INTERNAL;
         }
 
+        if (priv->is_tp) {
+                priv->need_prologue = false;
+                return 0;
+        }
+
         pev = &priv->pev;
         for (i = 0; i < pev->ntevs; i++) {
                 struct probe_trace_event *tev = &pev->tevs[i];
@@ -607,9 +643,18 @@ int bpf__probe(struct bpf_object *obj)
                 if (err)
                         goto out;
 
-                err = bpf_program__get_private(prog, (void **)&priv);
-                if (err || !priv)
+                priv = bpf_program__priv(prog);
+                if (IS_ERR(priv) || !priv) {
+                        err = PTR_ERR(priv);
                         goto out;
+                }
+
+                if (priv->is_tp) {
+                        bpf_program__set_tracepoint(prog);
+                        continue;
+                }
+
+                bpf_program__set_kprobe(prog);
                 pev = &priv->pev;
 
                 err = convert_perf_probe_events(pev, 1);
@@ -645,13 +690,12 @@ int bpf__unprobe(struct bpf_object *obj)
 {
         int err, ret = 0;
         struct bpf_program *prog;
-        struct bpf_prog_priv *priv;
 
         bpf_object__for_each_program(prog, obj) {
+                struct bpf_prog_priv *priv = bpf_program__priv(prog);
                 int i;
 
-                err = bpf_program__get_private(prog, (void **)&priv);
-                if (err || !priv)
+                if (IS_ERR(priv) || !priv || priv->is_tp)
                         continue;
 
                 for (i = 0; i < priv->pev.ntevs; i++) {
@@ -694,26 +738,34 @@ int bpf__load(struct bpf_object *obj)
         return 0;
 }
 
-int bpf__foreach_tev(struct bpf_object *obj,
-                     bpf_prog_iter_callback_t func,
-                     void *arg)
+int bpf__foreach_event(struct bpf_object *obj,
+                       bpf_prog_iter_callback_t func,
+                       void *arg)
 {
         struct bpf_program *prog;
         int err;
 
         bpf_object__for_each_program(prog, obj) {
+                struct bpf_prog_priv *priv = bpf_program__priv(prog);
                 struct probe_trace_event *tev;
                 struct perf_probe_event *pev;
-                struct bpf_prog_priv *priv;
                 int i, fd;
 
-                err = bpf_program__get_private(prog,
-                                (void **)&priv);
-                if (err || !priv) {
+                if (IS_ERR(priv) || !priv) {
                         pr_debug("bpf: failed to get private field\n");
                         return -BPF_LOADER_ERRNO__INTERNAL;
                 }
 
+                if (priv->is_tp) {
+                        fd = bpf_program__fd(prog);
+                        err = (*func)(priv->sys_name, priv->evt_name, fd, arg);
+                        if (err) {
+                                pr_debug("bpf: tracepoint call back failed, stop iterate\n");
+                                return err;
+                        }
+                        continue;
+                }
+
                 pev = &priv->pev;
                 for (i = 0; i < pev->ntevs; i++) {
                         tev = &pev->tevs[i];
@@ -731,7 +783,7 @@ int bpf__foreach_tev(struct bpf_object *obj,
                                 return fd;
                         }
 
-                        err = (*func)(tev, fd, arg);
+                        err = (*func)(tev->group, tev->event, fd, arg);
                         if (err) {
                                 pr_debug("bpf: call back failed, stop iterate\n");
                                 return err;
@@ -897,15 +949,12 @@ bpf_map_priv__clone(struct bpf_map_priv *priv)
 static int
 bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
 {
-        struct bpf_map_priv *priv;
-        const char *map_name;
-        int err;
+        const char *map_name = bpf_map__name(map);
+        struct bpf_map_priv *priv = bpf_map__priv(map);
 
-        map_name = bpf_map__get_name(map);
-        err = bpf_map__get_private(map, (void **)&priv);
-        if (err) {
+        if (IS_ERR(priv)) {
                 pr_debug("Failed to get private from map %s\n", map_name);
-                return err;
+                return PTR_ERR(priv);
         }
 
         if (!priv) {
@@ -916,7 +965,7 @@ bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
                 }
                 INIT_LIST_HEAD(&priv->ops_list);
 
-                if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+                if (bpf_map__set_priv(map, priv, bpf_map_priv__clear)) {
                         free(priv);
                         return -BPF_LOADER_ERRNO__INTERNAL;
                 }
@@ -948,30 +997,26 @@ static int
 __bpf_map__config_value(struct bpf_map *map,
                         struct parse_events_term *term)
 {
-        struct bpf_map_def def;
         struct bpf_map_op *op;
-        const char *map_name;
-        int err;
+        const char *map_name = bpf_map__name(map);
+        const struct bpf_map_def *def = bpf_map__def(map);
 
-        map_name = bpf_map__get_name(map);
-
-        err = bpf_map__get_def(map, &def);
-        if (err) {
+        if (IS_ERR(def)) {
                 pr_debug("Unable to get map definition from '%s'\n",
                          map_name);
                 return -BPF_LOADER_ERRNO__INTERNAL;
         }
 
-        if (def.type != BPF_MAP_TYPE_ARRAY) {
+        if (def->type != BPF_MAP_TYPE_ARRAY) {
                 pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
                          map_name);
                 return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
         }
-        if (def.key_size < sizeof(unsigned int)) {
+        if (def->key_size < sizeof(unsigned int)) {
                 pr_debug("Map %s has incorrect key size\n", map_name);
                 return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
         }
-        switch (def.value_size) {
+        switch (def->value_size) {
         case 1:
         case 2:
         case 4:
@@ -1014,12 +1059,10 @@ __bpf_map__config_event(struct bpf_map *map,
                         struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
-        struct bpf_map_def def;
+        const struct bpf_map_def *def;
         struct bpf_map_op *op;
-        const char *map_name;
-        int err;
+        const char *map_name = bpf_map__name(map);
 
-        map_name = bpf_map__get_name(map);
         evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
         if (!evsel) {
                 pr_debug("Event (for '%s') '%s' doesn't exist\n",
@@ -1027,18 +1070,18 @@ __bpf_map__config_event(struct bpf_map *map,
                 return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
         }
 
-        err = bpf_map__get_def(map, &def);
-        if (err) {
+        def = bpf_map__def(map);
+        if (IS_ERR(def)) {
                 pr_debug("Unable to get map definition from '%s'\n",
                          map_name);
-                return err;
+                return PTR_ERR(def);
         }
 
         /*
          * No need to check key_size and value_size:
          * kernel has already checked them.
          */
-        if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+        if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
                 pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
                          map_name);
                 return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
@@ -1087,9 +1130,8 @@ config_map_indices_range_check(struct parse_events_term *term,
                                const char *map_name)
 {
         struct parse_events_array *array = &term->array;
-        struct bpf_map_def def;
+        const struct bpf_map_def *def;
         unsigned int i;
-        int err;
 
         if (!array->nr_ranges)
                 return 0;
@@ -1099,8 +1141,8 @@ config_map_indices_range_check(struct parse_events_term *term,
                 return -BPF_LOADER_ERRNO__INTERNAL;
         }
 
-        err = bpf_map__get_def(map, &def);
-        if (err) {
+        def = bpf_map__def(map);
+        if (IS_ERR(def)) {
                 pr_debug("ERROR: Unable to get map definition from '%s'\n",
                          map_name);
                 return -BPF_LOADER_ERRNO__INTERNAL;
@@ -1111,7 +1153,7 @@ config_map_indices_range_check(struct parse_events_term *term,
                 size_t length = array->ranges[i].length;
                 unsigned int idx = start + length - 1;
 
-                if (idx >= def.max_entries) {
+                if (idx >= def->max_entries) {
                         pr_debug("ERROR: index %d too large\n", idx);
                         return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
                 }
@@ -1147,7 +1189,7 @@ bpf__obj_config_map(struct bpf_object *obj,
                 goto out;
         }
 
-        map = bpf_object__get_map_by_name(obj, map_name);
+        map = bpf_object__find_map_by_name(obj, map_name);
         if (!map) {
                 pr_debug("ERROR: Map %s doesn't exist\n", map_name);
                 err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
@@ -1204,14 +1246,14 @@ out:
 }
 
 typedef int (*map_config_func_t)(const char *name, int map_fd,
-                                 struct bpf_map_def *pdef,
+                                 const struct bpf_map_def *pdef,
                                  struct bpf_map_op *op,
                                  void *pkey, void *arg);
 
 static int
 foreach_key_array_all(map_config_func_t func,
                       void *arg, const char *name,
-                      int map_fd, struct bpf_map_def *pdef,
+                      int map_fd, const struct bpf_map_def *pdef,
                       struct bpf_map_op *op)
 {
         unsigned int i;
@@ -1231,7 +1273,7 @@ foreach_key_array_all(map_config_func_t func,
 static int
 foreach_key_array_ranges(map_config_func_t func, void *arg,
                          const char *name, int map_fd,
-                         struct bpf_map_def *pdef,
+                         const struct bpf_map_def *pdef,
                          struct bpf_map_op *op)
 {
         unsigned int i, j;
@@ -1261,15 +1303,12 @@ bpf_map_config_foreach_key(struct bpf_map *map,
                            void *arg)
 {
         int err, map_fd;
-        const char *name;
         struct bpf_map_op *op;
-        struct bpf_map_def def;
-        struct bpf_map_priv *priv;
+        const struct bpf_map_def *def;
+        const char *name = bpf_map__name(map);
+        struct bpf_map_priv *priv = bpf_map__priv(map);
 
-        name = bpf_map__get_name(map);
-
-        err = bpf_map__get_private(map, (void **)&priv);
-        if (err) {
+        if (IS_ERR(priv)) {
                 pr_debug("ERROR: failed to get private from map %s\n", name);
                 return -BPF_LOADER_ERRNO__INTERNAL;
         }
@@ -1278,29 +1317,29 @@ bpf_map_config_foreach_key(struct bpf_map *map,
                 return 0;
         }
 
-        err = bpf_map__get_def(map, &def);
-        if (err) {
+        def = bpf_map__def(map);
+        if (IS_ERR(def)) {
                 pr_debug("ERROR: failed to get definition from map %s\n", name);
                 return -BPF_LOADER_ERRNO__INTERNAL;
         }
-        map_fd = bpf_map__get_fd(map);
+        map_fd = bpf_map__fd(map);
         if (map_fd < 0) {
                 pr_debug("ERROR: failed to get fd from map %s\n", name);
                 return map_fd;
         }
 
         list_for_each_entry(op, &priv->ops_list, list) {
-                switch (def.type) {
+                switch (def->type) {
                 case BPF_MAP_TYPE_ARRAY:
                 case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
                         switch (op->key_type) {
                         case BPF_MAP_KEY_ALL:
                                 err = foreach_key_array_all(func, arg, name,
-                                                            map_fd, &def, op);
+                                                            map_fd, def, op);
                                 break;
                         case BPF_MAP_KEY_RANGES:
                                 err = foreach_key_array_ranges(func, arg, name,
-                                                               map_fd, &def,
+                                                               map_fd, def,
                                                                op);
                                 break;
                         default:
@@ -1410,7 +1449,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
 
 static int
 apply_obj_config_map_for_key(const char *name, int map_fd,
-                             struct bpf_map_def *pdef __maybe_unused,
+                             const struct bpf_map_def *pdef,
                              struct bpf_map_op *op,
                              void *pkey, void *arg __maybe_unused)
 {
@@ -1475,9 +1514,9 @@ int bpf__apply_obj_config(void)
 
 #define bpf__for_each_stdout_map(pos, obj, objtmp)      \
         bpf__for_each_map(pos, obj, objtmp)             \
-                if (bpf_map__get_name(pos) &&           \
+                if (bpf_map__name(pos) &&               \
                         (strcmp("__bpf_stdout__",       \
-                                bpf_map__get_name(pos)) == 0))
+                                bpf_map__name(pos)) == 0))
 
 int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 {
@@ -1489,10 +1528,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
         bool need_init = false;
 
         bpf__for_each_stdout_map(map, obj, tmp) {
-                struct bpf_map_priv *priv;
+                struct bpf_map_priv *priv = bpf_map__priv(map);
 
-                err = bpf_map__get_private(map, (void **)&priv);
-                if (err)
+                if (IS_ERR(priv))
                         return -BPF_LOADER_ERRNO__INTERNAL;
 
                 /*
@@ -1520,10 +1558,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
         }
 
         bpf__for_each_stdout_map(map, obj, tmp) {
-                struct bpf_map_priv *priv;
+                struct bpf_map_priv *priv = bpf_map__priv(map);
 
-                err = bpf_map__get_private(map, (void **)&priv);
-                if (err)
+                if (IS_ERR(priv))
                         return -BPF_LOADER_ERRNO__INTERNAL;
                 if (priv)
                         continue;
@@ -1533,7 +1570,7 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
                         if (!priv)
                                 return -ENOMEM;
 
-                        err = bpf_map__set_private(map, priv, bpf_map_priv__clear);
+                        err = bpf_map__set_priv(map, priv, bpf_map_priv__clear);
                         if (err) {
                                 bpf_map_priv__clear(map, priv);
                                 return err;
@@ -1607,7 +1644,7 @@ bpf_loader_strerror(int err, char *buf, size_t size)
                 snprintf(buf, size, "Unknown bpf loader error %d", err);
         else
                 snprintf(buf, size, "%s",
-                         strerror_r(err, sbuf, sizeof(sbuf)));
+                         str_error_r(err, sbuf, sizeof(sbuf)));
 
         buf[size - 1] = '\0';
         return -1;
@@ -1677,7 +1714,7 @@ int bpf__strerror_load(struct bpf_object *obj,
 {
         bpf__strerror_head(err, buf, size);
         case LIBBPF_ERRNO__KVER: {
-                unsigned int obj_kver = bpf_object__get_kversion(obj);
+                unsigned int obj_kver = bpf_object__kversion(obj);
                 unsigned int real_kver;
 
                 if (fetch_kernel_version(&real_kver, NULL, 0)) {
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 941e17275aa7..f2b737b225f2 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -46,7 +46,7 @@ struct bpf_object;
 struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
-typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
+typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event,
                                         int fd, void *arg);
 
 #ifdef HAVE_LIBBPF_SUPPORT
@@ -67,8 +67,8 @@ int bpf__strerror_probe(struct bpf_object *obj, int err,
 int bpf__load(struct bpf_object *obj);
 int bpf__strerror_load(struct bpf_object *obj, int err,
                        char *buf, size_t size);
-int bpf__foreach_tev(struct bpf_object *obj,
-                     bpf_prog_iter_callback_t func, void *arg);
+int bpf__foreach_event(struct bpf_object *obj,
+                       bpf_prog_iter_callback_t func, void *arg);
 
 int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
                     struct perf_evlist *evlist, int *error_pos);
@@ -107,9 +107,9 @@ static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0
 static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; }
 
 static inline int
-bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
-                 bpf_prog_iter_callback_t func __maybe_unused,
-                 void *arg __maybe_unused)
+bpf__foreach_event(struct bpf_object *obj __maybe_unused,
+                   bpf_prog_iter_callback_t func __maybe_unused,
+                   void *arg __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 67e5966503b2..5651f3c12f93 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -17,6 +17,7 @@
 #include "tool.h"
 #include "header.h"
 #include "vdso.h"
+#include "probe-file.h"
 
 
 static bool no_buildid_cache;
@@ -144,7 +145,28 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...)
         return ret;
 }
 
-static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
+char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
+                                    size_t size)
+{
+        bool retry_old = true;
+
+        snprintf(bf, size, "%s/%s/%s/kallsyms",
+                 buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+retry:
+        if (!access(bf, F_OK))
+                return bf;
+        if (retry_old) {
+                /* Try old style kallsyms cache */
+                snprintf(bf, size, "%s/%s/%s",
+                         buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+                retry_old = false;
+                goto retry;
+        }
+
+        return NULL;
+}
+
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size)
 {
         char *tmp = bf;
         int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir,
@@ -154,23 +176,107 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size)
         return bf;
 }
 
+char *build_id_cache__origname(const char *sbuild_id)
+{
+        char *linkname;
+        char buf[PATH_MAX];
+        char *ret = NULL, *p;
+        size_t offs = 5;        /* == strlen("../..") */
+
+        linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+        if (!linkname)
+                return NULL;
+
+        if (readlink(linkname, buf, PATH_MAX) < 0)
+                goto out;
+        /* The link should be "../..<origpath>/<sbuild_id>" */
+        p = strrchr(buf, '/');  /* Cut off the "/<sbuild_id>" */
+        if (p && (p > buf + offs)) {
+                *p = '\0';
+                if (buf[offs + 1] == '[')
+                        offs++; /*
+                                 * This is a DSO name, like [kernel.kallsyms].
+                                 * Skip the first '/', since this is not the
+                                 * cache of a regular file.
+                                 */
+                ret = strdup(buf + offs);       /* Skip "../..[/]" */
+        }
+out:
+        free(linkname);
+        return ret;
+}
+
+/* Check if the given build_id cache is valid on current running system */
+static bool build_id_cache__valid_id(char *sbuild_id)
+{
+        char real_sbuild_id[SBUILD_ID_SIZE] = "";
+        char *pathname;
+        int ret = 0;
+        bool result = false;
+
+        pathname = build_id_cache__origname(sbuild_id);
+        if (!pathname)
+                return false;
+
+        if (!strcmp(pathname, DSO__NAME_KALLSYMS))
+                ret = sysfs__sprintf_build_id("/", real_sbuild_id);
+        else if (pathname[0] == '/')
+                ret = filename__sprintf_build_id(pathname, real_sbuild_id);
+        else
+                ret = -EINVAL;  /* Should we support other special DSO cache? */
+        if (ret >= 0)
+                result = (strcmp(sbuild_id, real_sbuild_id) == 0);
+        free(pathname);
+
+        return result;
+}
+
+static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
+{
+        return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
+}
+
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
-        char build_id_hex[SBUILD_ID_SIZE];
+        bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
+        bool is_vdso = dso__is_vdso((struct dso *)dso);
+        char sbuild_id[SBUILD_ID_SIZE];
+        char *linkname;
+        bool alloc = (bf == NULL);
+        int ret;
 
         if (!dso->has_build_id)
                 return NULL;
 
-        build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex);
-        return build_id__filename(build_id_hex, bf, size);
+        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+        linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
+        if (!linkname)
+                return NULL;
+
+        /* Check if old style build_id cache */
+        if (is_regular_file(linkname))
+                ret = asnprintf(&bf, size, "%s", linkname);
+        else
+                ret = asnprintf(&bf, size, "%s/%s", linkname,
+                         build_id_cache__basename(is_kallsyms, is_vdso));
+        if (ret < 0 || (!alloc && size < (unsigned int)ret))
+                bf = NULL;
+        free(linkname);
+
+        return bf;
 }
 
 bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
 {
-        char *id_name, *ch;
+        char *id_name = NULL, *ch;
         struct stat sb;
+        char sbuild_id[SBUILD_ID_SIZE];
 
-        id_name = dso__build_id_filename(dso, bf, size);
+        if (!dso->has_build_id)
+                goto err;
+
+        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+        id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
         if (!id_name)
                 goto err;
         if (access(id_name, F_OK))
@@ -194,18 +300,14 @@ bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
         if (ch - 3 < bf)
                 goto err;
 
+        free(id_name);
         return strncmp(".ko", ch - 3, 3) == 0;
 err:
-        /*
-         * If dso__build_id_filename work, get id_name again,
-         * because id_name points to bf and is broken.
-         */
-        if (id_name)
-                id_name = dso__build_id_filename(dso, bf, size);
         pr_err("Invalid build id: %s\n", id_name ? :
                                          dso->long_name ? :
                                          dso->short_name ? :
                                          "[unknown]");
+        free(id_name);
         return false;
 }
 
@@ -340,8 +442,132 @@ void disable_buildid_cache(void)
         no_buildid_cache = true;
 }
 
-static char *build_id_cache__dirname_from_path(const char *name,
-                                               bool is_kallsyms, bool is_vdso)
+static bool lsdir_bid_head_filter(const char *name __maybe_unused,
+                                  struct dirent *d __maybe_unused)
+{
+        return (strlen(d->d_name) == 2) &&
+                isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]);
+}
+
+static bool lsdir_bid_tail_filter(const char *name __maybe_unused,
+                                  struct dirent *d __maybe_unused)
+{
+        int i = 0;
+        while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3)
+                i++;
+        return (i == SBUILD_ID_SIZE - 3) && (d->d_name[i] == '\0');
+}
+
+struct strlist *build_id_cache__list_all(bool validonly)
+{
+        struct strlist *toplist, *linklist = NULL, *bidlist;
+        struct str_node *nd, *nd2;
+        char *topdir, *linkdir = NULL;
+        char sbuild_id[SBUILD_ID_SIZE];
+
+        /* for filename__ functions */
+        if (validonly)
+                symbol__init(NULL);
+
+        /* Open the top-level directory */
+        if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0)
+                return NULL;
+
+        bidlist = strlist__new(NULL, NULL);
+        if (!bidlist)
+                goto out;
+
+        toplist = lsdir(topdir, lsdir_bid_head_filter);
+        if (!toplist) {
+                pr_debug("Error in lsdir(%s): %d\n", topdir, errno);
+                /* If there is no buildid cache, return an empty list */
+                if (errno == ENOENT)
+                        goto out;
+                goto err_out;
+        }
+
+        strlist__for_each_entry(nd, toplist) {
+                if (asprintf(&linkdir, "%s/%s", topdir, nd->s) < 0)
+                        goto err_out;
+                /* Open the lower-level directory */
+                linklist = lsdir(linkdir, lsdir_bid_tail_filter);
+                if (!linklist) {
+                        pr_debug("Error in lsdir(%s): %d\n", linkdir, errno);
+                        goto err_out;
+                }
+                strlist__for_each_entry(nd2, linklist) {
+                        if (snprintf(sbuild_id, SBUILD_ID_SIZE, "%s%s",
+                                     nd->s, nd2->s) != SBUILD_ID_SIZE - 1)
+                                goto err_out;
+                        if (validonly && !build_id_cache__valid_id(sbuild_id))
+                                continue;
+                        if (strlist__add(bidlist, sbuild_id) < 0)
+                                goto err_out;
+                }
+                strlist__delete(linklist);
+                zfree(&linkdir);
+        }
+
+out_free:
+        strlist__delete(toplist);
+out:
+        free(topdir);
+
+        return bidlist;
+
+err_out:
+        strlist__delete(linklist);
+        zfree(&linkdir);
+        strlist__delete(bidlist);
+        bidlist = NULL;
+        goto out_free;
+}
+
+static bool str_is_build_id(const char *maybe_sbuild_id, size_t len)
+{
+        size_t i;
+
+        for (i = 0; i < len; i++) {
+                if (!isxdigit(maybe_sbuild_id[i]))
+                        return false;
+        }
+        return true;
+}
+
+/* Return the valid complete build-id */
+char *build_id_cache__complement(const char *incomplete_sbuild_id)
+{
+        struct strlist *bidlist;
+        struct str_node *nd, *cand = NULL;
+        char *sbuild_id = NULL;
+        size_t len = strlen(incomplete_sbuild_id);
+
+        if (len >= SBUILD_ID_SIZE ||
+            !str_is_build_id(incomplete_sbuild_id, len))
+                return NULL;
+
+        bidlist = build_id_cache__list_all(true);
+        if (!bidlist)
+                return NULL;
+
+        strlist__for_each_entry(nd, bidlist) {
+                if (strncmp(nd->s, incomplete_sbuild_id, len) != 0)
+                        continue;
+                if (cand) {     /* Error: There are more than 2 candidates. */
+                        cand = NULL;
+                        break;
+                }
+                cand = nd;
+        }
+        if (cand)
+                sbuild_id = strdup(cand->s);
+        strlist__delete(bidlist);
+
+        return sbuild_id;
+}
+
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+                               bool is_kallsyms, bool is_vdso)
 {
         char *realname = (char *)name, *filename;
         bool slash = is_kallsyms || is_vdso;
@@ -352,8 +578,9 @@ static char *build_id_cache__dirname_from_path(const char *name,
                         return NULL;
         }
 
-        if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "",
-                     is_vdso ? DSO__NAME_VDSO : realname) < 0)
+        if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "",
+                     is_vdso ? DSO__NAME_VDSO : realname,
+                     sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
                 filename = NULL;
 
         if (!slash)
@@ -368,7 +595,7 @@ int build_id_cache__list_build_ids(const char *pathname,
         char *dir_name;
         int ret = 0;
 
-        dir_name = build_id_cache__dirname_from_path(pathname, false, false);
+        dir_name = build_id_cache__cachedir(NULL, pathname, false, false);
         if (!dir_name)
                 return -ENOMEM;
 
@@ -380,12 +607,36 @@ int build_id_cache__list_build_ids(const char *pathname,
         return ret;
 }
 
+#if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT)
+static int build_id_cache__add_sdt_cache(const char *sbuild_id,
+                                          const char *realname)
+{
+        struct probe_cache *cache;
+        int ret;
+
+        cache = probe_cache__new(sbuild_id);
+        if (!cache)
+                return -1;
+
+        ret = probe_cache__scan_sdt(cache, realname);
+        if (ret >= 0) {
+                pr_debug("Found %d SDTs in %s\n", ret, realname);
+                if (probe_cache__commit(cache) < 0)
+                        ret = -1;
+        }
+        probe_cache__delete(cache);
+        return ret;
+}
+#else
+#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0)
+#endif
+
 int build_id_cache__add_s(const char *sbuild_id, const char *name,
                           bool is_kallsyms, bool is_vdso)
 {
         const size_t size = PATH_MAX;
         char *realname = NULL, *filename = NULL, *dir_name = NULL,
-             *linkname = zalloc(size), *targetname, *tmp;
+             *linkname = zalloc(size), *tmp;
         int err = -1;
 
         if (!is_kallsyms) {
@@ -394,14 +645,22 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                         goto out_free;
         }
 
-        dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso);
+        dir_name = build_id_cache__cachedir(sbuild_id, name,
+                                            is_kallsyms, is_vdso);
         if (!dir_name)
                 goto out_free;
 
+        /* Remove old style build-id cache */
+        if (is_regular_file(dir_name))
+                if (unlink(dir_name))
+                        goto out_free;
+
         if (mkdir_p(dir_name, 0755))
                 goto out_free;
 
-        if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) {
+        /* Save the allocated buildid dirname */
+        if (asprintf(&filename, "%s/%s", dir_name,
+                     build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
                 filename = NULL;
                 goto out_free;
         }
@@ -415,7 +674,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                         goto out_free;
         }
 
-        if (!build_id__filename(sbuild_id, linkname, size))
+        if (!build_id_cache__linkname(sbuild_id, linkname, size))
                 goto out_free;
         tmp = strrchr(linkname, '/');
         *tmp = '\0';
@@ -424,11 +683,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                 goto out_free;
 
         *tmp = '/';
-        targetname = filename + strlen(buildid_dir) - 5;
-        memcpy(targetname, "../..", 5);
+        tmp = dir_name + strlen(buildid_dir) - 5;
+        memcpy(tmp, "../..", 5);
 
-        if (symlink(targetname, linkname) == 0)
+        if (symlink(tmp, linkname) == 0)
                 err = 0;
+
+        /* Update SDT cache : error is just warned */
+        if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+                pr_debug("Failed to update/scan SDT cache for %s\n", realname);
+
 out_free:
         if (!is_kallsyms)
                 free(realname);
@@ -452,7 +716,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
 bool build_id_cache__cached(const char *sbuild_id)
 {
         bool ret = false;
-        char *filename = build_id__filename(sbuild_id, NULL, 0);
+        char *filename = build_id_cache__linkname(sbuild_id, NULL, 0);
 
         if (filename && !access(filename, F_OK))
                 ret = true;
@@ -471,7 +735,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
         if (filename == NULL || linkname == NULL)
                 goto out_free;
 
-        if (!build_id__filename(sbuild_id, linkname, size))
+        if (!build_id_cache__linkname(sbuild_id, linkname, size))
                 goto out_free;
 
         if (access(linkname, F_OK))
@@ -489,7 +753,7 @@ int build_id_cache__remove_s(const char *sbuild_id)
         tmp = strrchr(linkname, '/') + 1;
         snprintf(tmp, size - (tmp - linkname), "%s", filename);
 
-        if (unlink(linkname))
+        if (rm_rf(linkname))
                 goto out_free;
 
         err = 0;
@@ -501,7 +765,7 @@ out_free:
 
 static int dso__cache_build_id(struct dso *dso, struct machine *machine)
 {
-        bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+        bool is_kallsyms = dso__is_kallsyms(dso);
         bool is_vdso = dso__is_vdso(dso);
         const char *name = dso->long_name;
         char nm[PATH_MAX];
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 64af3e20610d..d27990610f9f 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -14,6 +14,8 @@ struct dso;
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
+char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
+                                    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
@@ -28,6 +30,12 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
 int perf_session__write_buildid_table(struct perf_session *session, int fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
+char *build_id_cache__origname(const char *sbuild_id);
+char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
+char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
+                               bool is_kallsyms, bool is_vdso);
+struct strlist *build_id_cache__list_all(bool validonly);
+char *build_id_cache__complement(const char *incomplete_sbuild_id);
 int build_id_cache__list_build_ids(const char *pathname,
                                    struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 0d814bb74661..512c0c83fbc6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -1,40 +1,20 @@
 #ifndef __PERF_CACHE_H
 #define __PERF_CACHE_H
 
-#include <stdbool.h>
-#include "util.h"
 #include "strbuf.h"
 #include <subcmd/pager.h>
-#include "../perf.h"
 #include "../ui/ui.h"
 
 #include <linux/string.h>
 
 #define CMD_EXEC_PATH "--exec-path"
-#define CMD_PERF_DIR "--perf-dir="
-#define CMD_WORK_TREE "--work-tree="
 #define CMD_DEBUGFS_DIR "--debugfs-dir="
 
-#define PERF_DIR_ENVIRONMENT "PERF_DIR"
-#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE"
 #define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH"
-#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf"
 #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
-extern const char *config_exclusive_filename;
-
-typedef int (*config_fn_t)(const char *, const char *, void *);
-int perf_default_config(const char *, const char *, void *);
-int perf_config(config_fn_t fn, void *);
-int perf_config_int(const char *, const char *);
-u64 perf_config_u64(const char *, const char *);
-int perf_config_bool(const char *, const char *);
-int config_error_nonbool(const char *);
-const char *perf_config_dirname(const char *, const char *);
-const char *perf_etc_perfconfig(void);
-
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
 
@@ -45,9 +25,6 @@ static inline int is_absolute_path(const char *path)
         return path[0] == '/';
 }
 
-char *strip_path_suffix(const char *path, const char *suffix);
-
 char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
-char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2)));
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 65e2a4f7cb4e..13e75549c440 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -94,6 +94,7 @@ struct callchain_param {
         enum perf_call_graph_mode record_mode;
         u32                     dump_size;
         enum chain_mode         mode;
+        u16                     max_stack;
         u32                     print_limit;
         double                  min_percent;
         sort_chain_func_t       sort;
@@ -105,6 +106,7 @@ struct callchain_param {
 };
 
 extern struct callchain_param callchain_param;
+extern struct callchain_param callchain_param_default;
 
 struct callchain_list {
         u64                     ip;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 90aa1b46b2e5..8fdee24725a7 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
         /*
          * check if cgrp is already defined, if so we reuse it
          */
-        evlist__for_each(evlist, counter) {
+        evlist__for_each_entry(evlist, counter) {
                 cgrp = counter->cgrp;
                 if (!cgrp)
                         continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
          * if add cgroup N, then need to find event N
          */
         n = 0;
-        evlist__for_each(evlist, counter) {
+        evlist__for_each_entry(evlist, counter) {
                 if (n == nr_cgroups)
                         goto found;
                 n++;
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index 2babddaa2481..f0dcd0ee0afa 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -4,18 +4,24 @@
 #include "cloexec.h"
 #include "asm/bug.h"
 #include "debug.h"
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6)
 int __weak sched_getcpu(void)
 {
+#ifdef __NR_getcpu
+        unsigned cpu;
+        int err = syscall(__NR_getcpu, &cpu, NULL, NULL);
+        if (!err)
+                return cpu;
+#else
         errno = ENOSYS;
+#endif
         return -1;
 }
-#endif
-#endif
 
 static int perf_flag_probe(void)
 {
@@ -58,7 +64,7 @@ static int perf_flag_probe(void)
 
         WARN_ONCE(err != EINVAL && err != EBUSY,
                   "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-                  err, strerror_r(err, sbuf, sizeof(sbuf)));
+                  err, str_error_r(err, sbuf, sizeof(sbuf)));
 
         /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
         while (1) {
@@ -76,7 +82,7 @@ static int perf_flag_probe(void)
 
         if (WARN_ONCE(fd < 0 && err != EBUSY,
                       "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-                      err, strerror_r(err, sbuf, sizeof(sbuf))))
+                      err, str_error_r(err, sbuf, sizeof(sbuf))))
                 return -1;
 
         return 0;
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 43e84aa27e4a..dbbf89b050a5 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,7 +1,11 @@
 #include <linux/kernel.h>
 #include "cache.h"
+#include "config.h"
+#include <stdlib.h>
+#include <stdio.h>
 #include "color.h"
 #include <math.h>
+#include <unistd.h>
 
 int perf_use_color_default = -1;
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index dad7d8272168..18dae745034f 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,6 +26,7 @@ static FILE *config_file;
 static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
+static struct perf_config_set *config_set;
 
 const char *config_exclusive_filename;
 
@@ -275,7 +276,8 @@ static int perf_parse_file(config_fn_t fn, void *data)
                         break;
                 }
         }
-        die("bad config file line %d in %s", config_linenr, config_file_name);
+        pr_err("bad config file line %d in %s\n", config_linenr, config_file_name);
+        return -1;
 }
 
 static int parse_unit_factor(const char *end, unsigned long *val)
@@ -371,7 +373,7 @@ int perf_config_bool(const char *name, const char *value)
         return !!perf_config_bool_or_int(name, value, &discard);
 }
 
-const char *perf_config_dirname(const char *name, const char *value)
+static const char *perf_config_dirname(const char *name, const char *value)
 {
         if (!name)
                 return NULL;
@@ -477,54 +479,6 @@ static int perf_config_global(void)
         return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0);
 }
 
-int perf_config(config_fn_t fn, void *data)
-{
-        int ret = 0, found = 0;
-        const char *home = NULL;
-
-        /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
-        if (config_exclusive_filename)
-                return perf_config_from_file(fn, config_exclusive_filename, data);
-        if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
-                ret += perf_config_from_file(fn, perf_etc_perfconfig(),
-                                            data);
-                found += 1;
-        }
-
-        home = getenv("HOME");
-        if (perf_config_global() && home) {
-                char *user_config = strdup(mkpath("%s/.perfconfig", home));
-                struct stat st;
-
-                if (user_config == NULL) {
-                        warning("Not enough memory to process %s/.perfconfig, "
-                                "ignoring it.", home);
-                        goto out;
-                }
-
-                if (stat(user_config, &st) < 0)
-                        goto out_free;
-
-                if (st.st_uid && (st.st_uid != geteuid())) {
-                        warning("File %s not owned by current user or root, "
-                                "ignoring it.", user_config);
-                        goto out_free;
-                }
-
-                if (!st.st_size)
-                        goto out_free;
-
-                ret += perf_config_from_file(fn, user_config, data);
-                found += 1;
-out_free:
-                free(user_config);
-        }
-out:
-        if (found == 0)
-                return -1;
-        return ret;
-}
-
 static struct perf_config_section *find_section(struct list_head *sections,
                                                 const char *section_name)
 {
@@ -609,8 +563,12 @@ static int collect_config(const char *var, const char *value,
         struct perf_config_section *section = NULL;
         struct perf_config_item *item = NULL;
         struct perf_config_set *set = perf_config_set;
-        struct list_head *sections = &set->sections;
+        struct list_head *sections;
+
+        if (set == NULL)
+                return -1;
 
+        sections = &set->sections;
         key = ptr = strdup(var);
         if (!key) {
                 pr_debug("%s: strdup failed\n", __func__);
@@ -641,22 +599,115 @@ static int collect_config(const char *var, const char *value,
 
 out_free:
         free(key);
-        perf_config_set__delete(set);
         return -1;
 }
 
+static int perf_config_set__init(struct perf_config_set *set)
+{
+        int ret = -1;
+        const char *home = NULL;
+
+        /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
+        if (config_exclusive_filename)
+                return perf_config_from_file(collect_config, config_exclusive_filename, set);
+        if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) {
+                if (perf_config_from_file(collect_config, perf_etc_perfconfig(), set) < 0)
+                        goto out;
+        }
+
+        home = getenv("HOME");
+        if (perf_config_global() && home) {
+                char *user_config = strdup(mkpath("%s/.perfconfig", home));
+                struct stat st;
+
+                if (user_config == NULL) {
+                        warning("Not enough memory to process %s/.perfconfig, "
+                                "ignoring it.", home);
+                        goto out;
+                }
+
+                if (stat(user_config, &st) < 0)
+                        goto out_free;
+
+                if (st.st_uid && (st.st_uid != geteuid())) {
+                        warning("File %s not owned by current user or root, "
+                                "ignoring it.", user_config);
+                        goto out_free;
+                }
+
+                if (!st.st_size)
+                        goto out_free;
+
+                ret = perf_config_from_file(collect_config, user_config, set);
+
+out_free:
+                free(user_config);
+        }
+out:
+        return ret;
+}
+
 struct perf_config_set *perf_config_set__new(void)
 {
         struct perf_config_set *set = zalloc(sizeof(*set));
 
         if (set) {
                 INIT_LIST_HEAD(&set->sections);
-                perf_config(collect_config, set);
+                if (perf_config_set__init(set) < 0) {
+                        perf_config_set__delete(set);
+                        set = NULL;
+                }
         }
 
         return set;
 }
 
+int perf_config(config_fn_t fn, void *data)
+{
+        int ret = 0;
+        char key[BUFSIZ];
+        struct perf_config_section *section;
+        struct perf_config_item *item;
+
+        if (config_set == NULL)
+                return -1;
+
+        perf_config_set__for_each_entry(config_set, section, item) {
+                char *value = item->value;
+
+                if (value) {
+                        scnprintf(key, sizeof(key), "%s.%s",
+                                  section->name, item->name);
+                        ret = fn(key, value, data);
+                        if (ret < 0) {
+                                pr_err("Error: wrong config key-value pair %s=%s\n",
+                                       key, value);
+                                break;
+                        }
+                }
+        }
+
+        return ret;
+}
+
+void perf_config__init(void)
+{
+        if (config_set == NULL)
+                config_set = perf_config_set__new();
+}
+
+void perf_config__exit(void)
+{
+        perf_config_set__delete(config_set);
+        config_set = NULL;
+}
+
+void perf_config__refresh(void)
+{
+        perf_config__exit();
+        perf_config__init();
+}
+
 static void perf_config_item__delete(struct perf_config_item *item)
 {
         zfree(&item->name);
@@ -693,6 +744,9 @@ static void perf_config_set__purge(struct perf_config_set *set)
 
 void perf_config_set__delete(struct perf_config_set *set)
 {
+        if (set == NULL)
+                return;
+
         perf_config_set__purge(set);
         free(set);
 }
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index 22ec626ac718..6f813d46045e 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -20,7 +20,47 @@ struct perf_config_set {
         struct list_head sections;
 };
 
+extern const char *config_exclusive_filename;
+
+typedef int (*config_fn_t)(const char *, const char *, void *);
+int perf_default_config(const char *, const char *, void *);
+int perf_config(config_fn_t fn, void *);
+int perf_config_int(const char *, const char *);
+u64 perf_config_u64(const char *, const char *);
+int perf_config_bool(const char *, const char *);
+int config_error_nonbool(const char *);
+const char *perf_etc_perfconfig(void);
+
 struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
+void perf_config__init(void);
+void perf_config__exit(void);
+void perf_config__refresh(void);
+
+/**
+ * perf_config_sections__for_each - iterate thru all the sections
+ * @list: list_head instance to iterate
+ * @section: struct perf_config_section iterator
+ */
+#define perf_config_sections__for_each_entry(list, section)     \
+        list_for_each_entry(section, list, node)
+
+/**
+ * perf_config_items__for_each - iterate thru all the items
+ * @list: list_head instance to iterate
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_items__for_each_entry(list, item)   \
+        list_for_each_entry(item, list, node)
+
+/**
+ * perf_config_set__for_each - iterate thru all the config section-item pairs
+ * @set: evlist instance to iterate
+ * @section: struct perf_config_section iterator
+ * @item: struct perf_config_item iterator
+ */
+#define perf_config_set__for_each_entry(set, section, item)                     \
+        perf_config_sections__for_each_entry(&set->sections, section)           \
+        perf_config_items__for_each_entry(&section->items, item)
 
 #endif /* __PERF_CONFIG_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 02d801670f30..2c0b52264a46 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -236,13 +236,12 @@ struct cpu_map *cpu_map__new_data(struct cpu_map_data *data)
 
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp)
 {
-        int i;
-        size_t printed = fprintf(fp, "%d cpu%s: ",
-                                 map->nr, map->nr > 1 ? "s" : "");
-        for (i = 0; i < map->nr; ++i)
-                printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]);
+#define BUFSIZE 1024
+        char buf[BUFSIZE];
 
-        return printed + fprintf(fp, "\n");
+        cpu_map__snprint(map, buf, sizeof(buf));
+        return fprintf(fp, "%s\n", buf);
+#undef BUFSIZE
 }
 
 struct cpu_map *cpu_map__dummy_new(void)
@@ -590,12 +589,65 @@ int cpu__setup_cpunode_map(void)
 
 bool cpu_map__has(struct cpu_map *cpus, int cpu)
 {
+        return cpu_map__idx(cpus, cpu) != -1;
+}
+
+int cpu_map__idx(struct cpu_map *cpus, int cpu)
+{
         int i;
 
         for (i = 0; i < cpus->nr; ++i) {
                 if (cpus->map[i] == cpu)
-                        return true;
+                        return i;
+        }
+
+        return -1;
+}
+
+int cpu_map__cpu(struct cpu_map *cpus, int idx)
+{
+        return cpus->map[idx];
+}
+
+size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
+{
+        int i, cpu, start = -1;
+        bool first = true;
+        size_t ret = 0;
+
+#define COMMA first ? "" : ","
+
+        for (i = 0; i < map->nr + 1; i++) {
+                bool last = i == map->nr;
+
+                cpu = last ? INT_MAX : map->map[i];
+
+                if (start == -1) {
+                        start = i;
+                        if (last) {
+                                ret += snprintf(buf + ret, size - ret,
+                                                "%s%d", COMMA,
+                                                map->map[i]);
+                        }
+                } else if (((i - start) != (cpu - map->map[start])) || last) {
+                        int end = i - 1;
+
+                        if (start == end) {
+                                ret += snprintf(buf + ret, size - ret,
+                                                "%s%d", COMMA,
+                                                map->map[start]);
+                        } else {
+                                ret += snprintf(buf + ret, size - ret,
+                                                "%s%d-%d", COMMA,
+                                                map->map[start], map->map[end]);
+                        }
+                        first = false;
+                        start = i;
+                }
         }
 
-        return false;
+#undef COMMA
+
+        pr_debug("cpumask list: %s\n", buf);
+        return ret;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 1a0a35073ce1..06bd689f5989 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -19,6 +19,7 @@ struct cpu_map *cpu_map__empty_new(int nr);
 struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
 struct cpu_map *cpu_map__read(FILE *file);
+size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket_id(int cpu);
 int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
@@ -67,5 +68,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
                        int (*f)(struct cpu_map *map, int cpu, void *data),
                        void *data);
 
+int cpu_map__cpu(struct cpu_map *cpus, int idx);
 bool cpu_map__has(struct cpu_map *cpus, int cpu);
+int cpu_map__idx(struct cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 9f53020c3269..4f979bb27b6c 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -26,6 +26,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "machine.h"
+#include "config.h"
 
 #define pr_N(n, fmt, ...) \
         eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
@@ -68,6 +69,9 @@ struct ctf_writer {
                 };
                 struct bt_ctf_field_type *array[6];
         } data;
+        struct bt_ctf_event_class       *comm_class;
+        struct bt_ctf_event_class       *exit_class;
+        struct bt_ctf_event_class       *fork_class;
 };
 
 struct convert {
@@ -76,6 +80,7 @@ struct convert {
 
         u64                     events_size;
         u64                     events_count;
+        u64                     non_sample_count;
 
         /* Ordered events configured queue size. */
         u64                     queue_size;
@@ -140,6 +145,36 @@ FUNC_VALUE_SET(s64)
 FUNC_VALUE_SET(u64)
 __FUNC_VALUE_SET(u64_hex, u64)
 
+static int string_set_value(struct bt_ctf_field *field, const char *string);
+static __maybe_unused int
+value_set_string(struct ctf_writer *cw, struct bt_ctf_event *event,
+                 const char *name, const char *string)
+{
+        struct bt_ctf_field_type *type = cw->data.string;
+        struct bt_ctf_field *field;
+        int ret = 0;
+
+        field = bt_ctf_field_create(type);
+        if (!field) {
+                pr_err("failed to create a field %s\n", name);
+                return -1;
+        }
+
+        ret = string_set_value(field, string);
+        if (ret) {
+                pr_err("failed to set value %s\n", name);
+                goto err_put_field;
+        }
+
+        ret = bt_ctf_event_set_payload(event, name, field);
+        if (ret)
+                pr_err("failed to set payload %s\n", name);
+
+err_put_field:
+        bt_ctf_field_put(field);
+        return ret;
+}
+
 static struct bt_ctf_field_type*
 get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
 {
@@ -731,6 +766,72 @@ static int process_sample_event(struct perf_tool *tool,
         return cs ? 0 : -1;
 }
 
+#define __NON_SAMPLE_SET_FIELD(_name, _type, _field)    \
+do {                                                    \
+        ret = value_set_##_type(cw, event, #_field, _event->_name._field);\
+        if (ret)                                        \
+                return -1;                              \
+} while(0)
+
+#define __FUNC_PROCESS_NON_SAMPLE(_name, body)  \
+static int process_##_name##_event(struct perf_tool *tool,      \
+                                   union perf_event *_event,    \
+                                   struct perf_sample *sample,  \
+                                   struct machine *machine)     \
+{                                                               \
+        struct convert *c = container_of(tool, struct convert, tool);\
+        struct ctf_writer *cw = &c->writer;                     \
+        struct bt_ctf_event_class *event_class = cw->_name##_class;\
+        struct bt_ctf_event *event;                             \
+        struct ctf_stream *cs;                                  \
+        int ret;                                                \
+                                                                \
+        c->non_sample_count++;                                  \
+        c->events_size += _event->header.size;                  \
+        event = bt_ctf_event_create(event_class);               \
+        if (!event) {                                           \
+                pr_err("Failed to create an CTF event\n");      \
+                return -1;                                      \
+        }                                                       \
+                                                                \
+        bt_ctf_clock_set_time(cw->clock, sample->time);         \
+        body                                                    \
+        cs = ctf_stream(cw, 0);                                 \
+        if (cs) {                                               \
+                if (is_flush_needed(cs))                        \
+                        ctf_stream__flush(cs);                  \
+                                                                \
+                cs->count++;                                    \
+                bt_ctf_stream_append_event(cs->stream, event);  \
+        }                                                       \
+        bt_ctf_event_put(event);                                \
+                                                                \
+        return perf_event__process_##_name(tool, _event, sample, machine);\
+}
+
+__FUNC_PROCESS_NON_SAMPLE(comm,
+        __NON_SAMPLE_SET_FIELD(comm, u32, pid);
+        __NON_SAMPLE_SET_FIELD(comm, u32, tid);
+        __NON_SAMPLE_SET_FIELD(comm, string, comm);
+)
+__FUNC_PROCESS_NON_SAMPLE(fork,
+        __NON_SAMPLE_SET_FIELD(fork, u32, pid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, ppid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, tid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, ptid);
+        __NON_SAMPLE_SET_FIELD(fork, u64, time);
+)
+
+__FUNC_PROCESS_NON_SAMPLE(exit,
+        __NON_SAMPLE_SET_FIELD(fork, u32, pid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, ppid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, tid);
+        __NON_SAMPLE_SET_FIELD(fork, u32, ptid);
+        __NON_SAMPLE_SET_FIELD(fork, u64, time);
+)
+#undef __NON_SAMPLE_SET_FIELD
+#undef __FUNC_PROCESS_NON_SAMPLE
+
 /* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
 static char *change_name(char *name, char *orig_name, int dup)
 {
@@ -997,7 +1098,7 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
         struct perf_evsel *evsel;
         int ret;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 ret = add_event(cw, evsel);
                 if (ret)
                         return ret;
@@ -1005,12 +1106,86 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
         return 0;
 }
 
+#define __NON_SAMPLE_ADD_FIELD(t, n)                                            \
+        do {                                                    \
+                pr2("  field '%s'\n", #n);                      \
+                if (bt_ctf_event_class_add_field(event_class, cw->data.t, #n)) {\
+                        pr_err("Failed to add field '%s';\n", #n);\
+                        return -1;                              \
+                }                                               \
+        } while(0)
+
+#define __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(_name, body)          \
+static int add_##_name##_event(struct ctf_writer *cw)           \
+{                                                               \
+        struct bt_ctf_event_class *event_class;                 \
+        int ret;                                                \
+                                                                \
+        pr("Adding "#_name" event\n");                          \
+        event_class = bt_ctf_event_class_create("perf_" #_name);\
+        if (!event_class)                                       \
+                return -1;                                      \
+        body                                                    \
+                                                                \
+        ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);\
+        if (ret) {                                              \
+                pr("Failed to add event class '"#_name"' into stream.\n");\
+                return ret;                                     \
+        }                                                       \
+                                                                \
+        cw->_name##_class = event_class;                        \
+        bt_ctf_event_class_put(event_class);                    \
+        return 0;                                               \
+}
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(comm,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(string, comm);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(fork,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, ppid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u32, ptid);
+        __NON_SAMPLE_ADD_FIELD(u64, time);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, ppid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u32, ptid);
+        __NON_SAMPLE_ADD_FIELD(u64, time);
+)
+
+#undef __NON_SAMPLE_ADD_FIELD
+#undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS
+
+static int setup_non_sample_events(struct ctf_writer *cw,
+                                   struct perf_session *session __maybe_unused)
+{
+        int ret;
+
+        ret = add_comm_event(cw);
+        if (ret)
+                return ret;
+        ret = add_exit_event(cw);
+        if (ret)
+                return ret;
+        ret = add_fork_event(cw);
+        if (ret)
+                return ret;
+        return 0;
+}
+
 static void cleanup_events(struct perf_session *session)
 {
         struct perf_evlist *evlist = session->evlist;
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 struct evsel_priv *priv;
 
                 priv = evsel->priv;
@@ -1273,13 +1448,14 @@ static int convert__config(const char *var, const char *value, void *cb)
         return 0;
 }
 
-int bt_convert__perf2ctf(const char *input, const char *path, bool force)
+int bt_convert__perf2ctf(const char *input, const char *path,
+                         struct perf_data_convert_opts *opts)
 {
         struct perf_session *session;
         struct perf_data_file file = {
                 .path = input,
                 .mode = PERF_DATA_MODE_READ,
-                .force = force,
+                .force = opts->force,
         };
         struct convert c = {
                 .tool = {
@@ -1299,6 +1475,12 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
         struct ctf_writer *cw = &c.writer;
         int err = -1;
 
+        if (opts->all) {
+                c.tool.comm = process_comm_event;
+                c.tool.exit = process_exit_event;
+                c.tool.fork = process_fork_event;
+        }
+
         perf_config(convert__config, &c);
 
         /* CTF writer */
@@ -1323,6 +1505,9 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
         if (setup_events(cw, session))
                 goto free_session;
 
+        if (opts->all && setup_non_sample_events(cw, session))
+                goto free_session;
+
         if (setup_streams(cw, session))
                 goto free_session;
 
@@ -1337,10 +1522,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
                 file.path, path);
 
         fprintf(stderr,
-                "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n",
+                "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
                 (double) c.events_size / 1024.0 / 1024.0,
                 c.events_count);
 
+        if (!c.non_sample_count)
+                fprintf(stderr, ") ]\n");
+        else
+                fprintf(stderr, ", %" PRIu64 " non-samples) ]\n", c.non_sample_count);
+
         cleanup_events(session);
         perf_session__delete(session);
         ctf_writer__cleanup(cw);
diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h
index 4c204342a9d8..9a3b587f76c1 100644
--- a/tools/perf/util/data-convert-bt.h
+++ b/tools/perf/util/data-convert-bt.h
@@ -1,8 +1,10 @@
 #ifndef __DATA_CONVERT_BT_H
 #define __DATA_CONVERT_BT_H
+#include "data-convert.h"
 #ifdef HAVE_LIBBABELTRACE_SUPPORT
 
-int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, bool force);
+int bt_convert__perf2ctf(const char *input_name, const char *to_ctf,
+                         struct perf_data_convert_opts *opts);
 
 #endif /* HAVE_LIBBABELTRACE_SUPPORT */
 #endif /* __DATA_CONVERT_BT_H */
diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h
new file mode 100644
index 000000000000..5314962fe95b
--- /dev/null
+++ b/tools/perf/util/data-convert.h
@@ -0,0 +1,9 @@
+#ifndef __DATA_CONVERT_H
+#define __DATA_CONVERT_H
+
+struct perf_data_convert_opts {
+        bool force;
+        bool all;
+};
+
+#endif /* __DATA_CONVERT_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index be83516155ee..60bfc9ca1e22 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -57,7 +57,7 @@ static int open_file_read(struct perf_data_file *file)
                 int err = errno;
 
                 pr_err("failed to open %s: %s", file->path,
-                        strerror_r(err, sbuf, sizeof(sbuf)));
+                        str_error_r(err, sbuf, sizeof(sbuf)));
                 if (err == ENOENT && !strcmp(file->path, "perf.data"))
                         pr_err("  (try 'perf record' first)");
                 pr_err("\n");
@@ -99,7 +99,7 @@ static int open_file_write(struct perf_data_file *file)
 
         if (fd < 0)
                 pr_err("failed to open %s : %s\n", file->path,
-                        strerror_r(errno, sbuf, sizeof(sbuf)));
+                        str_error_r(errno, sbuf, sizeof(sbuf)));
 
         return fd;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index c9a6dc173e74..b0c2b5c5d337 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -233,17 +233,6 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym,
         return 0;
 }
 
-static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
-{
-        if (thread->pid_ == thread->tid)
-                return thread__get(thread);
-
-        if (thread->pid_ == -1)
-                return NULL;
-
-        return machine__find_thread(machine, thread->pid_, thread->pid_);
-}
-
 static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
                           u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
 {
@@ -382,7 +371,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
         if (err)
                 return err;
 
-        main_thread = get_main_thread(al->machine, thread);
+        main_thread = thread__main_thread(al->machine, thread);
         if (main_thread)
                 comm = machine__thread_exec_comm(al->machine, main_thread);
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 14bafda79eda..d242adc3d5a2 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -38,7 +38,7 @@ extern int debug_data_convert;
 #define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
 
-#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+#define STRERR_BUFSIZE  128     /* For the buffer size of str_error_r */
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c
new file mode 100644
index 000000000000..f9dafa888c06
--- /dev/null
+++ b/tools/perf/util/demangle-rust.c
@@ -0,0 +1,269 @@
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+
+#include "demangle-rust.h"
+
+/*
+ * Mangled Rust symbols look like this:
+ *
+ *     _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a
+ *
+ * The original symbol is:
+ *
+ *     <std::sys::fd::FileDesc as core::ops::Drop>::drop
+ *
+ * The last component of the path is a 64-bit hash in lowercase hex, prefixed
+ * with "h". Rust does not have a global namespace between crates, an illusion
+ * which Rust maintains by using the hash to distinguish things that would
+ * otherwise have the same symbol.
+ *
+ * Any path component not starting with a XID_Start character is prefixed with
+ * "_".
+ *
+ * The following escape sequences are used:
+ *
+ *     ","  =>  $C$
+ *     "@"  =>  $SP$
+ *     "*"  =>  $BP$
+ *     "&"  =>  $RF$
+ *     "<"  =>  $LT$
+ *     ">"  =>  $GT$
+ *     "("  =>  $LP$
+ *     ")"  =>  $RP$
+ *     " "  =>  $u20$
+ *     "'"  =>  $u27$
+ *     "["  =>  $u5b$
+ *     "]"  =>  $u5d$
+ *     "~"  =>  $u7e$
+ *
+ * A double ".." means "::" and a single "." means "-".
+ *
+ * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$
+ */
+
+static const char *hash_prefix = "::h";
+static const size_t hash_prefix_len = 3;
+static const size_t hash_len = 16;
+
+static bool is_prefixed_hash(const char *start);
+static bool looks_like_rust(const char *sym, size_t len);
+static bool unescape(const char **in, char **out, const char *seq, char value);
+
+/*
+ * INPUT:
+ *     sym: symbol that has been through BFD-demangling
+ *
+ * This function looks for the following indicators:
+ *
+ *  1. The hash must consist of "h" followed by 16 lowercase hex digits.
+ *
+ *  2. As a sanity check, the hash must use between 5 and 15 of the 16 possible
+ *     hex digits. This is true of 99.9998% of hashes so once in your life you
+ *     may see a false negative. The point is to notice path components that
+ *     could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In
+ *     this case a false positive (non-Rust symbol has an important path
+ *     component removed because it looks like a Rust hash) is worse than a
+ *     false negative (the rare Rust symbol is not demangled) so this sets the
+ *     balance in favor of false negatives.
+ *
+ *  3. There must be no characters other than a-zA-Z0-9 and _.:$
+ *
+ *  4. There must be no unrecognized $-sign sequences.
+ *
+ *  5. There must be no sequence of three or more dots in a row ("...").
+ */
+bool
+rust_is_mangled(const char *sym)
+{
+        size_t len, len_without_hash;
+
+        if (!sym)
+                return false;
+
+        len = strlen(sym);
+        if (len <= hash_prefix_len + hash_len)
+                /* Not long enough to contain "::h" + hash + something else */
+                return false;
+
+        len_without_hash = len - (hash_prefix_len + hash_len);
+        if (!is_prefixed_hash(sym + len_without_hash))
+                return false;
+
+        return looks_like_rust(sym, len_without_hash);
+}
+
+/*
+ * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex
+ * digits must comprise between 5 and 15 (inclusive) distinct digits.
+ */
+static bool is_prefixed_hash(const char *str)
+{
+        const char *end;
+        bool seen[16];
+        size_t i;
+        int count;
+
+        if (strncmp(str, hash_prefix, hash_prefix_len))
+                return false;
+        str += hash_prefix_len;
+
+        memset(seen, false, sizeof(seen));
+        for (end = str + hash_len; str < end; str++)
+                if (*str >= '0' && *str <= '9')
+                        seen[*str - '0'] = true;
+                else if (*str >= 'a' && *str <= 'f')
+                        seen[*str - 'a' + 10] = true;
+                else
+                        return false;
+
+        /* Count how many distinct digits seen */
+        count = 0;
+        for (i = 0; i < 16; i++)
+                if (seen[i])
+                        count++;
+
+        return count >= 5 && count <= 15;
+}
+
+static bool looks_like_rust(const char *str, size_t len)
+{
+        const char *end = str + len;
+
+        while (str < end)
+                switch (*str) {
+                case '$':
+                        if (!strncmp(str, "$C$", 3))
+                                str += 3;
+                        else if (!strncmp(str, "$SP$", 4)
+                                        || !strncmp(str, "$BP$", 4)
+                                        || !strncmp(str, "$RF$", 4)
+                                        || !strncmp(str, "$LT$", 4)
+                                        || !strncmp(str, "$GT$", 4)
+                                        || !strncmp(str, "$LP$", 4)
+                                        || !strncmp(str, "$RP$", 4))
+                                str += 4;
+                        else if (!strncmp(str, "$u20$", 5)
+                                        || !strncmp(str, "$u27$", 5)
+                                        || !strncmp(str, "$u5b$", 5)
+                                        || !strncmp(str, "$u5d$", 5)
+                                        || !strncmp(str, "$u7e$", 5))
+                                str += 5;
+                        else
+                                return false;
+                        break;
+                case '.':
+                        /* Do not allow three or more consecutive dots */
+                        if (!strncmp(str, "...", 3))
+                                return false;
+                        /* Fall through */
+                case 'a' ... 'z':
+                case 'A' ... 'Z':
+                case '0' ... '9':
+                case '_':
+                case ':':
+                        str++;
+                        break;
+                default:
+                        return false;
+                }
+
+        return true;
+}
+
+/*
+ * INPUT:
+ *     sym: symbol for which rust_is_mangled(sym) returns true
+ *
+ * The input is demangled in-place because the mangled name is always longer
+ * than the demangled one.
+ */
+void
+rust_demangle_sym(char *sym)
+{
+        const char *in;
+        char *out;
+        const char *end;
+
+        if (!sym)
+                return;
+
+        in = sym;
+        out = sym;
+        end = sym + strlen(sym) - (hash_prefix_len + hash_len);
+
+        while (in < end)
+                switch (*in) {
+                case '$':
+                        if (!(unescape(&in, &out, "$C$", ',')
+                                        || unescape(&in, &out, "$SP$", '@')
+                                        || unescape(&in, &out, "$BP$", '*')
+                                        || unescape(&in, &out, "$RF$", '&')
+                                        || unescape(&in, &out, "$LT$", '<')
+                                        || unescape(&in, &out, "$GT$", '>')
+                                        || unescape(&in, &out, "$LP$", '(')
+                                        || unescape(&in, &out, "$RP$", ')')
+                                        || unescape(&in, &out, "$u20$", ' ')
+                                        || unescape(&in, &out, "$u27$", '\'')
+                                        || unescape(&in, &out, "$u5b$", '[')
+                                        || unescape(&in, &out, "$u5d$", ']')
+                                        || unescape(&in, &out, "$u7e$", '~'))) {
+                                pr_err("demangle-rust: unexpected escape sequence");
+                                goto done;
+                        }
+                        break;
+                case '_':
+                        /*
+                         * If this is the start of a path component and the next
+                         * character is an escape sequence, ignore the
+                         * underscore. The mangler inserts an underscore to make
+                         * sure the path component begins with a XID_Start
+                         * character.
+                         */
+                        if ((in == sym || in[-1] == ':') && in[1] == '$')
+                                in++;
+                        else
+                                *out++ = *in++;
+                        break;
+                case '.':
+                        if (in[1] == '.') {
+                                /* ".." becomes "::" */
+                                *out++ = ':';
+                                *out++ = ':';
+                                in += 2;
+                        } else {
+                                /* "." becomes "-" */
+                                *out++ = '-';
+                                in++;
+                        }
+                        break;
+                case 'a' ... 'z':
+                case 'A' ... 'Z':
+                case '0' ... '9':
+                case ':':
+                        *out++ = *in++;
+                        break;
+                default:
+                        pr_err("demangle-rust: unexpected character '%c' in symbol\n",
+                                *in);
+                        goto done;
+                }
+
+done:
+        *out = '\0';
+}
+
+static bool unescape(const char **in, char **out, const char *seq, char value)
+{
+        size_t len = strlen(seq);
+
+        if (strncmp(*in, seq, len))
+                return false;
+
+        **out = value;
+
+        *in += len;
+        *out += 1;
+
+        return true;
+}
diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h
new file mode 100644
index 000000000000..7b41ead7e0dd
--- /dev/null
+++ b/tools/perf/util/demangle-rust.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_DEMANGLE_RUST
+#define __PERF_DEMANGLE_RUST 1
+
+bool rust_is_mangled(const char *str);
+void rust_demangle_sym(char *str);
+
+#endif /* __PERF_DEMANGLE_RUST */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 5d286f5d7906..774f6ec884d5 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -335,7 +335,7 @@ static int do_open(char *name)
                         return fd;
 
                 pr_debug("dso open failed: %s\n",
-                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                         str_error_r(errno, sbuf, sizeof(sbuf)));
                 if (!dso__data_open_cnt || errno != EMFILE)
                         break;
 
@@ -442,17 +442,27 @@ static rlim_t get_fd_limit(void)
         return limit;
 }
 
-static bool may_cache_fd(void)
+static rlim_t fd_limit;
+
+/*
+ * Used only by tests/dso-data.c to reset the environment
+ * for tests. I dont expect we should change this during
+ * standard runtime.
+ */
+void reset_fd_limit(void)
 {
-        static rlim_t limit;
+        fd_limit = 0;
+}
 
-        if (!limit)
-                limit = get_fd_limit();
+static bool may_cache_fd(void)
+{
+        if (!fd_limit)
+                fd_limit = get_fd_limit();
 
-        if (limit == RLIM_INFINITY)
+        if (fd_limit == RLIM_INFINITY)
                 return true;
 
-        return limit > (rlim_t) dso__data_open_cnt;
+        return fd_limit > (rlim_t) dso__data_open_cnt;
 }
 
 /*
@@ -776,7 +786,7 @@ static int data_file_size(struct dso *dso, struct machine *machine)
         if (fstat(dso->data.fd, &st) < 0) {
                 ret = -errno;
                 pr_err("dso cache fstat failed: %s\n",
-                       strerror_r(errno, sbuf, sizeof(sbuf)));
+                       str_error_r(errno, sbuf, sizeof(sbuf)));
                 dso->data.status = DSO_DATA_STATUS_ERROR;
                 goto out;
         }
@@ -1356,7 +1366,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
         BUG_ON(buflen == 0);
 
         if (errnum >= 0) {
-                const char *err = strerror_r(errnum, buf, buflen);
+                const char *err = str_error_r(errnum, buf, buflen);
 
                 if (err != buf)
                         scnprintf(buf, buflen, "%s", err);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 0953280629cf..ecc4bbd3f82e 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -4,6 +4,7 @@
 #include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
+#include <sys/types.h>
 #include <stdbool.h>
 #include <pthread.h>
 #include <linux/types.h>
@@ -349,10 +350,17 @@ static inline bool dso__is_kcore(struct dso *dso)
                dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
+static inline bool dso__is_kallsyms(struct dso *dso)
+{
+        return dso->kernel && dso->long_name[0] != '/';
+}
+
 void dso__free_a2l(struct dso *dso);
 
 enum dso_type dso__type(struct dso *dso, struct machine *machine);
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen);
 
+void reset_fd_limit(void);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 49a11d9d8b8f..bb964e86b09d 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -18,10 +18,13 @@ void perf_env__exit(struct perf_env *env)
         zfree(&env->cmdline_argv);
         zfree(&env->sibling_cores);
         zfree(&env->sibling_threads);
-        zfree(&env->numa_nodes);
         zfree(&env->pmu_mappings);
         zfree(&env->cpu);
 
+        for (i = 0; i < env->nr_numa_nodes; i++)
+                cpu_map__put(env->numa_nodes[i].map);
+        zfree(&env->numa_nodes);
+
         for (i = 0; i < env->caches_cnt; i++)
                 cpu_cache_level__free(&env->caches[i]);
         zfree(&env->caches);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 56cffb60a0b4..b164dfd2dcbf 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -2,6 +2,7 @@
 #define __PERF_ENV_H
 
 #include <linux/types.h>
+#include "cpumap.h"
 
 struct cpu_topology_map {
         int     socket_id;
@@ -18,6 +19,13 @@ struct cpu_cache_level {
         char    *map;
 };
 
+struct numa_node {
+        u32              node;
+        u64              mem_total;
+        u64              mem_free;
+        struct cpu_map  *map;
+};
+
 struct perf_env {
         char                    *hostname;
         char                    *os_release;
@@ -40,11 +48,11 @@ struct perf_env {
         const char              **cmdline_argv;
         char                    *sibling_cores;
         char                    *sibling_threads;
-        char                    *numa_nodes;
         char                    *pmu_mappings;
         struct cpu_topology_map *cpu;
         struct cpu_cache_level  *caches;
         int                      caches_cnt;
+        struct numa_node        *numa_nodes;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9b141f12329e..e20438b784be 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1092,7 +1092,7 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
         struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
         size_t ret;
 
-        ret = fprintf(fp, " nr: ");
+        ret = fprintf(fp, ": ");
 
         if (cpus)
                 ret += cpu_map__fprintf(cpus, fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e82ba90cc969..097b3ed77fdd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -15,6 +15,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
+#include "asm/bug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -27,8 +28,8 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+static void perf_mmap__munmap(struct perf_mmap *map);
+static void perf_mmap__put(struct perf_mmap *map);
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
@@ -44,7 +45,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
         perf_evlist__set_maps(evlist, cpus, threads);
         fdarray__init(&evlist->pollfd, 64);
         evlist->workload.pid = -1;
-        evlist->backward = false;
+        evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -100,7 +101,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 perf_evsel__calc_id_pos(evsel);
 
         perf_evlist__set_id_pos(evlist);
@@ -110,7 +111,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos, *n;
 
-        evlist__for_each_safe(evlist, n, pos) {
+        evlist__for_each_entry_safe(evlist, n, pos) {
                 list_del_init(&pos->node);
                 pos->evlist = NULL;
                 perf_evsel__delete(pos);
@@ -122,11 +123,15 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
         zfree(&evlist->mmap);
+        zfree(&evlist->backward_mmap);
         fdarray__exit(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+        if (evlist == NULL)
+                return;
+
         perf_evlist__munmap(evlist);
         perf_evlist__close(evlist);
         cpu_map__put(evlist->cpus);
@@ -161,7 +166,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 __perf_evlist__propagate_maps(evlist, evsel);
 }
 
@@ -190,7 +195,7 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel, *temp;
 
-        __evlist__for_each_safe(list, temp, evsel) {
+        __evlist__for_each_entry_safe(list, temp, evsel) {
                 list_del_init(&evsel->node);
                 perf_evlist__add(evlist, evsel);
         }
@@ -205,7 +210,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
         leader->nr_members = evsel->idx - leader->idx + 1;
 
-        __evlist__for_each(list, evsel) {
+        __evlist__for_each_entry(list, evsel) {
                 evsel->leader = leader;
         }
 }
@@ -234,31 +239,13 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
 
 int perf_evlist__add_default(struct perf_evlist *evlist)
 {
-        struct perf_event_attr attr = {
-                .type = PERF_TYPE_HARDWARE,
-                .config = PERF_COUNT_HW_CPU_CYCLES,
-        };
-        struct perf_evsel *evsel;
-
-        event_attr_init(&attr);
+        struct perf_evsel *evsel = perf_evsel__new_cycles();
 
-        perf_event_attr__set_max_precise_ip(&attr);
-
-        evsel = perf_evsel__new(&attr);
         if (evsel == NULL)
-                goto error;
-
-        /* use asprintf() because free(evsel) assumes name is allocated */
-        if (asprintf(&evsel->name, "cycles%.*s",
-                     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
-                goto error_free;
+                return -ENOMEM;
 
         perf_evlist__add(evlist, evsel);
         return 0;
-error_free:
-        perf_evsel__delete(evsel);
-error:
-        return -ENOMEM;
 }
 
 int perf_evlist__add_dummy(struct perf_evlist *evlist)
@@ -296,7 +283,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
         return 0;
 
 out_delete_partial_list:
-        __evlist__for_each_safe(&head, n, evsel)
+        __evlist__for_each_entry_safe(&head, n, evsel)
                 perf_evsel__delete(evsel);
         return -1;
 }
@@ -317,7 +304,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
                     (int)evsel->attr.config == id)
                         return evsel;
@@ -332,7 +319,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
                     (strcmp(evsel->name, name) == 0))
                         return evsel;
@@ -367,7 +354,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                         continue;
                 perf_evsel__disable(pos);
@@ -380,7 +367,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                         continue;
                 perf_evsel__enable(pos);
@@ -448,7 +435,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
         int nfds = 0;
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->system_wide)
                         nfds += nr_cpus;
                 else
@@ -462,15 +449,16 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
         return 0;
 }
 
-static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+                                     struct perf_mmap *map, short revent)
 {
-        int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+        int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
         /*
          * Save the idx so that when we filter out fds POLLHUP'ed we can
          * close the associated evlist->mmap[] entry.
          */
         if (pos >= 0) {
-                evlist->pollfd.priv[pos].idx = idx;
+                evlist->pollfd.priv[pos].ptr = map;
 
                 fcntl(fd, F_SETFL, O_NONBLOCK);
         }
@@ -480,20 +468,22 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
 {
-        return __perf_evlist__add_pollfd(evlist, fd, -1);
+        return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN);
 }
 
-static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
+                                         void *arg __maybe_unused)
 {
-        struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+        struct perf_mmap *map = fda->priv[fd].ptr;
 
-        perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+        if (map)
+                perf_mmap__put(map);
 }
 
 int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
 {
         return fdarray__filter(&evlist->pollfd, revents_and_mask,
-                               perf_evlist__munmap_filtered);
+                               perf_evlist__munmap_filtered, NULL);
 }
 
 int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
@@ -647,8 +637,8 @@ static int perf_evlist__event2id(struct perf_evlist *evlist,
         return 0;
 }
 
-static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
-                                                   union perf_event *event)
+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;
@@ -684,8 +674,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
         int i;
 
+        if (!evlist->backward_mmap)
+                return 0;
+
         for (i = 0; i < evlist->nr_mmaps; i++) {
-                int fd = evlist->mmap[i].fd;
+                int fd = evlist->backward_mmap[i].fd;
                 int err;
 
                 if (fd < 0)
@@ -697,12 +690,12 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
         return 0;
 }
 
-int perf_evlist__pause(struct perf_evlist *evlist)
+static int perf_evlist__pause(struct perf_evlist *evlist)
 {
         return perf_evlist__set_paused(evlist, true);
 }
 
-int perf_evlist__resume(struct perf_evlist *evlist)
+static int perf_evlist__resume(struct perf_evlist *evlist)
 {
         return perf_evlist__set_paused(evlist, false);
 }
@@ -777,9 +770,8 @@ broken_event:
         return event;
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
 {
-        struct perf_mmap *md = &evlist->mmap[idx];
         u64 head;
         u64 old = md->prev;
 
@@ -791,13 +783,12 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
         head = perf_mmap__read_head(md);
 
-        return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+        return perf_mmap__read(md, check_messup, old, head, &md->prev);
 }
 
 union perf_event *
-perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
+perf_mmap__read_backward(struct perf_mmap *md)
 {
-        struct perf_mmap *md = &evlist->mmap[idx];
         u64 head, end;
         u64 start = md->prev;
 
@@ -832,9 +823,38 @@ perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
         return perf_mmap__read(md, false, start, end, &md->prev);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
+{
+        struct perf_mmap *md = &evlist->mmap[idx];
+
+        /*
+         * Check messup is required for forward overwritable ring buffer:
+         * memory pointed by md->prev can be overwritten in this case.
+         * No need for read-write ring buffer: kernel stop outputting when
+         * it hit md->prev (perf_mmap__consume()).
+         */
+        return perf_mmap__read_forward(md, evlist->overwrite);
+}
+
+union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 {
         struct perf_mmap *md = &evlist->mmap[idx];
+
+        /*
+         * No need to check messup for backward ring buffer:
+         * We can always read arbitrary long data from a backward
+         * ring buffer unless we forget to pause it before reading.
+         */
+        return perf_mmap__read_backward(md);
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+        return perf_evlist__mmap_read_forward(evlist, idx);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *md)
+{
         u64 head;
 
         if (!atomic_read(&md->refcnt))
@@ -844,36 +864,44 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
         md->prev = head;
 }
 
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+{
+        perf_mmap__read_catchup(&evlist->mmap[idx]);
+}
+
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
         return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
-static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+static void perf_mmap__get(struct perf_mmap *map)
 {
-        atomic_inc(&evlist->mmap[idx].refcnt);
+        atomic_inc(&map->refcnt);
 }
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+static void perf_mmap__put(struct perf_mmap *md)
 {
-        BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
+        BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
 
-        if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
-                __perf_evlist__munmap(evlist, idx);
+        if (atomic_dec_and_test(&md->refcnt))
+                perf_mmap__munmap(md);
 }
 
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 {
-        struct perf_mmap *md = &evlist->mmap[idx];
-
-        if (!evlist->overwrite) {
+        if (!overwrite) {
                 u64 old = md->prev;
 
                 perf_mmap__write_tail(md, old);
         }
 
         if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-                perf_evlist__mmap_put(evlist, idx);
+                perf_mmap__put(md);
+}
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+        perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
 int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
@@ -904,41 +932,52 @@ void __weak auxtrace_mmap_params__set_idx(
 {
 }
 
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+static void perf_mmap__munmap(struct perf_mmap *map)
 {
-        if (evlist->mmap[idx].base != NULL) {
-                munmap(evlist->mmap[idx].base, evlist->mmap_len);
-                evlist->mmap[idx].base = NULL;
-                evlist->mmap[idx].fd = -1;
-                atomic_set(&evlist->mmap[idx].refcnt, 0);
+        if (map->base != NULL) {
+                munmap(map->base, perf_mmap__mmap_len(map));
+                map->base = NULL;
+                map->fd = -1;
+                atomic_set(&map->refcnt, 0);
         }
-        auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
+        auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-void perf_evlist__munmap(struct perf_evlist *evlist)
+static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
         int i;
 
-        if (evlist->mmap == NULL)
-                return;
+        if (evlist->mmap)
+                for (i = 0; i < evlist->nr_mmaps; i++)
+                        perf_mmap__munmap(&evlist->mmap[i]);
 
-        for (i = 0; i < evlist->nr_mmaps; i++)
-                __perf_evlist__munmap(evlist, i);
+        if (evlist->backward_mmap)
+                for (i = 0; i < evlist->nr_mmaps; i++)
+                        perf_mmap__munmap(&evlist->backward_mmap[i]);
+}
 
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+        perf_evlist__munmap_nofree(evlist);
         zfree(&evlist->mmap);
+        zfree(&evlist->backward_mmap);
 }
 
-static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
         int i;
+        struct perf_mmap *map;
 
         evlist->nr_mmaps = cpu_map__nr(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));
+        map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+        if (!map)
+                return NULL;
+
         for (i = 0; i < evlist->nr_mmaps; i++)
-                evlist->mmap[i].fd = -1;
-        return evlist->mmap != NULL ? 0 : -ENOMEM;
+                map[i].fd = -1;
+        return map;
 }
 
 struct mmap_params {
@@ -947,8 +986,8 @@ struct mmap_params {
         struct auxtrace_mmap_params auxtrace_mp;
 };
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
-                               struct mmap_params *mp, int fd)
+static int perf_mmap__mmap(struct perf_mmap *map,
+                           struct mmap_params *mp, int fd)
 {
         /*
          * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -963,35 +1002,61 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
          * evlist layer can't just drop it when filtering events in
          * perf_evlist__filter_pollfd().
          */
-        atomic_set(&evlist->mmap[idx].refcnt, 2);
-        evlist->mmap[idx].prev = 0;
-        evlist->mmap[idx].mask = mp->mask;
-        evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
-                                      MAP_SHARED, fd, 0);
-        if (evlist->mmap[idx].base == MAP_FAILED) {
+        atomic_set(&map->refcnt, 2);
+        map->prev = 0;
+        map->mask = mp->mask;
+        map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+                         MAP_SHARED, fd, 0);
+        if (map->base == MAP_FAILED) {
                 pr_debug2("failed to mmap perf event ring buffer, error %d\n",
                           errno);
-                evlist->mmap[idx].base = NULL;
+                map->base = NULL;
                 return -1;
         }
-        evlist->mmap[idx].fd = fd;
+        map->fd = fd;
 
-        if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
-                                &mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+        if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+                                &mp->auxtrace_mp, map->base, fd))
                 return -1;
 
         return 0;
 }
 
+static bool
+perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
+                         struct perf_evsel *evsel)
+{
+        if (evsel->attr.write_backward)
+                return false;
+        return true;
+}
+
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                                        struct mmap_params *mp, int cpu,
-                                       int thread, int *output)
+                                       int thread, int *_output, int *_output_backward)
 {
         struct perf_evsel *evsel;
+        int revent;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
+                struct perf_mmap *maps = evlist->mmap;
+                int *output = _output;
                 int fd;
 
+                if (evsel->attr.write_backward) {
+                        output = _output_backward;
+                        maps = evlist->backward_mmap;
+
+                        if (!maps) {
+                                maps = perf_evlist__alloc_mmap(evlist);
+                                if (!maps)
+                                        return -1;
+                                evlist->backward_mmap = maps;
+                                if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
+                                        perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+                        }
+                }
+
                 if (evsel->system_wide && thread)
                         continue;
 
@@ -999,15 +1064,18 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
                 if (*output == -1) {
                         *output = fd;
-                        if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
+
+                        if (perf_mmap__mmap(&maps[idx], mp, *output)  < 0)
                                 return -1;
                 } else {
                         if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
                                 return -1;
 
-                        perf_evlist__mmap_get(evlist, idx);
+                        perf_mmap__get(&maps[idx]);
                 }
 
+                revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0;
+
                 /*
                  * The system_wide flag causes a selected event to be opened
                  * always without a pid.  Consequently it will never get a
@@ -1016,8 +1084,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
                  * Therefore don't add it for polling.
                  */
                 if (!evsel->system_wide &&
-                    __perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
-                        perf_evlist__mmap_put(evlist, idx);
+                    __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) {
+                        perf_mmap__put(&maps[idx]);
                         return -1;
                 }
 
@@ -1043,13 +1111,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
         pr_debug2("perf event ring buffer mmapped per cpu\n");
         for (cpu = 0; cpu < nr_cpus; cpu++) {
                 int output = -1;
+                int output_backward = -1;
 
                 auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
                                               true);
 
                 for (thread = 0; thread < nr_threads; thread++) {
                         if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-                                                        thread, &output))
+                                                        thread, &output, &output_backward))
                                 goto out_unmap;
                 }
         }
@@ -1057,8 +1126,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
         return 0;
 
 out_unmap:
-        for (cpu = 0; cpu < nr_cpus; cpu++)
-                __perf_evlist__munmap(evlist, cpu);
+        perf_evlist__munmap_nofree(evlist);
         return -1;
 }
 
@@ -1071,20 +1139,20 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
         pr_debug2("perf event ring buffer mmapped per thread\n");
         for (thread = 0; thread < nr_threads; thread++) {
                 int output = -1;
+                int output_backward = -1;
 
                 auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
                                               false);
 
                 if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-                                                &output))
+                                                &output, &output_backward))
                         goto out_unmap;
         }
 
         return 0;
 
 out_unmap:
-        for (thread = 0; thread < nr_threads; thread++)
-                __perf_evlist__munmap(evlist, thread);
+        perf_evlist__munmap_nofree(evlist);
         return -1;
 }
 
@@ -1217,7 +1285,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
                 .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
         };
 
-        if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+        if (!evlist->mmap)
+                evlist->mmap = perf_evlist__alloc_mmap(evlist);
+        if (!evlist->mmap)
                 return -ENOMEM;
 
         if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
@@ -1231,7 +1301,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
         auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
                                    auxtrace_pages, auxtrace_overwrite);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
                     evsel->sample_id == NULL &&
                     perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -1307,7 +1377,7 @@ void __perf_evlist__set_sample_bit(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 __perf_evsel__set_sample_bit(evsel, bit);
 }
 
@@ -1316,7 +1386,7 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 __perf_evsel__reset_sample_bit(evsel, bit);
 }
 
@@ -1327,7 +1397,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
         const int ncpus = cpu_map__nr(evlist->cpus),
                   nthreads = thread_map__nr(evlist->threads);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->filter == NULL)
                         continue;
 
@@ -1350,7 +1420,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
         struct perf_evsel *evsel;
         int err = 0;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
 
@@ -1404,7 +1474,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
         if (evlist->id_pos < 0 || evlist->is_pos < 0)
                 return false;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (pos->id_pos != evlist->id_pos ||
                     pos->is_pos != evlist->is_pos)
                         return false;
@@ -1420,7 +1490,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
         if (evlist->combined_sample_type)
                 return evlist->combined_sample_type;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 evlist->combined_sample_type |= evsel->attr.sample_type;
 
         return evlist->combined_sample_type;
@@ -1437,7 +1507,7 @@ u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist)
         struct perf_evsel *evsel;
         u64 branch_type = 0;
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 branch_type |= evsel->attr.branch_sample_type;
         return branch_type;
 }
@@ -1448,7 +1518,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
         u64 read_format = first->attr.read_format;
         u64 sample_type = first->attr.sample_type;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (read_format != pos->attr.read_format)
                         return false;
         }
@@ -1505,7 +1575,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
         struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-        evlist__for_each_continue(evlist, pos) {
+        evlist__for_each_entry_continue(evlist, pos) {
                 if (first->attr.sample_id_all != pos->attr.sample_id_all)
                         return false;
         }
@@ -1532,7 +1602,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
         int nthreads = thread_map__nr(evlist->threads);
         int n;
 
-        evlist__for_each_reverse(evlist, evsel) {
+        evlist__for_each_entry_reverse(evlist, evsel) {
                 n = evsel->cpus ? evsel->cpus->nr : ncpus;
                 perf_evsel__close(evsel, n, nthreads);
         }
@@ -1586,7 +1656,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
         perf_evlist__update_id_pos(evlist);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 err = perf_evsel__open(evsel, evsel->cpus, evsel->threads);
                 if (err < 0)
                         goto out_err;
@@ -1747,7 +1817,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
         struct perf_evsel *evsel;
         size_t printed = 0;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
                                    perf_evsel__name(evsel));
         }
@@ -1759,7 +1829,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist,
                                int err, char *buf, size_t size)
 {
         int printed, value;
-        char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+        char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
 
         switch (err) {
         case EACCES:
@@ -1811,7 +1881,7 @@ out_default:
 
 int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
 {
-        char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+        char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf));
         int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
 
         switch (err) {
@@ -1849,7 +1919,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
         if (move_evsel == perf_evlist__first(evlist))
                 return;
 
-        evlist__for_each_safe(evlist, n, evsel) {
+        evlist__for_each_entry_safe(evlist, n, evsel) {
                 if (evsel->leader == move_evsel->leader)
                         list_move_tail(&evsel->node, &move);
         }
@@ -1865,7 +1935,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
         if (tracking_evsel->tracking)
                 return;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel != tracking_evsel)
                         evsel->tracking = false;
         }
@@ -1879,7 +1949,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (!evsel->name)
                         continue;
                 if (strcmp(str, evsel->name) == 0)
@@ -1888,3 +1958,61 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 
         return NULL;
 }
+
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
+                                  enum bkw_mmap_state state)
+{
+        enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
+        enum action {
+                NONE,
+                PAUSE,
+                RESUME,
+        } action = NONE;
+
+        if (!evlist->backward_mmap)
+                return;
+
+        switch (old_state) {
+        case BKW_MMAP_NOTREADY: {
+                if (state != BKW_MMAP_RUNNING)
+                        goto state_err;;
+                break;
+        }
+        case BKW_MMAP_RUNNING: {
+                if (state != BKW_MMAP_DATA_PENDING)
+                        goto state_err;
+                action = PAUSE;
+                break;
+        }
+        case BKW_MMAP_DATA_PENDING: {
+                if (state != BKW_MMAP_EMPTY)
+                        goto state_err;
+                break;
+        }
+        case BKW_MMAP_EMPTY: {
+                if (state != BKW_MMAP_RUNNING)
+                        goto state_err;
+                action = RESUME;
+                break;
+        }
+        default:
+                WARN_ONCE(1, "Shouldn't get there\n");
+        }
+
+        evlist->bkw_mmap_state = state;
+
+        switch (action) {
+        case PAUSE:
+                perf_evlist__pause(evlist);
+                break;
+        case RESUME:
+                perf_evlist__resume(evlist);
+                break;
+        case NONE:
+        default:
+                break;
+        }
+
+state_err:
+        return;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index d740fb877ab6..4fd034f22d2f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -35,6 +35,40 @@ struct perf_mmap {
         char             event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
+static inline size_t
+perf_mmap__mmap_len(struct perf_mmap *map)
+{
+        return map->mask + 1 + page_size;
+}
+
+/*
+ * State machine of bkw_mmap_state:
+ *
+ *                     .________________(forbid)_____________.
+ *                     |                                     V
+ * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY
+ *                     ^  ^              |   ^               |
+ *                     |  |__(forbid)____/   |___(forbid)___/|
+ *                     |                                     |
+ *                      \_________________(3)_______________/
+ *
+ * NOTREADY     : Backward ring buffers are not ready
+ * RUNNING      : Backward ring buffers are recording
+ * DATA_PENDING : We are required to collect data from backward ring buffers
+ * EMPTY        : We have collected data from backward ring buffers.
+ *
+ * (0): Setup backward ring buffer
+ * (1): Pause ring buffers for reading
+ * (2): Read from ring buffers
+ * (3): Resume ring buffers for recording
+ */
+enum bkw_mmap_state {
+        BKW_MMAP_NOTREADY,
+        BKW_MMAP_RUNNING,
+        BKW_MMAP_DATA_PENDING,
+        BKW_MMAP_EMPTY,
+};
+
 struct perf_evlist {
         struct list_head entries;
         struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
@@ -44,17 +78,18 @@ struct perf_evlist {
         bool             overwrite;
         bool             enabled;
         bool             has_user_cpus;
-        bool             backward;
         size_t           mmap_len;
         int              id_pos;
         int              is_pos;
         u64              combined_sample_type;
+        enum bkw_mmap_state bkw_mmap_state;
         struct {
                 int     cork_fd;
                 pid_t   pid;
         } workload;
         struct fdarray   pollfd;
         struct perf_mmap *mmap;
+        struct perf_mmap *backward_mmap;
         struct thread_map *threads;
         struct cpu_map    *cpus;
         struct perf_evsel *selected;
@@ -129,16 +164,24 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist,
 
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
+
+union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup);
+union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+void perf_mmap__read_catchup(struct perf_mmap *md);
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite);
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
+                                                 int idx);
 union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
                                                   int idx);
 void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
 
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
-int perf_evlist__pause(struct perf_evlist *evlist);
-int perf_evlist__resume(struct perf_evlist *evlist);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
@@ -249,70 +292,70 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
                            struct perf_evsel *move_evsel);
 
 /**
- * __evlist__for_each - iterate thru all the evsels
+ * __evlist__for_each_entry - iterate thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each(list, evsel) \
+#define __evlist__for_each_entry(list, evsel) \
         list_for_each_entry(evsel, list, node)
 
 /**
- * evlist__for_each - iterate thru all the evsels
+ * evlist__for_each_entry - iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each(evlist, evsel) \
-        __evlist__for_each(&(evlist)->entries, evsel)
+#define evlist__for_each_entry(evlist, evsel) \
+        __evlist__for_each_entry(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_continue - continue iteration thru all the evsels
+ * __evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_continue(list, evsel) \
+#define __evlist__for_each_entry_continue(list, evsel) \
         list_for_each_entry_continue(evsel, list, node)
 
 /**
- * evlist__for_each_continue - continue iteration thru all the evsels
+ * evlist__for_each_entry_continue - continue iteration thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_continue(evlist, evsel) \
-        __evlist__for_each_continue(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_continue(evlist, evsel) \
+        __evlist__for_each_entry_continue(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @list: list_head instance to iterate
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_reverse(list, evsel) \
+#define __evlist__for_each_entry_reverse(list, evsel) \
         list_for_each_entry_reverse(evsel, list, node)
 
 /**
- * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  */
-#define evlist__for_each_reverse(evlist, evsel) \
-        __evlist__for_each_reverse(&(evlist)->entries, evsel)
+#define evlist__for_each_entry_reverse(evlist, evsel) \
+        __evlist__for_each_entry_reverse(&(evlist)->entries, evsel)
 
 /**
- * __evlist__for_each_safe - safely iterate thru all the evsels
+ * __evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @list: list_head instance to iterate
  * @tmp: struct evsel temp iterator
  * @evsel: struct evsel iterator
  */
-#define __evlist__for_each_safe(list, tmp, evsel) \
+#define __evlist__for_each_entry_safe(list, tmp, evsel) \
         list_for_each_entry_safe(evsel, tmp, list, node)
 
 /**
- * evlist__for_each_safe - safely iterate thru all the evsels
+ * evlist__for_each_entry_safe - safely iterate thru all the evsels
  * @evlist: evlist instance to iterate
  * @evsel: struct evsel iterator
  * @tmp: struct evsel temp iterator
  */
-#define evlist__for_each_safe(evlist, tmp, evsel) \
-        __evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
+        __evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel)
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
                                      struct perf_evsel *tracking_evsel);
@@ -321,4 +364,7 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
 
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
+
+struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+                                            union perf_event *event);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5d7037ef7d3b..d9b80ef881cd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -200,6 +200,24 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel,
         evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+        return evsel->name &&
+               !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
                       struct perf_event_attr *attr, int idx)
 {
@@ -235,6 +253,34 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         return evsel;
 }
 
+struct perf_evsel *perf_evsel__new_cycles(void)
+{
+        struct perf_event_attr attr = {
+                .type   = PERF_TYPE_HARDWARE,
+                .config = PERF_COUNT_HW_CPU_CYCLES,
+        };
+        struct perf_evsel *evsel;
+
+        event_attr_init(&attr);
+
+        perf_event_attr__set_max_precise_ip(&attr);
+
+        evsel = perf_evsel__new(&attr);
+        if (evsel == NULL)
+                goto out;
+
+        /* use asprintf() because free(evsel) assumes name is allocated */
+        if (asprintf(&evsel->name, "cycles%.*s",
+                     attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
+                goto error_free;
+out:
+        return evsel;
+error_free:
+        perf_evsel__delete(evsel);
+        evsel = NULL;
+        goto out;
+}
+
 /*
  * Returns pointer with encoded error via <linux/err.h> interface.
  */
@@ -572,6 +618,8 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,
 
         perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
+        attr->sample_max_stack = param->max_stack;
+
         if (param->record_mode == CALLCHAIN_LBR) {
                 if (!opts->branch_stack) {
                         if (attr->exclude_user) {
@@ -635,7 +683,8 @@ static void apply_config_terms(struct perf_evsel *evsel,
         struct perf_event_attr *attr = &evsel->attr;
         struct callchain_param param;
         u32 dump_size = 0;
-        char *callgraph_buf = NULL;
+        int max_stack = 0;
+        const char *callgraph_buf = NULL;
 
         /* callgraph default */
         param.record_mode = callchain_param.record_mode;
@@ -662,6 +711,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
                 case PERF_EVSEL__CONFIG_TERM_STACK_USER:
                         dump_size = term->val.stack_user;
                         break;
+                case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
+                        max_stack = term->val.max_stack;
+                        break;
                 case PERF_EVSEL__CONFIG_TERM_INHERIT:
                         /*
                          * attr->inherit should has already been set by
@@ -671,13 +723,21 @@ static void apply_config_terms(struct perf_evsel *evsel,
                          */
                         attr->inherit = term->val.inherit ? 1 : 0;
                         break;
+                case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
+                        attr->write_backward = term->val.overwrite ? 1 : 0;
+                        break;
                 default:
                         break;
                 }
         }
 
         /* User explicitly set per-event callgraph, clear the old setting and reset. */
-        if ((callgraph_buf != NULL) || (dump_size > 0)) {
+        if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
+                if (max_stack) {
+                        param.max_stack = max_stack;
+                        if (callgraph_buf == NULL)
+                                callgraph_buf = "fp";
+                }
 
                 /* parse callgraph parameters */
                 if (callgraph_buf != NULL) {
@@ -747,6 +807,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 
         attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
         attr->inherit       = !opts->no_inherit;
+        attr->write_backward = opts->overwrite ? 1 : 0;
 
         perf_evsel__set_sample_bit(evsel, IP);
         perf_evsel__set_sample_bit(evsel, TID);
@@ -821,7 +882,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
                 perf_evsel__set_sample_bit(evsel, REGS_INTR);
         }
 
-        if (target__has_cpu(&opts->target))
+        if (target__has_cpu(&opts->target) || opts->sample_cpu)
                 perf_evsel__set_sample_bit(evsel, CPU);
 
         if (opts->period)
@@ -1329,6 +1390,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
         PRINT_ATTRf(clockid, p_signed);
         PRINT_ATTRf(sample_regs_intr, p_hex);
         PRINT_ATTRf(aux_watermark, p_unsigned);
+        PRINT_ATTRf(sample_max_stack, p_unsigned);
 
         return ret;
 }
@@ -1347,6 +1409,9 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
         int pid = -1, err;
         enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+        if (perf_missing_features.write_backward && evsel->attr.write_backward)
+                return -EINVAL;
+
         if (evsel->system_wide)
                 nthreads = 1;
         else
@@ -1377,8 +1442,6 @@ fallback_missing_features:
         if (perf_missing_features.lbr_flags)
                 evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
                                      PERF_SAMPLE_BRANCH_NO_CYCLES);
-        if (perf_missing_features.write_backward)
-                evsel->attr.write_backward = false;
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
@@ -1441,12 +1504,6 @@ retry_open:
                                 err = -EINVAL;
                                 goto out_close;
                         }
-
-                        if (evsel->overwrite &&
-                            perf_missing_features.write_backward) {
-                                err = -EINVAL;
-                                goto out_close;
-                        }
                 }
         }
 
@@ -1484,7 +1541,10 @@ try_fallback:
          * Must probe features in the order they were added to the
          * perf_event_attr interface.
          */
-        if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
+        if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
+                perf_missing_features.write_backward = true;
+                goto out_close;
+        } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
                 perf_missing_features.clockid_wrong = true;
                 goto fallback_missing_features;
         } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
@@ -1509,12 +1569,7 @@ try_fallback:
                           PERF_SAMPLE_BRANCH_NO_FLAGS))) {
                 perf_missing_features.lbr_flags = true;
                 goto fallback_missing_features;
-        } else if (!perf_missing_features.write_backward &&
-                        evsel->attr.write_backward) {
-                perf_missing_features.write_backward = true;
-                goto fallback_missing_features;
         }
-
 out_close:
         do {
                 while (--thread >= 0) {
@@ -2239,17 +2294,11 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
         return sample->raw_data + offset;
 }
 
-u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
-                       const char *name)
+u64 format_field__intval(struct format_field *field, struct perf_sample *sample,
+                         bool needs_swap)
 {
-        struct format_field *field = perf_evsel__field(evsel, name);
-        void *ptr;
         u64 value;
-
-        if (!field)
-                return 0;
-
-        ptr = sample->raw_data + field->offset;
+        void *ptr = sample->raw_data + field->offset;
 
         switch (field->size) {
         case 1:
@@ -2267,7 +2316,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
                 return 0;
         }
 
-        if (!evsel->needs_swap)
+        if (!needs_swap)
                 return value;
 
         switch (field->size) {
@@ -2284,6 +2333,17 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
         return 0;
 }
 
+u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
+                       const char *name)
+{
+        struct format_field *field = perf_evsel__field(evsel, name);
+
+        if (!field)
+                return 0;
+
+        return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
+}
+
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
                           char *msg, size_t msgsize)
 {
@@ -2372,6 +2432,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
          "No such device - did you specify an out-of-range profile CPU?");
                 break;
         case EOPNOTSUPP:
+                if (evsel->attr.sample_period != 0)
+                        return scnprintf(msg, size, "%s",
+        "PMU Hardware doesn't support sampling/overflow-interrupts.");
                 if (evsel->attr.precise_ip)
                         return scnprintf(msg, size, "%s",
         "\'precise\' request may not be supported. Try removing 'p' modifier.");
@@ -2389,6 +2452,8 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
         "We found oprofile daemon running, please stop it and try again.");
                 break;
         case EINVAL:
+                if (evsel->attr.write_backward && perf_missing_features.write_backward)
+                        return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
                 if (perf_missing_features.clockid)
                         return scnprintf(msg, size, "clockid feature not supported.");
                 if (perf_missing_features.clockid_wrong)
@@ -2402,6 +2467,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
         "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
         "/bin/dmesg may provide additional information.\n"
         "No CONFIG_PERF_EVENTS=y kernel support configured?",
-                         err, strerror_r(err, sbuf, sizeof(sbuf)),
+                         err, str_error_r(err, sbuf, sizeof(sbuf)),
                          perf_evsel__name(evsel));
 }
+
+char *perf_evsel__env_arch(struct perf_evsel *evsel)
+{
+        if (evsel && evsel->evlist && evsel->evlist->env)
+                return evsel->evlist->env->arch;
+        return NULL;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c1f10159804c..4d44129e050b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -44,6 +44,8 @@ enum {
         PERF_EVSEL__CONFIG_TERM_CALLGRAPH,
         PERF_EVSEL__CONFIG_TERM_STACK_USER,
         PERF_EVSEL__CONFIG_TERM_INHERIT,
+        PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+        PERF_EVSEL__CONFIG_TERM_OVERWRITE,
         PERF_EVSEL__CONFIG_TERM_MAX,
 };
 
@@ -56,7 +58,9 @@ struct perf_evsel_config_term {
                 bool    time;
                 char    *callgraph;
                 u64     stack_user;
+                int     max_stack;
                 bool    inherit;
+                bool    overwrite;
         } val;
 };
 
@@ -112,7 +116,6 @@ struct perf_evsel {
         bool                    tracking;
         bool                    per_pkg;
         bool                    precise_max;
-        bool                    overwrite;
         /* parse modifier helper */
         int                     exclude_GH;
         int                     nr_members;
@@ -172,6 +175,8 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
         return perf_evsel__newtp_idx(sys, name, 0);
 }
 
+struct perf_evsel *perf_evsel__new_cycles(void);
+
 struct event_format *event_format__new(const char *sys, const char *name);
 
 void perf_evsel__init(struct perf_evsel *evsel,
@@ -259,6 +264,8 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel,
 
 struct format_field;
 
+u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap);
+
 struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name);
 
 #define perf_evsel__match(evsel, t, c)          \
@@ -351,23 +358,7 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
         return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
 }
 
-/**
- * perf_evsel__is_function_event - Return whether given evsel is a function
- * trace event
- *
- * @evsel - evsel selector to be tested
- *
- * Return %true if event is function trace event
- */
-static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
-{
-#define FUNCTION_EVENT "ftrace:function"
-
-        return evsel->name &&
-               !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
-
-#undef FUNCTION_EVENT
-}
+bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
@@ -431,4 +422,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
                              attr__fprintf_f attr__fprintf, void *priv);
 
+char *perf_evsel__env_arch(struct perf_evsel *evsel);
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h
new file mode 100644
index 000000000000..116debe7a995
--- /dev/null
+++ b/tools/perf/util/group.h
@@ -0,0 +1,7 @@
+#ifndef GROUP_H
+#define GROUP_H 1
+
+bool arch_topdown_check_group(bool *warn);
+void arch_topdown_group_warn(void);
+
+#endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 08852dde1378..8f0db4007282 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -336,7 +336,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 ret = do_write(fd, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
@@ -801,7 +801,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         const char *name = evsel->group_name ?: "{anon_group}";
@@ -1306,42 +1306,19 @@ static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
 static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
                                 FILE *fp)
 {
-        u32 nr, c, i;
-        char *str, *tmp;
-        uint64_t mem_total, mem_free;
-
-        /* nr nodes */
-        nr = ph->env.nr_numa_nodes;
-        str = ph->env.numa_nodes;
-
-        for (i = 0; i < nr; i++) {
-                /* node number */
-                c = strtoul(str, &tmp, 0);
-                if (*tmp != ':')
-                        goto error;
-
-                str = tmp + 1;
-                mem_total = strtoull(str, &tmp, 0);
-                if (*tmp != ':')
-                        goto error;
+        int i;
+        struct numa_node *n;
 
-                str = tmp + 1;
-                mem_free = strtoull(str, &tmp, 0);
-                if (*tmp != ':')
-                        goto error;
+        for (i = 0; i < ph->env.nr_numa_nodes; i++) {
+                n = &ph->env.numa_nodes[i];
 
                 fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
                             " free = %"PRIu64" kB\n",
-                        c, mem_total, mem_free);
+                        n->node, n->mem_total, n->mem_free);
 
-                str = tmp + 1;
-                fprintf(fp, "# node%u cpu list : %s\n", c, str);
-
-                str += strlen(str) + 1;
+                fprintf(fp, "# node%u cpu list : ", n->node);
+                cpu_map__fprintf(n->map, fp);
         }
-        return;
-error:
-        fprintf(fp, "# numa topology : not available\n");
 }
 
 static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
@@ -1425,7 +1402,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
         session = container_of(ph, struct perf_session, header);
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1703,7 +1680,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->idx == idx)
                         return evsel;
         }
@@ -1906,11 +1883,10 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
                                  struct perf_header *ph, int fd,
                                  void *data __maybe_unused)
 {
+        struct numa_node *nodes, *n;
         ssize_t ret;
-        u32 nr, node, i;
+        u32 nr, i;
         char *str;
-        uint64_t mem_total, mem_free;
-        struct strbuf sb;
 
         /* nr nodes */
         ret = readn(fd, &nr, sizeof(nr));
@@ -1921,47 +1897,47 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
                 nr = bswap_32(nr);
 
         ph->env.nr_numa_nodes = nr;
-        if (strbuf_init(&sb, 256) < 0)
-                return -1;
+        nodes = zalloc(sizeof(*nodes) * nr);
+        if (!nodes)
+                return -ENOMEM;
 
         for (i = 0; i < nr; i++) {
+                n = &nodes[i];
+
                 /* node number */
-                ret = readn(fd, &node, sizeof(node));
-                if (ret != sizeof(node))
+                ret = readn(fd, &n->node, sizeof(u32));
+                if (ret != sizeof(n->node))
                         goto error;
 
-                ret = readn(fd, &mem_total, sizeof(u64));
+                ret = readn(fd, &n->mem_total, sizeof(u64));
                 if (ret != sizeof(u64))
                         goto error;
 
-                ret = readn(fd, &mem_free, sizeof(u64));
+                ret = readn(fd, &n->mem_free, sizeof(u64));
                 if (ret != sizeof(u64))
                         goto error;
 
                 if (ph->needs_swap) {
-                        node = bswap_32(node);
-                        mem_total = bswap_64(mem_total);
-                        mem_free = bswap_64(mem_free);
+                        n->node      = bswap_32(n->node);
+                        n->mem_total = bswap_64(n->mem_total);
+                        n->mem_free  = bswap_64(n->mem_free);
                 }
 
-                if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
-                                node, mem_total, mem_free) < 0)
-                        goto error;
-
                 str = do_read_string(fd, ph);
                 if (!str)
                         goto error;
 
-                /* include a NULL character at the end */
-                if (strbuf_add(&sb, str, strlen(str) + 1) < 0)
+                n->map = cpu_map__new(str);
+                if (!n->map)
                         goto error;
+
                 free(str);
         }
-        ph->env.numa_nodes = strbuf_detach(&sb, NULL);
+        ph->env.numa_nodes = nodes;
         return 0;
 
 error:
-        strbuf_release(&sb);
+        free(nodes);
         return -1;
 }
 
@@ -2075,7 +2051,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
         session->evlist->nr_groups = nr_groups;
 
         i = nr = 0;
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (evsel->idx == (int) desc[i].leader_idx) {
                         evsel->leader = evsel;
                         /* {anon_group} is a dummy name */
@@ -2383,7 +2359,7 @@ int perf_session__write_header(struct perf_session *session,
 
         lseek(fd, sizeof(f_header), SEEK_SET);
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 evsel->id_offset = lseek(fd, 0, SEEK_CUR);
                 err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
@@ -2394,7 +2370,7 @@ int perf_session__write_header(struct perf_session *session,
 
         attr_offset = lseek(fd, 0, SEEK_CUR);
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 f_attr = (struct perf_file_attr){
                         .attr = evsel->attr,
                         .ids  = {
@@ -2828,7 +2804,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
         struct perf_evsel *pos;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
                     perf_evsel__prepare_tracepoint_event(pos, pevent))
                         return -1;
@@ -3127,7 +3103,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
         struct perf_evsel *evsel;
         int err = 0;
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
                                                   evsel->id, process);
                 if (err) {
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index d62ccaeeadd6..2821f8d77e52 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -1,4 +1,6 @@
 #include "cache.h"
+#include "config.h"
+#include <stdio.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d1f19e0012d4..de15dbcdcecf 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -79,7 +79,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
         len = thread__comm_len(h->thread);
         if (hists__new_col_len(hists, HISTC_COMM, len))
-                hists__set_col_len(hists, HISTC_THREAD, len + 6);
+                hists__set_col_len(hists, HISTC_THREAD, len + 8);
 
         if (h->ms.map) {
                 len = dso__name_len(h->ms.map->dso);
@@ -352,86 +352,114 @@ void hists__delete_entries(struct hists *hists)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template,
-                                          bool sample_self)
+static int hist_entry__init(struct hist_entry *he,
+                            struct hist_entry *template,
+                            bool sample_self)
 {
-        size_t callchain_size = 0;
-        struct hist_entry *he;
+        *he = *template;
 
-        if (symbol_conf.use_callchain)
-                callchain_size = sizeof(struct callchain_root);
+        if (symbol_conf.cumulate_callchain) {
+                he->stat_acc = malloc(sizeof(he->stat));
+                if (he->stat_acc == NULL)
+                        return -ENOMEM;
+                memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+                if (!sample_self)
+                        memset(&he->stat, 0, sizeof(he->stat));
+        }
+
+        map__get(he->ms.map);
+
+        if (he->branch_info) {
+                /*
+                 * This branch info is (a part of) allocated from
+                 * sample__resolve_bstack() and will be freed after
+                 * adding new entries.  So we need to save a copy.
+                 */
+                he->branch_info = malloc(sizeof(*he->branch_info));
+                if (he->branch_info == NULL) {
+                        map__zput(he->ms.map);
+                        free(he->stat_acc);
+                        return -ENOMEM;
+                }
+
+                memcpy(he->branch_info, template->branch_info,
+                       sizeof(*he->branch_info));
+
+                map__get(he->branch_info->from.map);
+                map__get(he->branch_info->to.map);
+        }
+
+        if (he->mem_info) {
+                map__get(he->mem_info->iaddr.map);
+                map__get(he->mem_info->daddr.map);
+        }
 
-        he = zalloc(sizeof(*he) + callchain_size);
+        if (symbol_conf.use_callchain)
+                callchain_init(he->callchain);
 
-        if (he != NULL) {
-                *he = *template;
+        if (he->raw_data) {
+                he->raw_data = memdup(he->raw_data, he->raw_size);
 
-                if (symbol_conf.cumulate_callchain) {
-                        he->stat_acc = malloc(sizeof(he->stat));
-                        if (he->stat_acc == NULL) {
-                                free(he);
-                                return NULL;
+                if (he->raw_data == NULL) {
+                        map__put(he->ms.map);
+                        if (he->branch_info) {
+                                map__put(he->branch_info->from.map);
+                                map__put(he->branch_info->to.map);
+                                free(he->branch_info);
+                        }
+                        if (he->mem_info) {
+                                map__put(he->mem_info->iaddr.map);
+                                map__put(he->mem_info->daddr.map);
                         }
-                        memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
-                        if (!sample_self)
-                                memset(&he->stat, 0, sizeof(he->stat));
+                        free(he->stat_acc);
+                        return -ENOMEM;
                 }
+        }
+        INIT_LIST_HEAD(&he->pairs.node);
+        thread__get(he->thread);
 
-                map__get(he->ms.map);
+        if (!symbol_conf.report_hierarchy)
+                he->leaf = true;
 
-                if (he->branch_info) {
-                        /*
-                         * This branch info is (a part of) allocated from
-                         * sample__resolve_bstack() and will be freed after
-                         * adding new entries.  So we need to save a copy.
-                         */
-                        he->branch_info = malloc(sizeof(*he->branch_info));
-                        if (he->branch_info == NULL) {
-                                map__zput(he->ms.map);
-                                free(he->stat_acc);
-                                free(he);
-                                return NULL;
-                        }
+        return 0;
+}
 
-                        memcpy(he->branch_info, template->branch_info,
-                               sizeof(*he->branch_info));
+static void *hist_entry__zalloc(size_t size)
+{
+        return zalloc(size + sizeof(struct hist_entry));
+}
 
-                        map__get(he->branch_info->from.map);
-                        map__get(he->branch_info->to.map);
-                }
+static void hist_entry__free(void *ptr)
+{
+        free(ptr);
+}
 
-                if (he->mem_info) {
-                        map__get(he->mem_info->iaddr.map);
-                        map__get(he->mem_info->daddr.map);
-                }
+static struct hist_entry_ops default_ops = {
+        .new    = hist_entry__zalloc,
+        .free   = hist_entry__free,
+};
 
-                if (symbol_conf.use_callchain)
-                        callchain_init(he->callchain);
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+                                          bool sample_self)
+{
+        struct hist_entry_ops *ops = template->ops;
+        size_t callchain_size = 0;
+        struct hist_entry *he;
+        int err = 0;
 
-                if (he->raw_data) {
-                        he->raw_data = memdup(he->raw_data, he->raw_size);
+        if (!ops)
+                ops = template->ops = &default_ops;
 
-                        if (he->raw_data == NULL) {
-                                map__put(he->ms.map);
-                                if (he->branch_info) {
-                                        map__put(he->branch_info->from.map);
-                                        map__put(he->branch_info->to.map);
-                                        free(he->branch_info);
-                                }
-                                if (he->mem_info) {
-                                        map__put(he->mem_info->iaddr.map);
-                                        map__put(he->mem_info->daddr.map);
-                                }
-                                free(he->stat_acc);
-                                free(he);
-                                return NULL;
-                        }
-                }
-                INIT_LIST_HEAD(&he->pairs.node);
-                thread__get(he->thread);
+        if (symbol_conf.use_callchain)
+                callchain_size = sizeof(struct callchain_root);
 
-                if (!symbol_conf.report_hierarchy)
-                        he->leaf = true;
+        he = ops->new(callchain_size);
+        if (he) {
+                err = hist_entry__init(he, template, sample_self);
+                if (err) {
+                        ops->free(he);
+                        he = NULL;
+                }
         }
 
         return he;
@@ -531,13 +559,15 @@ out:
         return he;
 }
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
-                                      struct addr_location *al,
-                                      struct symbol *sym_parent,
-                                      struct branch_info *bi,
-                                      struct mem_info *mi,
-                                      struct perf_sample *sample,
-                                      bool sample_self)
+static struct hist_entry*
+__hists__add_entry(struct hists *hists,
+                   struct addr_location *al,
+                   struct symbol *sym_parent,
+                   struct branch_info *bi,
+                   struct mem_info *mi,
+                   struct perf_sample *sample,
+                   bool sample_self,
+                   struct hist_entry_ops *ops)
 {
         struct hist_entry entry = {
                 .thread = al->thread,
@@ -564,11 +594,37 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                 .transaction = sample->transaction,
                 .raw_data = sample->raw_data,
                 .raw_size = sample->raw_size,
+                .ops = ops,
         };
 
         return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
+struct hist_entry *hists__add_entry(struct hists *hists,
+                                    struct addr_location *al,
+                                    struct symbol *sym_parent,
+                                    struct branch_info *bi,
+                                    struct mem_info *mi,
+                                    struct perf_sample *sample,
+                                    bool sample_self)
+{
+        return __hists__add_entry(hists, al, sym_parent, bi, mi,
+                                  sample, sample_self, NULL);
+}
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+                                        struct hist_entry_ops *ops,
+                                        struct addr_location *al,
+                                        struct symbol *sym_parent,
+                                        struct branch_info *bi,
+                                        struct mem_info *mi,
+                                        struct perf_sample *sample,
+                                        bool sample_self)
+{
+        return __hists__add_entry(hists, al, sym_parent, bi, mi,
+                                  sample, sample_self, ops);
+}
+
 static int
 iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
                     struct addr_location *al __maybe_unused)
@@ -622,8 +678,8 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al
          */
         sample->period = cost;
 
-        he = __hists__add_entry(hists, al, iter->parent, NULL, mi,
-                                sample, true);
+        he = hists__add_entry(hists, al, iter->parent, NULL, mi,
+                              sample, true);
         if (!he)
                 return -ENOMEM;
 
@@ -727,8 +783,8 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
         sample->period = 1;
         sample->weight = bi->flags.cycles ? bi->flags.cycles : 1;
 
-        he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-                                sample, true);
+        he = hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
+                              sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -764,8 +820,8 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location
         struct perf_sample *sample = iter->sample;
         struct hist_entry *he;
 
-        he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-                                sample, true);
+        he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+                              sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -825,8 +881,8 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
         struct hist_entry *he;
         int err = 0;
 
-        he = __hists__add_entry(hists, al, iter->parent, NULL, NULL,
-                                sample, true);
+        he = hists__add_entry(hists, al, iter->parent, NULL, NULL,
+                              sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -900,8 +956,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
                 }
         }
 
-        he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
-                                sample, false);
+        he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL,
+                              sample, false);
         if (he == NULL)
                 return -ENOMEM;
 
@@ -1043,6 +1099,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__delete(struct hist_entry *he)
 {
+        struct hist_entry_ops *ops = he->ops;
+
         thread__zput(he->thread);
         map__zput(he->ms.map);
 
@@ -1067,7 +1125,7 @@ void hist_entry__delete(struct hist_entry *he)
         free_callchain(he->callchain);
         free(he->trace_output);
         free(he->raw_data);
-        free(he);
+        ops->free(he);
 }
 
 /*
@@ -1081,7 +1139,7 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
                                    struct perf_hpp_fmt *fmt, int printed)
 {
         if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
-                const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+                const int width = fmt->width(fmt, hpp, he->hists);
                 if (printed < width) {
                         advance_hpp(hpp, printed);
                         printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
@@ -1614,7 +1672,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 }
 
 static void output_resort(struct hists *hists, struct ui_progress *prog,
-                          bool use_callchain)
+                          bool use_callchain, hists__resort_cb_t cb)
 {
         struct rb_root *root;
         struct rb_node *next;
@@ -1653,6 +1711,9 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
                 n = rb_entry(next, struct hist_entry, rb_node_in);
                 next = rb_next(&n->rb_node_in);
 
+                if (cb && cb(n))
+                        continue;
+
                 __hists__insert_output_entry(&hists->entries, n, min_callchain_hits, use_callchain);
                 hists__inc_stats(hists, n);
 
@@ -1673,12 +1734,18 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
         else
                 use_callchain = symbol_conf.use_callchain;
 
-        output_resort(evsel__hists(evsel), prog, use_callchain);
+        output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
 }
 
 void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
-        output_resort(hists, prog, symbol_conf.use_callchain);
+        output_resort(hists, prog, symbol_conf.use_callchain, NULL);
+}
+
+void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
+                             hists__resort_cb_t cb)
+{
+        output_resort(hists, prog, symbol_conf.use_callchain, cb);
 }
 
 static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
@@ -2199,7 +2266,7 @@ size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
         struct perf_evsel *pos;
         size_t ret = 0;
 
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
                 ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp);
         }
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 7b54ccf1b737..0a1edf1ab450 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -10,6 +10,7 @@
 #include "ui/progress.h"
 
 struct hist_entry;
+struct hist_entry_ops;
 struct addr_location;
 struct symbol;
 
@@ -120,13 +121,23 @@ extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
 extern const struct hist_iter_ops hist_iter_cumulative;
 
-struct hist_entry *__hists__add_entry(struct hists *hists,
-                                      struct addr_location *al,
-                                      struct symbol *parent,
-                                      struct branch_info *bi,
-                                      struct mem_info *mi,
-                                      struct perf_sample *sample,
-                                      bool sample_self);
+struct hist_entry *hists__add_entry(struct hists *hists,
+                                    struct addr_location *al,
+                                    struct symbol *parent,
+                                    struct branch_info *bi,
+                                    struct mem_info *mi,
+                                    struct perf_sample *sample,
+                                    bool sample_self);
+
+struct hist_entry *hists__add_entry_ops(struct hists *hists,
+                                        struct hist_entry_ops *ops,
+                                        struct addr_location *al,
+                                        struct symbol *sym_parent,
+                                        struct branch_info *bi,
+                                        struct mem_info *mi,
+                                        struct perf_sample *sample,
+                                        bool sample_self);
+
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
                          int max_stack_depth, void *arg);
 
@@ -142,8 +153,12 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
                                    struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+typedef int (*hists__resort_cb_t)(struct hist_entry *he);
+
 void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
+void hists__output_resort_cb(struct hists *hists, struct ui_progress *prog,
+                             hists__resort_cb_t cb);
 int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
@@ -159,7 +174,8 @@ void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
-                      int max_cols, float min_pcnt, FILE *fp);
+                      int max_cols, float min_pcnt, FILE *fp,
+                      bool use_callchain);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
@@ -214,9 +230,9 @@ struct perf_hpp {
 struct perf_hpp_fmt {
         const char *name;
         int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                      struct perf_evsel *evsel);
+                      struct hists *hists);
         int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                     struct perf_evsel *evsel);
+                     struct hists *hists);
         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,
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
deleted file mode 100644
index 3a3a0f16456a..000000000000
--- a/tools/perf/util/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
-#define _PERF_ASM_ALTERNATIVE_ASM_H
-
-/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
-
-#define altinstruction_entry #
-#define ALTERNATIVE_2 #
-
-#endif
diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h
deleted file mode 100644
index 2a9bdc066307..000000000000
--- a/tools/perf/util/include/asm/byteorder.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <asm/types.h>
-#include "../../../../include/uapi/linux/swab.h"
diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h
deleted file mode 100644
index 8b137891791f..000000000000
--- a/tools/perf/util/include/asm/unistd_32.h
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h
deleted file mode 100644
index 8b137891791f..000000000000
--- a/tools/perf/util/include/asm/unistd_64.h
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
deleted file mode 100644
index c10a35e1afb8..000000000000
--- a/tools/perf/util/include/linux/const.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/uapi/linux/const.h"
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 9df996085563..749e6f2e37ca 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -422,7 +422,8 @@ static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
 }
 
 static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
-                                    struct auxtrace_buffer *buffer)
+                                    struct auxtrace_buffer *buffer,
+                                    struct thread *thread)
 {
         struct branch *branch;
         size_t sz, bsz = sizeof(struct branch);
@@ -444,6 +445,12 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
                 if (!branch->from && !branch->to)
                         continue;
                 intel_bts_get_branch_type(btsq, branch);
+                if (btsq->bts->synth_opts.thread_stack)
+                        thread_stack__event(thread, btsq->sample_flags,
+                                            le64_to_cpu(branch->from),
+                                            le64_to_cpu(branch->to),
+                                            btsq->intel_pt_insn.length,
+                                            buffer->buffer_nr + 1);
                 if (filter && !(filter & btsq->sample_flags))
                         continue;
                 err = intel_bts_synth_branch_sample(btsq, branch);
@@ -507,12 +514,13 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
                 goto out_put;
         }
 
-        if (!btsq->bts->synth_opts.callchain && thread &&
+        if (!btsq->bts->synth_opts.callchain &&
+            !btsq->bts->synth_opts.thread_stack && thread &&
             (!old_buffer || btsq->bts->sampling_mode ||
              (btsq->bts->snapshot_mode && !buffer->consecutive)))
                 thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
 
-        err = intel_bts_process_buffer(btsq, buffer);
+        err = intel_bts_process_buffer(btsq, buffer, thread);
 
         auxtrace_buffer__drop_data(buffer);
 
@@ -777,7 +785,7 @@ static int intel_bts_synth_events(struct intel_bts *bts,
         u64 id;
         int err;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type == bts->pmu_type && evsel->ids) {
                         found = true;
                         break;
@@ -905,10 +913,14 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
         if (dump_trace)
                 return 0;
 
-        if (session->itrace_synth_opts && session->itrace_synth_opts->set)
+        if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
                 bts->synth_opts = *session->itrace_synth_opts;
-        else
+        } else {
                 itrace_synth_opts__set_default(&bts->synth_opts);
+                if (session->itrace_synth_opts)
+                        bts->synth_opts.thread_stack =
+                                session->itrace_synth_opts->thread_stack;
+        }
 
         if (bts->synth_opts.calls)
                 bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 0611d619a42e..9b742ea8bfe8 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -7,8 +7,11 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
         $(call rule_mkdir)
         @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
+# Busybox's diff doesn't have -I, avoid warning in the case
+
 $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
-        @(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
+        @(diff -I 2>&1 | grep -q 'option requires an argument' && \
+        test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
         diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
         diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
         diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
index 517567347aac..54e961659514 100644
--- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
+++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk
@@ -72,12 +72,14 @@ BEGIN {
         lprefix_expr = "\\((66|F2|F3)\\)"
         max_lprefix = 4
 
-        # All opcodes starting with lower-case 'v' or with (v1) superscript
+        # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
         # accepts VEX prefix
-        vexok_opcode_expr = "^v.*"
+        vexok_opcode_expr = "^[vk].*"
         vexok_expr = "\\(v1\\)"
         # All opcodes with (v) superscript supports *only* VEX prefix
         vexonly_expr = "\\(v\\)"
+        # All opcodes with (ev) superscript supports *only* EVEX prefix
+        evexonly_expr = "\\(ev\\)"
 
         prefix_expr = "\\(Prefix\\)"
         prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -95,6 +97,7 @@ BEGIN {
         prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
         prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
         prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+        prefix_num["EVEX"] = "INAT_PFX_EVEX"
 
         clear_vars()
 }
@@ -319,7 +322,9 @@ function convert_operands(count,opnd,       i,j,imm,mod)
                         flags = add_flags(flags, "INAT_MODRM")
 
                 # check VEX codes
-                if (match(ext, vexonly_expr))
+                if (match(ext, evexonly_expr))
+                        flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+                else if (match(ext, vexonly_expr))
                         flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
                 else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
                         flags = add_flags(flags, "INAT_VEXOK")
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 611645e903a8..125ecd2a300d 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2   13      /* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3   14      /* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX   15      /* EVEX prefix */
 
 #define INAT_LSTPFX_MAX 3
 #define INAT_LGCPFX_MAX 11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT    (1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK      (1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY    (1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY   (1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)   (pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)   (esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
         attr &= INAT_PFX_MASK;
-        return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+        return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+               attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+        return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-        return attr & INAT_VEXONLY;
+        return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+        return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c
index 9f26eae6c9f0..ca983e2bea8b 100644
--- a/tools/perf/util/intel-pt-decoder/insn.c
+++ b/tools/perf/util/intel-pt-decoder/insn.c
@@ -155,14 +155,24 @@ found:
                         /*
                          * In 32-bits mode, if the [7:6] bits (mod bits of
                          * ModRM) on the second byte are not 11b, it is
-                         * LDS or LES.
+                         * LDS or LES or BOUND.
                          */
                         if (X86_MODRM_MOD(b2) != 3)
                                 goto vex_end;
                 }
                 insn->vex_prefix.bytes[0] = b;
                 insn->vex_prefix.bytes[1] = b2;
-                if (inat_is_vex3_prefix(attr)) {
+                if (inat_is_evex_prefix(attr)) {
+                        b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+                        insn->vex_prefix.bytes[2] = b2;
+                        b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+                        insn->vex_prefix.bytes[3] = b2;
+                        insn->vex_prefix.nbytes = 4;
+                        insn->next_byte += 4;
+                        if (insn->x86_64 && X86_VEX_W(b2))
+                                /* VEX.W overrides opnd_size */
+                                insn->opnd_bytes = 8;
+                } else if (inat_is_vex3_prefix(attr)) {
                         b2 = peek_nbyte_next(insn_byte_t, insn, 2);
                         insn->vex_prefix.bytes[2] = b2;
                         insn->vex_prefix.nbytes = 3;
@@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn)
                 m = insn_vex_m_bits(insn);
                 p = insn_vex_p_bits(insn);
                 insn->attr = inat_get_avx_attribute(op, m, p);
-                if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
+                if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+                    (!inat_accept_vex(insn->attr) &&
+                     !inat_is_group(insn->attr)))
                         insn->attr = 0; /* This instruction is bad */
                 goto end;       /* VEX has only 1 byte for opcode */
         }
diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h
index dd12da0f4593..e23578c7b1be 100644
--- a/tools/perf/util/intel-pt-decoder/insn.h
+++ b/tools/perf/util/intel-pt-decoder/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)  ((vex) & 0x20)  /* VEX3 Byte1 */
 #define X86_VEX_L(vex)  ((vex) & 0x04)  /* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex) ((vex) & 0x03)          /* EVEX Byte1 */
 #define X86_VEX3_M(vex) ((vex) & 0x1f)          /* VEX3 Byte1 */
 #define X86_VEX2_M      1                       /* VEX2.M always 1 */
 #define X86_VEX_V(vex)  (((vex) & 0x78) >> 3)   /* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
         return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+        if (!insn->prefixes.got)
+                insn_get_prefixes(insn);
+        return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
         if (insn->vex_prefix.nbytes == 2)       /* 2 bytes VEX */
                 return X86_VEX2_M;
-        else
+        else if (insn->vex_prefix.nbytes == 3)  /* 3 bytes VEX */
                 return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+        else                                    /* EVEX */
+                return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index d388de72eaca..767be7c76034 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -13,12 +13,17 @@
 # opcode: escape # escaped-name
 # EndTable
 #
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
 #<group maps>
 # GrpTable: GrpXXX
 # reg:  mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
 # EndTable
 #
 # AVX Superscripts
+#  (ev): this opcode requires EVEX prefix.
+#  (evo): this opcode is changed by EVEX prefix (EVEX opcode)
 #  (v): this opcode requires VEX prefix.
 #  (v1): this opcode only supports 128bit VEX.
 #
@@ -137,7 +142,7 @@ AVXcode:
 # 0x60 - 0x6f
 60: PUSHA/PUSHAD (i64)
 61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
 64: SEG=FS (Prefix)
 65: SEG=GS (Prefix)
@@ -399,17 +404,17 @@ AVXcode: 1
 3f:
 # 0x0f 0x40-0x4f
 40: CMOVO Gv,Ev
-41: CMOVNO Gv,Ev
-42: CMOVB/C/NAE Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
 43: CMOVAE/NB/NC Gv,Ev
-44: CMOVE/Z Gv,Ev
-45: CMOVNE/NZ Gv,Ev
-46: CMOVBE/NA Gv,Ev
-47: CMOVA/NBE Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
 48: CMOVS Gv,Ev
 49: CMOVNS Gv,Ev
-4a: CMOVP/PE Gv,Ev
-4b: CMOVNP/PO Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
 4c: CMOVL/NGE Gv,Ev
 4d: CMOVNL/GE Gv,Ev
 4e: CMOVLE/NG Gv,Ev
@@ -426,7 +431,7 @@ AVXcode: 1
 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
-5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
@@ -447,7 +452,7 @@ AVXcode: 1
 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
-6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
 # 0x0f 0x70-0x7f
 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
 71: Grp12 (1A)
@@ -458,14 +463,14 @@ AVXcode: 1
 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
 # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
 77: emms | vzeroupper | vzeroall
-78: VMREAD Ey,Gy
-79: VMWRITE Gy,Ey
-7a:
-7b:
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
-7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
 80: JO Jz (f64)
@@ -485,16 +490,16 @@ AVXcode: 1
 8e: JLE/JNG Jz (f64)
 8f: JNLE/JG Jz (f64)
 # 0x0f 0x90-0x9f
-90: SETO Eb
-91: SETNO Eb
-92: SETB/C/NAE Eb
-93: SETAE/NB/NC Eb
+90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
+91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
 94: SETE/Z Eb
 95: SETNE/NZ Eb
 96: SETBE/NA Eb
 97: SETA/NBE Eb
-98: SETS Eb
-99: SETNS Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
 9a: SETP/PE Eb
 9b: SETNP/PO Eb
 9c: SETL/NGE Eb
@@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
 d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
 d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
 da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
-db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
 dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
 dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
 de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
-df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xe0-0xef
 e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
 e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
@@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
 e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
 e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
 e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
-e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
 e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
 e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
 e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
 ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
-eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
 ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
 ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
 ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
-ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0xf0-0xff
 f0: vlddqu Vx,Mx (F2)
 f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
@@ -626,81 +631,105 @@ AVXcode: 2
 0e: vtestps Vx,Wx (66),(v)
 0f: vtestpd Vx,Wx (66),(v)
 # 0x0f 0x38 0x10-0x1f
-10: pblendvb Vdq,Wdq (66)
-11:
-12:
-13: vcvtph2ps Vx,Wx,Ib (66),(v)
-14: blendvps Vdq,Wdq (66)
-15: blendvpd Vdq,Wdq (66)
-16: vpermps Vqq,Hqq,Wqq (66),(v)
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
 17: vptest Vx,Wx (66)
 18: vbroadcastss Vx,Wd (66),(v)
-19: vbroadcastsd Vqq,Wq (66),(v)
-1a: vbroadcastf128 Vqq,Mdq (66),(v)
-1b:
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
-1f:
+1f: vpabsq Vx,Wx (66),(ev)
 # 0x0f 0x38 0x20-0x2f
-20: vpmovsxbw Vx,Ux/Mq (66),(v1)
-21: vpmovsxbd Vx,Ux/Md (66),(v1)
-22: vpmovsxbq Vx,Ux/Mw (66),(v1)
-23: vpmovsxwd Vx,Ux/Mq (66),(v1)
-24: vpmovsxwq Vx,Ux/Md (66),(v1)
-25: vpmovsxdq Vx,Ux/Mq (66),(v1)
-26:
-27:
-28: vpmuldq Vx,Hx,Wx (66),(v1)
-29: vpcmpeqq Vx,Hx,Wx (66),(v1)
-2a: vmovntdqa Vx,Mx (66),(v1)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
 2b: vpackusdw Vx,Hx,Wx (66),(v1)
-2c: vmaskmovps Vx,Hx,Mx (66),(v)
-2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
 2e: vmaskmovps Mx,Hx,Vx (66),(v)
 2f: vmaskmovpd Mx,Hx,Vx (66),(v)
 # 0x0f 0x38 0x30-0x3f
-30: vpmovzxbw Vx,Ux/Mq (66),(v1)
-31: vpmovzxbd Vx,Ux/Md (66),(v1)
-32: vpmovzxbq Vx,Ux/Mw (66),(v1)
-33: vpmovzxwd Vx,Ux/Mq (66),(v1)
-34: vpmovzxwq Vx,Ux/Md (66),(v1)
-35: vpmovzxdq Vx,Ux/Mq (66),(v1)
-36: vpermd Vqq,Hqq,Wqq (66),(v)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
 37: vpcmpgtq Vx,Hx,Wx (66),(v1)
-38: vpminsb Vx,Hx,Wx (66),(v1)
-39: vpminsd Vx,Hx,Wx (66),(v1)
-3a: vpminuw Vx,Hx,Wx (66),(v1)
-3b: vpminud Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
 3c: vpmaxsb Vx,Hx,Wx (66),(v1)
-3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
 3e: vpmaxuw Vx,Hx,Wx (66),(v1)
-3f: vpmaxud Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
 # 0x0f 0x38 0x40-0x8f
-40: vpmulld Vx,Hx,Wx (66),(v1)
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
 41: vphminposuw Vdq,Wdq (66),(v1)
-42:
-43:
-44:
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
 45: vpsrlvd/q Vx,Hx,Wx (66),(v)
-46: vpsravd Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
 47: vpsllvd/q Vx,Hx,Wx (66),(v)
-# Skip 0x48-0x57
+# Skip 0x48-0x4b
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+# Skip 0x50-0x57
 58: vpbroadcastd Vx,Wx (66),(v)
-59: vpbroadcastq Vx,Wx (66),(v)
-5a: vbroadcasti128 Vqq,Mdq (66),(v)
-# Skip 0x5b-0x77
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+# Skip 0x5c-0x63
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+# Skip 0x67-0x74
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
 78: vpbroadcastb Vx,Wx (66),(v)
 79: vpbroadcastw Vx,Wx (66),(v)
-# Skip 0x7a-0x7f
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
 81: INVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
 # 0x0f 0x38 0x90-0xbf (FMA)
-90: vgatherdd/q Vx,Hx,Wx (66),(v)
-91: vgatherqd/q Vx,Hx,Wx (66),(v)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
 92: vgatherdps/d Vx,Hx,Wx (66),(v)
 93: vgatherqps/d Vx,Hx,Wx (66),(v)
 94:
@@ -715,6 +744,10 @@ AVXcode: 2
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
 a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
@@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
 af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
 b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
 b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
 b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
-c8: sha1nexte Vdq,Wdq
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
 c9: sha1msg1 Vdq,Wdq
-ca: sha1msg2 Vdq,Wdq
-cb: sha256rnds2 Vdq,Wdq
-cc: sha256msg1 Vdq,Wdq
-cd: sha256msg2 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -763,15 +801,15 @@ AVXcode: 3
 00: vpermq Vqq,Wqq,Ib (66),(v)
 01: vpermpd Vqq,Wqq,Ib (66),(v)
 02: vpblendd Vx,Hx,Wx,Ib (66),(v)
-03:
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
 04: vpermilps Vx,Wx,Ib (66),(v)
 05: vpermilpd Vx,Wx,Ib (66),(v)
 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
 07:
-08: vroundps Vx,Wx,Ib (66)
-09: vroundpd Vx,Wx,Ib (66)
-0a: vroundss Vss,Wss,Ib (66),(v1)
-0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
 0c: vblendps Vx,Hx,Wx,Ib (66)
 0d: vblendpd Vx,Hx,Wx,Ib (66)
 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
@@ -780,26 +818,51 @@ AVXcode: 3
 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
 16: vpextrd/q Ey,Vdq,Ib (66),(v1)
 17: vextractps Ed,Vdq,Ib (66),(v1)
-18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
-19: vextractf128 Wdq,Vqq,Ib (66),(v)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
 1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
-38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
-39: vextracti128 Wdq,Vqq,Ib (66),(v)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
 40: vdpps Vx,Hx,Wx,Ib (66)
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
-42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev)
 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
@@ -927,8 +990,10 @@ GrpTable: Grp12
 EndTable
 
 GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
-4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
 EndTable
 
@@ -947,7 +1012,7 @@ GrpTable: Grp15
 4: XSAVE
 5: XRSTOR | lfence (11B)
 6: XSAVEOPT | clwb (66) | mfence (11B)
-7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
+7: clflush | clflushopt (66) | sfence (11B)
 EndTable
 
 GrpTable: Grp16
@@ -963,6 +1028,20 @@ GrpTable: Grp17
 3: BLSI By,Ey (v)
 EndTable
 
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 137196990012..551ff6f640be 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -39,6 +39,7 @@
 #include "auxtrace.h"
 #include "tsc.h"
 #include "intel-pt.h"
+#include "config.h"
 
 #include "intel-pt-decoder/intel-pt-log.h"
 #include "intel-pt-decoder/intel-pt-decoder.h"
@@ -556,7 +557,7 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
                     !evsel->attr.exclude_kernel)
                         return false;
@@ -572,7 +573,7 @@ static bool intel_pt_return_compression(struct intel_pt *pt)
         if (!pt->noretcomp_bit)
                 return true;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (intel_pt_get_config(pt, &evsel->attr, &config) &&
                     (config & pt->noretcomp_bit))
                         return false;
@@ -592,7 +593,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
         for (shift = 0, config = pt->mtc_freq_bits; !(config & 1); shift++)
                 config >>= 1;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (intel_pt_get_config(pt, &evsel->attr, &config))
                         return (config & pt->mtc_freq_bits) >> shift;
         }
@@ -608,7 +609,7 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt)
         if (!pt->tsc_bit || !pt->cap_user_time_zero)
                 return true;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
                         return true;
                 if (intel_pt_get_config(pt, &evsel->attr, &config)) {
@@ -625,7 +626,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
                     !evsel->attr.exclude_kernel)
                         return true;
@@ -642,7 +643,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt)
         if (!pt->tsc_bit)
                 return false;
 
-        evlist__for_each(pt->session->evlist, evsel) {
+        evlist__for_each_entry(pt->session->evlist, evsel) {
                 if (intel_pt_get_config(pt, &evsel->attr, &config)) {
                         if (config & pt->tsc_bit)
                                 have_tsc = true;
@@ -1233,7 +1234,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
         if (!(state->type & INTEL_PT_BRANCH))
                 return 0;
 
-        if (pt->synth_opts.callchain)
+        if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
                 thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
                                     state->to_ip, ptq->insn_len,
                                     state->trace_nr);
@@ -1850,7 +1851,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
         u64 id;
         int err;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type == pt->pmu_type && evsel->ids) {
                         found = true;
                         break;
@@ -1930,7 +1931,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
                 pt->sample_transactions = true;
                 pt->transactions_id = id;
                 id += 1;
-                evlist__for_each(evlist, evsel) {
+                evlist__for_each_entry(evlist, evsel) {
                         if (evsel->id && evsel->id[0] == pt->transactions_id) {
                                 if (evsel->name)
                                         zfree(&evsel->name);
@@ -1968,7 +1969,7 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each_reverse(evlist, evsel) {
+        evlist__for_each_entry_reverse(evlist, evsel) {
                 const char *name = perf_evsel__name(evsel);
 
                 if (!strcmp(name, "sched:sched_switch"))
@@ -1982,7 +1983,7 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.context_switch)
                         return true;
         }
@@ -2136,6 +2137,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
                         pt->synth_opts.branches = false;
                         pt->synth_opts.callchain = true;
                 }
+                if (session->itrace_synth_opts)
+                        pt->synth_opts.thread_stack =
+                                session->itrace_synth_opts->thread_stack;
         }
 
         if (pt->synth_opts.log)
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index aa6877d36858..020b9ca1b47e 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -57,21 +57,21 @@ static inline struct int_node *intlist__next(struct int_node *in)
 }
 
 /**
- * intlist_for_each      - iterate over a intlist
+ * intlist__for_each_entry      - iterate over a intlist
  * @pos:        the &struct int_node to use as a loop cursor.
  * @ilist:      the &struct intlist for loop.
  */
-#define intlist__for_each(pos, ilist)   \
+#define intlist__for_each_entry(pos, ilist)     \
         for (pos = intlist__first(ilist); pos; pos = intlist__next(pos))
 
 /**
- * intlist_for_each_safe - iterate over a intlist safe against removal of
+ * intlist__for_each_entry_safe - iterate over a intlist safe against removal of
  *                         int_node
  * @pos:        the &struct int_node to use as a loop cursor.
  * @n:          another &struct int_node to use as temporary storage.
  * @ilist:      the &struct intlist for loop.
  */
-#define intlist__for_each_safe(pos, n, ilist)   \
+#define intlist__for_each_entry_safe(pos, n, ilist)     \
         for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\
              pos = n, n = intlist__next(n))
 #endif /* __PERF_INTLIST_H */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 86afe9618bb0..9f3305f6b6d5 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -108,7 +108,7 @@ jit_validate_events(struct perf_session *session)
         /*
          * check that all events use CLOCK_MONOTONIC
          */
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
                         return -1;
         }
diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c
index e521d1516df6..f616e4f65b67 100644
--- a/tools/perf/util/levenshtein.c
+++ b/tools/perf/util/levenshtein.c
@@ -1,5 +1,7 @@
-#include "cache.h"
 #include "levenshtein.h"
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
 
 /*
  * This function implements the Damerau-Levenshtein algorithm to
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
new file mode 100644
index 000000000000..6559bc586643
--- /dev/null
+++ b/tools/perf/util/libunwind/arm64.c
@@ -0,0 +1,40 @@
+/*
+ * This file setups defines to compile arch specific binary from the
+ * generic one.
+ *
+ * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch
+ * name and the defination of this function is included directly from
+ * 'arch/arm64/util/unwind-libunwind.c', to make sure that this function
+ * is defined no matter what arch the host is.
+ *
+ * Finally, the arch specific unwind methods are exported which will
+ * be assigned to each arm64 thread.
+ */
+
+#define REMOTE_UNWIND_LIBUNWIND
+
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP
+
+#include "unwind.h"
+#include "debug.h"
+#include "libunwind-aarch64.h"
+#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
+#include "../../arch/arm64/util/unwind-libunwind.c"
+
+/* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind,
+ * assign NO_LIBUNWIND_DEBUG_FRAME_AARCH64 to it for compiling arm64
+ * unwind methods.
+ */
+#undef NO_LIBUNWIND_DEBUG_FRAME
+#ifdef NO_LIBUNWIND_DEBUG_FRAME_AARCH64
+#define NO_LIBUNWIND_DEBUG_FRAME
+#endif
+#include "util/unwind-libunwind-local.c"
+
+struct unwind_libunwind_ops *
+arm64_unwind_libunwind_ops = &_unwind_libunwind_ops;
diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c
new file mode 100644
index 000000000000..957ffff72428
--- /dev/null
+++ b/tools/perf/util/libunwind/x86_32.c
@@ -0,0 +1,43 @@
+/*
+ * This file setups defines to compile arch specific binary from the
+ * generic one.
+ *
+ * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch
+ * name and the defination of this function is included directly from
+ * 'arch/x86/util/unwind-libunwind.c', to make sure that this function
+ * is defined no matter what arch the host is.
+ *
+ * Finally, the arch specific unwind methods are exported which will
+ * be assigned to each x86 thread.
+ */
+
+#define REMOTE_UNWIND_LIBUNWIND
+
+/* Define arch specific functions & regs for libunwind, should be
+ * defined before including "unwind.h"
+ */
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum)
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP
+
+#include "unwind.h"
+#include "debug.h"
+#include "libunwind-x86.h"
+#include <../../../../arch/x86/include/uapi/asm/perf_regs.h>
+
+/* HAVE_ARCH_X86_64_SUPPORT is used in'arch/x86/util/unwind-libunwind.c'
+ * for x86_32, we undef it to compile code for x86_32 only.
+ */
+#undef HAVE_ARCH_X86_64_SUPPORT
+#include "../../arch/x86/util/unwind-libunwind.c"
+
+/* Explicitly define NO_LIBUNWIND_DEBUG_FRAME, because non-ARM has no
+ * dwarf_find_debug_frame() function.
+ */
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+#define NO_LIBUNWIND_DEBUG_FRAME
+#endif
+#include "util/unwind-libunwind-local.c"
+
+struct unwind_libunwind_ops *
+x86_32_unwind_libunwind_ops = &_unwind_libunwind_ops;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 33071d6159bc..bf7216b8731d 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -3,11 +3,14 @@
  * Copyright (C) 2015, Huawei Inc.
  */
 
+#include <errno.h>
 #include <limits.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include "debug.h"
 #include "llvm-utils.h"
+#include "config.h"
+#include "util.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE                          \
                 "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
@@ -42,6 +45,8 @@ int perf_llvm_config(const char *var, const char *value)
                 llvm_param.kbuild_dir = strdup(value);
         else if (!strcmp(var, "kbuild-opts"))
                 llvm_param.kbuild_opts = strdup(value);
+        else if (!strcmp(var, "dump-obj"))
+                llvm_param.dump_obj = !!perf_config_bool(var, value);
         else
                 return -1;
         llvm_param.user_set_param = true;
@@ -103,7 +108,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
         file = popen(cmd, "r");
         if (!file) {
                 pr_err("ERROR: unable to popen cmd: %s\n",
-                       strerror_r(errno, serr, sizeof(serr)));
+                       str_error_r(errno, serr, sizeof(serr)));
                 return -EINVAL;
         }
 
@@ -137,7 +142,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz)
 
         if (ferror(file)) {
                 pr_err("ERROR: error occurred when reading from pipe: %s\n",
-                       strerror_r(errno, serr, sizeof(serr)));
+                       str_error_r(errno, serr, sizeof(serr)));
                 err = -EIO;
                 goto errout;
         }
@@ -326,6 +331,42 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
         pr_debug("include option is set to %s\n", *kbuild_include_opts);
 }
 
+static void
+dump_obj(const char *path, void *obj_buf, size_t size)
+{
+        char *obj_path = strdup(path);
+        FILE *fp;
+        char *p;
+
+        if (!obj_path) {
+                pr_warning("WARNING: No enough memory, skip object dumping\n");
+                return;
+        }
+
+        p = strrchr(obj_path, '.');
+        if (!p || (strcmp(p, ".c") != 0)) {
+                pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n",
+                           obj_path);
+                goto out;
+        }
+
+        p[1] = 'o';
+        fp = fopen(obj_path, "wb");
+        if (!fp) {
+                pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n",
+                           obj_path, strerror(errno));
+                goto out;
+        }
+
+        pr_info("LLVM: dumping %s\n", obj_path);
+        if (fwrite(obj_buf, size, 1, fp) != 1)
+                pr_warning("WARNING: failed to write to file '%s': %s, skip object dumping\n",
+                           obj_path, strerror(errno));
+        fclose(fp);
+out:
+        free(obj_path);
+}
+
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
                       size_t *p_obj_buf_sz)
 {
@@ -343,7 +384,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
         if (path[0] != '-' && realpath(path, abspath) == NULL) {
                 err = errno;
                 pr_err("ERROR: problems with path %s: %s\n",
-                       path, strerror_r(err, serr, sizeof(serr)));
+                       path, str_error_r(err, serr, sizeof(serr)));
                 return -err;
         }
 
@@ -371,7 +412,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
         if (nr_cpus_avail <= 0) {
                 pr_err(
 "WARNING:\tunable to get available CPUs in this system: %s\n"
-"        \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr)));
+"        \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr)));
                 nr_cpus_avail = 128;
         }
         snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
@@ -411,6 +452,10 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 
         free(kbuild_dir);
         free(kbuild_include_opts);
+
+        if (llvm_param.dump_obj)
+                dump_obj(path, obj_buf, obj_buf_sz);
+
         if (!p_obj_buf)
                 free(obj_buf);
         else
diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h
index 23b9a743fe72..9f501cef06a1 100644
--- a/tools/perf/util/llvm-utils.h
+++ b/tools/perf/util/llvm-utils.h
@@ -30,6 +30,11 @@ struct llvm_param {
          */
         const char *kbuild_opts;
         /*
+         * Default is false. If set to true, write compiling result
+         * to object file.
+         */
+        bool dump_obj;
+        /*
          * Default is false. If one of the above fields is set by user
          * explicitly then user_set_llvm is set to true. This is used
          * for perf test. If user doesn't set anything in .perfconfig
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b1772180c820..cb6388dbdd98 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -138,8 +138,10 @@ void machine__exit(struct machine *machine)
 
 void machine__delete(struct machine *machine)
 {
-        machine__exit(machine);
-        free(machine);
+        if (machine) {
+                machine__exit(machine);
+                free(machine);
+        }
 }
 
 void machines__init(struct machines *machines)
@@ -1091,12 +1093,20 @@ static int machine__set_modules_path(struct machine *machine)
 
         return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
+int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+                                const char *name __maybe_unused)
+{
+        return 0;
+}
 
 static int machine__create_module(void *arg, const char *name, u64 start)
 {
         struct machine *machine = arg;
         struct map *map;
 
+        if (arch__fix_module_text_start(&start, name) < 0)
+                return -1;
+
         map = machine__findnew_module_map(machine, start, name);
         if (map == NULL)
                 return -1;
@@ -1353,11 +1363,16 @@ int machine__process_mmap2_event(struct machine *machine,
         if (map == NULL)
                 goto out_problem_map;
 
-        thread__insert_map(thread, map);
+        ret = thread__insert_map(thread, map);
+        if (ret)
+                goto out_problem_insert;
+
         thread__put(thread);
         map__put(map);
         return 0;
 
+out_problem_insert:
+        map__put(map);
 out_problem_map:
         thread__put(thread);
 out_problem:
@@ -1403,11 +1418,16 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
         if (map == NULL)
                 goto out_problem_map;
 
-        thread__insert_map(thread, map);
+        ret = thread__insert_map(thread, map);
+        if (ret)
+                goto out_problem_insert;
+
         thread__put(thread);
         map__put(map);
         return 0;
 
+out_problem_insert:
+        map__put(map);
 out_problem_map:
         thread__put(thread);
 out_problem:
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 41ac9cfd416b..20739f746bc4 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -216,6 +216,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
                                         const char *filename);
+int arch__fix_module_text_start(u64 *start, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
                              enum map_type type, bool no_kcore, symbol_filter_t filter);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b19bcd3b7128..728129ac653a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -15,6 +15,7 @@
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
 
@@ -311,6 +312,9 @@ int map__load(struct map *map, symbol_filter_t filter)
                         pr_warning("%.*s was updated (is prelink enabled?). "
                                 "Restart the long running apps that use it!\n",
                                    (int)real_len, name);
+                } else if (filter) {
+                        pr_warning("no symbols passed the given filter.\n");
+                        return -2;      /* Empty but maybe by the filter */
                 } else {
                         pr_warning("no symbols found in %s, maybe install "
                                    "a debug package?\n", name);
@@ -744,9 +748,10 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
                       struct map_groups *parent, enum map_type type)
 {
+        struct map_groups *mg = thread->mg;
         int err = -ENOMEM;
         struct map *map;
         struct maps *maps = &parent->maps[type];
@@ -757,6 +762,11 @@ int map_groups__clone(struct map_groups *mg,
                 struct map *new = map__clone(map);
                 if (new == NULL)
                         goto out_unlock;
+
+                err = unwind__prepare_access(thread, new, NULL);
+                if (err)
+                        goto out_unlock;
+
                 map_groups__insert(mg, new);
                 map__put(new);
         }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7309d64ce39e..d83396ceecba 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -194,7 +194,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
                                          struct map **mapp, symbol_filter_t filter);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
                       struct map_groups *parent, enum map_type type);
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 75465f89a413..bbc368e7d1e4 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -10,18 +10,33 @@
 #include "debug.h"
 #include "symbol.h"
 
+unsigned int perf_mem_events__loads_ldlat = 30;
+
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-        E("ldlat-loads",        "cpu/mem-loads,ldlat=30/P",     "mem-loads"),
+        E("ldlat-loads",        "cpu/mem-loads,ldlat=%u/P",     "mem-loads"),
         E("ldlat-stores",       "cpu/mem-stores/P",             "mem-stores"),
 };
 #undef E
 
 #undef E
 
+static char mem_loads_name[100];
+static bool mem_loads_name__init;
+
 char *perf_mem_events__name(int i)
 {
+        if (i == PERF_MEM_EVENTS__LOAD) {
+                if (!mem_loads_name__init) {
+                        mem_loads_name__init = true;
+                        scnprintf(mem_loads_name, sizeof(mem_loads_name),
+                                  perf_mem_events[i].name,
+                                  perf_mem_events__loads_ldlat);
+                }
+                return mem_loads_name;
+        }
+
         return (char *)perf_mem_events[i].name;
 }
 
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 5d6d93066a6e..7f69bf9d789d 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -18,6 +18,7 @@ enum {
 };
 
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c6fd0479f4cd..6c913c3914fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -20,6 +20,7 @@
 #include "pmu.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "probe-file.h"
 #include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
@@ -436,7 +437,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
-                             char *sys, char *name)
+                             const char *sys, const char *name)
 {
         char help[BUFSIZ];
 
@@ -466,7 +467,7 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 }
 
 static int add_tracepoint(struct list_head *list, int *idx,
-                          char *sys_name, char *evt_name,
+                          const char *sys_name, const char *evt_name,
                           struct parse_events_error *err,
                           struct list_head *head_config)
 {
@@ -491,7 +492,7 @@ static int add_tracepoint(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_multi_event(struct list_head *list, int *idx,
-                                      char *sys_name, char *evt_name,
+                                      const char *sys_name, const char *evt_name,
                                       struct parse_events_error *err,
                                       struct list_head *head_config)
 {
@@ -533,7 +534,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_event(struct list_head *list, int *idx,
-                                char *sys_name, char *evt_name,
+                                const char *sys_name, const char *evt_name,
                                 struct parse_events_error *err,
                                 struct list_head *head_config)
 {
@@ -545,7 +546,7 @@ static int add_tracepoint_event(struct list_head *list, int *idx,
 }
 
 static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
-                                    char *sys_name, char *evt_name,
+                                    const char *sys_name, const char *evt_name,
                                     struct parse_events_error *err,
                                     struct list_head *head_config)
 {
@@ -584,7 +585,7 @@ struct __add_bpf_event_param {
         struct list_head *head_config;
 };
 
-static int add_bpf_event(struct probe_trace_event *tev, int fd,
+static int add_bpf_event(const char *group, const char *event, int fd,
                          void *_param)
 {
         LIST_HEAD(new_evsels);
@@ -595,27 +596,27 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
         int err;
 
         pr_debug("add bpf event %s:%s and attach bpf program %d\n",
-                 tev->group, tev->event, fd);
+                 group, event, fd);
 
-        err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-                                          tev->event, evlist->error,
+        err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group,
+                                          event, evlist->error,
                                           param->head_config);
         if (err) {
                 struct perf_evsel *evsel, *tmp;
 
                 pr_debug("Failed to add BPF event %s:%s\n",
-                         tev->group, tev->event);
+                         group, event);
                 list_for_each_entry_safe(evsel, tmp, &new_evsels, node) {
                         list_del(&evsel->node);
                         perf_evsel__delete(evsel);
                 }
                 return err;
         }
-        pr_debug("adding %s:%s\n", tev->group, tev->event);
+        pr_debug("adding %s:%s\n", group, event);
 
         list_for_each_entry(pos, &new_evsels, node) {
                 pr_debug("adding %s:%s to %p\n",
-                         tev->group, tev->event, pos);
+                         group, event, pos);
                 pos->bpf_fd = fd;
         }
         list_splice(&new_evsels, list);
@@ -661,7 +662,7 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data,
                 goto errout;
         }
 
-        err = bpf__foreach_tev(obj, add_bpf_event, &param);
+        err = bpf__foreach_event(obj, add_bpf_event, &param);
         if (err) {
                 snprintf(errbuf, sizeof(errbuf),
                          "Attach events in BPF object failed");
@@ -900,6 +901,9 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
         [PARSE_EVENTS__TERM_TYPE_STACKSIZE]             = "stack-size",
         [PARSE_EVENTS__TERM_TYPE_NOINHERIT]             = "no-inherit",
         [PARSE_EVENTS__TERM_TYPE_INHERIT]               = "inherit",
+        [PARSE_EVENTS__TERM_TYPE_MAX_STACK]             = "max-stack",
+        [PARSE_EVENTS__TERM_TYPE_OVERWRITE]             = "overwrite",
+        [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]           = "no-overwrite",
 };
 
 static bool config_term_shrinked;
@@ -992,9 +996,18 @@ do {									   \
         case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
                 CHECK_TYPE_VAL(NUM);
                 break;
+        case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+                CHECK_TYPE_VAL(NUM);
+                break;
+        case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+                CHECK_TYPE_VAL(NUM);
+                break;
         case PARSE_EVENTS__TERM_TYPE_NAME:
                 CHECK_TYPE_VAL(STR);
                 break;
+        case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+                CHECK_TYPE_VAL(NUM);
+                break;
         default:
                 err->str = strdup("unknown term");
                 err->idx = term->err_term;
@@ -1040,6 +1053,9 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
         case PARSE_EVENTS__TERM_TYPE_STACKSIZE:
         case PARSE_EVENTS__TERM_TYPE_INHERIT:
         case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
+        case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+        case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+        case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
                 return config_term_common(attr, term, err);
         default:
                 if (err) {
@@ -1109,6 +1125,15 @@ do {								\
                 case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
                         ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1);
                         break;
+                case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+                        ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
+                        break;
+                case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
+                        ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
+                        break;
+                case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+                        ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1);
+                        break;
                 default:
                         break;
                 }
@@ -1118,7 +1143,7 @@ do {								\
 }
 
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
-                                char *sys, char *event,
+                                const char *sys, const char *event,
                                 struct parse_events_error *err,
                                 struct list_head *head_config)
 {
@@ -1388,7 +1413,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
         if (!add && get_event_modifier(&mod, str, NULL))
                 return -EINVAL;
 
-        __evlist__for_each(list, evsel) {
+        __evlist__for_each_entry(list, evsel) {
                 if (add && get_event_modifier(&mod, str, evsel))
                         return -EINVAL;
 
@@ -1414,7 +1439,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
         struct perf_evsel *evsel;
 
-        __evlist__for_each(list, evsel) {
+        __evlist__for_each_entry(list, evsel) {
                 if (!evsel->name)
                         evsel->name = strdup(name);
         }
@@ -1976,6 +2001,85 @@ static bool is_event_supported(u8 type, unsigned config)
         return ret;
 }
 
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+                      bool name_only)
+{
+        struct probe_cache *pcache;
+        struct probe_cache_entry *ent;
+        struct strlist *bidlist, *sdtlist;
+        struct strlist_config cfg = {.dont_dupstr = true};
+        struct str_node *nd, *nd2;
+        char *buf, *path, *ptr = NULL;
+        bool show_detail = false;
+        int ret;
+
+        sdtlist = strlist__new(NULL, &cfg);
+        if (!sdtlist) {
+                pr_debug("Failed to allocate new strlist for SDT\n");
+                return;
+        }
+        bidlist = build_id_cache__list_all(true);
+        if (!bidlist) {
+                pr_debug("Failed to get buildids: %d\n", errno);
+                return;
+        }
+        strlist__for_each_entry(nd, bidlist) {
+                pcache = probe_cache__new(nd->s);
+                if (!pcache)
+                        continue;
+                list_for_each_entry(ent, &pcache->entries, node) {
+                        if (!ent->sdt)
+                                continue;
+                        if (subsys_glob &&
+                            !strglobmatch(ent->pev.group, subsys_glob))
+                                continue;
+                        if (event_glob &&
+                            !strglobmatch(ent->pev.event, event_glob))
+                                continue;
+                        ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
+                                        ent->pev.event, nd->s);
+                        if (ret > 0)
+                                strlist__add(sdtlist, buf);
+                }
+                probe_cache__delete(pcache);
+        }
+        strlist__delete(bidlist);
+
+        strlist__for_each_entry(nd, sdtlist) {
+                buf = strchr(nd->s, '@');
+                if (buf)
+                        *(buf++) = '\0';
+                if (name_only) {
+                        printf("%s ", nd->s);
+                        continue;
+                }
+                nd2 = strlist__next(nd);
+                if (nd2) {
+                        ptr = strchr(nd2->s, '@');
+                        if (ptr)
+                                *ptr = '\0';
+                        if (strcmp(nd->s, nd2->s) == 0)
+                                show_detail = true;
+                }
+                if (show_detail) {
+                        path = build_id_cache__origname(buf);
+                        ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
+                        if (ret > 0) {
+                                printf("  %-50s [%s]\n", buf, "SDT event");
+                                free(buf);
+                        }
+                } else
+                        printf("  %-50s [%s]\n", nd->s, "SDT event");
+                if (nd2) {
+                        if (strcmp(nd->s, nd2->s) != 0)
+                                show_detail = false;
+                        if (ptr)
+                                *ptr = '@';
+                }
+        }
+        strlist__delete(sdtlist);
+}
+
 int print_hwcache_events(const char *event_glob, bool name_only)
 {
         unsigned int type, op, i, evt_i = 0, evt_num = 0;
@@ -2158,6 +2262,8 @@ void print_events(const char *event_glob, bool name_only)
         }
 
         print_tracepoint_events(NULL, NULL, name_only);
+
+        print_sdt_events(NULL, NULL, name_only);
 }
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
@@ -2322,9 +2428,9 @@ static void config_terms_list(char *buf, size_t buf_sz)
 char *parse_events_formats_error_string(char *additional_terms)
 {
         char *str;
-        /* "branch_type" is the longest name */
+        /* "no-overwrite" is the longest name */
         char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
-                          (sizeof("branch_type") - 1)];
+                          (sizeof("no-overwrite") - 1)];
 
         config_terms_list(static_terms, sizeof(static_terms));
         /* valid terms */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index d740c3ca9a1d..d1edbf8cc66a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -68,6 +68,9 @@ enum {
         PARSE_EVENTS__TERM_TYPE_STACKSIZE,
         PARSE_EVENTS__TERM_TYPE_NOINHERIT,
         PARSE_EVENTS__TERM_TYPE_INHERIT,
+        PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+        PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
+        PARSE_EVENTS__TERM_TYPE_OVERWRITE,
         __PARSE_EVENTS__TERM_TYPE_NR,
 };
 
@@ -133,7 +136,7 @@ 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,
-                                char *sys, char *event,
+                                const char *sys, const char *event,
                                 struct parse_events_error *error,
                                 struct list_head *head_config);
 int parse_events_load_bpf(struct parse_events_evlist *data,
@@ -182,6 +185,8 @@ void print_symbol_events(const char *event_glob, unsigned type,
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
                              bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+                      bool name_only);
 int is_valid_tracepoint(const char *event_string);
 
 int valid_event_mount(const char *eventfs);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 1477fbc78993..7a2519435da0 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -199,8 +199,11 @@ branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE
 time                    { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph              { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size              { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
+max-stack               { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
 inherit                 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit              { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
+overwrite               { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
+no-overwrite            { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 ,                       { return ','; }
 "/"                     { BEGIN(INITIAL); return '/'; }
 {name_minus}            { return str(yyscanner, PE_NAME); }
@@ -259,6 +262,7 @@ cycles-ct					{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 cycles-t                                        { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-loads                                       { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 mem-stores                                      { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
+topdown-[a-z-]+                                 { return str(yyscanner, PE_KERNEL_PMU_EVENT); }
 
 L1-dcache|l1-d|l1d|L1-data              |
 L1-icache|l1-i|l1i|L1-instruction       |
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 3bf6bf82ff2d..7c7630be5a89 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -11,17 +11,13 @@
  * which is what it's designed for.
  */
 #include "cache.h"
+#include "util.h"
+#include <limits.h>
 
 static char bad_path[] = "/bad-path/";
 /*
- * Two hacks:
+ * One hack:
  */
-
-static const char *get_perf_dir(void)
-{
-        return ".";
-}
-
 static char *get_pathname(void)
 {
         static char pathname_array[4][PATH_MAX];
@@ -54,60 +50,3 @@ char *mkpath(const char *fmt, ...)
                 return bad_path;
         return cleanup_path(pathname);
 }
-
-char *perf_path(const char *fmt, ...)
-{
-        const char *perf_dir = get_perf_dir();
-        char *pathname = get_pathname();
-        va_list args;
-        unsigned len;
-
-        len = strlen(perf_dir);
-        if (len > PATH_MAX-100)
-                return bad_path;
-        memcpy(pathname, perf_dir, len);
-        if (len && perf_dir[len-1] != '/')
-                pathname[len++] = '/';
-        va_start(args, fmt);
-        len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args);
-        va_end(args);
-        if (len >= PATH_MAX)
-                return bad_path;
-        return cleanup_path(pathname);
-}
-
-/* strip arbitrary amount of directory separators at end of path */
-static inline int chomp_trailing_dir_sep(const char *path, int len)
-{
-        while (len && is_dir_sep(path[len - 1]))
-                len--;
-        return len;
-}
-
-/*
- * If path ends with suffix (complete path components), returns the
- * part before suffix (sans trailing directory separators).
- * Otherwise returns NULL.
- */
-char *strip_path_suffix(const char *path, const char *suffix)
-{
-        int path_len = strlen(path), suffix_len = strlen(suffix);
-
-        while (suffix_len) {
-                if (!path_len)
-                        return NULL;
-
-                if (is_dir_sep(path[path_len - 1])) {
-                        if (!is_dir_sep(suffix[suffix_len - 1]))
-                                return NULL;
-                        path_len = chomp_trailing_dir_sep(path, path_len);
-                        suffix_len = chomp_trailing_dir_sep(suffix, suffix_len);
-                }
-                else if (path[--path_len] != suffix[--suffix_len])
-                        return NULL;
-        }
-
-        if (path_len && !is_dir_sep(path[path_len - 1]))
-                return NULL;
-        return strndup(path, chomp_trailing_dir_sep(path, path_len));
-}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 74401a20106d..953dc1ab2ed7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -67,7 +67,6 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
         return ret;
 }
 
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
@@ -103,10 +102,8 @@ out:
 
 void exit_probe_symbol_maps(void)
 {
-        if (host_machine) {
-                machine__delete(host_machine);
-                host_machine = NULL;
-        }
+        machine__delete(host_machine);
+        host_machine = NULL;
         symbol__exit();
 }
 
@@ -471,7 +468,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
                 err = kernel_get_module_dso(module, &dso);
                 if (err < 0) {
                         if (!dso || dso->load_errno == 0) {
-                                if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+                                if (!str_error_r(-err, reason, STRERR_BUFSIZE))
                                         strcpy(reason, "(unknown)");
                         } else
                                 dso__strerror_load(dso, reason, STRERR_BUFSIZE);
@@ -809,7 +806,7 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 error:
         if (ferror(fp)) {
                 pr_warning("File read error: %s\n",
-                           strerror_r(errno, sbuf, sizeof(sbuf)));
+                           str_error_r(errno, sbuf, sizeof(sbuf)));
                 return -1;
         }
         return 0;
@@ -889,7 +886,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
         fp = fopen(lr->path, "r");
         if (fp == NULL) {
                 pr_warning("Failed to open %s: %s\n", lr->path,
-                           strerror_r(errno, sbuf, sizeof(sbuf)));
+                           str_error_r(errno, sbuf, sizeof(sbuf)));
                 return -errno;
         }
         /* Skip to starting line number */
@@ -899,7 +896,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
                         goto end;
         }
 
-        intlist__for_each(ln, lr->line_list) {
+        intlist__for_each_entry(ln, lr->line_list) {
                 for (; ln->i > l; l++) {
                         ret = show_one_line(fp, l - lr->offset);
                         if (ret < 0)
@@ -983,7 +980,7 @@ static int show_available_vars_at(struct debuginfo *dinfo,
                 zfree(&vl->point.symbol);
                 nvars = 0;
                 if (vl->vars) {
-                        strlist__for_each(node, vl->vars) {
+                        strlist__for_each_entry(node, vl->vars) {
                                 var = strchr(node->s, '\t') + 1;
                                 if (strfilter__compare(_filter, var)) {
                                         fprintf(stdout, "\t\t%s\n", node->s);
@@ -1200,6 +1197,34 @@ err:
         return err;
 }
 
+static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev)
+{
+        char *ptr;
+
+        ptr = strchr(*arg, ':');
+        if (ptr) {
+                *ptr = '\0';
+                if (!pev->sdt && !is_c_func_name(*arg))
+                        goto ng_name;
+                pev->group = strdup(*arg);
+                if (!pev->group)
+                        return -ENOMEM;
+                *arg = ptr + 1;
+        } else
+                pev->group = NULL;
+        if (!pev->sdt && !is_c_func_name(*arg)) {
+ng_name:
+                semantic_error("%s is bad for event name -it must "
+                               "follow C symbol-naming rule.\n", *arg);
+                return -EINVAL;
+        }
+        pev->event = strdup(*arg);
+        if (pev->event == NULL)
+                return -ENOMEM;
+
+        return 0;
+}
+
 /* Parse probepoint definition. */
 static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
@@ -1207,33 +1232,64 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
         char *ptr, *tmp;
         char c, nc = 0;
         bool file_spec = false;
+        int ret;
+
         /*
          * <Syntax>
-         * perf probe [EVENT=]SRC[:LN|;PTN]
-         * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
-         *
-         * TODO:Group name support
+         * perf probe [GRP:][EVENT=]SRC[:LN|;PTN]
+         * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
+         * perf probe %[GRP:]SDT_EVENT
          */
         if (!arg)
                 return -EINVAL;
 
+        /*
+         * If the probe point starts with '%',
+         * or starts with "sdt_" and has a ':' but no '=',
+         * then it should be a SDT/cached probe point.
+         */
+        if (arg[0] == '%' ||
+            (!strncmp(arg, "sdt_", 4) &&
+             !!strchr(arg, ':') && !strchr(arg, '='))) {
+                pev->sdt = true;
+                if (arg[0] == '%')
+                        arg++;
+        }
+
         ptr = strpbrk(arg, ";=@+%");
+        if (pev->sdt) {
+                if (ptr) {
+                        if (*ptr != '@') {
+                                semantic_error("%s must be an SDT name.\n",
+                                               arg);
+                                return -EINVAL;
+                        }
+                        /* This must be a target file name or build id */
+                        tmp = build_id_cache__complement(ptr + 1);
+                        if (tmp) {
+                                pev->target = build_id_cache__origname(tmp);
+                                free(tmp);
+                        } else
+                                pev->target = strdup(ptr + 1);
+                        if (!pev->target)
+                                return -ENOMEM;
+                        *ptr = '\0';
+                }
+                ret = parse_perf_probe_event_name(&arg, pev);
+                if (ret == 0) {
+                        if (asprintf(&pev->point.function, "%%%s", pev->event) < 0)
+                                ret = -errno;
+                }
+                return ret;
+        }
+
         if (ptr && *ptr == '=') {       /* Event name */
                 *ptr = '\0';
                 tmp = ptr + 1;
-                if (strchr(arg, ':')) {
-                        semantic_error("Group name is not supported yet.\n");
-                        return -ENOTSUP;
-                }
-                if (!is_c_func_name(arg)) {
-                        semantic_error("%s is bad for event name -it must "
-                                       "follow C symbol-naming rule.\n", arg);
-                        return -EINVAL;
-                }
-                pev->event = strdup(arg);
-                if (pev->event == NULL)
-                        return -ENOMEM;
-                pev->group = NULL;
+                ret = parse_perf_probe_event_name(&arg, pev);
+                if (ret < 0)
+                        return ret;
+
                 arg = tmp;
         }
 
@@ -1545,7 +1601,9 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev)
                 return true;
 
         for (i = 0; i < pev->nargs; i++)
-                if (is_c_varname(pev->args[i].var))
+                if (is_c_varname(pev->args[i].var) ||
+                    !strcmp(pev->args[i].var, "$params") ||
+                    !strcmp(pev->args[i].var, "$vars"))
                         return true;
 
         return false;
@@ -1603,6 +1661,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev)
         p = strchr(argv[1], ':');
         if (p) {
                 tp->module = strndup(argv[1], p - argv[1]);
+                if (!tp->module) {
+                        ret = -ENOMEM;
+                        goto out;
+                }
+                tev->uprobes = (tp->module[0] == '/');
                 p++;
         } else
                 p = argv[1];
@@ -1712,7 +1775,7 @@ out:
 }
 
 /* Compose only probe point (not argument) */
-static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
+char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 {
         struct strbuf buf;
         char *tmp, *ret = NULL;
@@ -1751,30 +1814,36 @@ out:
         return ret;
 }
 
-#if 0
 char *synthesize_perf_probe_command(struct perf_probe_event *pev)
 {
-        char *buf;
-        int i, len, ret;
+        struct strbuf buf;
+        char *tmp, *ret = NULL;
+        int i;
 
-        buf = synthesize_perf_probe_point(&pev->point);
-        if (!buf)
+        if (strbuf_init(&buf, 64))
                 return NULL;
+        if (pev->event)
+                if (strbuf_addf(&buf, "%s:%s=", pev->group ?: PERFPROBE_GROUP,
+                                pev->event) < 0)
+                        goto out;
+
+        tmp = synthesize_perf_probe_point(&pev->point);
+        if (!tmp || strbuf_addstr(&buf, tmp) < 0)
+                goto out;
+        free(tmp);
 
-        len = strlen(buf);
         for (i = 0; i < pev->nargs; i++) {
-                ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s",
-                                 pev->args[i].name);
-                if (ret <= 0) {
-                        free(buf);
-                        return NULL;
-                }
-                len += ret;
+                tmp = synthesize_perf_probe_arg(pev->args + i);
+                if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0)
+                        goto out;
+                free(tmp);
         }
 
-        return buf;
+        ret = strbuf_detach(&buf, NULL);
+out:
+        strbuf_release(&buf);
+        return ret;
 }
-#endif
 
 static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
                                             struct strbuf *buf, int depth)
@@ -2026,6 +2095,79 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
         memset(pev, 0, sizeof(*pev));
 }
 
+#define strdup_or_goto(str, label)      \
+({ char *__p = NULL; if (str && !(__p = strdup(str))) goto label; __p; })
+
+static int perf_probe_point__copy(struct perf_probe_point *dst,
+                                  struct perf_probe_point *src)
+{
+        dst->file = strdup_or_goto(src->file, out_err);
+        dst->function = strdup_or_goto(src->function, out_err);
+        dst->lazy_line = strdup_or_goto(src->lazy_line, out_err);
+        dst->line = src->line;
+        dst->retprobe = src->retprobe;
+        dst->offset = src->offset;
+        return 0;
+
+out_err:
+        clear_perf_probe_point(dst);
+        return -ENOMEM;
+}
+
+static int perf_probe_arg__copy(struct perf_probe_arg *dst,
+                                struct perf_probe_arg *src)
+{
+        struct perf_probe_arg_field *field, **ppfield;
+
+        dst->name = strdup_or_goto(src->name, out_err);
+        dst->var = strdup_or_goto(src->var, out_err);
+        dst->type = strdup_or_goto(src->type, out_err);
+
+        field = src->field;
+        ppfield = &(dst->field);
+        while (field) {
+                *ppfield = zalloc(sizeof(*field));
+                if (!*ppfield)
+                        goto out_err;
+                (*ppfield)->name = strdup_or_goto(field->name, out_err);
+                (*ppfield)->index = field->index;
+                (*ppfield)->ref = field->ref;
+                field = field->next;
+                ppfield = &((*ppfield)->next);
+        }
+        return 0;
+out_err:
+        return -ENOMEM;
+}
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+                           struct perf_probe_event *src)
+{
+        int i;
+
+        dst->event = strdup_or_goto(src->event, out_err);
+        dst->group = strdup_or_goto(src->group, out_err);
+        dst->target = strdup_or_goto(src->target, out_err);
+        dst->uprobes = src->uprobes;
+
+        if (perf_probe_point__copy(&dst->point, &src->point) < 0)
+                goto out_err;
+
+        dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs);
+        if (!dst->args)
+                goto out_err;
+        dst->nargs = src->nargs;
+
+        for (i = 0; i < src->nargs; i++)
+                if (perf_probe_arg__copy(&dst->args[i], &src->args[i]) < 0)
+                        goto out_err;
+        return 0;
+
+out_err:
+        clear_perf_probe_event(dst);
+        return -ENOMEM;
+}
+
 void clear_probe_trace_event(struct probe_trace_event *tev)
 {
         struct probe_trace_arg_ref *ref, *next;
@@ -2253,7 +2395,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe,
         if (!rawlist)
                 return -ENOMEM;
 
-        strlist__for_each(ent, rawlist) {
+        strlist__for_each_entry(ent, rawlist) {
                 ret = parse_probe_trace_command(ent->s, &tev);
                 if (ret >= 0) {
                         if (!filter_probe_trace_event(&tev, filter))
@@ -2286,6 +2428,9 @@ int show_perf_probe_events(struct strfilter *filter)
 
         setup_pager();
 
+        if (probe_conf.cache)
+                return probe_cache__show_all_caches(filter);
+
         ret = init_probe_symbol_maps(false);
         if (ret < 0)
                 return ret;
@@ -2394,17 +2539,24 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
         char buf[64];
         int ret;
 
-        if (pev->event)
+        /* If probe_event or trace_event already have the name, reuse it */
+        if (pev->event && !pev->sdt)
                 event = pev->event;
-        else
+        else if (tev->event)
+                event = tev->event;
+        else {
+                /* Or generate new one from probe point */
                 if (pev->point.function &&
                         (strncmp(pev->point.function, "0x", 2) != 0) &&
                         !strisglob(pev->point.function))
                         event = pev->point.function;
                 else
                         event = tev->point.realname;
-        if (pev->group)
+        }
+        if (pev->group && !pev->sdt)
                 group = pev->group;
+        else if (tev->group)
+                group = tev->group;
         else
                 group = PERFPROBE_GROUP;
 
@@ -2426,40 +2578,60 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
         return 0;
 }
 
-static int __add_probe_trace_events(struct perf_probe_event *pev,
-                                     struct probe_trace_event *tevs,
-                                     int ntevs, bool allow_suffix)
+static int __open_probe_file_and_namelist(bool uprobe,
+                                          struct strlist **namelist)
 {
-        int i, fd, ret;
-        struct probe_trace_event *tev = NULL;
-        struct strlist *namelist;
+        int fd;
 
-        fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
+        fd = probe_file__open(PF_FL_RW | (uprobe ? PF_FL_UPROBE : 0));
         if (fd < 0)
                 return fd;
 
         /* Get current event names */
-        namelist = probe_file__get_namelist(fd);
-        if (!namelist) {
+        *namelist = probe_file__get_namelist(fd);
+        if (!(*namelist)) {
                 pr_debug("Failed to get current event list.\n");
-                ret = -ENOMEM;
-                goto close_out;
+                close(fd);
+                return -ENOMEM;
         }
+        return fd;
+}
+
+static int __add_probe_trace_events(struct perf_probe_event *pev,
+                                     struct probe_trace_event *tevs,
+                                     int ntevs, bool allow_suffix)
+{
+        int i, fd[2] = {-1, -1}, up, ret;
+        struct probe_trace_event *tev = NULL;
+        struct probe_cache *cache = NULL;
+        struct strlist *namelist[2] = {NULL, NULL};
+
+        up = pev->uprobes ? 1 : 0;
+        fd[up] = __open_probe_file_and_namelist(up, &namelist[up]);
+        if (fd[up] < 0)
+                return fd[up];
 
         ret = 0;
         for (i = 0; i < ntevs; i++) {
                 tev = &tevs[i];
+                up = tev->uprobes ? 1 : 0;
+                if (fd[up] == -1) {     /* Open the kprobe/uprobe_events */
+                        fd[up] = __open_probe_file_and_namelist(up,
+                                                                &namelist[up]);
+                        if (fd[up] < 0)
+                                goto close_out;
+                }
                 /* Skip if the symbol is out of .text or blacklisted */
-                if (!tev->point.symbol)
+                if (!tev->point.symbol && !pev->uprobes)
                         continue;
 
                 /* Set new name for tev (and update namelist) */
-                ret = probe_trace_event__set_name(tev, pev, namelist,
+                ret = probe_trace_event__set_name(tev, pev, namelist[up],
                                                   allow_suffix);
                 if (ret < 0)
                         break;
 
-                ret = probe_file__add_event(fd, tev);
+                ret = probe_file__add_event(fd[up], tev);
                 if (ret < 0)
                         break;
 
@@ -2473,10 +2645,21 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         }
         if (ret == -EINVAL && pev->uprobes)
                 warn_uprobe_event_compat(tev);
+        if (ret == 0 && probe_conf.cache) {
+                cache = probe_cache__new(pev->target);
+                if (!cache ||
+                    probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 ||
+                    probe_cache__commit(cache) < 0)
+                        pr_warning("Failed to add event to probe cache\n");
+                probe_cache__delete(cache);
+        }
 
-        strlist__delete(namelist);
 close_out:
-        close(fd);
+        for (up = 0; up < 2; up++) {
+                strlist__delete(namelist[up]);
+                if (fd[up] >= 0)
+                        close(fd[up]);
+        }
         return ret;
 }
 
@@ -2501,9 +2684,6 @@ static int find_probe_functions(struct map *map, char *name,
         return found;
 }
 
-#define strdup_or_goto(str, label)      \
-        ({ char *__p = strdup(str); if (!__p) goto label; __p; })
-
 void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
                                 struct probe_trace_event *tev __maybe_unused,
                                 struct map *map __maybe_unused,
@@ -2758,12 +2938,205 @@ errout:
 
 bool __weak arch__prefers_symtab(void) { return false; }
 
+/* Concatinate two arrays */
+static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
+{
+        void *ret;
+
+        ret = malloc(sz_a + sz_b);
+        if (ret) {
+                memcpy(ret, a, sz_a);
+                memcpy(ret + sz_a, b, sz_b);
+        }
+        return ret;
+}
+
+static int
+concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs,
+                          struct probe_trace_event **tevs2, int ntevs2)
+{
+        struct probe_trace_event *new_tevs;
+        int ret = 0;
+
+        if (ntevs == 0) {
+                *tevs = *tevs2;
+                *ntevs = ntevs2;
+                *tevs2 = NULL;
+                return 0;
+        }
+
+        if (*ntevs + ntevs2 > probe_conf.max_probes)
+                ret = -E2BIG;
+        else {
+                /* Concatinate the array of probe_trace_event */
+                new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs),
+                                  *tevs2, ntevs2 * sizeof(**tevs2));
+                if (!new_tevs)
+                        ret = -ENOMEM;
+                else {
+                        free(*tevs);
+                        *tevs = new_tevs;
+                        *ntevs += ntevs2;
+                }
+        }
+        if (ret < 0)
+                clear_probe_trace_events(*tevs2, ntevs2);
+        zfree(tevs2);
+
+        return ret;
+}
+
+/*
+ * Try to find probe_trace_event from given probe caches. Return the number
+ * of cached events found, if an error occurs return the error.
+ */
+static int find_cached_events(struct perf_probe_event *pev,
+                              struct probe_trace_event **tevs,
+                              const char *target)
+{
+        struct probe_cache *cache;
+        struct probe_cache_entry *entry;
+        struct probe_trace_event *tmp_tevs = NULL;
+        int ntevs = 0;
+        int ret = 0;
+
+        cache = probe_cache__new(target);
+        /* Return 0 ("not found") if the target has no probe cache. */
+        if (!cache)
+                return 0;
+
+        for_each_probe_cache_entry(entry, cache) {
+                /* Skip the cache entry which has no name */
+                if (!entry->pev.event || !entry->pev.group)
+                        continue;
+                if ((!pev->group || strglobmatch(entry->pev.group, pev->group)) &&
+                    strglobmatch(entry->pev.event, pev->event)) {
+                        ret = probe_cache_entry__get_event(entry, &tmp_tevs);
+                        if (ret > 0)
+                                ret = concat_probe_trace_events(tevs, &ntevs,
+                                                                &tmp_tevs, ret);
+                        if (ret < 0)
+                                break;
+                }
+        }
+        probe_cache__delete(cache);
+        if (ret < 0) {
+                clear_probe_trace_events(*tevs, ntevs);
+                zfree(tevs);
+        } else {
+                ret = ntevs;
+                if (ntevs > 0 && target && target[0] == '/')
+                        pev->uprobes = true;
+        }
+
+        return ret;
+}
+
+/* Try to find probe_trace_event from all probe caches */
+static int find_cached_events_all(struct perf_probe_event *pev,
+                                   struct probe_trace_event **tevs)
+{
+        struct probe_trace_event *tmp_tevs = NULL;
+        struct strlist *bidlist;
+        struct str_node *nd;
+        char *pathname;
+        int ntevs = 0;
+        int ret;
+
+        /* Get the buildid list of all valid caches */
+        bidlist = build_id_cache__list_all(true);
+        if (!bidlist) {
+                ret = -errno;
+                pr_debug("Failed to get buildids: %d\n", ret);
+                return ret;
+        }
+
+        ret = 0;
+        strlist__for_each_entry(nd, bidlist) {
+                pathname = build_id_cache__origname(nd->s);
+                ret = find_cached_events(pev, &tmp_tevs, pathname);
+                /* In the case of cnt == 0, we just skip it */
+                if (ret > 0)
+                        ret = concat_probe_trace_events(tevs, &ntevs,
+                                                        &tmp_tevs, ret);
+                free(pathname);
+                if (ret < 0)
+                        break;
+        }
+        strlist__delete(bidlist);
+
+        if (ret < 0) {
+                clear_probe_trace_events(*tevs, ntevs);
+                zfree(tevs);
+        } else
+                ret = ntevs;
+
+        return ret;
+}
+
+static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
+                                              struct probe_trace_event **tevs)
+{
+        struct probe_cache *cache;
+        struct probe_cache_entry *entry;
+        struct probe_trace_event *tev;
+        struct str_node *node;
+        int ret, i;
+
+        if (pev->sdt) {
+                /* For SDT/cached events, we use special search functions */
+                if (!pev->target)
+                        return find_cached_events_all(pev, tevs);
+                else
+                        return find_cached_events(pev, tevs, pev->target);
+        }
+        cache = probe_cache__new(pev->target);
+        if (!cache)
+                return 0;
+
+        entry = probe_cache__find(cache, pev);
+        if (!entry) {
+                /* SDT must be in the cache */
+                ret = pev->sdt ? -ENOENT : 0;
+                goto out;
+        }
+
+        ret = strlist__nr_entries(entry->tevlist);
+        if (ret > probe_conf.max_probes) {
+                pr_debug("Too many entries matched in the cache of %s\n",
+                         pev->target ? : "kernel");
+                ret = -E2BIG;
+                goto out;
+        }
+
+        *tevs = zalloc(ret * sizeof(*tev));
+        if (!*tevs) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        i = 0;
+        strlist__for_each_entry(node, entry->tevlist) {
+                tev = &(*tevs)[i++];
+                ret = parse_probe_trace_command(node->s, tev);
+                if (ret < 0)
+                        goto out;
+                /* Set the uprobes attribute as same as original */
+                tev->uprobes = pev->uprobes;
+        }
+        ret = i;
+
+out:
+        probe_cache__delete(cache);
+        return ret;
+}
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
                                          struct probe_trace_event **tevs)
 {
         int ret;
 
-        if (!pev->group) {
+        if (!pev->group && !pev->sdt) {
                 /* Set group name if not given */
                 if (!pev->uprobes) {
                         pev->group = strdup(PERFPROBE_GROUP);
@@ -2780,6 +3153,11 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
         if (ret > 0)
                 return ret;
 
+        /* At first, we need to lookup cache entry */
+        ret = find_probe_trace_events_from_cache(pev, tevs);
+        if (ret > 0 || pev->sdt)        /* SDT can be found only in the cache */
+                return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
+
         if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
                 ret = find_probe_trace_events_from_map(pev, tevs);
                 if (ret > 0)
@@ -2934,8 +3312,16 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 
         /* Load symbols with given filter */
         available_func_filter = _filter;
-        if (map__load(map, filter_available_functions)) {
-                pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+        ret = map__load(map, filter_available_functions);
+        if (ret) {
+                if (ret == -2) {
+                        char *str = strfilter__string(_filter);
+                        pr_err("Failed to find symbols matched to \"%s\"\n",
+                               str);
+                        free(str);
+                } else
+                        pr_err("Failed to load symbols in %s\n",
+                               (target) ? : "kernel");
                 goto end;
         }
         if (!dso__sorted_by_name(map->dso, map->type))
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5a27eb4fad05..e18ea9fe6385 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_conf {
         bool    show_location_range;
         bool    force_add;
         bool    no_inlines;
+        bool    cache;
         int     max_probes;
 };
 extern struct probe_conf probe_conf;
@@ -84,6 +85,7 @@ struct perf_probe_event {
         char                    *group; /* Group name */
         struct perf_probe_point point;  /* Probe point */
         int                     nargs;  /* Number of arguments */
+        bool                    sdt;    /* SDT/cached event flag */
         bool                    uprobes;        /* Uprobe event flag */
         char                    *target;        /* Target binary */
         struct perf_probe_arg   *args;  /* Arguments */
@@ -121,6 +123,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev);
 char *synthesize_perf_probe_command(struct perf_probe_event *pev);
 char *synthesize_probe_trace_command(struct probe_trace_event *tev);
 char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
+char *synthesize_perf_probe_point(struct perf_probe_point *pp);
+
+int perf_probe_event__copy(struct perf_probe_event *dst,
+                           struct perf_probe_event *src);
 
 /* Check the perf_probe_event needs debuginfo */
 bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 3fe6214970e6..9aed9c332da6 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  *
  */
+#include <sys/uio.h>
 #include "util.h"
 #include "event.h"
 #include "strlist.h"
@@ -49,7 +50,7 @@ static void print_open_warning(int err, bool uprobe)
         else
                 pr_warning("Failed to open %cprobe_events: %s\n",
                            uprobe ? 'u' : 'k',
-                           strerror_r(-err, sbuf, sizeof(sbuf)));
+                           str_error_r(-err, sbuf, sizeof(sbuf)));
 }
 
 static void print_both_open_warning(int kerr, int uerr)
@@ -63,9 +64,9 @@ static void print_both_open_warning(int kerr, int uerr)
         else {
                 char sbuf[STRERR_BUFSIZE];
                 pr_warning("Failed to open kprobe events: %s.\n",
-                           strerror_r(-kerr, sbuf, sizeof(sbuf)));
+                           str_error_r(-kerr, sbuf, sizeof(sbuf)));
                 pr_warning("Failed to open uprobe events: %s.\n",
-                           strerror_r(-uerr, sbuf, sizeof(sbuf)));
+                           str_error_r(-uerr, sbuf, sizeof(sbuf)));
         }
 }
 
@@ -177,7 +178,7 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
         if (!rawlist)
                 return NULL;
         sl = strlist__new(NULL, NULL);
-        strlist__for_each(ent, rawlist) {
+        strlist__for_each_entry(ent, rawlist) {
                 ret = parse_probe_trace_command(ent->s, &tev);
                 if (ret < 0)
                         break;
@@ -223,7 +224,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev)
                 if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
                         ret = -errno;
                         pr_warning("Failed to write event: %s\n",
-                                   strerror_r(errno, sbuf, sizeof(sbuf)));
+                                   str_error_r(errno, sbuf, sizeof(sbuf)));
                 }
         }
         free(buf);
@@ -261,7 +262,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
         return 0;
 error:
         pr_warning("Failed to delete event: %s\n",
-                   strerror_r(-ret, buf, sizeof(buf)));
+                   str_error_r(-ret, buf, sizeof(buf)));
         return ret;
 }
 
@@ -280,7 +281,7 @@ int probe_file__get_events(int fd, struct strfilter *filter,
         if (!namelist)
                 return -ENOENT;
 
-        strlist__for_each(ent, namelist) {
+        strlist__for_each_entry(ent, namelist) {
                 p = strchr(ent->s, ':');
                 if ((p && strfilter__compare(filter, p + 1)) ||
                     strfilter__compare(filter, ent->s)) {
@@ -298,7 +299,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist)
         int ret = 0;
         struct str_node *ent;
 
-        strlist__for_each(ent, namelist) {
+        strlist__for_each_entry(ent, namelist) {
                 ret = __del_trace_probe_event(fd, ent);
                 if (ret < 0)
                         break;
@@ -324,3 +325,533 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 
         return ret;
 }
+
+/* Caller must ensure to remove this entry from list */
+static void probe_cache_entry__delete(struct probe_cache_entry *entry)
+{
+        if (entry) {
+                BUG_ON(!list_empty(&entry->node));
+
+                strlist__delete(entry->tevlist);
+                clear_perf_probe_event(&entry->pev);
+                zfree(&entry->spev);
+                free(entry);
+        }
+}
+
+static struct probe_cache_entry *
+probe_cache_entry__new(struct perf_probe_event *pev)
+{
+        struct probe_cache_entry *entry = zalloc(sizeof(*entry));
+
+        if (entry) {
+                INIT_LIST_HEAD(&entry->node);
+                entry->tevlist = strlist__new(NULL, NULL);
+                if (!entry->tevlist)
+                        zfree(&entry);
+                else if (pev) {
+                        entry->spev = synthesize_perf_probe_command(pev);
+                        if (!entry->spev ||
+                            perf_probe_event__copy(&entry->pev, pev) < 0) {
+                                probe_cache_entry__delete(entry);
+                                return NULL;
+                        }
+                }
+        }
+
+        return entry;
+}
+
+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+                                 struct probe_trace_event **tevs)
+{
+        struct probe_trace_event *tev;
+        struct str_node *node;
+        int ret, i;
+
+        ret = strlist__nr_entries(entry->tevlist);
+        if (ret > probe_conf.max_probes)
+                return -E2BIG;
+
+        *tevs = zalloc(ret * sizeof(*tev));
+        if (!*tevs)
+                return -ENOMEM;
+
+        i = 0;
+        strlist__for_each_entry(node, entry->tevlist) {
+                tev = &(*tevs)[i++];
+                ret = parse_probe_trace_command(node->s, tev);
+                if (ret < 0)
+                        break;
+        }
+        return i;
+}
+
+/* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */
+static int probe_cache__open(struct probe_cache *pcache, const char *target)
+{
+        char cpath[PATH_MAX];
+        char sbuildid[SBUILD_ID_SIZE];
+        char *dir_name = NULL;
+        bool is_kallsyms = false;
+        int ret, fd;
+
+        if (target && build_id_cache__cached(target)) {
+                /* This is a cached buildid */
+                strncpy(sbuildid, target, SBUILD_ID_SIZE);
+                dir_name = build_id_cache__linkname(sbuildid, NULL, 0);
+                goto found;
+        }
+
+        if (!target || !strcmp(target, DSO__NAME_KALLSYMS)) {
+                target = DSO__NAME_KALLSYMS;
+                is_kallsyms = true;
+                ret = sysfs__sprintf_build_id("/", sbuildid);
+        } else
+                ret = filename__sprintf_build_id(target, sbuildid);
+
+        if (ret < 0) {
+                pr_debug("Failed to get build-id from %s.\n", target);
+                return ret;
+        }
+
+        /* If we have no buildid cache, make it */
+        if (!build_id_cache__cached(sbuildid)) {
+                ret = build_id_cache__add_s(sbuildid, target,
+                                            is_kallsyms, NULL);
+                if (ret < 0) {
+                        pr_debug("Failed to add build-id cache: %s\n", target);
+                        return ret;
+                }
+        }
+
+        dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+                                            false);
+found:
+        if (!dir_name) {
+                pr_debug("Failed to get cache from %s\n", target);
+                return -ENOMEM;
+        }
+
+        snprintf(cpath, PATH_MAX, "%s/probes", dir_name);
+        fd = open(cpath, O_CREAT | O_RDWR, 0644);
+        if (fd < 0)
+                pr_debug("Failed to open cache(%d): %s\n", fd, cpath);
+        free(dir_name);
+        pcache->fd = fd;
+
+        return fd;
+}
+
+static int probe_cache__load(struct probe_cache *pcache)
+{
+        struct probe_cache_entry *entry = NULL;
+        char buf[MAX_CMDLEN], *p;
+        int ret = 0;
+        FILE *fp;
+
+        fp = fdopen(dup(pcache->fd), "r");
+        if (!fp)
+                return -EINVAL;
+
+        while (!feof(fp)) {
+                if (!fgets(buf, MAX_CMDLEN, fp))
+                        break;
+                p = strchr(buf, '\n');
+                if (p)
+                        *p = '\0';
+                /* #perf_probe_event or %sdt_event */
+                if (buf[0] == '#' || buf[0] == '%') {
+                        entry = probe_cache_entry__new(NULL);
+                        if (!entry) {
+                                ret = -ENOMEM;
+                                goto out;
+                        }
+                        if (buf[0] == '%')
+                                entry->sdt = true;
+                        entry->spev = strdup(buf + 1);
+                        if (entry->spev)
+                                ret = parse_perf_probe_command(buf + 1,
+                                                                &entry->pev);
+                        else
+                                ret = -ENOMEM;
+                        if (ret < 0) {
+                                probe_cache_entry__delete(entry);
+                                goto out;
+                        }
+                        list_add_tail(&entry->node, &pcache->entries);
+                } else {        /* trace_probe_event */
+                        if (!entry) {
+                                ret = -EINVAL;
+                                goto out;
+                        }
+                        strlist__add(entry->tevlist, buf);
+                }
+        }
+out:
+        fclose(fp);
+        return ret;
+}
+
+static struct probe_cache *probe_cache__alloc(void)
+{
+        struct probe_cache *pcache = zalloc(sizeof(*pcache));
+
+        if (pcache) {
+                INIT_LIST_HEAD(&pcache->entries);
+                pcache->fd = -EINVAL;
+        }
+        return pcache;
+}
+
+void probe_cache__purge(struct probe_cache *pcache)
+{
+        struct probe_cache_entry *entry, *n;
+
+        list_for_each_entry_safe(entry, n, &pcache->entries, node) {
+                list_del_init(&entry->node);
+                probe_cache_entry__delete(entry);
+        }
+}
+
+void probe_cache__delete(struct probe_cache *pcache)
+{
+        if (!pcache)
+                return;
+
+        probe_cache__purge(pcache);
+        if (pcache->fd > 0)
+                close(pcache->fd);
+        free(pcache);
+}
+
+struct probe_cache *probe_cache__new(const char *target)
+{
+        struct probe_cache *pcache = probe_cache__alloc();
+        int ret;
+
+        if (!pcache)
+                return NULL;
+
+        ret = probe_cache__open(pcache, target);
+        if (ret < 0) {
+                pr_debug("Cache open error: %d\n", ret);
+                goto out_err;
+        }
+
+        ret = probe_cache__load(pcache);
+        if (ret < 0) {
+                pr_debug("Cache read error: %d\n", ret);
+                goto out_err;
+        }
+
+        return pcache;
+
+out_err:
+        probe_cache__delete(pcache);
+        return NULL;
+}
+
+static bool streql(const char *a, const char *b)
+{
+        if (a == b)
+                return true;
+
+        if (!a || !b)
+                return false;
+
+        return !strcmp(a, b);
+}
+
+struct probe_cache_entry *
+probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev)
+{
+        struct probe_cache_entry *entry = NULL;
+        char *cmd = synthesize_perf_probe_command(pev);
+
+        if (!cmd)
+                return NULL;
+
+        for_each_probe_cache_entry(entry, pcache) {
+                if (pev->sdt) {
+                        if (entry->pev.event &&
+                            streql(entry->pev.event, pev->event) &&
+                            (!pev->group ||
+                             streql(entry->pev.group, pev->group)))
+                                goto found;
+
+                        continue;
+                }
+                /* Hit if same event name or same command-string */
+                if ((pev->event &&
+                     (streql(entry->pev.group, pev->group) &&
+                      streql(entry->pev.event, pev->event))) ||
+                    (!strcmp(entry->spev, cmd)))
+                        goto found;
+        }
+        entry = NULL;
+
+found:
+        free(cmd);
+        return entry;
+}
+
+struct probe_cache_entry *
+probe_cache__find_by_name(struct probe_cache *pcache,
+                          const char *group, const char *event)
+{
+        struct probe_cache_entry *entry = NULL;
+
+        for_each_probe_cache_entry(entry, pcache) {
+                /* Hit if same event name or same command-string */
+                if (streql(entry->pev.group, group) &&
+                    streql(entry->pev.event, event))
+                        goto found;
+        }
+        entry = NULL;
+
+found:
+        return entry;
+}
+
+int probe_cache__add_entry(struct probe_cache *pcache,
+                           struct perf_probe_event *pev,
+                           struct probe_trace_event *tevs, int ntevs)
+{
+        struct probe_cache_entry *entry = NULL;
+        char *command;
+        int i, ret = 0;
+
+        if (!pcache || !pev || !tevs || ntevs <= 0) {
+                ret = -EINVAL;
+                goto out_err;
+        }
+
+        /* Remove old cache entry */
+        entry = probe_cache__find(pcache, pev);
+        if (entry) {
+                list_del_init(&entry->node);
+                probe_cache_entry__delete(entry);
+        }
+
+        ret = -ENOMEM;
+        entry = probe_cache_entry__new(pev);
+        if (!entry)
+                goto out_err;
+
+        for (i = 0; i < ntevs; i++) {
+                if (!tevs[i].point.symbol)
+                        continue;
+
+                command = synthesize_probe_trace_command(&tevs[i]);
+                if (!command)
+                        goto out_err;
+                strlist__add(entry->tevlist, command);
+                free(command);
+        }
+        list_add_tail(&entry->node, &pcache->entries);
+        pr_debug("Added probe cache: %d\n", ntevs);
+        return 0;
+
+out_err:
+        pr_debug("Failed to add probe caches\n");
+        probe_cache_entry__delete(entry);
+        return ret;
+}
+
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
+static unsigned long long sdt_note__get_addr(struct sdt_note *note)
+{
+        return note->bit32 ? (unsigned long long)note->addr.a32[0]
+                 : (unsigned long long)note->addr.a64[0];
+}
+
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
+{
+        struct probe_cache_entry *entry = NULL;
+        struct list_head sdtlist;
+        struct sdt_note *note;
+        char *buf;
+        char sdtgrp[64];
+        int ret;
+
+        INIT_LIST_HEAD(&sdtlist);
+        ret = get_sdt_note_list(&sdtlist, pathname);
+        if (ret < 0) {
+                pr_debug("Failed to get sdt note: %d\n", ret);
+                return ret;
+        }
+        list_for_each_entry(note, &sdtlist, note_list) {
+                ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider);
+                if (ret < 0)
+                        break;
+                /* Try to find same-name entry */
+                entry = probe_cache__find_by_name(pcache, sdtgrp, note->name);
+                if (!entry) {
+                        entry = probe_cache_entry__new(NULL);
+                        if (!entry) {
+                                ret = -ENOMEM;
+                                break;
+                        }
+                        entry->sdt = true;
+                        ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp,
+                                        note->name, note->name);
+                        if (ret < 0)
+                                break;
+                        entry->pev.event = strdup(note->name);
+                        entry->pev.group = strdup(sdtgrp);
+                        list_add_tail(&entry->node, &pcache->entries);
+                }
+                ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
+                                sdtgrp, note->name, pathname,
+                                sdt_note__get_addr(note));
+                if (ret < 0)
+                        break;
+                strlist__add(entry->tevlist, buf);
+                free(buf);
+                entry = NULL;
+        }
+        if (entry) {
+                list_del_init(&entry->node);
+                probe_cache_entry__delete(entry);
+        }
+        cleanup_sdt_note_list(&sdtlist);
+        return ret;
+}
+#endif
+
+static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd)
+{
+        struct str_node *snode;
+        struct stat st;
+        struct iovec iov[3];
+        const char *prefix = entry->sdt ? "%" : "#";
+        int ret;
+        /* Save stat for rollback */
+        ret = fstat(fd, &st);
+        if (ret < 0)
+                return ret;
+
+        pr_debug("Writing cache: %s%s\n", prefix, entry->spev);
+        iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1;
+        iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev);
+        iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1;
+        ret = writev(fd, iov, 3);
+        if (ret < (int)iov[1].iov_len + 2)
+                goto rollback;
+
+        strlist__for_each_entry(snode, entry->tevlist) {
+                iov[0].iov_base = (void *)snode->s;
+                iov[0].iov_len = strlen(snode->s);
+                iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1;
+                ret = writev(fd, iov, 2);
+                if (ret < (int)iov[0].iov_len + 1)
+                        goto rollback;
+        }
+        return 0;
+
+rollback:
+        /* Rollback to avoid cache file corruption */
+        if (ret > 0)
+                ret = -1;
+        if (ftruncate(fd, st.st_size) < 0)
+                ret = -2;
+
+        return ret;
+}
+
+int probe_cache__commit(struct probe_cache *pcache)
+{
+        struct probe_cache_entry *entry;
+        int ret = 0;
+
+        /* TBD: if we do not update existing entries, skip it */
+        ret = lseek(pcache->fd, 0, SEEK_SET);
+        if (ret < 0)
+                goto out;
+
+        ret = ftruncate(pcache->fd, 0);
+        if (ret < 0)
+                goto out;
+
+        for_each_probe_cache_entry(entry, pcache) {
+                ret = probe_cache_entry__write(entry, pcache->fd);
+                pr_debug("Cache committed: %d\n", ret);
+                if (ret < 0)
+                        break;
+        }
+out:
+        return ret;
+}
+
+static bool probe_cache_entry__compare(struct probe_cache_entry *entry,
+                                       struct strfilter *filter)
+{
+        char buf[128], *ptr = entry->spev;
+
+        if (entry->pev.event) {
+                snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event);
+                ptr = buf;
+        }
+        return strfilter__compare(filter, ptr);
+}
+
+int probe_cache__filter_purge(struct probe_cache *pcache,
+                              struct strfilter *filter)
+{
+        struct probe_cache_entry *entry, *tmp;
+
+        list_for_each_entry_safe(entry, tmp, &pcache->entries, node) {
+                if (probe_cache_entry__compare(entry, filter)) {
+                        pr_info("Removed cached event: %s\n", entry->spev);
+                        list_del_init(&entry->node);
+                        probe_cache_entry__delete(entry);
+                }
+        }
+        return 0;
+}
+
+static int probe_cache__show_entries(struct probe_cache *pcache,
+                                     struct strfilter *filter)
+{
+        struct probe_cache_entry *entry;
+
+        for_each_probe_cache_entry(entry, pcache) {
+                if (probe_cache_entry__compare(entry, filter))
+                        printf("%s\n", entry->spev);
+        }
+        return 0;
+}
+
+/* Show all cached probes */
+int probe_cache__show_all_caches(struct strfilter *filter)
+{
+        struct probe_cache *pcache;
+        struct strlist *bidlist;
+        struct str_node *nd;
+        char *buf = strfilter__string(filter);
+
+        pr_debug("list cache with filter: %s\n", buf);
+        free(buf);
+
+        bidlist = build_id_cache__list_all(true);
+        if (!bidlist) {
+                pr_debug("Failed to get buildids: %d\n", errno);
+                return -EINVAL;
+        }
+        strlist__for_each_entry(nd, bidlist) {
+                pcache = probe_cache__new(nd->s);
+                if (!pcache)
+                        continue;
+                if (!list_empty(&pcache->entries)) {
+                        buf = build_id_cache__origname(nd->s);
+                        printf("%s (%s):\n", buf, nd->s);
+                        free(buf);
+                        probe_cache__show_entries(pcache, filter);
+                }
+                probe_cache__delete(pcache);
+        }
+        strlist__delete(bidlist);
+
+        return 0;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 18ac9cf51c34..9577b5c0b487 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -5,9 +5,27 @@
 #include "strfilter.h"
 #include "probe-event.h"
 
+/* Cache of probe definitions */
+struct probe_cache_entry {
+        struct list_head        node;
+        bool                    sdt;
+        struct perf_probe_event pev;
+        char                    *spev;
+        struct strlist          *tevlist;
+};
+
+struct probe_cache {
+        int     fd;
+        struct list_head entries;
+};
+
 #define PF_FL_UPROBE    1
 #define PF_FL_RW        2
+#define for_each_probe_cache_entry(entry, pcache) \
+        list_for_each_entry(entry, &pcache->entries, node)
 
+/* probe-file.c depends on libelf */
+#ifdef HAVE_LIBELF_SUPPORT
 int probe_file__open(int flag);
 int probe_file__open_both(int *kfd, int *ufd, int flag);
 struct strlist *probe_file__get_namelist(int fd);
@@ -18,5 +36,29 @@ int probe_file__get_events(int fd, struct strfilter *filter,
                                   struct strlist *plist);
 int probe_file__del_strlist(int fd, struct strlist *namelist);
 
+int probe_cache_entry__get_event(struct probe_cache_entry *entry,
+                                 struct probe_trace_event **tevs);
 
+struct probe_cache *probe_cache__new(const char *target);
+int probe_cache__add_entry(struct probe_cache *pcache,
+                           struct perf_probe_event *pev,
+                           struct probe_trace_event *tevs, int ntevs);
+int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname);
+int probe_cache__commit(struct probe_cache *pcache);
+void probe_cache__purge(struct probe_cache *pcache);
+void probe_cache__delete(struct probe_cache *pcache);
+int probe_cache__filter_purge(struct probe_cache *pcache,
+                              struct strfilter *filter);
+struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache,
+                                            struct perf_probe_event *pev);
+struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache,
+                                        const char *group, const char *event);
+int probe_cache__show_all_caches(struct strfilter *filter);
+#else   /* ! HAVE_LIBELF_SUPPORT */
+static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
+{
+        return NULL;
+}
+#define probe_cache__delete(pcache) do {} while (0)
+#endif
 #endif
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1259839dbf6d..f2d9ff064e2d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -381,7 +381,7 @@ formatted:
                 if (ret >= 16)
                         ret = -E2BIG;
                 pr_warning("Failed to convert variable type: %s\n",
-                           strerror_r(-ret, sbuf, sizeof(sbuf)));
+                           str_error_r(-ret, sbuf, sizeof(sbuf)));
                 return ret;
         }
         tvar->type = strdup(buf);
@@ -809,7 +809,7 @@ static int find_lazy_match_lines(struct intlist *list,
         fp = fopen(fname, "r");
         if (!fp) {
                 pr_warning("Failed to open %s: %s\n", fname,
-                           strerror_r(errno, sbuf, sizeof(sbuf)));
+                           str_error_r(errno, sbuf, sizeof(sbuf)));
                 return -errno;
         }
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 36c6862119e3..b7d4f4aeee61 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -13,6 +13,7 @@ util/cpumap.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
+../lib/vsprintf.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 98f127abfa42..a5fbc012e3df 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -2,6 +2,7 @@
 #include <structmember.h>
 #include <inttypes.h>
 #include <poll.h>
+#include <linux/err.h>
 #include "evlist.h"
 #include "evsel.h"
 #include "event.h"
@@ -47,6 +48,7 @@ PyMODINIT_FUNC initperf(void);
 
 struct pyrf_event {
         PyObject_HEAD
+        struct perf_evsel *evsel;
         struct perf_sample sample;
         union perf_event   event;
 };
@@ -288,6 +290,85 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
         return ret;
 }
 
+static bool is_tracepoint(struct pyrf_event *pevent)
+{
+        return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT;
+}
+
+static PyObject*
+tracepoint_field(struct pyrf_event *pe, struct format_field *field)
+{
+        struct pevent *pevent = field->event->pevent;
+        void *data = pe->sample.raw_data;
+        PyObject *ret = NULL;
+        unsigned long long val;
+        unsigned int offset, len;
+
+        if (field->flags & FIELD_IS_ARRAY) {
+                offset = field->offset;
+                len    = field->size;
+                if (field->flags & FIELD_IS_DYNAMIC) {
+                        val     = pevent_read_number(pevent, data + offset, len);
+                        offset  = val;
+                        len     = offset >> 16;
+                        offset &= 0xffff;
+                }
+                if (field->flags & FIELD_IS_STRING &&
+                    is_printable_array(data + offset, len)) {
+                        ret = PyString_FromString((char *)data + offset);
+                } else {
+                        ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+                        field->flags &= ~FIELD_IS_STRING;
+                }
+        } else {
+                val = pevent_read_number(pevent, data + field->offset,
+                                         field->size);
+                if (field->flags & FIELD_IS_POINTER)
+                        ret = PyLong_FromUnsignedLong((unsigned long) val);
+                else if (field->flags & FIELD_IS_SIGNED)
+                        ret = PyLong_FromLong((long) val);
+                else
+                        ret = PyLong_FromUnsignedLong((unsigned long) val);
+        }
+
+        return ret;
+}
+
+static PyObject*
+get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
+{
+        const char *str = PyString_AsString(PyObject_Str(attr_name));
+        struct perf_evsel *evsel = pevent->evsel;
+        struct format_field *field;
+
+        if (!evsel->tp_format) {
+                struct event_format *tp_format;
+
+                tp_format = trace_event__tp_format_id(evsel->attr.config);
+                if (!tp_format)
+                        return NULL;
+
+                evsel->tp_format = tp_format;
+        }
+
+        field = pevent_find_any_field(evsel->tp_format, str);
+        if (!field)
+                return NULL;
+
+        return tracepoint_field(pevent, field);
+}
+
+static PyObject*
+pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name)
+{
+        PyObject *obj = NULL;
+
+        if (is_tracepoint(pevent))
+                obj = get_tracepoint_field(pevent, attr_name);
+
+        return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name);
+}
+
 static PyTypeObject pyrf_sample_event__type = {
         PyVarObject_HEAD_INIT(NULL, 0)
         .tp_name        = "perf.sample_event",
@@ -296,6 +377,7 @@ static PyTypeObject pyrf_sample_event__type = {
         .tp_doc         = pyrf_sample_event__doc,
         .tp_members     = pyrf_sample_event__members,
         .tp_repr        = (reprfunc)pyrf_sample_event__repr,
+        .tp_getattro    = (getattrofunc) pyrf_sample_event__getattro,
 };
 
 static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object.");
@@ -653,6 +735,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
         attr.precise_ip     = precise_ip;
         attr.mmap_data      = mmap_data;
         attr.sample_id_all  = sample_id_all;
+        attr.size           = sizeof(attr);
 
         perf_evsel__init(&pevsel->evsel, &attr, idx);
         return 0;
@@ -863,13 +946,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
         if (event != NULL) {
                 PyObject *pyevent = pyrf_event__new(event);
                 struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
-
-                perf_evlist__mmap_consume(evlist, cpu);
+                struct perf_evsel *evsel;
 
                 if (pyevent == NULL)
                         return PyErr_NoMemory();
 
-                err = perf_evlist__parse_sample(evlist, event, &pevent->sample);
+                evsel = perf_evlist__event2evsel(evlist, event);
+                if (!evsel)
+                        return Py_None;
+
+                pevent->evsel = evsel;
+
+                err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
+
+                /* Consume the even only after we parsed it out. */
+                perf_evlist__mmap_consume(evlist, cpu);
+
                 if (err)
                         return PyErr_Format(PyExc_OSError,
                                             "perf: can't parse sample, err=%d", err);
@@ -957,7 +1049,7 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
         if (i >= pevlist->evlist.nr_entries)
                 return NULL;
 
-        evlist__for_each(&pevlist->evlist, pos) {
+        evlist__for_each_entry(&pevlist->evlist, pos) {
                 if (i-- == 0)
                         break;
         }
@@ -1073,7 +1165,32 @@ static struct {
         { .name = NULL, },
 };
 
+static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
+                                  PyObject *args, PyObject *kwargs)
+{
+        struct event_format *tp_format;
+        static char *kwlist[] = { "sys", "name", NULL };
+        char *sys  = NULL;
+        char *name = NULL;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss", kwlist,
+                                         &sys, &name))
+                return NULL;
+
+        tp_format = trace_event__tp_format(sys, name);
+        if (IS_ERR(tp_format))
+                return PyInt_FromLong(-1);
+
+        return PyInt_FromLong(tp_format->id);
+}
+
 static PyMethodDef perf__methods[] = {
+        {
+                .ml_name  = "tracepoint",
+                .ml_meth  = (PyCFunction) pyrf__tracepoint,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("Get tracepoint config.")
+        },
         { .ml_name = NULL, }
 };
 
@@ -1100,6 +1217,33 @@ PyMODINIT_FUNC initperf(void)
         Py_INCREF(&pyrf_evsel__type);
         PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
 
+        Py_INCREF(&pyrf_mmap_event__type);
+        PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type);
+
+        Py_INCREF(&pyrf_lost_event__type);
+        PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type);
+
+        Py_INCREF(&pyrf_comm_event__type);
+        PyModule_AddObject(module, "comm_event", (PyObject *)&pyrf_comm_event__type);
+
+        Py_INCREF(&pyrf_task_event__type);
+        PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+        Py_INCREF(&pyrf_throttle_event__type);
+        PyModule_AddObject(module, "throttle_event", (PyObject *)&pyrf_throttle_event__type);
+
+        Py_INCREF(&pyrf_task_event__type);
+        PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type);
+
+        Py_INCREF(&pyrf_read_event__type);
+        PyModule_AddObject(module, "read_event", (PyObject *)&pyrf_read_event__type);
+
+        Py_INCREF(&pyrf_sample_event__type);
+        PyModule_AddObject(module, "sample_event", (PyObject *)&pyrf_sample_event__type);
+
+        Py_INCREF(&pyrf_context_switch_event__type);
+        PyModule_AddObject(module, "switch_event", (PyObject *)&pyrf_context_switch_event__type);
+
         Py_INCREF(&pyrf_thread_map__type);
         PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
 
diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c
index c6d4ee2de752..639d1da2f978 100644
--- a/tools/perf/util/quote.c
+++ b/tools/perf/util/quote.c
@@ -1,5 +1,7 @@
-#include "cache.h"
+#include <stdlib.h>
+#include "strbuf.h"
 #include "quote.h"
+#include "util.h"
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h
index e1ec19146fb0..055ca45bed99 100644
--- a/tools/perf/util/quote.h
+++ b/tools/perf/util/quote.h
@@ -2,7 +2,6 @@
 #define __PERF_QUOTE_H
 
 #include <stddef.h>
-#include <stdio.h>
 
 /* Help to copy the thing properly quoted for the shell safety.
  * any single quote is replaced with '\'', any exclamation point
@@ -24,6 +23,8 @@
  * sq_quote() in a real application.
  */
 
+struct strbuf;
+
 int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen);
 
 #endif /* __PERF_QUOTE_H */
diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h
index abc76e3d3098..808cc45611fe 100644
--- a/tools/perf/util/rb_resort.h
+++ b/tools/perf/util/rb_resort.h
@@ -35,7 +35,7 @@ DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname,
 
         struct rb_node *nd;
 
-        resort_rb__for_each(nd, threads) {
+        resort_rb__for_each_entry(nd, threads) {
                 struct thread *t = threads_entry;
                 printf("%s: %d\n", t->shortname, t->tid);
         }
@@ -123,7 +123,7 @@ static void __name##_sorted__init_entry(struct rb_node *nd,			\
 struct __name##_sorted_entry *__name##_entry;                                   \
 struct __name##_sorted *__name = __name##_sorted__new
 
-#define resort_rb__for_each(__nd, __name)                                       \
+#define resort_rb__for_each_entry(__nd, __name)                                 \
         for (__nd = rb_first(&__name->entries);                                 \
              __name##_entry = rb_entry(__nd, struct __name##_sorted_entry,      \
                                        rb_node), __nd;                          \
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 481792c7484b..98bf584853ea 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -148,7 +148,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 
         use_comm_exec = perf_can_comm_exec();
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 perf_evsel__config(evsel, opts, callchain);
                 if (evsel->tracking && use_comm_exec)
                         evsel->attr.comm_exec = 1;
@@ -161,18 +161,18 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
                  * match the id.
                  */
                 use_sample_identifier = perf_can_sample_identifier();
-                evlist__for_each(evlist, evsel)
+                evlist__for_each_entry(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         } else if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
 
-                evlist__for_each(evlist, evsel) {
+                evlist__for_each_entry(evlist, evsel) {
                         if (evsel->attr.sample_type == first->attr.sample_type)
                                 continue;
                         use_sample_identifier = perf_can_sample_identifier();
                         break;
                 }
-                evlist__for_each(evlist, evsel)
+                evlist__for_each_entry(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         }
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ff134700bf30..e0203b979474 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -273,7 +273,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
                 struct format_field *field, void *data)
 {
         bool is_array = field->flags & FIELD_IS_ARRAY;
-        PyObject *obj, *list = NULL;
+        PyObject *obj = NULL, *list = NULL;
         unsigned long long val;
         unsigned int item_size, n_items, i;
 
@@ -386,13 +386,12 @@ exit:
         return pylist;
 }
 
-
 static void python_process_tracepoint(struct perf_sample *sample,
                                       struct perf_evsel *evsel,
                                       struct addr_location *al)
 {
         struct event_format *event = evsel->tp_format;
-        PyObject *handler, *context, *t, *obj, *callchain;
+        PyObject *handler, *context, *t, *obj = NULL, *callchain;
         PyObject *dict = NULL;
         static char handler_name[256];
         struct format_field *field;
@@ -457,14 +456,26 @@ static void python_process_tracepoint(struct perf_sample *sample,
                 pydict_set_item_string_decref(dict, "common_callchain", callchain);
         }
         for (field = event->format.fields; field; field = field->next) {
-                if (field->flags & FIELD_IS_STRING) {
-                        int offset;
+                unsigned int offset, len;
+                unsigned long long val;
+
+                if (field->flags & FIELD_IS_ARRAY) {
+                        offset = field->offset;
+                        len    = field->size;
                         if (field->flags & FIELD_IS_DYNAMIC) {
-                                offset = *(int *)(data + field->offset);
+                                val     = pevent_read_number(scripting_context->pevent,
+                                                             data + offset, len);
+                                offset  = val;
+                                len     = offset >> 16;
                                 offset &= 0xffff;
-                        } else
-                                offset = field->offset;
-                        obj = PyString_FromString((char *)data + offset);
+                        }
+                        if (field->flags & FIELD_IS_STRING &&
+                            is_printable_array(data + offset, len)) {
+                                obj = PyString_FromString((char *) data + offset);
+                        } else {
+                                obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+                                field->flags &= ~FIELD_IS_STRING;
+                        }
                 } else { /* FIELD_IS_NUMERIC */
                         obj = get_field_numeric_entry(event, field, data);
                 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5214974e841a..5d61242a6e64 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -83,7 +83,7 @@ static bool perf_session__has_comm_exec(struct perf_session *session)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (evsel->attr.comm_exec)
                         return true;
         }
@@ -178,6 +178,8 @@ static void perf_session__delete_threads(struct perf_session *session)
 
 void perf_session__delete(struct perf_session *session)
 {
+        if (session == NULL)
+                return;
         auxtrace__free(session);
         auxtrace_index__free(&session->auxtrace_index);
         perf_session__destroy_kernel_maps(session);
@@ -593,6 +595,7 @@ do { 						\
         if (bswap_safe(f, 0))                   \
                 attr->f = bswap_##sz(attr->f);  \
 } while(0)
+#define bswap_field_16(f) bswap_field(f, 16)
 #define bswap_field_32(f) bswap_field(f, 32)
 #define bswap_field_64(f) bswap_field(f, 64)
 
@@ -608,6 +611,7 @@ do { 						\
         bswap_field_64(sample_regs_user);
         bswap_field_32(sample_stack_user);
         bswap_field_32(aux_watermark);
+        bswap_field_16(sample_max_stack);
 
         /*
          * After read_format are bitfields. Check read_format because
@@ -1495,10 +1499,27 @@ int perf_session__register_idle_thread(struct perf_session *session)
         return err;
 }
 
+static void
+perf_session__warn_order(const struct perf_session *session)
+{
+        const struct ordered_events *oe = &session->ordered_events;
+        struct perf_evsel *evsel;
+        bool should_warn = true;
+
+        evlist__for_each_entry(session->evlist, evsel) {
+                if (evsel->attr.write_backward)
+                        should_warn = false;
+        }
+
+        if (!should_warn)
+                return;
+        if (oe->nr_unordered_events != 0)
+                ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+}
+
 static void perf_session__warn_about_errors(const struct perf_session *session)
 {
         const struct events_stats *stats = &session->evlist->stats;
-        const struct ordered_events *oe = &session->ordered_events;
 
         if (session->tool->lost == perf_event__process_lost &&
             stats->nr_events[PERF_RECORD_LOST] != 0) {
@@ -1555,8 +1576,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
                             stats->nr_unprocessable_samples);
         }
 
-        if (oe->nr_unordered_events != 0)
-                ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+        perf_session__warn_order(session);
 
         events_stats__auxtrace_error_warn(stats);
 
@@ -1868,7 +1888,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(session->evlist, evsel) {
+        evlist__for_each_entry(session->evlist, evsel) {
                 if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
                         return true;
         }
@@ -1950,7 +1970,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
         struct perf_evsel *pos;
 
-        evlist__for_each(session->evlist, pos) {
+        evlist__for_each_entry(session->evlist, pos) {
                 if (pos->attr.type == type)
                         return pos;
         }
@@ -2105,7 +2125,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
         max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
                  sizeof(struct id_index_entry);
 
-        evlist__for_each(evlist, evsel)
+        evlist__for_each_entry(evlist, evsel)
                 nr += evsel->ids;
 
         n = nr > max_nr ? max_nr : nr;
@@ -2118,7 +2138,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool,
         ev->id_index.header.size = sz;
         ev->id_index.nr = n;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 u32 j;
 
                 for (j = 0; j < evsel->ids; j++) {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index c4e9bd70723c..947d21f38398 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -79,8 +79,8 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 {
         const char *comm = thread__comm_str(he->thread);
 
-        width = max(7U, width) - 6;
-        return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+        width = max(7U, width) - 8;
+        return repsep_snprintf(bf, size, "%7d:%-*.*s", he->thread->tid,
                                width, width, comm ?: "");
 }
 
@@ -95,7 +95,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void
 }
 
 struct sort_entry sort_thread = {
-        .se_header      = "  Pid:Command",
+        .se_header      = "    Pid:Command",
         .se_cmp         = sort__thread_cmp,
         .se_snprintf    = hist_entry__thread_snprintf,
         .se_filter      = hist_entry__thread_filter,
@@ -1218,7 +1218,7 @@ struct sort_entry sort_mem_daddr_dso = {
         .se_header      = "Data Object",
         .se_cmp         = sort__dso_daddr_cmp,
         .se_snprintf    = hist_entry__dso_daddr_snprintf,
-        .se_width_idx   = HISTC_MEM_DADDR_SYMBOL,
+        .se_width_idx   = HISTC_MEM_DADDR_DSO,
 };
 
 struct sort_entry sort_mem_locked = {
@@ -1488,7 +1488,7 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                              struct perf_evsel *evsel)
+                              struct hists *hists)
 {
         struct hpp_sort_entry *hse;
         size_t len = fmt->user_len;
@@ -1496,14 +1496,14 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
         if (!len)
-                len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+                len = hists__col_len(hists, hse->se->se_width_idx);
 
         return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
                              struct perf_hpp *hpp __maybe_unused,
-                             struct perf_evsel *evsel)
+                             struct hists *hists)
 {
         struct hpp_sort_entry *hse;
         size_t len = fmt->user_len;
@@ -1511,7 +1511,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
         hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
         if (!len)
-                len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx);
+                len = hists__col_len(hists, hse->se->se_width_idx);
 
         return len;
 }
@@ -1793,7 +1793,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde,
 }
 
 static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-                              struct perf_evsel *evsel __maybe_unused)
+                              struct hists *hists __maybe_unused)
 {
         struct hpp_dynamic_entry *hde;
         size_t len = fmt->user_len;
@@ -1808,7 +1808,7 @@ static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 
 static int __sort__hde_width(struct perf_hpp_fmt *fmt,
                              struct perf_hpp *hpp __maybe_unused,
-                             struct perf_evsel *evsel __maybe_unused)
+                             struct hists *hists __maybe_unused)
 {
         struct hpp_dynamic_entry *hde;
         size_t len = fmt->user_len;
@@ -2069,7 +2069,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
         }
 
         full_name = !!strchr(event_name, ':');
-        evlist__for_each(evlist, pos) {
+        evlist__for_each_entry(evlist, pos) {
                 /* case 2 */
                 if (full_name && !strcmp(pos->name, event_name))
                         return pos;
@@ -2125,7 +2125,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
         int ret;
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
 
@@ -2143,7 +2143,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
         struct perf_evsel *evsel;
         struct format_field *field;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
 
@@ -2381,6 +2381,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
                 if (sort__mode != SORT_MODE__MEMORY)
                         return -EINVAL;
 
+                if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+                        return -EINVAL;
+
                 if (sd->entry == &sort_mem_daddr_sym)
                         list->sym = 1;
 
@@ -2424,7 +2427,10 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
                 if (*tok) {
                         ret = sort_dimension__add(list, tok, evlist, level);
                         if (ret == -EINVAL) {
-                                error("Invalid --sort key: `%s'", tok);
+                                if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+                                        error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
+                                else
+                                        error("Invalid --sort key: `%s'", tok);
                                 break;
                         } else if (ret == -ESRCH) {
                                 error("Unknown --sort key: `%s'", tok);
@@ -2456,7 +2462,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist)
         if (evlist == NULL)
                 goto out_no_evlist;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (evsel->attr.type != PERF_TYPE_TRACEPOINT) {
                         use_trace = false;
                         break;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index ebb59cacd092..7ca37ea17395 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -67,6 +67,11 @@ struct hist_entry_diff {
         };
 };
 
+struct hist_entry_ops {
+        void    *(*new)(size_t size);
+        void    (*free)(void *ptr);
+};
+
 /**
  * struct hist_entry - histogram entry
  *
@@ -125,6 +130,7 @@ struct hist_entry {
         void                    *trace_output;
         struct perf_hpp_list    *hpp_list;
         struct hist_entry       *parent_he;
+        struct hist_entry_ops   *ops;
         union {
                 /* this is for hierarchical entry structure */
                 struct {
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index aa9efe08762b..8a2bbd2a4d82 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -36,6 +36,11 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
 static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
@@ -82,6 +87,11 @@ void perf_stat__reset_shadow_stats(void)
                 sizeof(runtime_transaction_stats));
         memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
         memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+        memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots));
+        memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired));
+        memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
+        memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
+        memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
 }
 
 /*
@@ -105,6 +115,16 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
                 update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
         else if (perf_stat_evsel__is(counter, ELISION_START))
                 update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+        else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
+                update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+        else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
+                update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+        else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
+                update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+        else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
+                update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+        else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
+                update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
                 update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
         else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
@@ -302,6 +322,107 @@ static void print_ll_cache_misses(int cpu,
         out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
+/*
+ * High level "TopDown" CPU core pipe line bottleneck break down.
+ *
+ * Basic concept following
+ * Yasin, A Top Down Method for Performance analysis and Counter architecture
+ * ISPASS14
+ *
+ * The CPU pipeline is divided into 4 areas that can be bottlenecks:
+ *
+ * Frontend -> Backend -> Retiring
+ * BadSpeculation in addition means out of order execution that is thrown away
+ * (for example branch mispredictions)
+ * Frontend is instruction decoding.
+ * Backend is execution, like computation and accessing data in memory
+ * Retiring is good execution that is not directly bottlenecked
+ *
+ * The formulas are computed in slots.
+ * A slot is an entry in the pipeline each for the pipeline width
+ * (for example a 4-wide pipeline has 4 slots for each cycle)
+ *
+ * Formulas:
+ * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) /
+ *                      TotalSlots
+ * Retiring = SlotsRetired / TotalSlots
+ * FrontendBound = FetchBubbles / TotalSlots
+ * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound
+ *
+ * The kernel provides the mapping to the low level CPU events and any scaling
+ * needed for the CPU pipeline width, for example:
+ *
+ * TotalSlots = Cycles * 4
+ *
+ * The scaling factor is communicated in the sysfs unit.
+ *
+ * In some cases the CPU may not be able to measure all the formulas due to
+ * missing events. In this case multiple formulas are combined, as possible.
+ *
+ * Full TopDown supports more levels to sub-divide each area: for example
+ * BackendBound into computing bound and memory bound. For now we only
+ * support Level 1 TopDown.
+ */
+
+static double sanitize_val(double x)
+{
+        if (x < 0 && x >= -0.02)
+                return 0.0;
+        return x;
+}
+
+static double td_total_slots(int ctx, int cpu)
+{
+        return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+}
+
+static double td_bad_spec(int ctx, int cpu)
+{
+        double bad_spec = 0;
+        double total_slots;
+        double total;
+
+        total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) -
+                avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) +
+                avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]);
+        total_slots = td_total_slots(ctx, cpu);
+        if (total_slots)
+                bad_spec = total / total_slots;
+        return sanitize_val(bad_spec);
+}
+
+static double td_retiring(int ctx, int cpu)
+{
+        double retiring = 0;
+        double total_slots = td_total_slots(ctx, cpu);
+        double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]);
+
+        if (total_slots)
+                retiring = ret_slots / total_slots;
+        return retiring;
+}
+
+static double td_fe_bound(int ctx, int cpu)
+{
+        double fe_bound = 0;
+        double total_slots = td_total_slots(ctx, cpu);
+        double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]);
+
+        if (total_slots)
+                fe_bound = fetch_bub / total_slots;
+        return fe_bound;
+}
+
+static double td_be_bound(int ctx, int cpu)
+{
+        double sum = (td_fe_bound(ctx, cpu) +
+                      td_bad_spec(ctx, cpu) +
+                      td_retiring(ctx, cpu));
+        if (sum == 0)
+                return 0;
+        return sanitize_val(1.0 - sum);
+}
+
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                    double avg, int cpu,
                                    struct perf_stat_output_ctx *out)
@@ -309,6 +430,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
         void *ctxp = out->ctx;
         print_metric_t print_metric = out->print_metric;
         double total, ratio = 0.0, total2;
+        const char *color = NULL;
         int ctx = evsel_context(evsel);
 
         if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
@@ -452,6 +574,46 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                                      avg / ratio);
                 else
                         print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
+        } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
+                double fe_bound = td_fe_bound(ctx, cpu);
+
+                if (fe_bound > 0.2)
+                        color = PERF_COLOR_RED;
+                print_metric(ctxp, color, "%8.1f%%", "frontend bound",
+                                fe_bound * 100.);
+        } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
+                double retiring = td_retiring(ctx, cpu);
+
+                if (retiring > 0.7)
+                        color = PERF_COLOR_GREEN;
+                print_metric(ctxp, color, "%8.1f%%", "retiring",
+                                retiring * 100.);
+        } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
+                double bad_spec = td_bad_spec(ctx, cpu);
+
+                if (bad_spec > 0.1)
+                        color = PERF_COLOR_RED;
+                print_metric(ctxp, color, "%8.1f%%", "bad speculation",
+                                bad_spec * 100.);
+        } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
+                double be_bound = td_be_bound(ctx, cpu);
+                const char *name = "backend bound";
+                static int have_recovery_bubbles = -1;
+
+                /* In case the CPU does not support topdown-recovery-bubbles */
+                if (have_recovery_bubbles < 0)
+                        have_recovery_bubbles = pmu_have_event("cpu",
+                                        "topdown-recovery-bubbles");
+                if (!have_recovery_bubbles)
+                        name = "backend bound/bad spec";
+
+                if (be_bound > 0.2)
+                        color = PERF_COLOR_RED;
+                if (td_total_slots(ctx, cpu) > 0)
+                        print_metric(ctxp, color, "%8.1f%%", name,
+                                        be_bound * 100.);
+                else
+                        print_metric(ctxp, NULL, NULL, name, 0);
         } else if (runtime_nsecs_stats[cpu].n != 0) {
                 char unit = 'M';
                 char unit_buf[10];
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ffa1d0653861..39345c2ddfc2 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -79,6 +79,11 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
         ID(TRANSACTION_START,   cpu/tx-start/),
         ID(ELISION_START,       cpu/el-start/),
         ID(CYCLES_IN_TX_CP,     cpu/cycles-ct/),
+        ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
+        ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
+        ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
+        ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
+        ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
 };
 #undef ID
 
@@ -157,7 +162,7 @@ int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 if (perf_evsel__alloc_stats(evsel, alloc_raw))
                         goto out_free;
         }
@@ -173,7 +178,7 @@ void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 perf_evsel__free_stat_priv(evsel);
                 perf_evsel__free_counts(evsel);
                 perf_evsel__free_prev_raw_counts(evsel);
@@ -184,7 +189,7 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        evlist__for_each(evlist, evsel) {
+        evlist__for_each_entry(evlist, evsel) {
                 perf_evsel__reset_stat_priv(evsel);
                 perf_evsel__reset_counts(evsel);
         }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 0150e786ccc7..c29bb94c48a4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -17,6 +17,11 @@ enum perf_stat_evsel_id {
         PERF_STAT_EVSEL_ID__TRANSACTION_START,
         PERF_STAT_EVSEL_ID__ELISION_START,
         PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+        PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS,
+        PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED,
+        PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
+        PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
+        PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
         PERF_STAT_EVSEL_ID__MAX,
 };
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index f95f682aa2b2..817593908d47 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,5 +1,5 @@
 #include "debug.h"
-#include "cache.h"
+#include "util.h"
 #include <linux/kernel.h>
 
 int prefixcmp(const char *str, const char *prefix)
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 54b409297d4a..b268a6648a5d 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -40,6 +40,9 @@
 
 #include <assert.h>
 #include <stdarg.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
 
 extern char strbuf_slopbuf[];
 struct strbuf {
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index ca990029e243..19207e50fce5 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -73,7 +73,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @pos:        the &struct str_node to use as a loop cursor.
  * @slist:      the &struct strlist for loop.
  */
-#define strlist__for_each(pos, slist)   \
+#define strlist__for_each_entry(pos, slist)     \
         for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
@@ -83,7 +83,7 @@ static inline struct str_node *strlist__next(struct str_node *sn)
  * @n:          another &struct str_node to use as temporary storage.
  * @slist:      the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, slist)   \
+#define strlist__for_each_entry_safe(pos, n, slist)     \
         for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
              pos = n, n = strlist__next(n))
 #endif /* __PERF_STRLIST_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 87a297dd8901..a34321e9b44d 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -7,6 +7,7 @@
 
 #include "symbol.h"
 #include "demangle-java.h"
+#include "demangle-rust.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -16,6 +17,7 @@
 #define EM_AARCH64      183  /* ARM 64 bit */
 #endif
 
+typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);
@@ -54,6 +56,14 @@ static int elf_getphdrnum(Elf *elf, size_t *dst)
 }
 #endif
 
+#ifndef HAVE_ELF_GETSHDRSTRNDX_SUPPORT
+static int elf_getshdrstrndx(Elf *elf __maybe_unused, size_t *dst __maybe_unused)
+{
+        pr_err("%s: update your libelf to > 0.140, this one lacks elf_getshdrstrndx().\n", __func__);
+        return -1;
+}
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
@@ -1072,6 +1082,13 @@ new_symbol:
                         demangled = bfd_demangle(NULL, elf_name, demangle_flags);
                         if (demangled == NULL)
                                 demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
+                        else if (rust_is_mangled(demangled))
+                                /*
+                                 * Input to Rust demangling is the BFD-demangled
+                                 * name which it Rust-demangles in place.
+                                 */
+                                rust_demangle_sym(demangled);
+
                         if (demangled != NULL)
                                 elf_name = demangled;
                 }
@@ -1781,6 +1798,260 @@ void kcore_extract__delete(struct kcore_extract *kce)
         unlink(kce->extract_filename);
 }
 
+#ifdef HAVE_GELF_GETNOTE_SUPPORT
+/**
+ * populate_sdt_note : Parse raw data and identify SDT note
+ * @elf: elf of the opened file
+ * @data: raw data of a section with description offset applied
+ * @len: note description size
+ * @type: type of the note
+ * @sdt_notes: List to add the SDT note
+ *
+ * Responsible for parsing the @data in section .note.stapsdt in @elf and
+ * if its an SDT note, it appends to @sdt_notes list.
+ */
+static int populate_sdt_note(Elf **elf, const char *data, size_t len,
+                             struct list_head *sdt_notes)
+{
+        const char *provider, *name;
+        struct sdt_note *tmp = NULL;
+        GElf_Ehdr ehdr;
+        GElf_Addr base_off = 0;
+        GElf_Shdr shdr;
+        int ret = -EINVAL;
+
+        union {
+                Elf64_Addr a64[NR_ADDR];
+                Elf32_Addr a32[NR_ADDR];
+        } buf;
+
+        Elf_Data dst = {
+                .d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT,
+                .d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT),
+                .d_off = 0, .d_align = 0
+        };
+        Elf_Data src = {
+                .d_buf = (void *) data, .d_type = ELF_T_ADDR,
+                .d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0,
+                .d_align = 0
+        };
+
+        tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note));
+        if (!tmp) {
+                ret = -ENOMEM;
+                goto out_err;
+        }
+
+        INIT_LIST_HEAD(&tmp->note_list);
+
+        if (len < dst.d_size + 3)
+                goto out_free_note;
+
+        /* Translation from file representation to memory representation */
+        if (gelf_xlatetom(*elf, &dst, &src,
+                          elf_getident(*elf, NULL)[EI_DATA]) == NULL) {
+                pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1));
+                goto out_free_note;
+        }
+
+        /* Populate the fields of sdt_note */
+        provider = data + dst.d_size;
+
+        name = (const char *)memchr(provider, '\0', data + len - provider);
+        if (name++ == NULL)
+                goto out_free_note;
+
+        tmp->provider = strdup(provider);
+        if (!tmp->provider) {
+                ret = -ENOMEM;
+                goto out_free_note;
+        }
+        tmp->name = strdup(name);
+        if (!tmp->name) {
+                ret = -ENOMEM;
+                goto out_free_prov;
+        }
+
+        if (gelf_getclass(*elf) == ELFCLASS32) {
+                memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
+                tmp->bit32 = true;
+        } else {
+                memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr));
+                tmp->bit32 = false;
+        }
+
+        if (!gelf_getehdr(*elf, &ehdr)) {
+                pr_debug("%s : cannot get elf header.\n", __func__);
+                ret = -EBADF;
+                goto out_free_name;
+        }
+
+        /* Adjust the prelink effect :
+         * Find out the .stapsdt.base section.
+         * This scn will help us to handle prelinking (if present).
+         * Compare the retrieved file offset of the base section with the
+         * base address in the description of the SDT note. If its different,
+         * then accordingly, adjust the note location.
+         */
+        if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
+                base_off = shdr.sh_offset;
+                if (base_off) {
+                        if (tmp->bit32)
+                                tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
+                                        tmp->addr.a32[1];
+                        else
+                                tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
+                                        tmp->addr.a64[1];
+                }
+        }
+
+        list_add_tail(&tmp->note_list, sdt_notes);
+        return 0;
+
+out_free_name:
+        free(tmp->name);
+out_free_prov:
+        free(tmp->provider);
+out_free_note:
+        free(tmp);
+out_err:
+        return ret;
+}
+
+/**
+ * construct_sdt_notes_list : constructs a list of SDT notes
+ * @elf : elf to look into
+ * @sdt_notes : empty list_head
+ *
+ * Scans the sections in 'elf' for the section
+ * .note.stapsdt. It, then calls populate_sdt_note to find
+ * out the SDT events and populates the 'sdt_notes'.
+ */
+static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes)
+{
+        GElf_Ehdr ehdr;
+        Elf_Scn *scn = NULL;
+        Elf_Data *data;
+        GElf_Shdr shdr;
+        size_t shstrndx, next;
+        GElf_Nhdr nhdr;
+        size_t name_off, desc_off, offset;
+        int ret = 0;
+
+        if (gelf_getehdr(elf, &ehdr) == NULL) {
+                ret = -EBADF;
+                goto out_ret;
+        }
+        if (elf_getshdrstrndx(elf, &shstrndx) != 0) {
+                ret = -EBADF;
+                goto out_ret;
+        }
+
+        /* Look for the required section */
+        scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL);
+        if (!scn) {
+                ret = -ENOENT;
+                goto out_ret;
+        }
+
+        if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) {
+                ret = -ENOENT;
+                goto out_ret;
+        }
+
+        data = elf_getdata(scn, NULL);
+
+        /* Get the SDT notes */
+        for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off,
+                                              &desc_off)) > 0; offset = next) {
+                if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) &&
+                    !memcmp(data->d_buf + name_off, SDT_NOTE_NAME,
+                            sizeof(SDT_NOTE_NAME))) {
+                        /* Check the type of the note */
+                        if (nhdr.n_type != SDT_NOTE_TYPE)
+                                goto out_ret;
+
+                        ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off),
+                                                nhdr.n_descsz, sdt_notes);
+                        if (ret < 0)
+                                goto out_ret;
+                }
+        }
+        if (list_empty(sdt_notes))
+                ret = -ENOENT;
+
+out_ret:
+        return ret;
+}
+
+/**
+ * get_sdt_note_list : Wrapper to construct a list of sdt notes
+ * @head : empty list_head
+ * @target : file to find SDT notes from
+ *
+ * This opens the file, initializes
+ * the ELF and then calls construct_sdt_notes_list.
+ */
+int get_sdt_note_list(struct list_head *head, const char *target)
+{
+        Elf *elf;
+        int fd, ret;
+
+        fd = open(target, O_RDONLY);
+        if (fd < 0)
+                return -EBADF;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (!elf) {
+                ret = -EBADF;
+                goto out_close;
+        }
+        ret = construct_sdt_notes_list(elf, head);
+        elf_end(elf);
+out_close:
+        close(fd);
+        return ret;
+}
+
+/**
+ * cleanup_sdt_note_list : free the sdt notes' list
+ * @sdt_notes: sdt notes' list
+ *
+ * Free up the SDT notes in @sdt_notes.
+ * Returns the number of SDT notes free'd.
+ */
+int cleanup_sdt_note_list(struct list_head *sdt_notes)
+{
+        struct sdt_note *tmp, *pos;
+        int nr_free = 0;
+
+        list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
+                list_del(&pos->note_list);
+                free(pos->name);
+                free(pos->provider);
+                free(pos);
+                nr_free++;
+        }
+        return nr_free;
+}
+
+/**
+ * sdt_notes__get_count: Counts the number of sdt events
+ * @start: list_head to sdt_notes list
+ *
+ * Returns the number of SDT notes in a list
+ */
+int sdt_notes__get_count(struct list_head *start)
+{
+        struct sdt_note *sdt_ptr;
+        int count = 0;
+
+        list_for_each_entry(sdt_ptr, start, note_list)
+                count++;
+        return count;
+}
+#endif
+
 void symbol__elf_init(void)
 {
         elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 54c4ff2b1cee..37e8d20ae03e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1430,7 +1430,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
          * Read the build id if possible. This is required for
          * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
          */
-        if (is_regular_file(name) &&
+        if (is_regular_file(dso->long_name) &&
             filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
                 dso__set_build_id(dso, build_id);
 
@@ -1626,7 +1626,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
         if (!dirs)
                 return -1;
 
-        strlist__for_each(nd, dirs) {
+        strlist__for_each_entry(nd, dirs) {
                 scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
                           "%s/%s/kallsyms", dir, nd->s);
                 if (!validate_kcore_addresses(kallsyms_filename, map)) {
@@ -1641,6 +1641,20 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
         return ret;
 }
 
+/*
+ * Use open(O_RDONLY) to check readability directly instead of access(R_OK)
+ * since access(R_OK) only checks with real UID/GID but open() use effective
+ * UID/GID and actual capabilities (e.g. /proc/kcore requires CAP_SYS_RAWIO).
+ */
+static bool filename__readable(const char *file)
+{
+        int fd = open(file, O_RDONLY);
+        if (fd < 0)
+                return false;
+        close(fd);
+        return true;
+}
+
 static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 {
         u8 host_build_id[BUILD_ID_SIZE];
@@ -1660,58 +1674,43 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
                                  sizeof(host_build_id)) == 0)
                 is_host = dso__build_id_equal(dso, host_build_id);
 
-        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-
-        scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
-                  DSO__NAME_KCORE, sbuild_id);
-
-        /* Use /proc/kallsyms if possible */
+        /* Try a fast path for /proc/kallsyms if possible */
         if (is_host) {
-                DIR *d;
-                int fd;
-
-                /* If no cached kcore go with /proc/kallsyms */
-                d = opendir(path);
-                if (!d)
-                        goto proc_kallsyms;
-                closedir(d);
-
                 /*
-                 * Do not check the build-id cache, until we know we cannot use
-                 * /proc/kcore.
+                 * Do not check the build-id cache, unless we know we cannot use
+                 * /proc/kcore or module maps don't match to /proc/kallsyms.
+                 * To check readability of /proc/kcore, do not use access(R_OK)
+                 * since /proc/kcore requires CAP_SYS_RAWIO to read and access
+                 * can't check it.
                  */
-                fd = open("/proc/kcore", O_RDONLY);
-                if (fd != -1) {
-                        close(fd);
-                        /* If module maps match go with /proc/kallsyms */
-                        if (!validate_kcore_addresses("/proc/kallsyms", map))
-                                goto proc_kallsyms;
-                }
-
-                /* Find kallsyms in build-id cache with kcore */
-                if (!find_matching_kcore(map, path, sizeof(path)))
-                        return strdup(path);
-
-                goto proc_kallsyms;
+                if (filename__readable("/proc/kcore") &&
+                    !validate_kcore_addresses("/proc/kallsyms", map))
+                        goto proc_kallsyms;
         }
 
+        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
         /* Find kallsyms in build-id cache with kcore */
+        scnprintf(path, sizeof(path), "%s/%s/%s",
+                  buildid_dir, DSO__NAME_KCORE, sbuild_id);
+
         if (!find_matching_kcore(map, path, sizeof(path)))
                 return strdup(path);
 
-        scnprintf(path, sizeof(path), "%s/%s/%s",
-                  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
+        /* Use current /proc/kallsyms if possible */
+        if (is_host) {
+proc_kallsyms:
+                return strdup("/proc/kallsyms");
+        }
 
-        if (access(path, F_OK)) {
+        /* Finally, find a cache of kallsyms */
+        if (!build_id_cache__kallsyms_path(sbuild_id, path, sizeof(path))) {
                 pr_err("No kallsyms or vmlinux with build-id %s was found\n",
                        sbuild_id);
                 return NULL;
         }
 
         return strdup(path);
-
-proc_kallsyms:
-        return strdup("/proc/kallsyms");
 }
 
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b10d558a8803..699f7cbcfe72 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -342,4 +342,26 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 
 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 
+/* structure containing an SDT note's info */
+struct sdt_note {
+        char *name;                     /* name of the note*/
+        char *provider;                 /* provider name */
+        bool bit32;                     /* whether the location is 32 bits? */
+        union {                         /* location, base and semaphore addrs */
+                Elf64_Addr a64[3];
+                Elf32_Addr a32[3];
+        } addr;
+        struct list_head note_list;     /* SDT notes' list */
+};
+
+int get_sdt_note_list(struct list_head *head, const char *target);
+int cleanup_sdt_note_list(struct list_head *sdt_notes);
+int sdt_notes__get_count(struct list_head *start);
+
+#define SDT_BASE_SCN ".stapsdt.base"
+#define SDT_NOTE_SCN  ".note.stapsdt"
+#define SDT_NOTE_TYPE 3
+#define SDT_NOTE_NAME "stapsdt"
+#define NR_ADDR 3
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index a53603b27e52..21c4d9b23c24 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -7,6 +7,7 @@
  */
 
 #include "target.h"
+#include "util.h"
 #include "debug.h"
 
 #include <pwd.h>
@@ -121,11 +122,7 @@ int target__strerror(struct target *target, int errnum,
         BUG_ON(buflen == 0);
 
         if (errnum >= 0) {
-                const char *err = strerror_r(errnum, buf, buflen);
-
-                if (err != buf)
-                        scnprintf(buf, buflen, "%s", err);
-
+                str_error_r(errnum, buf, buflen);
                 return 0;
         }
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 825086aa9a08..d3301529f6a7 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -616,3 +616,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
         return err;
 }
+
+size_t thread_stack__depth(struct thread *thread)
+{
+        if (!thread->ts)
+                return 0;
+        return thread->ts->cnt;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index ad44c7944b8e..b7e41c4ebfdd 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -87,6 +87,7 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
                           size_t sz, u64 ip);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread);
 
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, void *data),
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 45fcb715a36b..8b10a55410a2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -43,9 +43,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 thread->cpu = -1;
                 INIT_LIST_HEAD(&thread->comm_list);
 
-                if (unwind__prepare_access(thread) < 0)
-                        goto err_thread;
-
                 comm_str = malloc(32);
                 if (!comm_str)
                         goto err_thread;
@@ -201,10 +198,51 @@ size_t thread__fprintf(struct thread *thread, FILE *fp)
                map_groups__fprintf(thread->mg, fp);
 }
 
-void thread__insert_map(struct thread *thread, struct map *map)
+int thread__insert_map(struct thread *thread, struct map *map)
 {
+        int ret;
+
+        ret = unwind__prepare_access(thread, map, NULL);
+        if (ret)
+                return ret;
+
         map_groups__fixup_overlappings(thread->mg, map, stderr);
         map_groups__insert(thread->mg, map);
+
+        return 0;
+}
+
+static int __thread__prepare_access(struct thread *thread)
+{
+        bool initialized = false;
+        int i, err = 0;
+
+        for (i = 0; i < MAP__NR_TYPES; ++i) {
+                struct maps *maps = &thread->mg->maps[i];
+                struct map *map;
+
+                pthread_rwlock_rdlock(&maps->lock);
+
+                for (map = maps__first(maps); map; map = map__next(map)) {
+                        err = unwind__prepare_access(thread, map, &initialized);
+                        if (err || initialized)
+                                break;
+                }
+
+                pthread_rwlock_unlock(&maps->lock);
+        }
+
+        return err;
+}
+
+static int thread__prepare_access(struct thread *thread)
+{
+        int err = 0;
+
+        if (symbol_conf.use_callchain)
+                err = __thread__prepare_access(thread);
+
+        return err;
 }
 
 static int thread__clone_map_groups(struct thread *thread,
@@ -214,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
         /* This is new thread, we share map groups for process. */
         if (thread->pid_ == parent->pid_)
-                return 0;
+                return thread__prepare_access(thread);
 
         if (thread->mg == parent->mg) {
                 pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
@@ -224,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
         /* But this one is new process, copy maps. */
         for (i = 0; i < MAP__NR_TYPES; ++i)
-                if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+                if (map_groups__clone(thread, parent->mg, i) < 0)
                         return -ENOMEM;
 
         return 0;
@@ -265,3 +303,14 @@ void thread__find_cpumode_addr_location(struct thread *thread,
                         break;
         }
 }
+
+struct thread *thread__main_thread(struct machine *machine, struct thread *thread)
+{
+        if (thread->pid_ == thread->tid)
+                return thread__get(thread);
+
+        if (thread->pid_ == -1)
+                return NULL;
+
+        return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 45fba13c800b..99263cb6e6b6 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -9,11 +9,9 @@
 #include "symbol.h"
 #include <strlist.h>
 #include <intlist.h>
-#ifdef HAVE_LIBUNWIND_SUPPORT
-#include <libunwind.h>
-#endif
 
 struct thread_stack;
+struct unwind_libunwind_ops;
 
 struct thread {
         union {
@@ -36,7 +34,8 @@ struct thread {
         void                    *priv;
         struct thread_stack     *ts;
 #ifdef HAVE_LIBUNWIND_SUPPORT
-        unw_addr_space_t        addr_space;
+        void                            *addr_space;
+        struct unwind_libunwind_ops     *unwind_libunwind_ops;
 #endif
 };
 
@@ -77,10 +76,12 @@ int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
-void thread__insert_map(struct thread *thread, struct map *map);
+int thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
+struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
+
 void thread__find_addr_map(struct thread *thread,
                            u8 cpumode, enum map_type type, u64 addr,
                            struct addr_location *al);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5654fe15e036..40585f5b7027 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -202,7 +202,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
         if (!slist)
                 return NULL;
 
-        strlist__for_each(pos, slist) {
+        strlist__for_each_entry(pos, slist) {
                 pid = strtol(pos->s, &end_ptr, 10);
 
                 if (pid == INT_MIN || pid == INT_MAX ||
@@ -278,7 +278,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
         if (!slist)
                 return NULL;
 
-        strlist__for_each(pos, slist) {
+        strlist__for_each_entry(pos, slist) {
                 tid = strtol(pos->s, &end_ptr, 10);
 
                 if (tid == INT_MIN || tid == INT_MAX ||
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 8ae051e0ec79..c330780674fc 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -105,3 +105,11 @@ trace_event__tp_format(const char *sys, const char *name)
 
         return tp_format(sys, name);
 }
+
+struct event_format *trace_event__tp_format_id(int id)
+{
+        if (!tevent_initialized && trace_event__init2())
+                return ERR_PTR(-ENOMEM);
+
+        return pevent_find_event(tevent.pevent, id);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index bce5b1dac268..b0af9c81bb0d 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -23,6 +23,8 @@ int trace_event__register_resolver(struct machine *machine,
 struct event_format*
 trace_event__tp_format(const char *sys, const char *name);
 
+struct event_format *trace_event__tp_format_id(int id);
+
 int bigendian(void);
 
 void event_format__fprintf(struct event_format *event,
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
new file mode 100644
index 000000000000..97c0f8fc5561
--- /dev/null
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -0,0 +1,699 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ *      Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#ifndef REMOTE_UNWIND_LIBUNWIND
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#endif
+#include "callchain.h"
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "symbol.h"
+#include "util.h"
+#include "debug.h"
+#include "asm/bug.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+                                    unw_word_t ip,
+                                    unw_dyn_info_t *di,
+                                    unw_proc_info_t *pi,
+                                    int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+extern int
+UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
+                                 unw_word_t ip,
+                                 unw_word_t segbase,
+                                 const char *obj_name, unw_word_t start,
+                                 unw_word_t end);
+
+#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
+
+#define DW_EH_PE_FORMAT_MASK    0x0f    /* format of the encoded value */
+#define DW_EH_PE_APPL_MASK      0x70    /* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit           0xff
+#define DW_EH_PE_ptr            0x00    /* pointer-sized unsigned value */
+#define DW_EH_PE_udata4         0x03    /* unsigned 32-bit value */
+#define DW_EH_PE_udata8         0x04    /* unsigned 64-bit value */
+#define DW_EH_PE_sdata4         0x0b    /* signed 32-bit value */
+#define DW_EH_PE_sdata8         0x0c    /* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr         0x00    /* absolute value */
+#define DW_EH_PE_pcrel          0x10    /* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel        0x40    /* start-of-procedure-relative */
+#define DW_EH_PE_aligned        0x50    /* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect      0x80
+ * #define DW_EH_PE_uleb128       0x01
+ * #define DW_EH_PE_udata2        0x02
+ * #define DW_EH_PE_sleb128       0x09
+ * #define DW_EH_PE_sdata2        0x0a
+ * #define DW_EH_PE_textrel       0x20
+ * #define DW_EH_PE_datarel       0x30
+ */
+
+struct unwind_info {
+        struct perf_sample      *sample;
+        struct machine          *machine;
+        struct thread           *thread;
+};
+
+#define dw_read(ptr, type, end) ({      \
+        type *__p = (type *) ptr;       \
+        type  __v;                      \
+        if ((__p + 1) > (type *) end)   \
+                return -EINVAL;         \
+        __v = *__p++;                   \
+        ptr = (typeof(ptr)) __p;        \
+        __v;                            \
+        })
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+                                   u8 encoding)
+{
+        u8 *cur = *p;
+        *val = 0;
+
+        switch (encoding) {
+        case DW_EH_PE_omit:
+                *val = 0;
+                goto out;
+        case DW_EH_PE_ptr:
+                *val = dw_read(cur, unsigned long, end);
+                goto out;
+        default:
+                break;
+        }
+
+        switch (encoding & DW_EH_PE_APPL_MASK) {
+        case DW_EH_PE_absptr:
+                break;
+        case DW_EH_PE_pcrel:
+                *val = (unsigned long) cur;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        if ((encoding & 0x07) == 0x00)
+                encoding |= DW_EH_PE_udata4;
+
+        switch (encoding & DW_EH_PE_FORMAT_MASK) {
+        case DW_EH_PE_sdata4:
+                *val += dw_read(cur, s32, end);
+                break;
+        case DW_EH_PE_udata4:
+                *val += dw_read(cur, u32, end);
+                break;
+        case DW_EH_PE_sdata8:
+                *val += dw_read(cur, s64, end);
+                break;
+        case DW_EH_PE_udata8:
+                *val += dw_read(cur, u64, end);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+ out:
+        *p = cur;
+        return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({                 \
+        u64 __v;                                                \
+        if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {    \
+                return -EINVAL;                                 \
+        }                                                       \
+        __v;                                                    \
+        })
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+        u64 offset = 0;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return 0;
+
+        do {
+                if (gelf_getehdr(elf, &ehdr) == NULL)
+                        break;
+
+                if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
+                        break;
+
+                offset = shdr.sh_offset;
+        } while (0);
+
+        elf_end(elf);
+        return offset;
+}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        int retval = 0;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return 0;
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                goto out;
+
+        retval = (ehdr.e_type == ET_EXEC);
+
+out:
+        elf_end(elf);
+        pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+        return retval;
+}
+#endif
+
+struct table_entry {
+        u32 start_ip_offset;
+        u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+        unsigned char version;
+        unsigned char eh_frame_ptr_enc;
+        unsigned char fde_count_enc;
+        unsigned char table_enc;
+
+        /*
+         * The rest of the header is variable-length and consists of the
+         * following members:
+         *
+         *      encoded_t eh_frame_ptr;
+         *      encoded_t fde_count;
+         */
+
+        /* A single encoded pointer should not be more than 8 bytes. */
+        u64 enc[2];
+
+        /*
+         * struct {
+         *    encoded_t start_ip;
+         *    encoded_t fde_addr;
+         * } binary_search_table[fde_count];
+         */
+        char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+                               u64 offset, u64 *table_data, u64 *segbase,
+                               u64 *fde_count)
+{
+        struct eh_frame_hdr hdr;
+        u8 *enc = (u8 *) &hdr.enc;
+        u8 *end = (u8 *) &hdr.data;
+        ssize_t r;
+
+        r = dso__data_read_offset(dso, machine, offset,
+                                  (u8 *) &hdr, sizeof(hdr));
+        if (r != sizeof(hdr))
+                return -EINVAL;
+
+        /* We dont need eh_frame_ptr, just skip it. */
+        dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+        *fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+        *segbase    = offset;
+        *table_data = (enc - (u8 *) &hdr) + offset;
+        return 0;
+}
+
+static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
+                                     u64 *table_data, u64 *segbase,
+                                     u64 *fde_count)
+{
+        int ret = -EINVAL, fd;
+        u64 offset = dso->data.eh_frame_hdr_offset;
+
+        if (offset == 0) {
+                fd = dso__data_get_fd(dso, machine);
+                if (fd < 0)
+                        return -EINVAL;
+
+                /* Check the .eh_frame section for unwinding info */
+                offset = elf_section_offset(fd, ".eh_frame_hdr");
+                dso->data.eh_frame_hdr_offset = offset;
+                dso__data_put_fd(dso);
+        }
+
+        if (offset)
+                ret = unwind_spec_ehframe(dso, machine, offset,
+                                          table_data, segbase,
+                                          fde_count);
+
+        return ret;
+}
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int read_unwind_spec_debug_frame(struct dso *dso,
+                                        struct machine *machine, u64 *offset)
+{
+        int fd;
+        u64 ofs = dso->data.debug_frame_offset;
+
+        if (ofs == 0) {
+                fd = dso__data_get_fd(dso, machine);
+                if (fd < 0)
+                        return -EINVAL;
+
+                /* Check the .debug_frame section for unwinding info */
+                ofs = elf_section_offset(fd, ".debug_frame");
+                dso->data.debug_frame_offset = ofs;
+                dso__data_put_fd(dso);
+        }
+
+        *offset = ofs;
+        if (*offset)
+                return 0;
+
+        return -EINVAL;
+}
+#endif
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+        struct addr_location al;
+
+        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+                              MAP__FUNCTION, ip, &al);
+        if (!al.map) {
+                /*
+                 * We've seen cases (softice) where DWARF unwinder went
+                 * through non executable mmaps, which we need to lookup
+                 * in MAP__VARIABLE tree.
+                 */
+                thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
+                                      MAP__VARIABLE, ip, &al);
+        }
+        return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+               int need_unwind_info, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct map *map;
+        unw_dyn_info_t di;
+        u64 table_data, segbase, fde_count;
+        int ret = -EINVAL;
+
+        map = find_map(ip, ui);
+        if (!map || !map->dso)
+                return -EINVAL;
+
+        pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+        /* Check the .eh_frame section for unwinding info */
+        if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
+                                       &table_data, &segbase, &fde_count)) {
+                memset(&di, 0, sizeof(di));
+                di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
+                di.start_ip = map->start;
+                di.end_ip   = map->end;
+                di.u.rti.segbase    = map->start + segbase;
+                di.u.rti.table_data = map->start + table_data;
+                di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
+                                      / sizeof(unw_word_t);
+                ret = dwarf_search_unwind_table(as, ip, &di, pi,
+                                                need_unwind_info, arg);
+        }
+
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+        /* Check the .debug_frame section for unwinding info */
+        if (ret < 0 &&
+            !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+                int fd = dso__data_get_fd(map->dso, ui->machine);
+                int is_exec = elf_is_exec(fd, map->dso->name);
+                unw_word_t base = is_exec ? 0 : map->start;
+                const char *symfile;
+
+                if (fd >= 0)
+                        dso__data_put_fd(map->dso);
+
+                symfile = map->dso->symsrc_filename ?: map->dso->name;
+
+                memset(&di, 0, sizeof(di));
+                if (dwarf_find_debug_frame(0, &di, ip, base, symfile,
+                                           map->start, map->end))
+                        return dwarf_search_unwind_table(as, ip, &di, pi,
+                                                         need_unwind_info, arg);
+        }
+#endif
+
+        return ret;
+}
+
+static int access_fpreg(unw_addr_space_t __maybe_unused as,
+                        unw_regnum_t __maybe_unused num,
+                        unw_fpreg_t __maybe_unused *val,
+                        int __maybe_unused __write,
+                        void __maybe_unused *arg)
+{
+        pr_err("unwind: access_fpreg unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
+                                  unw_word_t __maybe_unused *dil_addr,
+                                  void __maybe_unused *arg)
+{
+        return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __maybe_unused as,
+                  unw_cursor_t __maybe_unused *cu,
+                  void __maybe_unused *arg)
+{
+        pr_err("unwind: resume unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __maybe_unused as,
+              unw_word_t __maybe_unused addr,
+                char __maybe_unused *bufp, size_t __maybe_unused buf_len,
+                unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
+{
+        pr_err("unwind: get_proc_name unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+                          unw_word_t *data)
+{
+        struct map *map;
+        ssize_t size;
+
+        map = find_map(addr, ui);
+        if (!map) {
+                pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+                return -1;
+        }
+
+        if (!map->dso)
+                return -1;
+
+        size = dso__data_read_addr(map->dso, map, ui->machine,
+                                   addr, (u8 *) data, sizeof(*data));
+
+        return !(size == sizeof(*data));
+}
+
+static int access_mem(unw_addr_space_t __maybe_unused as,
+                      unw_word_t addr, unw_word_t *valp,
+                      int __write, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct stack_dump *stack = &ui->sample->user_stack;
+        u64 start, end;
+        int offset;
+        int ret;
+
+        /* Don't support write, probably not needed. */
+        if (__write || !stack || !ui->sample->user_regs.regs) {
+                *valp = 0;
+                return 0;
+        }
+
+        ret = perf_reg_value(&start, &ui->sample->user_regs,
+                             LIBUNWIND__ARCH_REG_SP);
+        if (ret)
+                return ret;
+
+        end = start + stack->size;
+
+        /* Check overflow. */
+        if (addr + sizeof(unw_word_t) < addr)
+                return -EINVAL;
+
+        if (addr < start || addr + sizeof(unw_word_t) >= end) {
+                ret = access_dso_mem(ui, addr, valp);
+                if (ret) {
+                        pr_debug("unwind: access_mem %p not inside range"
+                                 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+                                 (void *) (uintptr_t) addr, start, end);
+                        *valp = 0;
+                        return ret;
+                }
+                return 0;
+        }
+
+        offset = addr - start;
+        *valp  = *(unw_word_t *)&stack->data[offset];
+        pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+                 (void *) (uintptr_t) addr, (unsigned long)*valp, offset);
+        return 0;
+}
+
+static int access_reg(unw_addr_space_t __maybe_unused as,
+                      unw_regnum_t regnum, unw_word_t *valp,
+                      int __write, void *arg)
+{
+        struct unwind_info *ui = arg;
+        int id, ret;
+        u64 val;
+
+        /* Don't support write, I suspect we don't need it. */
+        if (__write) {
+                pr_err("unwind: access_reg w %d\n", regnum);
+                return 0;
+        }
+
+        if (!ui->sample->user_regs.regs) {
+                *valp = 0;
+                return 0;
+        }
+
+        id = LIBUNWIND__ARCH_REG_ID(regnum);
+        if (id < 0)
+                return -EINVAL;
+
+        ret = perf_reg_value(&val, &ui->sample->user_regs, id);
+        if (ret) {
+                pr_err("unwind: can't read reg %d\n", regnum);
+                return ret;
+        }
+
+        *valp = (unw_word_t) val;
+        pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+        return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __maybe_unused as,
+                            unw_proc_info_t *pi __maybe_unused,
+                            void *arg __maybe_unused)
+{
+        pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread,
+                 unwind_entry_cb_t cb, void *arg)
+{
+        struct unwind_entry e;
+        struct addr_location al;
+
+        thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
+                                   MAP__FUNCTION, ip, &al);
+
+        e.ip = ip;
+        e.map = al.map;
+        e.sym = al.sym;
+
+        pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+                 al.sym ? al.sym->name : "''",
+                 ip,
+                 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+        return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+        switch (err) {
+        case UNW_EINVAL:
+                pr_err("unwind: Only supports local.\n");
+                break;
+        case UNW_EUNSPEC:
+                pr_err("unwind: Unspecified error.\n");
+                break;
+        case UNW_EBADREG:
+                pr_err("unwind: Register unavailable.\n");
+                break;
+        default:
+                break;
+        }
+}
+
+static unw_accessors_t accessors = {
+        .find_proc_info         = find_proc_info,
+        .put_unwind_info        = put_unwind_info,
+        .get_dyn_info_list_addr = get_dyn_info_list_addr,
+        .access_mem             = access_mem,
+        .access_reg             = access_reg,
+        .access_fpreg           = access_fpreg,
+        .resume                 = resume,
+        .get_proc_name          = get_proc_name,
+};
+
+static int _unwind__prepare_access(struct thread *thread)
+{
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return 0;
+
+        thread->addr_space = unw_create_addr_space(&accessors, 0);
+        if (!thread->addr_space) {
+                pr_err("unwind: Can't create unwind address space.\n");
+                return -ENOMEM;
+        }
+
+        unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
+        return 0;
+}
+
+static void _unwind__flush_access(struct thread *thread)
+{
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return;
+
+        unw_flush_cache(thread->addr_space, 0, 0);
+}
+
+static void _unwind__finish_access(struct thread *thread)
+{
+        if (callchain_param.record_mode != CALLCHAIN_DWARF)
+                return;
+
+        unw_destroy_addr_space(thread->addr_space);
+}
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+                       void *arg, int max_stack)
+{
+        u64 val;
+        unw_word_t ips[max_stack];
+        unw_addr_space_t addr_space;
+        unw_cursor_t c;
+        int ret, i = 0;
+
+        ret = perf_reg_value(&val, &ui->sample->user_regs,
+                             LIBUNWIND__ARCH_REG_IP);
+        if (ret)
+                return ret;
+
+        ips[i++] = (unw_word_t) val;
+
+        /*
+         * If we need more than one entry, do the DWARF
+         * unwind itself.
+         */
+        if (max_stack - 1 > 0) {
+                WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
+                addr_space = ui->thread->addr_space;
+
+                if (addr_space == NULL)
+                        return -1;
+
+                ret = unw_init_remote(&c, addr_space, ui);
+                if (ret)
+                        display_error(ret);
+
+                while (!ret && (unw_step(&c) > 0) && i < max_stack) {
+                        unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+                        ++i;
+                }
+
+                max_stack = i;
+        }
+
+        /*
+         * Display what we got based on the order setup.
+         */
+        for (i = 0; i < max_stack && !ret; i++) {
+                int j = i;
+
+                if (callchain_param.order == ORDER_CALLER)
+                        j = max_stack - i - 1;
+                ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
+        }
+
+        return ret;
+}
+
+static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+                        struct thread *thread,
+                        struct perf_sample *data, int max_stack)
+{
+        struct unwind_info ui = {
+                .sample       = data,
+                .thread       = thread,
+                .machine      = thread->mg->machine,
+        };
+
+        if (!data->user_regs.regs)
+                return -EINVAL;
+
+        if (max_stack <= 0)
+                return -EINVAL;
+
+        return get_entries(&ui, cb, arg, max_stack);
+}
+
+static struct unwind_libunwind_ops
+_unwind_libunwind_ops = {
+        .prepare_access = _unwind__prepare_access,
+        .flush_access   = _unwind__flush_access,
+        .finish_access  = _unwind__finish_access,
+        .get_entries    = _unwind__get_entries,
+};
+
+#ifndef REMOTE_UNWIND_LIBUNWIND
+struct unwind_libunwind_ops *
+local_unwind_libunwind_ops = &_unwind_libunwind_ops;
+#endif
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 63687d3a344e..6d542a4e0648 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,682 +1,83 @@
-/*
- * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
- *
- * Lots of this code have been borrowed or heavily inspired from parts of
- * the libunwind 0.99 code which are (amongst other contributors I may have
- * forgotten):
- *
- * Copyright (C) 2002-2007 Hewlett-Packard Co
- *      Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
- *
- * And the bugs have been added by:
- *
- * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
- * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
- *
- */
-
-#include <elf.h>
-#include <gelf.h>
-#include <fcntl.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <linux/list.h>
-#include <libunwind.h>
-#include <libunwind-ptrace.h>
-#include "callchain.h"
+#include "unwind.h"
 #include "thread.h"
 #include "session.h"
-#include "perf_regs.h"
-#include "unwind.h"
-#include "symbol.h"
-#include "util.h"
 #include "debug.h"
-#include "asm/bug.h"
-
-extern int
-UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
-                                    unw_word_t ip,
-                                    unw_dyn_info_t *di,
-                                    unw_proc_info_t *pi,
-                                    int need_unwind_info, void *arg);
-
-#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
-
-extern int
-UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
-                                 unw_word_t ip,
-                                 unw_word_t segbase,
-                                 const char *obj_name, unw_word_t start,
-                                 unw_word_t end);
-
-#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
-
-#define DW_EH_PE_FORMAT_MASK    0x0f    /* format of the encoded value */
-#define DW_EH_PE_APPL_MASK      0x70    /* how the value is to be applied */
-
-/* Pointer-encoding formats: */
-#define DW_EH_PE_omit           0xff
-#define DW_EH_PE_ptr            0x00    /* pointer-sized unsigned value */
-#define DW_EH_PE_udata4         0x03    /* unsigned 32-bit value */
-#define DW_EH_PE_udata8         0x04    /* unsigned 64-bit value */
-#define DW_EH_PE_sdata4         0x0b    /* signed 32-bit value */
-#define DW_EH_PE_sdata8         0x0c    /* signed 64-bit value */
-
-/* Pointer-encoding application: */
-#define DW_EH_PE_absptr         0x00    /* absolute value */
-#define DW_EH_PE_pcrel          0x10    /* rel. to addr. of encoded value */
-
-/*
- * The following are not documented by LSB v1.3, yet they are used by
- * GCC, presumably they aren't documented by LSB since they aren't
- * used on Linux:
- */
-#define DW_EH_PE_funcrel        0x40    /* start-of-procedure-relative */
-#define DW_EH_PE_aligned        0x50    /* aligned pointer */
+#include "arch/common.h"
 
-/* Flags intentionaly not handled, since they're not needed:
- * #define DW_EH_PE_indirect      0x80
- * #define DW_EH_PE_uleb128       0x01
- * #define DW_EH_PE_udata2        0x02
- * #define DW_EH_PE_sleb128       0x09
- * #define DW_EH_PE_sdata2        0x0a
- * #define DW_EH_PE_textrel       0x20
- * #define DW_EH_PE_datarel       0x30
- */
+struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
+struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
+struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops;
 
-struct unwind_info {
-        struct perf_sample      *sample;
-        struct machine          *machine;
-        struct thread           *thread;
-};
-
-#define dw_read(ptr, type, end) ({      \
-        type *__p = (type *) ptr;       \
-        type  __v;                      \
-        if ((__p + 1) > (type *) end)   \
-                return -EINVAL;         \
-        __v = *__p++;                   \
-        ptr = (typeof(ptr)) __p;        \
-        __v;                            \
-        })
-
-static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
-                                   u8 encoding)
+static void unwind__register_ops(struct thread *thread,
+                          struct unwind_libunwind_ops *ops)
 {
-        u8 *cur = *p;
-        *val = 0;
-
-        switch (encoding) {
-        case DW_EH_PE_omit:
-                *val = 0;
-                goto out;
-        case DW_EH_PE_ptr:
-                *val = dw_read(cur, unsigned long, end);
-                goto out;
-        default:
-                break;
-        }
-
-        switch (encoding & DW_EH_PE_APPL_MASK) {
-        case DW_EH_PE_absptr:
-                break;
-        case DW_EH_PE_pcrel:
-                *val = (unsigned long) cur;
-                break;
-        default:
-                return -EINVAL;
-        }
-
-        if ((encoding & 0x07) == 0x00)
-                encoding |= DW_EH_PE_udata4;
-
-        switch (encoding & DW_EH_PE_FORMAT_MASK) {
-        case DW_EH_PE_sdata4:
-                *val += dw_read(cur, s32, end);
-                break;
-        case DW_EH_PE_udata4:
-                *val += dw_read(cur, u32, end);
-                break;
-        case DW_EH_PE_sdata8:
-                *val += dw_read(cur, s64, end);
-                break;
-        case DW_EH_PE_udata8:
-                *val += dw_read(cur, u64, end);
-                break;
-        default:
-                return -EINVAL;
-        }
-
- out:
-        *p = cur;
-        return 0;
-}
-
-#define dw_read_encoded_value(ptr, end, enc) ({                 \
-        u64 __v;                                                \
-        if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {    \
-                return -EINVAL;                                 \
-        }                                                       \
-        __v;                                                    \
-        })
-
-static u64 elf_section_offset(int fd, const char *name)
-{
-        Elf *elf;
-        GElf_Ehdr ehdr;
-        GElf_Shdr shdr;
-        u64 offset = 0;
-
-        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-        if (elf == NULL)
-                return 0;
-
-        do {
-                if (gelf_getehdr(elf, &ehdr) == NULL)
-                        break;
-
-                if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
-                        break;
-
-                offset = shdr.sh_offset;
-        } while (0);
-
-        elf_end(elf);
-        return offset;
+        thread->unwind_libunwind_ops = ops;
 }
 
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-static int elf_is_exec(int fd, const char *name)
+int unwind__prepare_access(struct thread *thread, struct map *map,
+                           bool *initialized)
 {
-        Elf *elf;
-        GElf_Ehdr ehdr;
-        int retval = 0;
+        const char *arch;
+        enum dso_type dso_type;
+        struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops;
+        int err;
 
-        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-        if (elf == NULL)
+        if (thread->addr_space) {
+                pr_debug("unwind: thread map already set, dso=%s\n",
+                         map->dso->name);
+                if (initialized)
+                        *initialized = true;
                 return 0;
-        if (gelf_getehdr(elf, &ehdr) == NULL)
-                goto out;
-
-        retval = (ehdr.e_type == ET_EXEC);
-
-out:
-        elf_end(elf);
-        pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
-        return retval;
-}
-#endif
-
-struct table_entry {
-        u32 start_ip_offset;
-        u32 fde_offset;
-};
-
-struct eh_frame_hdr {
-        unsigned char version;
-        unsigned char eh_frame_ptr_enc;
-        unsigned char fde_count_enc;
-        unsigned char table_enc;
-
-        /*
-         * The rest of the header is variable-length and consists of the
-         * following members:
-         *
-         *      encoded_t eh_frame_ptr;
-         *      encoded_t fde_count;
-         */
-
-        /* A single encoded pointer should not be more than 8 bytes. */
-        u64 enc[2];
-
-        /*
-         * struct {
-         *    encoded_t start_ip;
-         *    encoded_t fde_addr;
-         * } binary_search_table[fde_count];
-         */
-        char data[0];
-} __packed;
-
-static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
-                               u64 offset, u64 *table_data, u64 *segbase,
-                               u64 *fde_count)
-{
-        struct eh_frame_hdr hdr;
-        u8 *enc = (u8 *) &hdr.enc;
-        u8 *end = (u8 *) &hdr.data;
-        ssize_t r;
-
-        r = dso__data_read_offset(dso, machine, offset,
-                                  (u8 *) &hdr, sizeof(hdr));
-        if (r != sizeof(hdr))
-                return -EINVAL;
-
-        /* We dont need eh_frame_ptr, just skip it. */
-        dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
-
-        *fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
-        *segbase    = offset;
-        *table_data = (enc - (u8 *) &hdr) + offset;
-        return 0;
-}
-
-static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
-                                     u64 *table_data, u64 *segbase,
-                                     u64 *fde_count)
-{
-        int ret = -EINVAL, fd;
-        u64 offset = dso->data.eh_frame_hdr_offset;
-
-        if (offset == 0) {
-                fd = dso__data_get_fd(dso, machine);
-                if (fd < 0)
-                        return -EINVAL;
-
-                /* Check the .eh_frame section for unwinding info */
-                offset = elf_section_offset(fd, ".eh_frame_hdr");
-                dso->data.eh_frame_hdr_offset = offset;
-                dso__data_put_fd(dso);
         }
 
-        if (offset)
-                ret = unwind_spec_ehframe(dso, machine, offset,
-                                          table_data, segbase,
-                                          fde_count);
+        /* env->arch is NULL for live-mode (i.e. perf top) */
+        if (!thread->mg->machine->env || !thread->mg->machine->env->arch)
+                goto out_register;
 
-        return ret;
-}
-
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-static int read_unwind_spec_debug_frame(struct dso *dso,
-                                        struct machine *machine, u64 *offset)
-{
-        int fd;
-        u64 ofs = dso->data.debug_frame_offset;
-
-        if (ofs == 0) {
-                fd = dso__data_get_fd(dso, machine);
-                if (fd < 0)
-                        return -EINVAL;
-
-                /* Check the .debug_frame section for unwinding info */
-                ofs = elf_section_offset(fd, ".debug_frame");
-                dso->data.debug_frame_offset = ofs;
-                dso__data_put_fd(dso);
-        }
-
-        *offset = ofs;
-        if (*offset)
+        dso_type = dso__type(map->dso, thread->mg->machine);
+        if (dso_type == DSO__TYPE_UNKNOWN)
                 return 0;
 
-        return -EINVAL;
-}
-#endif
-
-static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
-{
-        struct addr_location al;
-
-        thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-                              MAP__FUNCTION, ip, &al);
-        if (!al.map) {
-                /*
-                 * We've seen cases (softice) where DWARF unwinder went
-                 * through non executable mmaps, which we need to lookup
-                 * in MAP__VARIABLE tree.
-                 */
-                thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-                                      MAP__VARIABLE, ip, &al);
-        }
-        return al.map;
-}
-
-static int
-find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
-               int need_unwind_info, void *arg)
-{
-        struct unwind_info *ui = arg;
-        struct map *map;
-        unw_dyn_info_t di;
-        u64 table_data, segbase, fde_count;
-        int ret = -EINVAL;
-
-        map = find_map(ip, ui);
-        if (!map || !map->dso)
-                return -EINVAL;
-
-        pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
-
-        /* Check the .eh_frame section for unwinding info */
-        if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
-                                       &table_data, &segbase, &fde_count)) {
-                memset(&di, 0, sizeof(di));
-                di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
-                di.start_ip = map->start;
-                di.end_ip   = map->end;
-                di.u.rti.segbase    = map->start + segbase;
-                di.u.rti.table_data = map->start + table_data;
-                di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
-                                      / sizeof(unw_word_t);
-                ret = dwarf_search_unwind_table(as, ip, &di, pi,
-                                                need_unwind_info, arg);
-        }
-
-#ifndef NO_LIBUNWIND_DEBUG_FRAME
-        /* Check the .debug_frame section for unwinding info */
-        if (ret < 0 &&
-            !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-                int fd = dso__data_get_fd(map->dso, ui->machine);
-                int is_exec = elf_is_exec(fd, map->dso->name);
-                unw_word_t base = is_exec ? 0 : map->start;
-                const char *symfile;
-
-                if (fd >= 0)
-                        dso__data_put_fd(map->dso);
-
-                symfile = map->dso->symsrc_filename ?: map->dso->name;
-
-                memset(&di, 0, sizeof(di));
-                if (dwarf_find_debug_frame(0, &di, ip, base, symfile,
-                                           map->start, map->end))
-                        return dwarf_search_unwind_table(as, ip, &di, pi,
-                                                         need_unwind_info, arg);
-        }
-#endif
-
-        return ret;
-}
-
-static int access_fpreg(unw_addr_space_t __maybe_unused as,
-                        unw_regnum_t __maybe_unused num,
-                        unw_fpreg_t __maybe_unused *val,
-                        int __maybe_unused __write,
-                        void __maybe_unused *arg)
-{
-        pr_err("unwind: access_fpreg unsupported\n");
-        return -UNW_EINVAL;
-}
-
-static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as,
-                                  unw_word_t __maybe_unused *dil_addr,
-                                  void __maybe_unused *arg)
-{
-        return -UNW_ENOINFO;
-}
-
-static int resume(unw_addr_space_t __maybe_unused as,
-                  unw_cursor_t __maybe_unused *cu,
-                  void __maybe_unused *arg)
-{
-        pr_err("unwind: resume unsupported\n");
-        return -UNW_EINVAL;
-}
+        arch = normalize_arch(thread->mg->machine->env->arch);
 
-static int
-get_proc_name(unw_addr_space_t __maybe_unused as,
-              unw_word_t __maybe_unused addr,
-                char __maybe_unused *bufp, size_t __maybe_unused buf_len,
-                unw_word_t __maybe_unused *offp, void __maybe_unused *arg)
-{
-        pr_err("unwind: get_proc_name unsupported\n");
-        return -UNW_EINVAL;
-}
-
-static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
-                          unw_word_t *data)
-{
-        struct map *map;
-        ssize_t size;
-
-        map = find_map(addr, ui);
-        if (!map) {
-                pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
-                return -1;
+        if (!strcmp(arch, "x86")) {
+                if (dso_type != DSO__TYPE_64BIT)
+                        ops = x86_32_unwind_libunwind_ops;
+        } else if (!strcmp(arch, "arm64") || !strcmp(arch, "arm")) {
+                if (dso_type == DSO__TYPE_64BIT)
+                        ops = arm64_unwind_libunwind_ops;
         }
 
-        if (!map->dso)
+        if (!ops) {
+                pr_err("unwind: target platform=%s is not supported\n", arch);
                 return -1;
-
-        size = dso__data_read_addr(map->dso, map, ui->machine,
-                                   addr, (u8 *) data, sizeof(*data));
-
-        return !(size == sizeof(*data));
-}
-
-static int access_mem(unw_addr_space_t __maybe_unused as,
-                      unw_word_t addr, unw_word_t *valp,
-                      int __write, void *arg)
-{
-        struct unwind_info *ui = arg;
-        struct stack_dump *stack = &ui->sample->user_stack;
-        u64 start, end;
-        int offset;
-        int ret;
-
-        /* Don't support write, probably not needed. */
-        if (__write || !stack || !ui->sample->user_regs.regs) {
-                *valp = 0;
-                return 0;
-        }
-
-        ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
-        if (ret)
-                return ret;
-
-        end = start + stack->size;
-
-        /* Check overflow. */
-        if (addr + sizeof(unw_word_t) < addr)
-                return -EINVAL;
-
-        if (addr < start || addr + sizeof(unw_word_t) >= end) {
-                ret = access_dso_mem(ui, addr, valp);
-                if (ret) {
-                        pr_debug("unwind: access_mem %p not inside range"
-                                 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
-                                 (void *) (uintptr_t) addr, start, end);
-                        *valp = 0;
-                        return ret;
-                }
-                return 0;
-        }
-
-        offset = addr - start;
-        *valp  = *(unw_word_t *)&stack->data[offset];
-        pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
-                 (void *) (uintptr_t) addr, (unsigned long)*valp, offset);
-        return 0;
-}
-
-static int access_reg(unw_addr_space_t __maybe_unused as,
-                      unw_regnum_t regnum, unw_word_t *valp,
-                      int __write, void *arg)
-{
-        struct unwind_info *ui = arg;
-        int id, ret;
-        u64 val;
-
-        /* Don't support write, I suspect we don't need it. */
-        if (__write) {
-                pr_err("unwind: access_reg w %d\n", regnum);
-                return 0;
-        }
-
-        if (!ui->sample->user_regs.regs) {
-                *valp = 0;
-                return 0;
-        }
-
-        id = libunwind__arch_reg_id(regnum);
-        if (id < 0)
-                return -EINVAL;
-
-        ret = perf_reg_value(&val, &ui->sample->user_regs, id);
-        if (ret) {
-                pr_err("unwind: can't read reg %d\n", regnum);
-                return ret;
-        }
-
-        *valp = (unw_word_t) val;
-        pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
-        return 0;
-}
-
-static void put_unwind_info(unw_addr_space_t __maybe_unused as,
-                            unw_proc_info_t *pi __maybe_unused,
-                            void *arg __maybe_unused)
-{
-        pr_debug("unwind: put_unwind_info called\n");
-}
-
-static int entry(u64 ip, struct thread *thread,
-                 unwind_entry_cb_t cb, void *arg)
-{
-        struct unwind_entry e;
-        struct addr_location al;
-
-        thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-                                   MAP__FUNCTION, ip, &al);
-
-        e.ip = ip;
-        e.map = al.map;
-        e.sym = al.sym;
-
-        pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
-                 al.sym ? al.sym->name : "''",
-                 ip,
-                 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
-
-        return cb(&e, arg);
-}
-
-static void display_error(int err)
-{
-        switch (err) {
-        case UNW_EINVAL:
-                pr_err("unwind: Only supports local.\n");
-                break;
-        case UNW_EUNSPEC:
-                pr_err("unwind: Unspecified error.\n");
-                break;
-        case UNW_EBADREG:
-                pr_err("unwind: Register unavailable.\n");
-                break;
-        default:
-                break;
-        }
-}
-
-static unw_accessors_t accessors = {
-        .find_proc_info         = find_proc_info,
-        .put_unwind_info        = put_unwind_info,
-        .get_dyn_info_list_addr = get_dyn_info_list_addr,
-        .access_mem             = access_mem,
-        .access_reg             = access_reg,
-        .access_fpreg           = access_fpreg,
-        .resume                 = resume,
-        .get_proc_name          = get_proc_name,
-};
-
-int unwind__prepare_access(struct thread *thread)
-{
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
-                return 0;
-
-        thread->addr_space = unw_create_addr_space(&accessors, 0);
-        if (!thread->addr_space) {
-                pr_err("unwind: Can't create unwind address space.\n");
-                return -ENOMEM;
         }
+out_register:
+        unwind__register_ops(thread, ops);
 
-        unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL);
-        return 0;
+        err = thread->unwind_libunwind_ops->prepare_access(thread);
+        if (initialized)
+                *initialized = err ? false : true;
+        return err;
 }
 
 void unwind__flush_access(struct thread *thread)
 {
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
-                return;
-
-        unw_flush_cache(thread->addr_space, 0, 0);
+        if (thread->unwind_libunwind_ops)
+                thread->unwind_libunwind_ops->flush_access(thread);
 }
 
 void unwind__finish_access(struct thread *thread)
 {
-        if (callchain_param.record_mode != CALLCHAIN_DWARF)
-                return;
-
-        unw_destroy_addr_space(thread->addr_space);
-}
-
-static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
-                       void *arg, int max_stack)
-{
-        u64 val;
-        unw_word_t ips[max_stack];
-        unw_addr_space_t addr_space;
-        unw_cursor_t c;
-        int ret, i = 0;
-
-        ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP);
-        if (ret)
-                return ret;
-
-        ips[i++] = (unw_word_t) val;
-
-        /*
-         * If we need more than one entry, do the DWARF
-         * unwind itself.
-         */
-        if (max_stack - 1 > 0) {
-                WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL");
-                addr_space = ui->thread->addr_space;
-
-                if (addr_space == NULL)
-                        return -1;
-
-                ret = unw_init_remote(&c, addr_space, ui);
-                if (ret)
-                        display_error(ret);
-
-                while (!ret && (unw_step(&c) > 0) && i < max_stack) {
-                        unw_get_reg(&c, UNW_REG_IP, &ips[i]);
-                        ++i;
-                }
-
-                max_stack = i;
-        }
-
-        /*
-         * Display what we got based on the order setup.
-         */
-        for (i = 0; i < max_stack && !ret; i++) {
-                int j = i;
-
-                if (callchain_param.order == ORDER_CALLER)
-                        j = max_stack - i - 1;
-                ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0;
-        }
-
-        return ret;
+        if (thread->unwind_libunwind_ops)
+                thread->unwind_libunwind_ops->finish_access(thread);
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-                        struct thread *thread,
-                        struct perf_sample *data, int max_stack)
+                         struct thread *thread,
+                         struct perf_sample *data, int max_stack)
 {
-        struct unwind_info ui = {
-                .sample       = data,
-                .thread       = thread,
-                .machine      = thread->mg->machine,
-        };
-
-        if (!data->user_regs.regs)
-                return -EINVAL;
-
-        if (max_stack <= 0)
-                return -EINVAL;
-
-        return get_entries(&ui, cb, arg, max_stack);
+        if (thread->unwind_libunwind_ops)
+                return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+        return 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index 12790cf94618..61fb1e90ff51 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -14,18 +14,42 @@ struct unwind_entry {
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
+struct unwind_libunwind_ops {
+        int (*prepare_access)(struct thread *thread);
+        void (*flush_access)(struct thread *thread);
+        void (*finish_access)(struct thread *thread);
+        int (*get_entries)(unwind_entry_cb_t cb, void *arg,
+                           struct thread *thread,
+                           struct perf_sample *data, int max_stack);
+};
+
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                         struct thread *thread,
                         struct perf_sample *data, int max_stack);
 /* libunwind specific */
 #ifdef HAVE_LIBUNWIND_SUPPORT
-int libunwind__arch_reg_id(int regnum);
-int unwind__prepare_access(struct thread *thread);
+#ifndef LIBUNWIND__ARCH_REG_ID
+#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum)
+#endif
+
+#ifndef LIBUNWIND__ARCH_REG_SP
+#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP
+#endif
+
+#ifndef LIBUNWIND__ARCH_REG_IP
+#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP
+#endif
+
+int LIBUNWIND__ARCH_REG_ID(int regnum);
+int unwind__prepare_access(struct thread *thread, struct map *map,
+                           bool *initialized);
 void unwind__flush_access(struct thread *thread);
 void unwind__finish_access(struct thread *thread);
 #else
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+                                         struct map *map __maybe_unused,
+                                         bool *initialized __maybe_unused)
 {
         return 0;
 }
@@ -44,7 +68,9 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
         return 0;
 }
 
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+                                         struct map *map __maybe_unused,
+                                         bool *initialized __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 23504ad5d6dd..cee559d8c9e8 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -19,12 +19,19 @@
 #include "callchain.h"
 #include "strlist.h"
 
-struct callchain_param  callchain_param = {
-        .mode   = CHAIN_GRAPH_ABS,
-        .min_percent = 0.5,
-        .order  = ORDER_CALLEE,
-        .key    = CCKEY_FUNCTION,
-        .value  = CCVAL_PERCENT,
+#define CALLCHAIN_PARAM_DEFAULT                 \
+        .mode           = CHAIN_GRAPH_ABS,      \
+        .min_percent    = 0.5,                  \
+        .order          = ORDER_CALLEE,         \
+        .key            = CCKEY_FUNCTION,       \
+        .value          = CCVAL_PERCENT,        \
+
+struct callchain_param callchain_param = {
+        CALLCHAIN_PARAM_DEFAULT
+};
+
+struct callchain_param callchain_param_default = {
+        CALLCHAIN_PARAM_DEFAULT
 };
 
 /*
@@ -97,20 +104,17 @@ int rm_rf(char *path)
                 scnprintf(namebuf, sizeof(namebuf), "%s/%s",
                           path, d->d_name);
 
-                ret = stat(namebuf, &statbuf);
+                /* We have to check symbolic link itself */
+                ret = lstat(namebuf, &statbuf);
                 if (ret < 0) {
                         pr_debug("stat failed: %s\n", namebuf);
                         break;
                 }
 
-                if (S_ISREG(statbuf.st_mode))
-                        ret = unlink(namebuf);
-                else if (S_ISDIR(statbuf.st_mode))
+                if (S_ISDIR(statbuf.st_mode))
                         ret = rm_rf(namebuf);
-                else {
-                        pr_debug("unknown file: %s\n", namebuf);
-                        ret = -1;
-                }
+                else
+                        ret = unlink(namebuf);
         }
         closedir(dir);
 
@@ -742,3 +746,19 @@ void print_binary(unsigned char *data, size_t len,
         }
         printer(BINARY_PRINT_DATA_END, -1, extra);
 }
+
+int is_printable_array(char *p, unsigned int len)
+{
+        unsigned int i;
+
+        if (!p || !len || p[len - 1] != 0)
+                return 0;
+
+        len--;
+
+        for (i = 0; i < len; i++) {
+                if (!isprint(p[i]) && !isspace(p[i]))
+                        return 0;
+        }
+        return 1;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1e8c3167b9fb..e5f55477491d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -72,7 +72,6 @@
 #include <sys/ioctl.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
-#include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/tracing_path.h>
@@ -360,4 +359,10 @@ typedef void (*print_binary_t)(enum binary_printer_ops,
 void print_binary(unsigned char *data, size_t len,
                   size_t bytes_per_line, print_binary_t printer,
                   void *extra);
+
+#if !defined(__GLIBC__) && !defined(__ANDROID__)
+extern int sched_getcpu(void);
+#endif
+
+int is_printable_array(char *p, unsigned int len);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 44d440da15dc..7bdcad484225 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -134,8 +134,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
         return dso;
 }
 
-#if BITS_PER_LONG == 64
-
 static enum dso_type machine__thread_dso_type(struct machine *machine,
                                               struct thread *thread)
 {
@@ -156,6 +154,8 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
         return dso_type;
 }
 
+#if BITS_PER_LONG == 64
+
 static int vdso__do_copy_compat(FILE *f, int fd)
 {
         char buf[4096];
@@ -283,8 +283,38 @@ static int __machine__findnew_vdso_compat(struct machine *machine,
 
 #endif
 
+static struct dso *machine__find_vdso(struct machine *machine,
+                                      struct thread *thread)
+{
+        struct dso *dso = NULL;
+        enum dso_type dso_type;
+
+        dso_type = machine__thread_dso_type(machine, thread);
+        switch (dso_type) {
+        case DSO__TYPE_32BIT:
+                dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+                if (!dso) {
+                        dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
+                                           true);
+                        if (dso && dso_type != dso__type(dso, machine))
+                                dso = NULL;
+                }
+                break;
+        case DSO__TYPE_X32BIT:
+                dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+                break;
+        case DSO__TYPE_64BIT:
+        case DSO__TYPE_UNKNOWN:
+        default:
+                dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+                break;
+        }
+
+        return dso;
+}
+
 struct dso *machine__findnew_vdso(struct machine *machine,
-                                  struct thread *thread __maybe_unused)
+                                  struct thread *thread)
 {
         struct vdso_info *vdso_info;
         struct dso *dso = NULL;
@@ -297,6 +327,10 @@ struct dso *machine__findnew_vdso(struct machine *machine,
         if (!vdso_info)
                 goto out_unlock;
 
+        dso = machine__find_vdso(machine, thread);
+        if (dso)
+                goto out_unlock;
+
 #if BITS_PER_LONG == 64
         if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
                 goto out_unlock;