Merge tag 'doc-4.11-images' of git://git.lwn.net/linux into drm-misc-next

Pointer for Markus's image conversion work. We need this so we can merge all the pretty drm graphs for 4.12. Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
author: Daniel Vetter <daniel.vetter@ffwll.ch> 2017-03-14 10:07:33 -0400
committer: Daniel Vetter <daniel.vetter@ffwll.ch> 2017-03-14 10:07:33 -0400
commit: b70366e5d31788650b2a5cec5cd13ea80ac7e44a (patch)
tree: d972ffd190111d699200448494fda333d28b2486 /tools/perf
parent: f42e181935d5e5670c87d31ae48063a495bbacae (diff)
parent: db6ccf23e8ba40fc2e8914ec9c0eb950df71d9fe (diff)
147 files changed, 4816 insertions, 538 deletions
diff --git a/tools/perf/Build b/tools/perf/Build
index b12d5d1666e3..9b79f8d7db50 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@ perf-y += builtin-annotate.o
 perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
 perf-y += builtin-help.o
 perf-y += builtin-sched.o
 perf-y += builtin-buildid-list.o
 perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
 perf-y += builtin-list.o
 perf-y += builtin-record.o
 perf-y += builtin-report.o
@@ -39,8 +41,7 @@ CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
 CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"       \
                              -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))"   \
-                              -DPREFIX="BUILD_STR($(prefix_SQ))"                \
+                              -DPREFIX="BUILD_STR($(prefix_SQ))"
-                              -include $(OUTPUT)PERF-VERSION-FILE
 CFLAGS_builtin-trace.o     += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 CFLAGS_builtin-report.o    += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 CFLAGS_builtin-report.o    += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 8ffbd272952d..a89273d8e744 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -39,6 +39,10 @@ OPTIONS
 --verbose::
        Be more verbose. (Show symbol address, etc)
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
 -D::
 --dump-raw-trace::
        Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 3f06730c7f47..2da07e51e119 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -248,7 +248,7 @@ output fields set for caheline offsets output:
             Code address, Code symbol, Shared Object, Source line
  dso   - coalesced by shared object
-By default the coalescing is setup with 'pid,tid,iaddr'.
+By default the coalescing is setup with 'pid,iaddr'.
 STDIO OUTPUT
 ------------
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 9365b75fd04f..5b4fff3adc4b 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -498,6 +498,18 @@ record.*::
                But if this option is 'no-cache', it will not update the build-id cache.
                'skip' skips post-processing and does not update the cache.
+diff.*::
+        diff.order::
+                This option sets the number of columns to sort the result.
+                The default is 0, which means sorting by baseline.
+                Setting it to 1 will sort the result by delta (or other
+                compute method selected).
+        diff.compute::
+                This options sets the method for computing the diff result.
+                Possible values are 'delta', 'delta-abs', 'ratio' and
+                'wdiff'.  Default is 'delta'.
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 3e9490b9c533..a79c84ae61aa 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -73,6 +73,10 @@ OPTIONS
        Be verbose, for instance, show the raw counts in addition to the
        diff.
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
 -f::
 --force::
        Don't do ownership validation.
@@ -86,8 +90,9 @@ OPTIONS
 -c::
 --compute::
-        Differential computation selection - delta,ratio,wdiff (default is delta).
+        Differential computation selection - delta, ratio, wdiff, delta-abs
-        See COMPARISON METHODS section for more info.
+        (default is delta-abs).  Default can be changed using diff.compute
+        config option.  See COMPARISON METHODS section for more info.
 -p::
 --period::
@@ -99,7 +104,11 @@ OPTIONS
 -o::
 --order::
-       Specify compute sorting column number.
+       Specify compute sorting column number.  0 means sorting by baseline
+       overhead and 1 (default) means sorting by computed value of column 1
+       (data from the first file other base baseline).  Values more than 1
+       can be used only if enough data files are provided.
+       The default value can be set using the diff.order config option.
 --percentage::
        Determine how to display the overhead percentage of filtered entries.
@@ -181,6 +190,10 @@ with:
    relative to how entries are filtered.  Use --percentage=absolute to
    prevent such fluctuation.
+delta-abs
+~~~~~~~~~
+Same as 'delta` method, but sort the result with the absolute values.
 ratio
 ~~~~~
 If specified the 'Ratio' column is displayed with value 'r' computed as:
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 000000000000..2d96de6132a9
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality.  It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+The following options apply to perf ftrace.
+OPTIONS
+-------
+-t::
+--tracer=::
+        Tracer to use: function_graph or function.
+-v::
+--verbose=::
+        Verbosity level.
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 000000000000..954ea9e21236
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+OPTIONS
+-------
+-v::
+--verbose=::
+        Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5054d9147f0f..b16003ec14a7 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -157,7 +157,7 @@ OPTIONS
 -a::
 --all-cpus::
-        System-wide collection from all CPUs.
+        System-wide collection from all CPUs (default if no target is specified).
 -p::
 --pid=::
@@ -421,9 +421,19 @@ Configure all used events to run in user space.
 --timestamp-filename
 Append timestamp to output file name.
--switch-output::
+--switch-output[=mode]::
 Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+  "signal" - when receiving a SIGUSR2 (default value) or
+  <size>   - when reaching the size threshold, size is expected to
+             be a number with appended unit character - B/K/M/G
+  <time>   - when reaching the time threshold, size is expected to
+             be a number with appended unit character - s/m/h/d
+             Note: the precision of  the size  threshold  hugely depends
+             on your configuration  - the number and size of  your  ring
+             buffers (-m). It is generally more precise for higher sizes
+             (like >5M), for lower values expect different sizes.
 A possible use case is to, given an external event, slice the perf.data file
 that gets then processed, possibly via a perf script, to decide if that
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index f2914f03ae7b..c04cc0647c16 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -25,6 +25,10 @@ OPTIONS
 --verbose::
        Be more verbose. (show symbol address, etc)
+-q::
+--quiet::
+        Do not show any message.  (Suppress -v)
 -n::
 --show-nr-samples::
        Show the number of samples for each symbol
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 76173969ab80..d33deddb0146 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -143,6 +143,8 @@ OPTIONS for 'perf sched timehist'
        stop time is not given (i.e, time string is 'x.y,') then analysis goes
        to end of file.
+--state::
+        Show task state when it switched out.
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a09ac4..4ed5f239ba7d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@ There are several variants of perf script:
  'perf script report <script> [args]' to run and display the results
  of <script>.  <script> is the name displayed in the output of 'perf
-  trace --list' i.e. the actual script name minus any language
+  script --list' i.e. the actual script name minus any language
  extension.  The perf.data output from a previous run of 'perf script
  record <script>' is used and should be present for this command to
  succeed.  [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@ OPTIONS
        Any command you can specify in a shell.
 -D::
--dump-raw-script=::
+--dump-raw-trace=::
        Display verbose dump of the trace data.
 -L::
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index d96ccd4844df..aecf2a87e7d6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -63,7 +63,7 @@ report::
 -a::
 --all-cpus::
-        system-wide collection from all CPUs
+        system-wide collection from all CPUs (default if no target is specified)
 -c::
 --scale::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 781b019751a4..afd728672b6f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,10 @@ OPTIONS
 -e::
 --expr::
-        List of syscalls to show, currently only syscall names.
+--event::
+        List of syscalls and other perf events (tracepoints, HW cache events,
+        etc) to show.
+        See 'perf list' for a complete list of events.
        Prefixing with ! shows all syscalls but the ones specified.  You may
        need to escape it.
@@ -135,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
         Show the kernel callchains on the syscall exit path.
--event::
-        Trace other events, see 'perf list' for a complete list.
 --max-stack::
        Set the stack depth limit when parsing the callchain, anything
        beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 8a6479c0eac9..170b0289a7bc 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -22,7 +22,7 @@ If you have debuginfo enabled, try: perf report -s sym,srcline
 For memory address profiling, try: perf mem record / perf mem report
 For tracepoint events, try: perf report -s trace_fields
 To record callchains for each sample: perf record -g
-To record every process run by an user: perf record -u <user>
+To record every process run by a user: perf record -u <user>
 Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a511e5f31e36..8672f835ae4e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -61,6 +61,7 @@ tools/include/asm-generic/bitops.h
 tools/include/linux/atomic.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
+tools/include/linux/compiler-gcc.h
 tools/include/linux/coresight-pmu.h
 tools/include/linux/filter.h
 tools/include/linux/hash.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 76c84f0eec52..27c9fbca7bd9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -144,8 +144,12 @@ ifndef DEBUG
 endif
 ifeq ($(DEBUG),0)
+ifeq ($(CC), clang)
+  CFLAGS += -O3
+else
  CFLAGS += -O6
 endif
+endif
 ifdef PARSER_DEBUG
  PARSER_DEBUG_BISON := -t
@@ -171,6 +175,10 @@ PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
 PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+ifeq ($(CC), clang)
+  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+endif
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
 FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
@@ -291,8 +299,10 @@ else
      endif
    endif
    ifneq ($(feature-dwarf), 1)
-      msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+      ifndef NO_DWARF
-      NO_DWARF := 1
+        msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+        NO_DWARF := 1
+      endif
    else
      ifneq ($(feature-dwarf_getlocations), 1)
        msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
@@ -595,6 +605,9 @@ else
      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      ifeq ($(CC), clang)
+        PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+      endif
      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
      ifneq ($(feature-libpython), 1)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8bb16aa9d661..79fe31f20a17 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32
 endif
 ifndef NO_JVMTI
        $(call QUIET_INSTALL, $(LIBJVMTI)) \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
                $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
 endif
        $(call QUIET_INSTALL, libexec) \
@@ -725,13 +726,13 @@ config-clean:
        $(call QUIET_CLEAN, config)
        $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean
        $(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
        $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
        $(Q)$(RM) $(OUTPUT).config-detected
        $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so
        $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
-                $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
+                $(OUTPUT)util/intel-pt-decoder/inat-tables.c \
                $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
                $(OUTPUT)pmu-events/pmu-events.c
        $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 18b13518d8d8..eebe1ec9d2ee 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 26759363f921..36e375f5a211 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
 /* This is included in perf/util/dwarf-regs.c */
 static const char * const aarch64_regstr_tbl[] = {
-        "%r0", "%r1", "%r2", "%r3", "%r4",
+        "%x0", "%x1", "%x2", "%x3", "%x4",
-        "%r5", "%r6", "%r7", "%r8", "%r9",
+        "%x5", "%x6", "%x7", "%x8", "%x9",
-        "%r10", "%r11", "%r12", "%r13", "%r14",
+        "%x10", "%x11", "%x12", "%x13", "%x14",
-        "%r15", "%r16", "%r17", "%r18", "%r19",
+        "%x15", "%x16", "%x17", "%x18", "%x19",
-        "%r20", "%r21", "%r22", "%r23", "%r24",
+        "%x20", "%x21", "%x22", "%x23", "%x24",
-        "%r25", "%r26", "%r27", "%r28", "%r29",
+        "%x25", "%x26", "%x27", "%x28", "%x29",
        "%lr", "%sp",
 };
 #endif
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index d49efeb8172e..068b6189157b 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -10,17 +10,20 @@
 #include <stddef.h>
 #include <dwarf-regs.h>
+#include <linux/ptrace.h> /* for struct user_pt_regs */
+#include "util.h"
 struct pt_regs_dwarfnum {
        const char *name;
        unsigned int dwarfnum;
 };
-#define STR(s) #s
 #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
 #define GPR_DWARFNUM_NAME(num) \
        {.name = STR(%x##num), .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define DWARFNUM2OFFSET(index) \
+        (index * sizeof((struct user_pt_regs *)0)->regs[0])
 /*
 * Reference:
@@ -78,3 +81,13 @@ const char *get_arch_regstr(unsigned int n)
                        return roff->name;
        return NULL;
 }
+int regs_query_register_offset(const char *name)
+{
+        const struct pt_regs_dwarfnum *roff;
+        for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+                if (!strcmp(roff->name, name))
+                        return DWARFNUM2OFFSET(roff->dwarfnum);
+        return -EINVAL;
+}
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index bfbb6b5f609c..da04b8c5568a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv,
        }
        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-        nsecs = futexbench_sanitize_numeric(nsecs);
-        nfutexes = futexbench_sanitize_numeric(nfutexes);
        sigfillset(&act.sa_mask);
        act.sa_sigaction = toggle_done;
@@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv,
        if (!nthreads) /* default to the number of CPUs */
                nthreads = ncpus;
-        else
-                nthreads = futexbench_sanitize_numeric(nthreads);
        worker = calloc(nthreads, sizeof(*worker));
        if (!worker)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6d9d6c40a916..91877777ec6e 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
                goto err;
        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-        nsecs = futexbench_sanitize_numeric(nsecs);
        sigfillset(&act.sa_mask);
        act.sa_sigaction = toggle_done;
@@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
        if (!nthreads)
                nthreads = ncpus;
-        else
-                nthreads = futexbench_sanitize_numeric(nthreads);
        worker = calloc(nthreads, sizeof(*worker));
        if (!worker)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index fd4ee95b689a..2b9705a8734c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv,
        if (!nthreads)
                nthreads = ncpus;
-        else
-                nthreads = futexbench_sanitize_numeric(nthreads);
        worker = calloc(nthreads, sizeof(*worker));
        if (!worker)
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index beaa6c142477..2c8fa67ad537 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv,
        sigaction(SIGINT, &act, NULL);
        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-        nwaking_threads = futexbench_sanitize_numeric(nwaking_threads);
        if (!nblocked_threads)
                nblocked_threads = ncpus;
-        else
-                nblocked_threads = futexbench_sanitize_numeric(nblocked_threads);
        /* some sanity checks */
        if (nwaking_threads > nblocked_threads || !nwaking_threads)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 46efcb98b5a4..e246b1b8388a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv,
        }
        ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-        nwakes = futexbench_sanitize_numeric(nwakes);
        sigfillset(&act.sa_mask);
        act.sa_sigaction = toggle_done;
@@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv,
        if (!nthreads)
                nthreads = ncpus;
-        else
-                nthreads = futexbench_sanitize_numeric(nthreads);
        worker = calloc(nthreads, sizeof(*worker));
        if (!worker)
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index ba7c735c0c62..b2e06d1190d0 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -7,7 +7,6 @@
 #ifndef _FUTEX_H
 #define _FUTEX_H
-#include <stdlib.h>
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
@@ -100,7 +99,4 @@ static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
 }
 #endif
-/* User input sanitation */
-#define futexbench_sanitize_numeric(__n) abs((__n))
 #endif /* _FUTEX_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..3083fc36282b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -43,6 +43,7 @@
 /*
 * Debug printf:
 */
+#undef dprintf
 #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
 struct thread_data {
@@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name)
                "GB/sec,", "total-speed",       "GB/sec total speed");
        if (g->p.show_details >= 2) {
-                char tname[32];
+                char tname[14 + 2 * 10 + 1];
                struct thread_data *td;
                for (p = 0; p < g->p.nr_proc; p++) {
                        for (t = 0; t < g->p.nr_threads; t++) {
-                                memset(tname, 0, 32);
+                                memset(tname, 0, sizeof(tname));
                                td = g->threads + p*g->p.nr_threads + t;
-                                snprintf(tname, 32, "process%d:thread%d", p, t);
+                                snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
                                print_res(tname, td->speed_gbs,
                                        "GB/sec",       "thread-speed", "GB/sec/thread speed");
                                print_res(tname, td->system_time_ns / NSEC_PER_SEC,
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ebb628332a6e..4f52d85f5ebc 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -410,6 +410,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
        OPT_INCR('v', "verbose", &verbose,
                    "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                    "dump raw trace in ASCII"),
        OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
@@ -463,6 +464,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
                annotate.sym_hist_filter = argv[0];
        }
+        if (quiet)
+                perf_quiet_option();
        file.path  = input_name;
        annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f8ca7a4ebabc..e2b21723bbf8 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -58,7 +58,7 @@ struct c2c_hist_entry {
        struct hist_entry       he;
 };
-static char const *coalesce_default = "pid,tid,iaddr";
+static char const *coalesce_default = "pid,iaddr";
 struct perf_c2c {
        struct perf_tool        tool;
@@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
                "mean_rmt,"
                "mean_lcl,"
                "mean_load,"
+                "tot_recs,"
                "cpucnt,",
                add_sym ? "symbol," : "",
                add_dso ? "dso," : "",
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 933aeec46f4a..1b96a3122228 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -17,6 +17,7 @@
 #include "util/symbol.h"
 #include "util/util.h"
 #include "util/data.h"
+#include "util/config.h"
 #include <stdlib.h>
 #include <math.h>
@@ -30,6 +31,7 @@ enum {
        PERF_HPP_DIFF__RATIO,
        PERF_HPP_DIFF__WEIGHTED_DIFF,
        PERF_HPP_DIFF__FORMULA,
+        PERF_HPP_DIFF__DELTA_ABS,
        PERF_HPP_DIFF__MAX_INDEX
 };
@@ -64,7 +66,7 @@ static bool force;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
-static unsigned int sort_compute;
+static unsigned int sort_compute = 1;
 static s64 compute_wdiff_w1;
 static s64 compute_wdiff_w2;
@@ -73,19 +75,22 @@ enum {
        COMPUTE_DELTA,
        COMPUTE_RATIO,
        COMPUTE_WEIGHTED_DIFF,
+        COMPUTE_DELTA_ABS,
        COMPUTE_MAX,
 };
 const char *compute_names[COMPUTE_MAX] = {
        [COMPUTE_DELTA] = "delta",
+        [COMPUTE_DELTA_ABS] = "delta-abs",
        [COMPUTE_RATIO] = "ratio",
        [COMPUTE_WEIGHTED_DIFF] = "wdiff",
 };
-static int compute;
+static int compute = COMPUTE_DELTA_ABS;
 static int compute_2_hpp[COMPUTE_MAX] = {
        [COMPUTE_DELTA]         = PERF_HPP_DIFF__DELTA,
+        [COMPUTE_DELTA_ABS]     = PERF_HPP_DIFF__DELTA_ABS,
        [COMPUTE_RATIO]         = PERF_HPP_DIFF__RATIO,
        [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF,
 };
@@ -111,6 +116,10 @@ static struct header_column {
                .name  = "Delta",
                .width = 7,
        },
+        [PERF_HPP_DIFF__DELTA_ABS] = {
+                .name  = "Delta Abs",
+                .width = 7,
+        },
        [PERF_HPP_DIFF__RATIO] = {
                .name  = "Ratio",
                .width = 14,
@@ -298,6 +307,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
 {
        switch (compute) {
        case COMPUTE_DELTA:
+        case COMPUTE_DELTA_ABS:
                return formula_delta(he, pair, buf, size);
        case COMPUTE_RATIO:
                return formula_ratio(he, pair, buf, size);
@@ -461,6 +471,7 @@ static void hists__precompute(struct hists *hists)
                        switch (compute) {
                        case COMPUTE_DELTA:
+                        case COMPUTE_DELTA_ABS:
                                compute_delta(he, pair);
                                break;
                        case COMPUTE_RATIO:
@@ -498,6 +509,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
                return cmp_doubles(l, r);
        }
+        case COMPUTE_DELTA_ABS:
+        {
+                double l = fabs(left->diff.period_ratio_delta);
+                double r = fabs(right->diff.period_ratio_delta);
+                return cmp_doubles(l, r);
+        }
        case COMPUTE_RATIO:
        {
                double l = left->diff.period_ratio;
@@ -564,7 +582,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
        if (!p_left || !p_right)
                return p_left ? -1 : 1;
-        if (c != COMPUTE_DELTA) {
+        if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
                /*
                 * The delta can be computed without the baseline, but
                 * others are not.  Put those entries which have no
@@ -607,6 +625,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
 }
 static int64_t
+hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
+                      struct hist_entry *left, struct hist_entry *right)
+{
+        struct data__file *d = fmt_to_data_file(fmt);
+        return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
+}
+static int64_t
 hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
                      struct hist_entry *left, struct hist_entry *right)
 {
@@ -633,6 +660,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
 }
 static int64_t
+hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+                              struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
+                                           sort_compute);
+}
+static int64_t
 hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
                          struct hist_entry *left, struct hist_entry *right)
 {
@@ -656,7 +691,7 @@ 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, !quiet, 0, 0, 0, stdout,
                       symbol_conf.use_callchain);
 }
@@ -704,12 +739,14 @@ static void data_process(void)
                                hists__link(hists_base, hists);
                }
-                fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+                if (!quiet) {
-                        perf_evsel__name(evsel_base));
+                        fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n",
+                                perf_evsel__name(evsel_base));
+                }
                first = false;
-                if (verbose || data__files_cnt > 2)
+                if (verbose > 0 || ((data__files_cnt > 2) && !quiet))
                        data__fprintf();
                /* Don't sort callchain for perf diff */
@@ -772,10 +809,11 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
        OPT_INCR('v', "verbose", &verbose,
                    "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
        OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
                    "Show only items with match in baseline"),
        OPT_CALLBACK('c', "compute", &compute,
-                     "delta,ratio,wdiff:w1,w2 (default delta)",
+                     "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
                     "Entries differential computation selection",
                     setup_compute),
        OPT_BOOLEAN('p', "period", &show_period,
@@ -945,6 +983,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
        switch (idx) {
        case PERF_HPP_DIFF__DELTA:
+        case PERF_HPP_DIFF__DELTA_ABS:
                if (pair->diff.computed)
                        diff = pair->diff.period_ratio_delta;
                else
@@ -1118,6 +1157,10 @@ static void data__hpp_register(struct data__file *d, int idx)
                fmt->color = hpp__color_wdiff;
                fmt->sort  = hist_entry__cmp_wdiff;
                break;
+        case PERF_HPP_DIFF__DELTA_ABS:
+                fmt->color = hpp__color_delta;
+                fmt->sort  = hist_entry__cmp_delta_abs;
+                break;
        default:
                fmt->sort  = hist_entry__cmp_nop;
                break;
@@ -1195,6 +1238,9 @@ static int ui_init(void)
        case COMPUTE_WEIGHTED_DIFF:
                fmt->sort = hist_entry__cmp_wdiff_idx;
                break;
+        case COMPUTE_DELTA_ABS:
+                fmt->sort = hist_entry__cmp_delta_abs_idx;
+                break;
        default:
                BUG_ON(1);
        }
@@ -1249,6 +1295,31 @@ static int data_init(int argc, const char **argv)
        return 0;
 }
+static int diff__config(const char *var, const char *value,
+                        void *cb __maybe_unused)
+{
+        if (!strcmp(var, "diff.order")) {
+                sort_compute = perf_config_int(var, value);
+                return 0;
+        }
+        if (!strcmp(var, "diff.compute")) {
+                if (!strcmp(value, "delta")) {
+                        compute = COMPUTE_DELTA;
+                } else if (!strcmp(value, "delta-abs")) {
+                        compute = COMPUTE_DELTA_ABS;
+                } else if (!strcmp(value, "ratio")) {
+                        compute = COMPUTE_RATIO;
+                } else if (!strcmp(value, "wdiff")) {
+                        compute = COMPUTE_WEIGHTED_DIFF;
+                } else {
+                        pr_err("Invalid compute method: %s\n", value);
+                        return -1;
+                }
+        }
+        return 0;
+}
 int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
        int ret = hists__init();
@@ -1256,8 +1327,13 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
        if (ret < 0)
                return ret;
+        perf_config(diff__config, NULL);
        argc = parse_options(argc, argv, options, diff_usage, 0);
+        if (quiet)
+                perf_quiet_option();
        if (symbol__init(NULL) < 0)
                return -1;
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 000000000000..c3e643666c72
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,265 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+#include "builtin.h"
+#include "perf.h"
+#include <unistd.h>
+#include <signal.h>
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+#include "util/config.h"
+#define DEFAULT_TRACER  "function_graph"
+struct perf_ftrace {
+        struct perf_evlist *evlist;
+        struct target target;
+        const char *tracer;
+};
+static bool done;
+static void sig_handler(int sig __maybe_unused)
+{
+        done = true;
+}
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+                                                siginfo_t *info __maybe_unused,
+                                                void *ucontext __maybe_unused)
+{
+        /* workload_exec_errno = info->si_value.sival_int; */
+        done = true;
+}
+static int write_tracing_file(const char *name, const char *val)
+{
+        char *file;
+        int fd, ret = -1;
+        ssize_t size = strlen(val);
+        file = get_tracing_file(name);
+        if (!file) {
+                pr_debug("cannot get tracing file: %s\n", name);
+                return -1;
+        }
+        fd = open(file, O_WRONLY);
+        if (fd < 0) {
+                pr_debug("cannot open tracing file: %s\n", name);
+                goto out;
+        }
+        if (write(fd, val, size) == size)
+                ret = 0;
+        else
+                pr_debug("write '%s' to tracing/%s failed\n", val, name);
+        close(fd);
+out:
+        put_tracing_file(file);
+        return ret;
+}
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+        if (write_tracing_file("tracing_on", "0") < 0)
+                return -1;
+        if (write_tracing_file("current_tracer", "nop") < 0)
+                return -1;
+        if (write_tracing_file("set_ftrace_pid", " ") < 0)
+                return -1;
+        return 0;
+}
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+        char *trace_file;
+        int trace_fd;
+        char *trace_pid;
+        char buf[4096];
+        struct pollfd pollfd = {
+                .events = POLLIN,
+        };
+        if (geteuid() != 0) {
+                pr_err("ftrace only works for root!\n");
+                return -1;
+        }
+        if (argc < 1)
+                return -1;
+        signal(SIGINT, sig_handler);
+        signal(SIGUSR1, sig_handler);
+        signal(SIGCHLD, sig_handler);
+        reset_tracing_files(ftrace);
+        /* reset ftrace buffer */
+        if (write_tracing_file("trace", "0") < 0)
+                goto out;
+        if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+                                          argv, false, ftrace__workload_exec_failed_signal) < 0)
+                goto out;
+        if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+                pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+                goto out;
+        }
+        if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+                pr_err("failed to allocate pid string\n");
+                goto out;
+        }
+        if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+                pr_err("failed to set pid: %s\n", trace_pid);
+                goto out_free_pid;
+        }
+        trace_file = get_tracing_file("trace_pipe");
+        if (!trace_file) {
+                pr_err("failed to open trace_pipe\n");
+                goto out_free_pid;
+        }
+        trace_fd = open(trace_file, O_RDONLY);
+        put_tracing_file(trace_file);
+        if (trace_fd < 0) {
+                pr_err("failed to open trace_pipe\n");
+                goto out_free_pid;
+        }
+        fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+        pollfd.fd = trace_fd;
+        if (write_tracing_file("tracing_on", "1") < 0) {
+                pr_err("can't enable tracing\n");
+                goto out_close_fd;
+        }
+        perf_evlist__start_workload(ftrace->evlist);
+        while (!done) {
+                if (poll(&pollfd, 1, -1) < 0)
+                        break;
+                if (pollfd.revents & POLLIN) {
+                        int n = read(trace_fd, buf, sizeof(buf));
+                        if (n < 0)
+                                break;
+                        if (fwrite(buf, n, 1, stdout) != 1)
+                                break;
+                }
+        }
+        write_tracing_file("tracing_on", "0");
+        /* read remaining buffer contents */
+        while (true) {
+                int n = read(trace_fd, buf, sizeof(buf));
+                if (n <= 0)
+                        break;
+                if (fwrite(buf, n, 1, stdout) != 1)
+                        break;
+        }
+out_close_fd:
+        close(trace_fd);
+out_free_pid:
+        free(trace_pid);
+out:
+        reset_tracing_files(ftrace);
+        return done ? 0 : -1;
+}
+static int perf_ftrace_config(const char *var, const char *value, void *cb)
+{
+        struct perf_ftrace *ftrace = cb;
+        if (prefixcmp(var, "ftrace."))
+                return 0;
+        if (strcmp(var, "ftrace.tracer"))
+                return -1;
+        if (!strcmp(value, "function_graph") ||
+            !strcmp(value, "function")) {
+                ftrace->tracer = value;
+                return 0;
+        }
+        pr_err("Please select \"function_graph\" (default) or \"function\"\n");
+        return -1;
+}
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+        int ret;
+        struct perf_ftrace ftrace = {
+                .tracer = DEFAULT_TRACER,
+                .target = { .uid = UINT_MAX, },
+        };
+        const char * const ftrace_usage[] = {
+                "perf ftrace [<options>] <command>",
+                "perf ftrace [<options>] -- <command> [<options>]",
+                NULL
+        };
+        const struct option ftrace_options[] = {
+        OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+                   "tracer to use: function_graph(default) or function"),
+        OPT_INCR('v', "verbose", &verbose,
+                 "be more verbose"),
+        OPT_END()
+        };
+        ret = perf_config(perf_ftrace_config, &ftrace);
+        if (ret < 0)
+                return -1;
+        argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+                            PARSE_OPT_STOP_AT_NON_OPTION);
+        if (!argc)
+                usage_with_options(ftrace_usage, ftrace_options);
+        ftrace.evlist = perf_evlist__new();
+        if (ftrace.evlist == NULL)
+                return -ENOMEM;
+        ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+        if (ret < 0)
+                goto out_delete_evlist;
+        ret = __cmd_ftrace(&ftrace, argc, argv);
+out_delete_evlist:
+        perf_evlist__delete(ftrace.evlist);
+        return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c78a21b..aed0d844e8c2 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
        const char * const builtin_help_subcommands[] = {
                "buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
                "record", "report", "bench", "stat", "timechart", "top", "annotate",
-                "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+                "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
 #ifdef HAVE_LIBELF_SUPPORT
                "probe",
 #endif
@@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
                NULL
        };
        const char *alias;
-        int rc = 0;
+        int rc;
        load_command_list("perf-", &main_cmds, &other_cmds);
-        perf_config(perf_help_config, &help_format);
+        rc = perf_config(perf_help_config, &help_format);
+        if (rc)
+                return rc;
        argc = parse_options_subcommand(argc, argv, builtin_help_options,
                        builtin_help_subcommands, builtin_help_usage, 0);
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 000000000000..224bfc454b4a
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+        int i;
+        struct machine *machine = machine__new_kallsyms();
+        if (machine == NULL) {
+                pr_err("Couldn't read /proc/kallsyms\n");
+                return -1;
+        }
+        for (i = 0; i < argc; ++i) {
+                struct map *map;
+                struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+                if (symbol == NULL) {
+                        printf("%s: not found\n", argv[i]);
+                        continue;
+                }
+                printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+                        symbol->name, map->dso->short_name, map->dso->long_name,
+                        map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+                        symbol->start, symbol->end);
+        }
+        machine__delete(machine);
+        return 0;
+}
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+        const struct option options[] = {
+        OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+        OPT_END()
+        };
+        const char * const kallsyms_usage[] = {
+                "perf kallsyms [<options>] symbol_name",
+                NULL
+        };
+        argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+        if (argc < 1)
+                usage_with_options(kallsyms_usage, options);
+        symbol_conf.sort_by_name = true;
+        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+        if (symbol__init(NULL) < 0)
+                return -1;
+        return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 915869e00d86..6da8d083e4e5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1065,7 +1065,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
                data = rb_entry(next, struct page_stat, node);
                sym = machine__find_kernel_function(machine, data->callsite, &map);
-                if (sym && sym->name)
+                if (sym)
                        caller = sym->name;
                else
                        scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1107,7 +1107,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
                data = rb_entry(next, struct page_stat, node);
                sym = machine__find_kernel_function(machine, data->callsite, &map);
-                if (sym && sym->name)
+                if (sym)
                        caller = sym->name;
                else
                        scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1920,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
                NULL
        };
        struct perf_session *session;
-        int ret = -1;
        const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
+        int ret = perf_config(kmem_config, NULL);
+        if (ret)
+                return ret;
-        perf_config(kmem_config, NULL);
        argc = parse_options_subcommand(argc, argv, kmem_options,
                                        kmem_subcommands, kmem_usage, 0);
@@ -1948,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
        if (session == NULL)
                return -1;
+        ret = -1;
        if (kmem_slab) {
                if (!perf_evlist__find_tracepoint_by_name(session->evlist,
                                                          "kmem:kmalloc")) {
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index ba9322ff858b..3b9d98b5feef 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,6 +14,7 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 #include "util/pmu.h"
+#include "util/debug.h"
 #include <subcmd/parse-options.h>
 static bool desc_flag = true;
@@ -29,6 +30,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                            "Print extra event descriptions. --no-desc to not print."),
                OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
                            "Print longer event descriptions."),
+                OPT_INCR(0, "debug", &verbose,
+                             "Enable debugging output"),
                OPT_END()
        };
        const char * const list_usage[] = {
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index cd7bc4d104e2..6114e07ca613 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -42,8 +42,8 @@ static int parse_record_events(const struct option *opt,
                fprintf(stderr, "%-13s%-*s%s\n",
                        e->tag,
-                        verbose ? 25 : 0,
+                        verbose > 0 ? 25 : 0,
-                        verbose ? perf_mem_events__name(j) : "",
+                        verbose > 0 ? perf_mem_events__name(j) : "",
                        e->supported ? ": available" : "");
        }
        exit(0);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f87996b0cb29..1fcebc31a508 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
        OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
                    "Enable kernel symbol demangling"),
        OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
+        OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+                   "Look for files with symbols relative to this directory"),
        OPT_END()
        };
        int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4ec10e9427d9..bc84a375295d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -46,6 +46,15 @@
 #include <asm/bug.h>
 #include <linux/time64.h>
+struct switch_output {
+        bool             enabled;
+        bool             signal;
+        unsigned long    size;
+        unsigned long    time;
+        const char      *str;
+        bool             set;
+};
 struct record {
        struct perf_tool        tool;
        struct record_opts      opts;
@@ -62,10 +71,33 @@ struct record {
        bool                    no_buildid_cache_set;
        bool                    buildid_all;
        bool                    timestamp_filename;
-        bool                    switch_output;
+        struct switch_output    switch_output;
        unsigned long long      samples;
 };
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+static bool switch_output_signal(struct record *rec)
+{
+        return rec->switch_output.signal &&
+               trigger_is_ready(&switch_output_trigger);
+}
+static bool switch_output_size(struct record *rec)
+{
+        return rec->switch_output.size &&
+               trigger_is_ready(&switch_output_trigger) &&
+               (rec->bytes_written >= rec->switch_output.size);
+}
+static bool switch_output_time(struct record *rec)
+{
+        return rec->switch_output.time &&
+               trigger_is_ready(&switch_output_trigger);
+}
 static int record__write(struct record *rec, void *bf, size_t size)
 {
        if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
        }
        rec->bytes_written += size;
+        if (switch_output_size(rec))
+                trigger_hit(&switch_output_trigger);
        return 0;
 }
@@ -193,10 +229,6 @@ static volatile int done;
 static volatile int signr = -1;
 static volatile int child_finished;
-static volatile int auxtrace_record__snapshot_started;
-static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
-static DEFINE_TRIGGER(switch_output_trigger);
 static void sig_handler(int sig)
 {
        if (sig == SIGCHLD)
@@ -386,7 +418,7 @@ static int record__mmap(struct record *rec)
 static int record__open(struct record *rec)
 {
-        char msg[512];
+        char msg[BUFSIZ];
        struct perf_evsel *pos;
        struct perf_evlist *evlist = rec->evlist;
        struct perf_session *session = rec->session;
@@ -400,7 +432,7 @@ static int record__open(struct record *rec)
 try_again:
                if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) {
                        if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                        ui__warning("%s\n", msg);
                                goto try_again;
                        }
@@ -623,22 +655,23 @@ record__finish_output(struct record *rec)
 static int record__synthesize_workload(struct record *rec, bool tail)
 {
-        struct {
+        int err;
-                struct thread_map map;
+        struct thread_map *thread_map;
-                struct thread_map_data map_data;
-        } thread_map;
        if (rec->opts.tail_synthesize != tail)
                return 0;
-        thread_map.map.nr = 1;
+        thread_map = thread_map__new_by_tid(rec->evlist->workload.pid);
-        thread_map.map.map[0].pid = rec->evlist->workload.pid;
+        if (thread_map == NULL)
-        thread_map.map.map[0].comm = NULL;
+                return -1;
-        return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
+        err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
                                                 process_synthesized_event,
                                                 &rec->session->machines.host,
                                                 rec->opts.sample_address,
                                                 rec->opts.proc_map_timeout);
+        thread_map__put(thread_map);
+        return err;
 }
 static int record__synthesize(struct record *rec, bool tail);
@@ -712,6 +745,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 }
 static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
 int __weak
 perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -842,11 +876,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
        signal(SIGTERM, sig_handler);
        signal(SIGSEGV, sigsegv_handler);
-        if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+        if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
                signal(SIGUSR2, snapshot_sig_handler);
                if (rec->opts.auxtrace_snapshot_mode)
                        trigger_on(&auxtrace_snapshot_trigger);
-                if (rec->switch_output)
+                if (rec->switch_output.enabled)
                        trigger_on(&switch_output_trigger);
        } else {
                signal(SIGUSR2, SIG_IGN);
@@ -1043,6 +1077,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                                err = fd;
                                goto out_child;
                        }
+                        /* re-arm the alarm */
+                        if (rec->switch_output.time)
+                                alarm(rec->switch_output.time);
                }
                if (hits == rec->samples) {
@@ -1352,6 +1390,78 @@ out_free:
        return ret;
 }
+static void switch_output_size_warn(struct record *rec)
+{
+        u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+        struct switch_output *s = &rec->switch_output;
+        wakeup_size /= 2;
+        if (s->size < wakeup_size) {
+                char buf[100];
+                unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+                pr_warning("WARNING: switch-output data size lower than "
+                           "wakeup kernel buffer size (%s) "
+                           "expect bigger perf.data sizes\n", buf);
+        }
+}
+static int switch_output_setup(struct record *rec)
+{
+        struct switch_output *s = &rec->switch_output;
+        static struct parse_tag tags_size[] = {
+                { .tag  = 'B', .mult = 1       },
+                { .tag  = 'K', .mult = 1 << 10 },
+                { .tag  = 'M', .mult = 1 << 20 },
+                { .tag  = 'G', .mult = 1 << 30 },
+                { .tag  = 0 },
+        };
+        static struct parse_tag tags_time[] = {
+                { .tag  = 's', .mult = 1        },
+                { .tag  = 'm', .mult = 60       },
+                { .tag  = 'h', .mult = 60*60    },
+                { .tag  = 'd', .mult = 60*60*24 },
+                { .tag  = 0 },
+        };
+        unsigned long val;
+        if (!s->set)
+                return 0;
+        if (!strcmp(s->str, "signal")) {
+                s->signal = true;
+                pr_debug("switch-output with SIGUSR2 signal\n");
+                goto enabled;
+        }
+        val = parse_tag_value(s->str, tags_size);
+        if (val != (unsigned long) -1) {
+                s->size = val;
+                pr_debug("switch-output with %s size threshold\n", s->str);
+                goto enabled;
+        }
+        val = parse_tag_value(s->str, tags_time);
+        if (val != (unsigned long) -1) {
+                s->time = val;
+                pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+                         s->str, s->time);
+                goto enabled;
+        }
+        return -1;
+enabled:
+        rec->timestamp_filename = true;
+        s->enabled              = true;
+        if (s->size && !rec->opts.no_buffering)
+                switch_output_size_warn(rec);
+        return 0;
+}
 static const char * const __record_usage[] = {
        "perf record [<options>] [<command>]",
        "perf record [<options>] -- <command> [<options>]",
@@ -1519,8 +1629,10 @@ static struct option __record_options[] = {
                    "Record build-id of all DSOs regardless of hits"),
        OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
                    "append timestamp to output filename"),
-        OPT_BOOLEAN(0, "switch-output", &record.switch_output,
+        OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
-                    "Switch output when receive SIGUSR2"),
+                          &record.switch_output.set, "signal,size,time",
+                          "Switch output when receive SIGUSR2 or cross size,time threshold",
+                          "signal"),
        OPT_BOOLEAN(0, "dry-run", &dry_run,
                    "Parse options then exit"),
        OPT_END()
@@ -1559,12 +1671,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
        if (rec->evlist == NULL)
                return -ENOMEM;
-        perf_config(perf_record_config, rec);
+        err = perf_config(perf_record_config, rec);
+        if (err)
+                return err;
        argc = parse_options(argc, argv, record_options, record_usage,
                            PARSE_OPT_STOP_AT_NON_OPTION);
+        if (quiet)
+                perf_quiet_option();
+        /* Make system wide (-a) the default target. */
        if (!argc && target__none(&rec->opts.target))
-                usage_with_options(record_usage, record_options);
+                rec->opts.target.system_wide = true;
        if (nr_cgroups && !rec->opts.target.system_wide) {
                usage_with_options_msg(record_usage, record_options,
@@ -1578,8 +1696,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
                return -EINVAL;
        }
-        if (rec->switch_output)
+        if (switch_output_setup(rec)) {
-                rec->timestamp_filename = true;
+                parse_options_usage(record_usage, record_options, "switch-output", 0);
+                return -EINVAL;
+        }
+        if (rec->switch_output.time) {
+                signal(SIGALRM, alarm_sig_handler);
+                alarm(rec->switch_output.time);
+        }
        if (!rec->itr) {
                rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1629,7 +1754,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
        if (rec->no_buildid_cache || rec->no_buildid) {
                disable_buildid_cache();
-        } else if (rec->switch_output) {
+        } else if (rec->switch_output.enabled) {
                /*
                 * In 'perf record --switch-output', disable buildid
                 * generation by default to reduce data file switching
@@ -1721,6 +1846,8 @@ out:
 static void snapshot_sig_handler(int sig __maybe_unused)
 {
+        struct record *rec = &record;
        if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
                trigger_hit(&auxtrace_snapshot_trigger);
                auxtrace_record__snapshot_started = 1;
@@ -1728,6 +1855,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
                        trigger_error(&auxtrace_snapshot_trigger);
        }
-        if (trigger_is_ready(&switch_output_trigger))
+        if (switch_output_signal(rec))
+                trigger_hit(&switch_output_trigger);
+}
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+        struct record *rec = &record;
+        if (switch_output_time(rec))
                trigger_hit(&switch_output_trigger);
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 06cc759a4597..0a88670e56f3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -320,6 +320,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
        size_t size = sizeof(buf);
        int socked_id = hists->socket_filter;
+        if (quiet)
+                return 0;
        if (symbol_conf.filter_relative) {
                nr_samples = hists->stats.nr_non_filtered_samples;
                nr_events = hists->stats.total_non_filtered_period;
@@ -372,7 +375,11 @@ 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);
+        if (!quiet) {
+                fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n",
+                        evlist->stats.total_lost_samples);
+        }
        evlist__for_each_entry(evlist, pos) {
                struct hists *hists = evsel__hists(pos);
                const char *evname = perf_evsel__name(pos);
@@ -382,7 +389,7 @@ 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, !quiet, 0, 0, rep->min_percent, stdout,
                               symbol_conf.use_callchain);
                fprintf(stdout, "\n\n");
        }
@@ -716,6 +723,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                    "input file name"),
        OPT_INCR('v', "verbose", &verbose,
                    "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"),
        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                    "dump raw trace in ASCII"),
        OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
@@ -847,7 +855,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
        if (ret < 0)
                return ret;
-        perf_config(report__config, &report);
+        ret = perf_config(report__config, &report);
+        if (ret)
+                return ret;
        argc = parse_options(argc, argv, options, report_usage, 0);
        if (argc) {
@@ -861,6 +871,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                report.symbol_filter_str = argv[0];
        }
+        if (quiet)
+                perf_quiet_option();
        if (symbol_conf.vmlinux_name &&
            access(symbol_conf.vmlinux_name, R_OK)) {
                pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
@@ -981,14 +994,14 @@ repeat:
                goto error;
        }
-        if (report.header || report.header_only) {
+        if ((report.header || report.header_only) && !quiet) {
                perf_session__fprintf_info(session, stdout,
                                           report.show_full_info);
                if (report.header_only) {
                        ret = 0;
                        goto error;
                }
-        } else if (use_browser == 0) {
+        } else if (use_browser == 0 && !quiet) {
                fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
                      stdout);
        }
@@ -1007,7 +1020,7 @@ repeat:
                 * providing it only in verbose mode not to bloat too
                 * much struct symbol.
                 */
-                if (verbose) {
+                if (verbose > 0) {
                        /*
                         * XXX: Need to provide a less kludgy way to ask for
                         * more space per symbol, the u32 is for the index on
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5b134b0d1ff3..b94cf0de715a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -77,6 +77,22 @@ struct sched_atom {
 #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING            0
+#define TASK_INTERRUPTIBLE      1
+#define TASK_UNINTERRUPTIBLE    2
+#define __TASK_STOPPED          4
+#define __TASK_TRACED           8
+/* in tsk->exit_state */
+#define EXIT_DEAD               16
+#define EXIT_ZOMBIE             32
+#define EXIT_TRACE              (EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD               64
+#define TASK_WAKEKILL           128
+#define TASK_WAKING             256
+#define TASK_PARKED             512
 enum thread_state {
        THREAD_SLEEPING = 0,
        THREAD_WAIT_CPU,
@@ -206,6 +222,7 @@ struct perf_sched {
        bool            show_cpu_visual;
        bool            show_wakeups;
        bool            show_migrations;
+        bool            show_state;
        u64             skipped_samples;
        const char      *time_str;
        struct perf_time_interval ptime;
@@ -216,13 +233,20 @@ struct perf_sched {
 struct thread_runtime {
        u64 last_time;      /* time of previous sched in/out event */
        u64 dt_run;         /* run time */
-        u64 dt_wait;        /* time between CPU access (off cpu) */
+        u64 dt_sleep;       /* time between CPU access by sleep (off cpu) */
+        u64 dt_iowait;      /* time between CPU access by iowait (off cpu) */
+        u64 dt_preempt;     /* time between CPU access by preempt (off cpu) */
        u64 dt_delay;       /* time between wakeup and sched-in */
        u64 ready_to_run;   /* time of wakeup */
        struct stats run_stats;
        u64 total_run_time;
+        u64 total_sleep_time;
+        u64 total_iowait_time;
+        u64 total_preempt_time;
+        u64 total_delay_time;
+        int last_state;
        u64 migrations;
 };
@@ -436,7 +460,7 @@ static struct task_desc *register_pid(struct perf_sched *sched,
        BUG_ON(!sched->tasks);
        sched->tasks[task->nr] = task;
-        if (verbose)
+        if (verbose > 0)
                printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
        return task;
@@ -770,7 +794,7 @@ replay_wakeup_event(struct perf_sched *sched,
        const u32 pid    = perf_evsel__intval(evsel, sample, "pid");
        struct task_desc *waker, *wakee;
-        if (verbose) {
+        if (verbose > 0) {
                printf("sched_wakeup event %p\n", evsel);
                printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
@@ -798,7 +822,7 @@ static int replay_switch_event(struct perf_sched *sched,
        int cpu = sample->cpu;
        s64 delta;
-        if (verbose)
+        if (verbose > 0)
                printf("sched_switch event %p\n", evsel);
        if (cpu >= MAX_CPUS || cpu < 0)
@@ -846,7 +870,7 @@ static int replay_fork_event(struct perf_sched *sched,
                goto out_put;
        }
-        if (verbose) {
+        if (verbose > 0) {
                printf("fork event\n");
                printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
                printf("...  child: %s/%d\n", thread__comm_str(child), child->tid);
@@ -1549,7 +1573,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
        timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
        color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-        if (new_shortname || (verbose && sched_in->tid)) {
+        if (new_shortname || (verbose > 0 && sched_in->tid)) {
                const char *pid_color = color;
                if (thread__has_color(sched_in))
@@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched)
        printf(" %-*s  %9s  %9s  %9s", comm_width,
                "task name", "wait time", "sch delay", "run time");
+        if (sched->show_state)
+                printf("  %s", "state");
        printf("\n");
        /*
@@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched)
        if (sched->show_cpu_visual)
                printf(" %*s ", ncpus, "");
-        printf(" %-*s  %9s  %9s  %9s\n", comm_width,
+        printf(" %-*s  %9s  %9s  %9s", comm_width,
               "[tid/pid]", "(msec)", "(msec)", "(msec)");
+        if (sched->show_state)
+                printf("  %5s", "");
+        printf("\n");
        /*
         * separator
         */
@@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched)
                graph_dotted_line, graph_dotted_line, graph_dotted_line,
                graph_dotted_line);
+        if (sched->show_state)
+                printf("  %.5s", graph_dotted_line);
        printf("\n");
 }
+static char task_state_char(struct thread *thread, int state)
+{
+        static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+        unsigned bit = state ? ffs(state) : 0;
+        /* 'I' for idle */
+        if (thread->tid == 0)
+                return 'I';
+        return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
 static void timehist_print_sample(struct perf_sched *sched,
                                  struct perf_sample *sample,
                                  struct addr_location *al,
                                  struct thread *thread,
-                                  u64 t)
+                                  u64 t, int state)
 {
        struct thread_runtime *tr = thread__priv(thread);
        u32 max_cpus = sched->max_cpu + 1;
        char tstr[64];
+        u64 wait_time;
        timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
        printf("%15s [%04d] ", tstr, sample->cpu);
@@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched,
        printf(" %-*s ", comm_width, timehist_get_commstr(thread));
-        print_sched_time(tr->dt_wait, 6);
+        wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+        print_sched_time(wait_time, 6);
        print_sched_time(tr->dt_delay, 6);
        print_sched_time(tr->dt_run, 6);
+        if (sched->show_state)
+                printf(" %5c ", task_state_char(thread, state));
        if (sched->show_wakeups)
                printf("  %-*s", comm_width, "");
@@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
                                         u64 t, u64 tprev)
 {
        r->dt_delay   = 0;
-        r->dt_wait    = 0;
+        r->dt_sleep   = 0;
+        r->dt_iowait  = 0;
+        r->dt_preempt = 0;
        r->dt_run     = 0;
        if (tprev) {
                r->dt_run = t - tprev;
                if (r->ready_to_run) {
@@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
                if (r->last_time > tprev)
                        pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
-                else if (r->last_time)
+                else if (r->last_time) {
-                        r->dt_wait = tprev - r->last_time;
+                        u64 dt_wait = tprev - r->last_time;
+                        if (r->last_state == TASK_RUNNING)
+                                r->dt_preempt = dt_wait;
+                        else if (r->last_state == TASK_UNINTERRUPTIBLE)
+                                r->dt_iowait = dt_wait;
+                        else
+                                r->dt_sleep = dt_wait;
+                }
        }
        update_stats(&r->run_stats, r->dt_run);
-        r->total_run_time += r->dt_run;
+        r->total_run_time     += r->dt_run;
+        r->total_delay_time   += r->dt_delay;
+        r->total_sleep_time   += r->dt_sleep;
+        r->total_iowait_time  += r->dt_iowait;
+        r->total_preempt_time += r->dt_preempt;
 }
 static bool is_idle_sample(struct perf_sample *sample,
@@ -1981,7 +2050,7 @@ static void save_task_callchain(struct perf_sched *sched,
        if (thread__resolve_callchain(thread, cursor, evsel, sample,
                                      NULL, NULL, sched->max_stack + 2) != 0) {
-                if (verbose)
+                if (verbose > 0)
                        error("Failed to resolve callchain. Skipping\n");
                return;
@@ -1998,7 +2067,7 @@ static void save_task_callchain(struct perf_sched *sched,
                        break;
                sym = node->sym;
-                if (sym && sym->name) {
+                if (sym) {
                        if (!strcmp(sym->name, "schedule") ||
                            !strcmp(sym->name, "__schedule") ||
                            !strcmp(sym->name, "preempt_schedule"))
@@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
        struct thread_runtime *tr = NULL;
        u64 tprev, t = sample->time;
        int rc = 0;
+        int state = perf_evsel__intval(evsel, sample, "prev_state");
        if (machine__resolve(machine, &al, sample) < 0) {
                pr_err("problem processing %d event. skipping it\n",
@@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
                         * time.  we only care total run time and run stat.
                         */
                        last_tr->dt_run = 0;
-                        last_tr->dt_wait = 0;
                        last_tr->dt_delay = 0;
+                        last_tr->dt_sleep = 0;
+                        last_tr->dt_iowait = 0;
+                        last_tr->dt_preempt = 0;
                        if (itr->cursor.nr)
                                callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
        }
        if (!sched->summary_only)
-                timehist_print_sample(sched, sample, &al, thread, t);
+                timehist_print_sample(sched, sample, &al, thread, t, state);
 out:
        if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -2470,6 +2543,9 @@ out:
                /* time of this sched_switch event becomes last time task seen */
                tr->last_time = sample->time;
+                /* last state is used to determine where to account wait time */
+                tr->last_state = state;
                /* sched out event for task so reset ready to run time */
                tr->ready_to_run = 0;
        }
@@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t,
        printf("\n");
 }
+static void print_thread_waittime(struct thread *t,
+                                  struct thread_runtime *r)
+{
+        printf("%*s   %5d  %9" PRIu64 " ",
+               comm_width, timehist_get_commstr(t), t->ppid,
+               (u64) r->run_stats.n);
+        print_sched_time(r->total_run_time, 8);
+        print_sched_time(r->total_sleep_time, 6);
+        printf(" ");
+        print_sched_time(r->total_iowait_time, 6);
+        printf(" ");
+        print_sched_time(r->total_preempt_time, 6);
+        printf(" ");
+        print_sched_time(r->total_delay_time, 6);
+        printf("\n");
+}
 struct total_run_stats {
+        struct perf_sched *sched;
        u64  sched_count;
        u64  task_count;
        u64  total_run_time;
@@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv)
                stats->task_count++;
                stats->sched_count += r->run_stats.n;
                stats->total_run_time += r->total_run_time;
-                print_thread_runtime(t, r);
+                if (stats->sched->show_state)
+                        print_thread_waittime(t, r);
+                else
+                        print_thread_runtime(t, r);
        }
        return 0;
@@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched,
        u64 hist_time = sched->hist_time.end - sched->hist_time.start;
        memset(&totals, 0, sizeof(totals));
+        totals.sched = sched;
        if (sched->idle_hist) {
                printf("\nIdle-time summary\n");
                printf("%*s  parent  sched-out  ", comm_width, "comm");
                printf("  idle-time   min-idle    avg-idle    max-idle  stddev  migrations\n");
+        } else if (sched->show_state) {
+                printf("\nWait-time summary\n");
+                printf("%*s  parent   sched-in  ", comm_width, "comm");
+                printf("   run-time      sleep      iowait     preempt       delay\n");
        } else {
                printf("\nRuntime summary\n");
                printf("%*s  parent   sched-in  ", comm_width, "comm");
                printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
        }
        printf("%*s            (count)  ", comm_width, "");
-        printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
+        printf("     (msec)     (msec)      (msec)      (msec)       %s\n",
+               sched->show_state ? "(msec)" : "%");
        printf("%.117s\n", graph_dotted_line);
        machine__for_each_thread(m, show_thread_runtime, &totals);
@@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
        OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
        OPT_STRING(0, "time", &sched.time_str, "str",
                   "Time span for analysis (start,stop)"),
+        OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
        OPT_PARENT(sched_options)
        };
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69fc4e7..c0783b4f7b6c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                    "Show the mmap events"),
        OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
                    "Show context switch events (if recorded)"),
-        OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+        OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
        OPT_BOOLEAN(0, "ns", &nanosecs,
                    "Use 9 decimal places when displaying time"),
        OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                             PARSE_OPT_STOP_AT_NON_OPTION);
        file.path = input_name;
+        file.force = symbol_conf.force;
        if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
                rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a02f2e965628..13b54999ad79 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -533,7 +533,7 @@ static int store_counter_ids(struct perf_evsel *counter)
 static int __run_perf_stat(int argc, const char **argv)
 {
        int interval = stat_config.interval;
-        char msg[512];
+        char msg[BUFSIZ];
        unsigned long long t0, t1;
        struct perf_evsel *counter;
        struct timespec ts;
@@ -573,7 +573,7 @@ try_again:
                        if (errno == EINVAL || errno == ENOSYS ||
                            errno == ENOENT || errno == EOPNOTSUPP ||
                            errno == ENXIO) {
-                                if (verbose)
+                                if (verbose > 0)
                                        ui__warning("%s event is not supported by the kernel.\n",
                                                    perf_evsel__name(counter));
                                counter->supported = false;
@@ -582,7 +582,7 @@ try_again:
                                    !(counter->leader->nr_members > 1))
                                        continue;
                        } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                        ui__warning("%s\n", msg);
                                goto try_again;
                        }
@@ -1765,7 +1765,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i
        cpu = map->map[idx];
-        if (cpu >= env->nr_cpus_online)
+        if (cpu >= env->nr_cpus_avail)
                return -1;
        return cpu;
@@ -2445,8 +2445,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
        } else if (big_num_opt == 0) /* User passed --no-big-num */
                big_num = false;
+        /* Make system wide (-a) the default target. */
        if (!argc && target__none(&target))
-                usage_with_options(stat_usage, stat_options);
+                target.system_wide = true;
        if (run_count < 0) {
                pr_err("Run count must be a positive number\n");
@@ -2538,7 +2539,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
        status = 0;
        for (run_idx = 0; forever || run_idx < run_count; run_idx++) {
-                if (run_count != 1 && verbose)
+                if (run_count != 1 && verbose > 0)
                        fprintf(output, "[ perf stat: executing run #%d ... ]\n",
                                run_idx + 1);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3df4178ba378..ab9077915763 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -643,7 +643,7 @@ repeat:
                case -1:
                        if (errno == EINTR)
                                continue;
-                        /* Fall trhu */
+                        __fallthrough;
                default:
                        c = getc(stdin);
                        tcsetattr(0, TCSAFLUSH, &save);
@@ -859,7 +859,7 @@ static void perf_top__mmap_read(struct perf_top *top)
 static int perf_top__start_counters(struct perf_top *top)
 {
-        char msg[512];
+        char msg[BUFSIZ];
        struct perf_evsel *counter;
        struct perf_evlist *evlist = top->evlist;
        struct record_opts *opts = &top->record_opts;
@@ -871,7 +871,7 @@ try_again:
                if (perf_evsel__open(counter, top->evlist->cpus,
                                     top->evlist->threads) < 0) {
                        if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose)
+                                if (verbose > 0)
                                        ui__warning("%s\n", msg);
                                goto try_again;
                        }
@@ -1216,7 +1216,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
        if (top.evlist == NULL)
                return -ENOMEM;
-        perf_config(perf_top_config, &top);
+        status = perf_config(perf_top_config, &top);
+        if (status)
+                return status;
        argc = parse_options(argc, argv, options, top_usage, 0);
        if (argc)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72b77fc..256f1fac6f7e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
+#include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
@@ -1398,7 +1399,7 @@ static struct syscall *trace__syscall_info(struct trace *trace,
        return &trace->syscalls.table[id];
 out_cant_read:
-        if (verbose) {
+        if (verbose > 0) {
                fprintf(trace->output, "Problems reading syscall %d", id);
                if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
                        fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
@@ -1800,10 +1801,10 @@ static void print_location(FILE *f, struct perf_sample *sample,
                           bool print_dso, bool print_sym)
 {
-        if ((verbose || print_dso) && al->map)
+        if ((verbose > 0 || print_dso) && al->map)
                fprintf(f, "%s@", al->map->dso->long_name);
-        if ((verbose || print_sym) && al->sym)
+        if ((verbose > 0 || print_sym) && al->sym)
                fprintf(f, "%s+0x%" PRIx64, al->sym->name,
                        al->addr - al->sym->start);
        else if (al->map)
@@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
                evsel->handler = handler;
 }
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+                                      int unset __maybe_unused)
+{
+        struct trace *trace = (struct trace *)opt->value;
+        const char *s = str;
+        char *sep = NULL, *lists[2] = { NULL, NULL, };
+        int len = strlen(str), err = -1, list;
+        char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+        char group_name[PATH_MAX];
+        if (strace_groups_dir == NULL)
+                return -1;
+        if (*s == '!') {
+                ++s;
+                trace->not_ev_qualifier = true;
+        }
+        while (1) {
+                if ((sep = strchr(s, ',')) != NULL)
+                        *sep = '\0';
+                list = 0;
+                if (syscalltbl__id(trace->sctbl, s) >= 0) {
+                        list = 1;
+                } else {
+                        path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+                        if (access(group_name, R_OK) == 0)
+                                list = 1;
+                }
+                if (lists[list]) {
+                        sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+                } else {
+                        lists[list] = malloc(len);
+                        if (lists[list] == NULL)
+                                goto out;
+                        strcpy(lists[list], s);
+                }
+                if (!sep)
+                        break;
+                *sep = ',';
+                s = sep + 1;
+        }
+        if (lists[1] != NULL) {
+                struct strlist_config slist_config = {
+                        .dirname = strace_groups_dir,
+                };
+                trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+                if (trace->ev_qualifier == NULL) {
+                        fputs("Not enough memory to parse event qualifier", trace->output);
+                        goto out;
+                }
+                if (trace__validate_ev_qualifier(trace))
+                        goto out;
+        }
+        err = 0;
+        if (lists[0]) {
+                struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+                                               "event selector. use 'perf list' to list available events",
+                                               parse_events_option);
+                err = parse_events_option(&o, lists[0], 0);
+        }
+out:
+        if (sep)
+                *sep = ',';
+        return err;
+}
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
        const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                .max_stack = UINT_MAX,
        };
        const char *output_name = NULL;
-        const char *ev_qualifier_str = NULL;
        const struct option trace_options[] = {
-        OPT_CALLBACK(0, "event", &trace.evlist, "event",
+        OPT_CALLBACK('e', "event", &trace, "event",
-                     "event selector. use 'perf list' to list available events",
+                     "event/syscall selector. use 'perf list' to list available events",
-                     parse_events_option),
+                     trace__parse_events_option),
        OPT_BOOLEAN(0, "comm", &trace.show_comm,
                    "show the thread COMM next to its id"),
        OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-        OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+        OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+                     trace__parse_events_option),
        OPT_STRING('o', "output", &output_name, "file", "output file name"),
        OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
        OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                return -1;
        }
-        if (!trace.trace_syscalls && ev_qualifier_str) {
+        if (!trace.trace_syscalls && trace.ev_qualifier) {
                pr_err("The -e option can't be used with --no-syscalls.\n");
                goto out;
        }
@@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
        trace.open_id = syscalltbl__id(trace.sctbl, "open");
-        if (ev_qualifier_str != NULL) {
-                const char *s = ev_qualifier_str;
-                struct strlist_config slist_config = {
-                        .dirname = system_path(STRACE_GROUPS_DIR),
-                };
-                trace.not_ev_qualifier = *s == '!';
-                if (trace.not_ev_qualifier)
-                        ++s;
-                trace.ev_qualifier = strlist__new(s, &slist_config);
-                if (trace.ev_qualifier == NULL) {
-                        fputs("Not enough memory to parse event qualifier",
-                              trace.output);
-                        err = -ENOMEM;
-                        goto out_close;
-                }
-                err = trace__validate_ev_qualifier(&trace);
-                if (err)
-                        goto out_close;
-        }
        err = target__validate(&trace.opts.target);
        if (err) {
                target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 0bcf68e98ccc..036e1e35b1a8 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix);
 int cmd_evlist(int argc, const char **argv, const char *prefix);
 int cmd_help(int argc, const char **argv, const char *prefix);
 int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_kallsyms(int argc, const char **argv, const char *prefix);
 int cmd_list(int argc, const char **argv, const char *prefix);
 int cmd_record(int argc, const char **argv, const char *prefix);
 int cmd_report(int argc, const char **argv, const char *prefix);
@@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix);
 int cmd_inject(int argc, const char **argv, const char *prefix);
 int cmd_mem(int argc, const char **argv, const char *prefix);
 int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_ftrace(int argc, const char **argv, const char *prefix);
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ab5cbaa170d0..ac3efd396a72 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -11,7 +11,9 @@ perf-data			mainporcelain common
 perf-diff                       mainporcelain common
 perf-config                     mainporcelain common
 perf-evlist                     mainporcelain common
+perf-ftrace                     mainporcelain common
 perf-inject                     mainporcelain common
+perf-kallsyms                   mainporcelain common
 perf-kmem                       mainporcelain common
 perf-kvm                        mainporcelain common
 perf-list                       mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index aa23b3347d6b..6d5479e03e0d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,7 +29,6 @@ const char perf_usage_string[] =
 const char perf_more_info_string[] =
        "See 'perf help COMMAND' for more information on a specific command.";
-int use_browser = -1;
 static int use_pager = -1;
 const char *input_name;
@@ -47,6 +46,7 @@ static struct cmd_struct commands[] = {
        { "diff",       cmd_diff,       0 },
        { "evlist",     cmd_evlist,     0 },
        { "help",       cmd_help,       0 },
+        { "kallsyms",   cmd_kallsyms,   0 },
        { "list",       cmd_list,       0 },
        { "record",     cmd_record,     0 },
        { "report",     cmd_report,     0 },
@@ -71,6 +71,7 @@ static struct cmd_struct commands[] = {
        { "inject",     cmd_inject,     0 },
        { "mem",        cmd_mem,        0 },
        { "data",       cmd_data,       0 },
+        { "ftrace",     cmd_ftrace,     0 },
 };
 struct pager_config {
@@ -89,11 +90,12 @@ static int pager_command_config(const char *var, const char *value, void *data)
 /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
 int check_pager_config(const char *cmd)
 {
+        int err;
        struct pager_config c;
        c.cmd = cmd;
        c.val = -1;
-        perf_config(pager_command_config, &c);
+        err = perf_config(pager_command_config, &c);
-        return c.val;
+        return err ?: c.val;
 }
 static int browser_command_config(const char *var, const char *value, void *data)
@@ -112,11 +114,12 @@ static int browser_command_config(const char *var, const char *value, void *data
 */
 static int check_browser_config(const char *cmd)
 {
+        int err;
        struct pager_config c;
        c.cmd = cmd;
        c.val = -1;
-        perf_config(browser_command_config, &c);
+        err = perf_config(browser_command_config, &c);
-        return c.val;
+        return err ?: c.val;
 }
 static void commit_pager_choice(void)
@@ -329,8 +332,6 @@ static int handle_alias(int *argcp, const char ***argv)
        return ret;
 }
-const char perf_version_string[] = PERF_VERSION;
 #define RUN_SETUP       (1<<0)
 #define USE_PAGER       (1<<1)
@@ -510,6 +511,7 @@ static void cache_line_size(int *cacheline_sizep)
 int main(int argc, const char **argv)
 {
+        int err;
        const char *cmd;
        char sbuf[STRERR_BUFSIZE];
        int value;
@@ -535,7 +537,9 @@ int main(int argc, const char **argv)
        srandom(time(NULL));
        perf_config__init();
-        perf_config(perf_default_config, NULL);
+        err = perf_config(perf_default_config, NULL);
+        if (err)
+                return err;
        set_buildid_dir(NULL);
        /* get debugfs/tracefs mount point from /proc/mounts */
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
new file mode 100644
index 000000000000..39387f7909b2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
new file mode 100644
index 000000000000..39387f7909b2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
new file mode 100644
index 000000000000..2efdc6772e0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -0,0 +1,322 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+        "Filter": "filter_opc=0x195",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x1e5",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x2A",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8A",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
new file mode 100644
index 000000000000..d7e2fda1d695
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
new file mode 100644
index 000000000000..ac4ad4d6357b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -0,0 +1,75 @@
+[
+    {
+        "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Umask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
new file mode 100644
index 000000000000..dc2586db0dfc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -0,0 +1,249 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xa",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency.  This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature.  This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x7",
+        "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the system is changing frequency.  This can not be filtered by thread ID.  One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x60",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+        "Filter": "filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+        "Filter": "filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+        "Filter": "filter_band2=3000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+        "Filter": "filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band2=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
new file mode 100644
index 000000000000..2f23cf0129e7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -0,0 +1,209 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+        "Filter": "filter_opc=0x195",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x1e5",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
+        "Filter": "filter_opc=0x182",
+        "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "UMask": "0xa",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xc",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
new file mode 100644
index 000000000000..63351876eb57
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
new file mode 100644
index 000000000000..e2cf6daa7b37
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -0,0 +1,79 @@
+[
+    {
+        "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0xc",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_M_RPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
new file mode 100644
index 000000000000..bbe36d547386
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -0,0 +1,248 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xa",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x7",
+        "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+        "Filter": "filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+        "Filter": "filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+        "Filter": "filter_band2=3000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+        "Filter": "filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band2=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
new file mode 100644
index 000000000000..e3bcd86c4f56
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
@@ -0,0 +1,42 @@
+[
+    {
+        "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x03",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "imc"
+    },
+    {
+        "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x03",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x02",
+        "Unit": "imc"
+    },
+    {
+        "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x01",
+        "EventName": "UNC_E_RPQ_INSERTS",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "edc_eclk"
+    },
+    {
+        "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x02",
+        "EventName": "UNC_E_WPQ_INSERTS",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "edc_eclk"
+    }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 41611d7f9873..eed09346a72a 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -135,7 +135,6 @@ static struct field {
        const char *field;
        const char *kernel;
 } fields[] = {
-        { "EventCode",  "event=" },
        { "UMask",      "umask=" },
        { "CounterMask", "cmask=" },
        { "Invert",     "inv=" },
@@ -189,6 +188,27 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val)
        return NULL;
 }
+static struct map {
+        const char *json;
+        const char *perf;
+} unit_to_pmu[] = {
+        { "CBO", "uncore_cbox" },
+        { "QPI LL", "uncore_qpi" },
+        { "SBO", "uncore_sbox" },
+        {}
+};
+static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val)
+{
+        int i;
+        for (i = 0; table[i].json; i++) {
+                if (json_streq(map, val, table[i].json))
+                        return table[i].perf;
+        }
+        return NULL;
+}
 #define EXPECT(e, t, m) do { if (!(e)) {                        \
        jsmntok_t *loc = (t);                                   \
        if (!(t)->start && (t) > tokens)                        \
@@ -270,7 +290,8 @@ static void print_events_table_prefix(FILE *fp, const char *tblname)
 }
 static int print_events_table_entry(void *data, char *name, char *event,
-                                    char *desc, char *long_desc)
+                                    char *desc, char *long_desc,
+                                    char *pmu, char *unit, char *perpkg)
 {
        struct perf_entry_data *pd = data;
        FILE *outfp = pd->outfp;
@@ -288,7 +309,12 @@ static int print_events_table_entry(void *data, char *name, char *event,
        fprintf(outfp, "\t.topic = \"%s\",\n", topic);
        if (long_desc && long_desc[0])
                fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc);
+        if (pmu)
+                fprintf(outfp, "\t.pmu = \"%s\",\n", pmu);
+        if (unit)
+                fprintf(outfp, "\t.unit = \"%s\",\n", unit);
+        if (perpkg)
+                fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
        fprintf(outfp, "},\n");
        return 0;
@@ -335,7 +361,8 @@ static char *real_event(const char *name, char *event)
 /* Call func with each event in the json file */
 int json_events(const char *fn,
          int (*func)(void *data, char *name, char *event, char *desc,
-                      char *long_desc),
+                      char *long_desc,
+                      char *pmu, char *unit, char *perpkg),
          void *data)
 {
        int err = -EIO;
@@ -343,6 +370,7 @@ int json_events(const char *fn,
        jsmntok_t *tokens, *tok;
        int i, j, len;
        char *map;
+        char buf[128];
        if (!fn)
                return -ENOENT;
@@ -356,6 +384,11 @@ int json_events(const char *fn,
                char *event = NULL, *desc = NULL, *name = NULL;
                char *long_desc = NULL;
                char *extra_desc = NULL;
+                char *pmu = NULL;
+                char *filter = NULL;
+                char *perpkg = NULL;
+                char *unit = NULL;
+                unsigned long long eventcode = 0;
                struct msrmap *msr = NULL;
                jsmntok_t *msrval = NULL;
                jsmntok_t *precise = NULL;
@@ -376,6 +409,16 @@ int json_events(const char *fn,
                        nz = !json_streq(map, val, "0");
                        if (match_field(map, field, nz, &event, val)) {
                                /* ok */
+                        } else if (json_streq(map, field, "EventCode")) {
+                                char *code = NULL;
+                                addfield(map, &code, "", "", val);
+                                eventcode |= strtoul(code, NULL, 0);
+                                free(code);
+                        } else if (json_streq(map, field, "ExtSel")) {
+                                char *code = NULL;
+                                addfield(map, &code, "", "", val);
+                                eventcode |= strtoul(code, NULL, 0) << 21;
+                                free(code);
                        } else if (json_streq(map, field, "EventName")) {
                                addfield(map, &name, "", "", val);
                        } else if (json_streq(map, field, "BriefDescription")) {
@@ -399,6 +442,28 @@ int json_events(const char *fn,
                                addfield(map, &extra_desc, ". ",
                                        " Supports address when precise",
                                        NULL);
+                        } else if (json_streq(map, field, "Unit")) {
+                                const char *ppmu;
+                                char *s;
+                                ppmu = field_to_perf(unit_to_pmu, map, val);
+                                if (ppmu) {
+                                        pmu = strdup(ppmu);
+                                } else {
+                                        if (!pmu)
+                                                pmu = strdup("uncore_");
+                                        addfield(map, &pmu, "", "", val);
+                                        for (s = pmu; *s; s++)
+                                                *s = tolower(*s);
+                                }
+                                addfield(map, &desc, ". ", "Unit: ", NULL);
+                                addfield(map, &desc, "", pmu, NULL);
+                        } else if (json_streq(map, field, "Filter")) {
+                                addfield(map, &filter, "", "", val);
+                        } else if (json_streq(map, field, "ScaleUnit")) {
+                                addfield(map, &unit, "", "", val);
+                        } else if (json_streq(map, field, "PerPkg")) {
+                                addfield(map, &perpkg, "", "", val);
                        }
                        /* ignore unknown fields */
                }
@@ -410,20 +475,29 @@ int json_events(const char *fn,
                                addfield(map, &extra_desc, " ",
                                                "(Precise event)", NULL);
                }
+                snprintf(buf, sizeof buf, "event=%#llx", eventcode);
+                addfield(map, &event, ",", buf, NULL);
                if (desc && extra_desc)
                        addfield(map, &desc, " ", extra_desc, NULL);
                if (long_desc && extra_desc)
                        addfield(map, &long_desc, " ", extra_desc, NULL);
+                if (filter)
+                        addfield(map, &event, ",", filter, NULL);
                if (msr != NULL)
                        addfield(map, &event, ",", msr->pname, msrval);
                fixname(name);
-                err = func(data, name, real_event(name, event), desc, long_desc);
+                err = func(data, name, real_event(name, event), desc, long_desc,
+                                pmu, unit, perpkg);
                free(event);
                free(desc);
                free(name);
                free(long_desc);
                free(extra_desc);
+                free(pmu);
+                free(filter);
+                free(perpkg);
+                free(unit);
                if (err)
                        break;
                tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index b0eb2744b498..71e13de31092 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -3,7 +3,9 @@
 int json_events(const char *fn,
                int (*func)(void *data, char *name, char *event, char *desc,
-                                char *long_desc),
+                                char *long_desc,
+                                char *pmu,
+                                char *unit, char *perpkg),
                void *data);
 char *get_cpu_str(void);
diff --git a/tools/perf/pmu-events/json.c b/tools/perf/pmu-events/json.c
index f67bbb0aa36e..0544398d6e2d 100644
--- a/tools/perf/pmu-events/json.c
+++ b/tools/perf/pmu-events/json.c
@@ -49,7 +49,7 @@ static char *mapfile(const char *fn, size_t *size)
        int err;
        int fd = open(fn, O_RDONLY);
-        if (fd < 0 && verbose && fn) {
+        if (fd < 0 && verbose > 0 && fn) {
                pr_err("Error opening events file '%s': %s\n", fn,
                                strerror(errno));
        }
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 2eaef595d8a0..c669a3cdb9f0 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -10,6 +10,9 @@ struct pmu_event {
        const char *desc;
        const char *topic;
        const char *long_desc;
+        const char *pmu;
+        const char *unit;
+        const char *perpkg;
 };
 /*
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6676c2dd6dcb..1cb3d9b540e9 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -44,6 +44,7 @@ perf-y += is_printable_array.o
 perf-y += bitmap.o
 perf-y += perf-hooks.o
 perf-y += clang.o
+perf-y += unit_number__scnprintf.o
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
        $(call rule_mkdir)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 28d1605b0338..88dc51f4c27b 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -144,7 +144,7 @@ static int run_dir(const char *d, const char *perf)
        int vcnt = min(verbose, (int) sizeof(v) - 1);
        char cmd[3*PATH_MAX];
-        if (verbose)
+        if (verbose > 0)
                vcnt++;
        snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 92343f43e44a..1a04fe77487d 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -5,11 +5,13 @@
 #include <util/evlist.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <api/fs/fs.h>
 #include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
 #define NR_ITERS       111
+#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
 #ifdef HAVE_LIBBPF_SUPPORT
@@ -54,6 +56,7 @@ static struct {
        const char *msg_load_fail;
        int (*target_func)(void);
        int expect_result;
+        bool    pin;
 } bpf_testcase_table[] = {
        {
                LLVM_TESTCASE_BASE,
@@ -63,6 +66,17 @@ static struct {
                "load bpf object failed",
                &epoll_wait_loop,
                (NR_ITERS + 1) / 2,
+                false,
+        },
+        {
+                LLVM_TESTCASE_BASE,
+                "BPF pinning",
+                "[bpf_pinning]",
+                "fix kbuild first",
+                "check your vmlinux setting?",
+                &epoll_wait_loop,
+                (NR_ITERS + 1) / 2,
+                true,
        },
 #ifdef HAVE_BPF_PROLOGUE
        {
@@ -73,6 +87,7 @@ static struct {
                "check your vmlinux setting?",
                &llseek_loop,
                (NR_ITERS + 1) / 4,
+                false,
        },
 #endif
        {
@@ -83,6 +98,7 @@ static struct {
                "libbpf error when dealing with relocation",
                NULL,
                0,
+                false,
        },
 };
@@ -226,10 +242,34 @@ static int __test__bpf(int idx)
                goto out;
        }
-        if (obj)
+        if (obj) {
                ret = do_test(obj,
                              bpf_testcase_table[idx].target_func,
                              bpf_testcase_table[idx].expect_result);
+                if (ret != TEST_OK)
+                        goto out;
+                if (bpf_testcase_table[idx].pin) {
+                        int err;
+                        if (!bpf_fs__mount()) {
+                                pr_debug("BPF filesystem not mounted\n");
+                                ret = TEST_FAIL;
+                                goto out;
+                        }
+                        err = mkdir(PERF_TEST_BPF_PATH, 0777);
+                        if (err && errno != EEXIST) {
+                                pr_debug("Failed to make perf_test dir: %s\n",
+                                         strerror(errno));
+                                ret = TEST_FAIL;
+                                goto out;
+                        }
+                        if (bpf_object__pin(obj, PERF_TEST_BPF_PATH))
+                                ret = TEST_FAIL;
+                        if (rm_rf(PERF_TEST_BPF_PATH))
+                                ret = TEST_FAIL;
+                }
+        }
 out:
        bpf__clear();
        return ret;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a77dcc0d24e3..83c4669cbc5b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -247,6 +247,10 @@ static struct test generic_tests[] = {
                }
        },
        {
+                .desc = "unit_number__scnprintf",
+                .func = test__unit_number__scnprint,
+        },
+        {
                .func = NULL,
        },
 };
@@ -295,7 +299,7 @@ static int run_test(struct test *test, int subtest)
                if (!dont_fork) {
                        pr_debug("test child forked, pid %d\n", getpid());
-                        if (!verbose) {
+                        if (verbose <= 0) {
                                int nullfd = open("/dev/null", O_WRONLY);
                                if (nullfd >= 0) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index ff5bc6363a79..d1f693041324 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -599,7 +599,7 @@ static int do_test_code_reading(bool try_kcore)
                                continue;
                        }
-                        if (verbose) {
+                        if (verbose > 0) {
                                char errbuf[512];
                                perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
                                pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index a2b5ff9bf83d..bc5982f42dc3 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -19,7 +19,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 {
        int printed = 0;
-        if (!verbose)
+        if (verbose <= 0)
                return 0;
        printed += fprintf(fp, "\n%s: ", prefix);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 02a33ebcd992..482b5365e68d 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
        struct bpf_object *obj;
        obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
-        if (IS_ERR(obj))
+        if (libbpf_get_error(obj))
                return TEST_FAIL;
        bpf_object__close(obj);
        return TEST_OK;
@@ -76,7 +76,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
         * Skip this test if user's .perfconfig doesn't set [llvm] section
         * and clang is not found in $PATH, and this is not perf test -v
         */
-        if (!force && (verbose == 0 &&
+        if (!force && (verbose <= 0 &&
                       !llvm_param.user_set_param &&
                       llvm__search_clang())) {
                pr_debug("No clang and no verbosive, skip this test\n");
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 20c2e641c422..1dc838014422 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1779,15 +1779,14 @@ static int test_pmu_events(void)
        }
        while (!ret && (ent = readdir(dir))) {
-#define MAX_NAME 100
                struct evlist_test e;
-                char name[MAX_NAME];
+                char name[2 * NAME_MAX + 1 + 12 + 3];
                /* 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);
+                snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name);
                e.name  = name;
                e.check = test__checkevent_pmu_events;
@@ -1795,11 +1794,10 @@ static int test_pmu_events(void)
                ret = test_event(&e);
                if (ret)
                        break;
-                snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+                snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
                e.name  = name;
                e.check = test__checkevent_pmu_events_mix;
                ret = test_event(&e);
-#undef MAX_NAME
        }
        closedir(dir);
@@ -1810,7 +1808,7 @@ static void debug_warn(const char *warn, va_list params)
 {
        char msg[1024];
-        if (!verbose)
+        if (verbose <= 0)
                return;
        vsnprintf(msg, sizeof(msg), warn, params);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 81c6eeaca0f5..65dcf48a92fb 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -50,7 +50,8 @@ static int process_events(union perf_event **events, size_t count)
 }
 struct test_attr_event {
-        struct attr_event attr;
+        struct perf_event_header header;
+        struct perf_event_attr   attr;
        u64 id;
 };
@@ -71,20 +72,16 @@ int test__parse_no_sample_id_all(int subtest __maybe_unused)
        int err;
        struct test_attr_event event1 = {
-                .attr = {
+                .header = {
-                        .header = {
+                        .type = PERF_RECORD_HEADER_ATTR,
-                                .type = PERF_RECORD_HEADER_ATTR,
+                        .size = sizeof(struct test_attr_event),
-                                .size = sizeof(struct test_attr_event),
-                        },
                },
                .id = 1,
        };
        struct test_attr_event event2 = {
-                .attr = {
+                .header = {
-                        .header = {
+                        .type = PERF_RECORD_HEADER_ATTR,
-                                .type = PERF_RECORD_HEADER_ATTR,
+                        .size = sizeof(struct test_attr_event),
-                                .size = sizeof(struct test_attr_event),
-                        },
                },
                .id = 2,
        };
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 8f2e1de6d0ea..87893f3ba5f1 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -66,7 +66,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
        if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
                evlist = perf_evlist__new_default();
-        if (evlist == NULL || argv == NULL) {
+        if (evlist == NULL) {
                pr_debug("Not enough memory to create evlist\n");
                goto out;
        }
@@ -172,13 +172,13 @@ int test__PERF_RECORD(int subtest __maybe_unused)
                                err = perf_evlist__parse_sample(evlist, event, &sample);
                                if (err < 0) {
-                                        if (verbose)
+                                        if (verbose > 0)
                                                perf_event__fprintf(event, stderr);
                                        pr_debug("Couldn't parse sample\n");
                                        goto out_delete_evlist;
                                }
-                                if (verbose) {
+                                if (verbose > 0) {
                                        pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
                                        perf_event__fprintf(event, stderr);
                                }
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 7a52834ee0d0..fa79509da535 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -15,7 +15,7 @@ int test__python_use(int subtest __maybe_unused)
        int ret;
        if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
-                     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+                     PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0)
                return -1;
        ret = system(cmd) ? -1 : 0;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a512f0c8ff5b..1fa9b9d83aa5 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -96,6 +96,7 @@ int test__perf_hooks(int subtest);
 int test__clang(int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
+int test__unit_number__scnprint(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 a4a4b4625ac3..f2d2e542d0ee 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -109,7 +109,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
        TEST_ASSERT_VAL("failed to allocate thread_map",
                        threads);
-        if (verbose)
+        if (verbose > 0)
                thread_map__fprintf(threads, stderr);
        TEST_ASSERT_VAL("failed to remove thread",
@@ -117,7 +117,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
        TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1);
-        if (verbose)
+        if (verbose > 0)
                thread_map__fprintf(threads, stderr);
        TEST_ASSERT_VAL("failed to remove thread",
@@ -125,7 +125,7 @@ int test__thread_map_remove(int subtest __maybe_unused)
        TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0);
-        if (verbose)
+        if (verbose > 0)
                thread_map__fprintf(threads, stderr);
        TEST_ASSERT_VAL("failed to not remove thread",
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 98fe69ac553c..803f893550d6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -65,7 +65,9 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
        session = perf_session__new(&file, false, NULL);
        TEST_ASSERT_VAL("can't get session", session);
-        for (i = 0; i < session->header.env.nr_cpus_online; i++) {
+        for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
+                if (!cpu_map__has(map, i))
+                        continue;
                pr_debug("CPU %d, core %d, socket %d\n", i,
                         session->header.env.cpu[i].core_id,
                         session->header.env.cpu[i].socket_id);
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
new file mode 100644
index 000000000000..623c2aa53c4a
--- /dev/null
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -0,0 +1,37 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "tests.h"
+#include "util.h"
+#include "debug.h"
+int test__unit_number__scnprint(int subtest __maybe_unused)
+{
+        struct {
+                u64              n;
+                const char      *str;
+        } test[] = {
+                { 1,                    "1B"    },
+                { 10*1024,              "10K"   },
+                { 20*1024*1024,         "20M"   },
+                { 30*1024*1024*1024ULL, "30G"   },
+                { 0,                    "0B"    },
+                { 0,                    NULL    },
+        };
+        unsigned i = 0;
+        while (test[i].str) {
+                char buf[100];
+                unit_number__scnprintf(buf, sizeof(buf), test[i].n);
+                pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n",
+                         test[i].n, test[i].str, buf);
+                if (strcmp(test[i].str, buf))
+                        return TEST_FAIL;
+                i++;
+        }
+        return TEST_OK;
+}
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index a5082331f246..862b043e5924 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -168,7 +168,7 @@ next_pair:
                err = -1;
        }
-        if (!verbose)
+        if (verbose <= 0)
                goto out;
        header_printed = false;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 641b40234a9d..fc4fb669ceee 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -501,8 +501,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
        return n;
 }
-static void hist_entry__set_folding(struct hist_entry *he,
+static void __hist_entry__set_folding(struct hist_entry *he,
-                                    struct hist_browser *hb, bool unfold)
+                                      struct hist_browser *hb, bool unfold)
 {
        hist_entry__init_have_children(he);
        he->unfolded = unfold ? he->has_children : false;
@@ -520,12 +520,34 @@ static void hist_entry__set_folding(struct hist_entry *he,
                he->nr_rows = 0;
 }
+static void hist_entry__set_folding(struct hist_entry *he,
+                                    struct hist_browser *browser, bool unfold)
+{
+        double percent;
+        percent = hist_entry__get_percent_limit(he);
+        if (he->filtered || percent < browser->min_pcnt)
+                return;
+        __hist_entry__set_folding(he, browser, unfold);
+        if (!he->depth || unfold)
+                browser->nr_hierarchy_entries++;
+        if (he->leaf)
+                browser->nr_callchain_rows += he->nr_rows;
+        else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+                browser->nr_hierarchy_entries++;
+                he->has_no_entry = true;
+                he->nr_rows = 1;
+        } else
+                he->has_no_entry = false;
+}
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
        struct rb_node *nd;
        struct hist_entry *he;
-        double percent;
        nd = rb_first(&browser->hists->entries);
        while (nd) {
@@ -535,21 +557,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
                nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
                hist_entry__set_folding(he, browser, unfold);
-                percent = hist_entry__get_percent_limit(he);
-                if (he->filtered || percent < browser->min_pcnt)
-                        continue;
-                if (!he->depth || unfold)
-                        browser->nr_hierarchy_entries++;
-                if (he->leaf)
-                        browser->nr_callchain_rows += he->nr_rows;
-                else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-                        browser->nr_hierarchy_entries++;
-                        he->has_no_entry = true;
-                        he->nr_rows = 1;
-                } else
-                        he->has_no_entry = false;
        }
 }
@@ -564,6 +571,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
        ui_browser__reset_index(&browser->b);
 }
+static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold)
+{
+        if (!browser->he_selection)
+                return;
+        hist_entry__set_folding(browser->he_selection, browser, unfold);
+        browser->b.nr_entries = hist_browser__nr_entries(browser);
+}
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
 {
        ui_browser__warning(browser, 4,
@@ -637,10 +653,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
                        /* Collapse the whole world. */
                        hist_browser__set_folding(browser, false);
                        break;
+                case 'c':
+                        /* Collapse the selected entry. */
+                        hist_browser__set_folding_selected(browser, false);
+                        break;
                case 'E':
                        /* Expand the whole world. */
                        hist_browser__set_folding(browser, true);
                        break;
+                case 'e':
+                        /* Expand the selected entry. */
+                        hist_browser__set_folding_selected(browser, true);
+                        break;
                case 'H':
                        browser->show_headers = !browser->show_headers;
                        hist_browser__update_rows(browser);
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 98a34664bb7e..9ce142de536d 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -73,7 +73,7 @@ static int map_browser__run(struct map_browser *browser)
        if (ui_browser__show(&browser->b, browser->map->dso->long_name,
                             "Press ESC to exit, %s / to search",
-                             verbose ? "" : "restart with -v to use") < 0)
+                             verbose > 0 ? "" : "restart with -v to use") < 0)
                return -1;
        while (1) {
@@ -81,7 +81,7 @@ static int map_browser__run(struct map_browser *browser)
                switch (key) {
                case '/':
-                        if (verbose)
+                        if (verbose > 0)
                                map_browser__search(browser);
                default:
                        break;
@@ -117,7 +117,7 @@ int map__browse(struct map *map)
                if (maxaddr < pos->end)
                        maxaddr = pos->end;
-                if (verbose) {
+                if (verbose > 0) {
                        u32 *idx = symbol__browser_index(pos);
                        *idx = mb.b.nr_entries;
                }
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 18cfcdc90356..5d632dca672a 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -648,7 +648,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
                ret += fmt->width(fmt, &dummy_hpp, hists);
        }
-        if (verbose && hists__has(hists, sym)) /* Addr + origin */
+        if (verbose > 0 && hists__has(hists, sym)) /* Addr + origin */
                ret += 3 + BITS_PER_LONG / 4;
        return ret;
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 1f6b0994f4f4..50d13e58210f 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -7,6 +7,7 @@
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 void *perf_gtk_handle;
+int use_browser = -1;
 #ifdef HAVE_GTK2_SUPPORT
 static int setup_gtk_browser(void)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3840e3a87057..5da376bc1afc 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -162,6 +162,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
+CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
        $(call rule_mkdir)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 06cc04e5806a..273f21fa32b5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1768,7 +1768,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
        printf("%-*.*s----\n",
               graph_dotted_len, graph_dotted_len, graph_dotted_line);
-        if (verbose)
+        if (verbose > 0)
                symbol__annotate_hits(sym, evsel);
        list_for_each_entry(pos, &notes->src->source, node) {
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 36c861103291..bc6bc7062eb4 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -670,13 +670,13 @@ int bpf__probe(struct bpf_object *obj)
                err = convert_perf_probe_events(pev, 1);
                if (err < 0) {
-                        pr_debug("bpf_probe: failed to convert perf probe events");
+                        pr_debug("bpf_probe: failed to convert perf probe events\n");
                        goto out;
                }
                err = apply_perf_probe_events(pev, 1);
                if (err < 0) {
-                        pr_debug("bpf_probe: failed to apply perf probe events");
+                        pr_debug("bpf_probe: failed to apply perf probe events\n");
                        goto out;
                }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8b610dd9e2f6..aba953421a03 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -48,6 +48,8 @@ static int parse_callchain_mode(const char *value)
                callchain_param.mode = CHAIN_FOLDED;
                return 0;
        }
+        pr_err("Invalid callchain mode: %s\n", value);
        return -1;
 }
@@ -63,6 +65,8 @@ static int parse_callchain_order(const char *value)
                callchain_param.order_set = true;
                return 0;
        }
+        pr_err("Invalid callchain order: %s\n", value);
        return -1;
 }
@@ -80,6 +84,8 @@ static int parse_callchain_sort_key(const char *value)
                callchain_param.branch_callstack = 1;
                return 0;
        }
+        pr_err("Invalid callchain sort key: %s\n", value);
        return -1;
 }
@@ -97,6 +103,8 @@ static int parse_callchain_value(const char *value)
                callchain_param.value = CCVAL_COUNT;
                return 0;
        }
+        pr_err("Invalid callchain config key: %s\n", value);
        return -1;
 }
@@ -210,13 +218,17 @@ int perf_callchain_config(const char *var, const char *value)
                return parse_callchain_sort_key(value);
        if (!strcmp(var, "threshold")) {
                callchain_param.min_percent = strtod(value, &endptr);
-                if (value == endptr)
+                if (value == endptr) {
+                        pr_err("Invalid callchain threshold: %s\n", value);
                        return -1;
+                }
        }
        if (!strcmp(var, "print-limit")) {
                callchain_param.print_limit = strtod(value, &endptr);
-                if (value == endptr)
+                if (value == endptr) {
+                        pr_err("Invalid callchain print limit: %s\n", value);
                        return -1;
+                }
        }
        return 0;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 8fdee24725a7..eafbf11442b2 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -12,8 +12,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 {
        FILE *fp;
        char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
+        char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
        char *token, *saved_ptr = NULL;
-        int found = 0;
        fp = fopen("/proc/mounts", "r");
        if (!fp)
@@ -24,31 +24,43 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
         * and inspect every cgroupfs mount point to find one that has
         * perf_event subsystem
         */
+        path_v1[0] = '\0';
+        path_v2[0] = '\0';
        while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
                                STR(PATH_MAX)"s %*d %*d\n",
                                mountpoint, type, tokens) == 3) {
-                if (!strcmp(type, "cgroup")) {
+                if (!path_v1[0] && !strcmp(type, "cgroup")) {
                        token = strtok_r(tokens, ",", &saved_ptr);
                        while (token != NULL) {
                                if (!strcmp(token, "perf_event")) {
-                                        found = 1;
+                                        strcpy(path_v1, mountpoint);
                                        break;
                                }
                                token = strtok_r(NULL, ",", &saved_ptr);
                        }
                }
-                if (found)
+                if (!path_v2[0] && !strcmp(type, "cgroup2"))
+                        strcpy(path_v2, mountpoint);
+                if (path_v1[0] && path_v2[0])
                        break;
        }
        fclose(fp);
-        if (!found)
+        if (path_v1[0])
+                path = path_v1;
+        else if (path_v2[0])
+                path = path_v2;
+        else
                return -1;
-        if (strlen(mountpoint) < maxlen) {
+        if (strlen(path) < maxlen) {
-                strcpy(buf, mountpoint);
+                strcpy(buf, path);
                return 0;
        }
        return -1;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3d906dbbef74..0c7d5a4975cd 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -386,8 +386,10 @@ static int perf_buildid_config(const char *var, const char *value)
        if (!strcmp(var, "buildid.dir")) {
                const char *dir = perf_config_dirname(var, value);
-                if (!dir)
+                if (!dir) {
+                        pr_err("Invalid buildid directory!\n");
                        return -1;
+                }
                strncpy(buildid_dir, dir, MAXPATHLEN-1);
                buildid_dir[MAXPATHLEN-1] = '\0';
        }
@@ -405,10 +407,9 @@ static int perf_default_core_config(const char *var __maybe_unused,
 static int perf_ui_config(const char *var, const char *value)
 {
        /* Add other config variables here. */
-        if (!strcmp(var, "ui.show-headers")) {
+        if (!strcmp(var, "ui.show-headers"))
                symbol_conf.show_hist_headers = perf_config_bool(var, value);
-                return 0;
-        }
        return 0;
 }
@@ -646,8 +647,13 @@ static int perf_config_set__init(struct perf_config_set *set)
                        goto out;
                }
-                if (stat(user_config, &st) < 0)
+                if (stat(user_config, &st) < 0) {
+                        if (errno == ENOENT)
+                                ret = 0;
                        goto out_free;
+                }
+                ret = 0;
                if (st.st_uid && (st.st_uid != geteuid())) {
                        warning("File %s not owned by current user or root, "
@@ -655,11 +661,8 @@ static int perf_config_set__init(struct perf_config_set *set)
                        goto out_free;
                }
-                if (!st.st_size)
+                if (st.st_size)
-                        goto out_free;
+                        ret = perf_config_from_file(collect_config, user_config, set);
-                ret = perf_config_from_file(collect_config, user_config, set);
 out_free:
                free(user_config);
        }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 2c0b52264a46..8c7504939113 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -9,6 +9,7 @@
 #include "asm/bug.h"
 static int max_cpu_num;
+static int max_present_cpu_num;
 static int max_node_num;
 static int *cpunode_map;
@@ -442,6 +443,7 @@ static void set_max_cpu_num(void)
        /* set up default */
        max_cpu_num = 4096;
+        max_present_cpu_num = 4096;
        mnt = sysfs__mountpoint();
        if (!mnt)
@@ -455,6 +457,17 @@ static void set_max_cpu_num(void)
        }
        ret = get_max_num(path, &max_cpu_num);
+        if (ret)
+                goto out;
+        /* get the highest present cpu number for a sparse allocation */
+        ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
+        if (ret == PATH_MAX) {
+                pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                goto out;
+        }
+        ret = get_max_num(path, &max_present_cpu_num);
 out:
        if (ret)
@@ -505,6 +518,15 @@ int cpu__max_cpu(void)
        return max_cpu_num;
 }
+int cpu__max_present_cpu(void)
+{
+        if (unlikely(!max_present_cpu_num))
+                set_max_cpu_num();
+        return max_present_cpu_num;
+}
 int cpu__get_node(int cpu)
 {
        if (unlikely(cpunode_map == NULL)) {
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 06bd689f5989..1a0549af8f5c 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -62,6 +62,7 @@ int cpu__setup_cpunode_map(void);
 int cpu__max_node(void);
 int cpu__max_cpu(void);
+int cpu__max_present_cpu(void);
 int cpu__get_node(int cpu);
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7123f4de32cc..4e6cbc99f08e 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1473,7 +1473,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                },
        };
        struct ctf_writer *cw = &c.writer;
-        int err = -1;
+        int err;
        if (opts->all) {
                c.tool.comm = process_comm_event;
@@ -1481,12 +1481,15 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                c.tool.fork = process_fork_event;
        }
-        perf_config(convert__config, &c);
+        err = perf_config(convert__config, &c);
+        if (err)
+                return err;
        /* CTF writer */
        if (ctf_writer__init(cw, path))
                return -1;
+        err = -1;
        /* perf.data session */
        session = perf_session__new(&file, 0, &c.tool);
        if (!session)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c1838b643108..03eb81f30d0d 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -203,11 +203,28 @@ int perf_debug_option(const char *str)
                v = (v < 0) || (v > 10) ? 0 : v;
        }
+        if (quiet)
+                v = -1;
        *var->ptr = v;
        free(s);
        return 0;
 }
+int perf_quiet_option(void)
+{
+        struct debug_variable *var = &debug_variables[0];
+        /* disable all debug messages */
+        while (var->name) {
+                *var->ptr = -1;
+                var++;
+        }
+        quiet = true;
+        return 0;
+}
 #define DEBUG_WRAPPER(__n, __l)                         \
 static int pr_ ## __n ## _wrapper(const char *fmt, ...) \
 {                                                       \
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index d242adc3d5a2..98832f5531d3 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -54,5 +54,6 @@ int veprintf(int level, int var, const char *fmt, va_list args);
 int perf_debug_option(const char *str);
 void perf_debug_setup(void);
+int perf_quiet_option(void);
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d2c6cdd9d42b..d38b62a700ca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -9,6 +9,13 @@
 #include "debug.h"
 #include "vdso.h"
+static const char * const debuglink_paths[] = {
+        "%.0s%s",
+        "%s/%s",
+        "%s/.debug/%s",
+        "/usr/lib/debug%s/%s"
+};
 char dso__symtab_origin(const struct dso *dso)
 {
        static const char origin[] = {
@@ -44,24 +51,43 @@ int dso__read_binary_type_filename(const struct dso *dso,
        size_t len;
        switch (type) {
-        case DSO_BINARY_TYPE__DEBUGLINK: {
+        case DSO_BINARY_TYPE__DEBUGLINK:
-                char *debuglink;
+        {
+                const char *last_slash;
+                char dso_dir[PATH_MAX];
+                char symfile[PATH_MAX];
+                unsigned int i;
                len = __symbol__join_symfs(filename, size, dso->long_name);
-                debuglink = filename + len;
+                last_slash = filename + len;
-                while (debuglink != filename && *debuglink != '/')
+                while (last_slash != filename && *last_slash != '/')
-                        debuglink--;
+                        last_slash--;
-                if (*debuglink == '/')
-                        debuglink++;
-                ret = -1;
+                strncpy(dso_dir, filename, last_slash - filename);
-                if (!is_regular_file(filename))
+                dso_dir[last_slash-filename] = '\0';
+                if (!is_regular_file(filename)) {
+                        ret = -1;
+                        break;
+                }
+                ret = filename__read_debuglink(filename, symfile, PATH_MAX);
+                if (ret)
                        break;
-                ret = filename__read_debuglink(filename, debuglink,
+                /* Check predefined locations where debug file might reside */
-                                               size - (debuglink - filename));
+                ret = -1;
+                for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
+                        snprintf(filename, size,
+                                        debuglink_paths[i], dso_dir, symfile);
+                        if (is_regular_file(filename)) {
+                                ret = 0;
+                                break;
+                        }
                }
                break;
+        }
        case DSO_BINARY_TYPE__BUILD_ID_CACHE:
                if (dso__build_id_filename(dso, filename, size) == NULL)
                        ret = -1;
@@ -925,7 +951,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root,
                if (rc == 0) {
                        /*
                         * In case the new DSO is a duplicate of an existing
-                         * one, print an one-time warning & put the new entry
+                         * one, print a one-time warning & put the new entry
                         * at the end of the list of duplicates.
                         */
                        if (!dso || (dso == this))
@@ -1032,7 +1058,7 @@ int dso__name_len(const struct dso *dso)
 {
        if (!dso)
                return strlen("[unknown]");
-        if (verbose)
+        if (verbose > 0)
                return dso->long_name_len;
        return dso->short_name_len;
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index bb964e86b09d..075fc77286bf 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -66,7 +66,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
                return 0;
        if (env->nr_cpus_avail == 0)
-                env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+                env->nr_cpus_avail = cpu__max_present_cpu();
        nr_cpus = env->nr_cpus_avail;
        if (nr_cpus == -1)
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8ab0d7da956b..4ea7ce72ed9c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,5 +1,5 @@
 #include <linux/types.h>
-#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
 #include "event.h"
 #include "debug.h"
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d92e02006fb8..b601f2814a30 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1184,7 +1184,7 @@ unsigned long perf_event_mlock_kb_in_pages(void)
        return pages;
 }
-static size_t perf_evlist__mmap_size(unsigned long pages)
+size_t perf_evlist__mmap_size(unsigned long pages)
 {
        if (pages == UINT_MAX)
                pages = perf_event_mlock_kb_in_pages();
@@ -1224,12 +1224,16 @@ static long parse_pages_arg(const char *str, unsigned long min,
        if (pages == 0 && min == 0) {
                /* leave number of pages at 0 */
        } else if (!is_power_of_2(pages)) {
+                char buf[100];
                /* round pages up to next power of 2 */
                pages = roundup_pow_of_two(pages);
                if (!pages)
                        return -EINVAL;
-                pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
-                        pages * page_size, pages);
+                unit_number__scnprintf(buf, sizeof(buf), pages * page_size);
+                pr_info("rounding mmap pages size to %s (%lu pages)\n",
+                        buf, pages);
        }
        if (pages > max)
@@ -1797,7 +1801,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
                 */
                ret = write(evlist->workload.cork_fd, &bf, 1);
                if (ret < 0)
-                        perror("enable to write to pipe");
+                        perror("unable to write to pipe");
                close(evlist->workload.cork_fd);
                return ret;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4fd034f22d2f..389b9ccdf8c7 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -218,6 +218,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
                      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
+size_t perf_evlist__mmap_size(unsigned long pages);
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 04e536ae4d88..ac59710b79e0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1448,8 +1448,8 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
        return true;
 }
-static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-                              struct thread_map *threads)
+                     struct thread_map *threads)
 {
        int cpu, thread, nthreads;
        unsigned long flags = PERF_FLAG_FD_CLOEXEC;
@@ -1459,6 +1459,30 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
        if (perf_missing_features.write_backward && evsel->attr.write_backward)
                return -EINVAL;
+        if (cpus == NULL) {
+                static struct cpu_map *empty_cpu_map;
+                if (empty_cpu_map == NULL) {
+                        empty_cpu_map = cpu_map__dummy_new();
+                        if (empty_cpu_map == NULL)
+                                return -ENOMEM;
+                }
+                cpus = empty_cpu_map;
+        }
+        if (threads == NULL) {
+                static struct thread_map *empty_thread_map;
+                if (empty_thread_map == NULL) {
+                        empty_thread_map = thread_map__new_by_tid(-1);
+                        if (empty_thread_map == NULL)
+                                return -ENOMEM;
+                }
+                threads = empty_thread_map;
+        }
        if (evsel->system_wide)
                nthreads = 1;
        else
@@ -1655,46 +1679,16 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
        perf_evsel__free_fd(evsel);
 }
-static struct {
-        struct cpu_map map;
-        int cpus[1];
-} empty_cpu_map = {
-        .map.nr = 1,
-        .cpus   = { -1, },
-};
-static struct {
-        struct thread_map map;
-        int threads[1];
-} empty_thread_map = {
-        .map.nr  = 1,
-        .threads = { -1, },
-};
-int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-                     struct thread_map *threads)
-{
-        if (cpus == NULL) {
-                /* Work around old compiler warnings about strict aliasing */
-                cpus = &empty_cpu_map.map;
-        }
-        if (threads == NULL)
-                threads = &empty_thread_map.map;
-        return __perf_evsel__open(evsel, cpus, threads);
-}
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
                             struct cpu_map *cpus)
 {
-        return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+        return perf_evsel__open(evsel, cpus, NULL);
 }
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
                                struct thread_map *threads)
 {
-        return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+        return perf_evsel__open(evsel, NULL, threads);
 }
 static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
@@ -2469,7 +2463,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                 "  -1: Allow use of (almost) all events by all users\n"
                 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
                 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
-                 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
+                 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
+                 "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
+                 "      kernel.perf_event_paranoid = -1\n" ,
                                 target->system_wide ? "system-wide " : "",
                                 perf_event_paranoid());
        case ENOENT:
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 6b2925542c0a..4ef5184819a0 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -168,7 +168,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                        if (symbol_conf.bt_stop_list &&
                            node->sym &&
-                            node->sym->name &&
                            strlist__has_entry(symbol_conf.bt_stop_list,
                                               node->sym->name)) {
                                break;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d89c9c7ef4e5..05714d548584 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -41,6 +41,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 #define PERF_MAGIC      __perf_magic2
+const char perf_version_string[] = PERF_VERSION;
 struct perf_file_attr {
        struct perf_event_attr  attr;
        struct perf_file_section        ids;
@@ -293,11 +295,7 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
        u32 nrc, nra;
        int ret;
-        nr = sysconf(_SC_NPROCESSORS_CONF);
+        nrc = cpu__max_present_cpu();
-        if (nr < 0)
-                return -1;
-        nrc = (u32)(nr & UINT_MAX);
        nr = sysconf(_SC_NPROCESSORS_ONLN);
        if (nr < 0)
@@ -503,24 +501,29 @@ static void free_cpu_topo(struct cpu_topo *tp)
 static struct cpu_topo *build_cpu_topology(void)
 {
-        struct cpu_topo *tp;
+        struct cpu_topo *tp = NULL;
        void *addr;
        u32 nr, i;
        size_t sz;
        long ncpus;
        int ret = -1;
+        struct cpu_map *map;
-        ncpus = sysconf(_SC_NPROCESSORS_CONF);
+        ncpus = cpu__max_present_cpu();
-        if (ncpus < 0)
+        /* build online CPU map */
+        map = cpu_map__new(NULL);
+        if (map == NULL) {
+                pr_debug("failed to get system cpumap\n");
                return NULL;
+        }
        nr = (u32)(ncpus & UINT_MAX);
        sz = nr * sizeof(char *);
        addr = calloc(1, sizeof(*tp) + 2 * sz);
        if (!addr)
-                return NULL;
+                goto out_free;
        tp = addr;
        tp->cpu_nr = nr;
@@ -530,10 +533,16 @@ static struct cpu_topo *build_cpu_topology(void)
        tp->thread_siblings = addr;
        for (i = 0; i < nr; i++) {
+                if (!cpu_map__has(map, i))
+                        continue;
                ret = build_cpu_topo(tp, i);
                if (ret < 0)
                        break;
        }
+out_free:
+        cpu_map__put(map);
        if (ret) {
                free_cpu_topo(tp);
                tp = NULL;
@@ -1124,7 +1133,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
        int nr, i;
        char *str;
-        int cpu_nr = ph->env.nr_cpus_online;
+        int cpu_nr = ph->env.nr_cpus_avail;
        nr = ph->env.nr_sibling_cores;
        str = ph->env.sibling_cores;
@@ -1779,7 +1788,7 @@ static int process_cpu_topology(struct perf_file_section *section,
        u32 nr, i;
        char *str;
        struct strbuf sb;
-        int cpu_nr = ph->env.nr_cpus_online;
+        int cpu_nr = ph->env.nr_cpus_avail;
        u64 size = 0;
        ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
@@ -1860,7 +1869,7 @@ static int process_cpu_topology(struct perf_file_section *section,
                if (ph->needs_swap)
                        nr = bswap_32(nr);
-                if (nr > (u32)cpu_nr) {
+                if (nr != (u32)-1 && nr > (u32)cpu_nr) {
                        pr_debug("socket_id number is too big."
                                 "You may need to upgrade the perf tool.\n");
                        goto free_cpu;
@@ -2801,8 +2810,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
        }
        event = pevent_find_event(pevent, evsel->attr.config);
-        if (event == NULL)
+        if (event == NULL) {
+                pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
                return -1;
+        }
        if (!evsel->name) {
                snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
@@ -3201,6 +3212,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
        case PERF_EVENT_UPDATE__SCALE:
                ev_scale = (struct event_update_event_scale *) ev->data;
                evsel->scale = ev_scale->scale;
+                break;
        case PERF_EVENT_UPDATE__CPUS:
                ev_cpus = (struct event_update_event_cpus *) ev->data;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 7d1b7d33e644..eaf72a938fb4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -69,7 +69,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
         */
        if (h->ms.sym) {
                symlen = h->ms.sym->namelen + 4;
-                if (verbose)
+                if (verbose > 0)
                        symlen += BITS_PER_LONG / 4 + 2 + 3;
                hists__new_col_len(hists, HISTC_SYMBOL, symlen);
        } else {
@@ -93,7 +93,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
        if (h->branch_info) {
                if (h->branch_info->from.sym) {
                        symlen = (int)h->branch_info->from.sym->namelen + 4;
-                        if (verbose)
+                        if (verbose > 0)
                                symlen += BITS_PER_LONG / 4 + 2 + 3;
                        hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
@@ -107,7 +107,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                if (h->branch_info->to.sym) {
                        symlen = (int)h->branch_info->to.sym->namelen + 4;
-                        if (verbose)
+                        if (verbose > 0)
                                symlen += BITS_PER_LONG / 4 + 2 + 3;
                        hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
@@ -2446,8 +2446,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
                symbol_conf.filter_relative = true;
        else if (!strcmp(arg, "absolute"))
                symbol_conf.filter_relative = false;
-        else
+        else {
+                pr_debug("Invalud percentage: %s\n", arg);
                return -1;
+        }
        return 0;
 }
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 9b742ea8bfe8..7aca5d6d7e1f 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in
        $(call rule_mkdir)
        $(call if_changed_dep,cc_o_c)
-CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
+CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
+ifneq ($(CC), clang)
+  CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
+endif
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e4e7dc781d21..7cf7f7aca4d2 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include <stdint.h>
 #include <inttypes.h>
+#include <linux/compiler.h>
 #include "../cache.h"
 #include "../util.h"
@@ -1746,6 +1747,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
                switch (decoder->packet.type) {
                case INTEL_PT_TIP_PGD:
                        decoder->continuous_period = false;
+                        __fallthrough;
                case INTEL_PT_TIP_PGE:
                case INTEL_PT_TIP:
                        intel_pt_log("ERROR: Unexpected packet\n");
@@ -1799,6 +1801,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
                        decoder->pge = false;
                        decoder->continuous_period = false;
                        intel_pt_clear_tx_flags(decoder);
+                        __fallthrough;
                case INTEL_PT_TNT:
                        decoder->have_tma = false;
                        intel_pt_log("ERROR: Unexpected packet\n");
@@ -1839,6 +1843,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
                switch (decoder->packet.type) {
                case INTEL_PT_TIP_PGD:
                        decoder->continuous_period = false;
+                        __fallthrough;
                case INTEL_PT_TIP_PGE:
                case INTEL_PT_TIP:
                        decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4f7b32020487..7528ae4f7e28 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/compiler.h>
 #include "intel-pt-pkt-decoder.h"
@@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
        case INTEL_PT_FUP:
                if (!(packet->count))
                        return snprintf(buf, buf_len, "%s no ip", name);
+                __fallthrough;
        case INTEL_PT_CYC:
        case INTEL_PT_VMCS:
        case INTEL_PT_MTC:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 85d5eeb66c75..da20cd5612e9 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2159,7 +2159,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
        addr_filters__init(&pt->filts);
-        perf_config(intel_pt_perf_config, pt);
+        err = perf_config(intel_pt_perf_config, pt);
+        if (err)
+                goto err_free;
        err = auxtrace_queues__init(&pt->queues);
        if (err)
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b23ff44cf214..824356488ce6 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -48,8 +48,10 @@ int perf_llvm_config(const char *var, const char *value)
                llvm_param.kbuild_opts = strdup(value);
        else if (!strcmp(var, "dump-obj"))
                llvm_param.dump_obj = !!perf_config_bool(var, value);
-        else
+        else {
+                pr_debug("Invalid LLVM config option: %s\n", value);
                return -1;
+        }
        llvm_param.user_set_param = true;
        return 0;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef54581..71c9720d4973 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -87,6 +87,25 @@ out_delete:
        return NULL;
 }
+struct machine *machine__new_kallsyms(void)
+{
+        struct machine *machine = machine__new_host();
+        /*
+         * FIXME:
+         * 1) MAP__FUNCTION will go away when we stop loading separate maps for
+         *    functions and data objects.
+         * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+         *    ask for not using the kcore parsing code, once this one is fixed
+         *    to create a map per module.
+         */
+        if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+                machine__delete(machine);
+                machine = NULL;
+        }
+        return machine;
+}
 static void dsos__purge(struct dsos *dsos)
 {
        struct dso *pos, *n;
@@ -763,7 +782,7 @@ static u64 machine__get_running_kernel_start(struct machine *machine,
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-        enum map_type type;
+        int type;
        u64 start = machine__get_running_kernel_start(machine, NULL);
        /* In case of renewal the kernel map, destroy previous one */
@@ -794,7 +813,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 void machine__destroy_kernel_maps(struct machine *machine)
 {
-        enum map_type type;
+        int type;
        for (type = 0; type < MAP__NR_TYPES; ++type) {
                struct kmap *kmap;
@@ -1546,7 +1565,7 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-        if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
+        if (!regexec(regex, sym->name, 0, NULL, 0))
                return 1;
        return 0;
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e56109..a28305029711 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -129,6 +129,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 struct machine *machine__new_host(void);
+struct machine *machine__new_kallsyms(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4f9a71c63026..0a943e7b1ea7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -387,10 +387,10 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 {
        const char *dsoname = "[unknown]";
-        if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+        if (map && map->dso) {
                if (symbol_conf.show_kernel_path && map->dso->long_name)
                        dsoname = map->dso->long_name;
-                else if (map->dso->name)
+                else
                        dsoname = map->dso->name;
        }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3c876b8ba4de..67a8aebc67ab 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -211,6 +211,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
                                closedir(evt_dir);
                                closedir(sys_dir);
                                path = zalloc(sizeof(*path));
+                                if (!path)
+                                        return NULL;
                                path->system = malloc(MAX_EVENT_LENGTH);
                                if (!path->system) {
                                        free(path);
@@ -252,8 +254,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name)
        if (path->system == NULL || path->name == NULL) {
                zfree(&path->system);
                zfree(&path->name);
-                free(path);
+                zfree(&path);
-                path = NULL;
        }
        return path;
@@ -310,10 +311,11 @@ __add_event(struct list_head *list, int *idx,
        event_attr_init(attr);
-        evsel = perf_evsel__new_idx(attr, (*idx)++);
+        evsel = perf_evsel__new_idx(attr, *idx);
        if (!evsel)
                return NULL;
+        (*idx)++;
        evsel->cpus     = cpu_map__get(cpus);
        evsel->own_cpus = cpu_map__get(cpus);
@@ -1477,10 +1479,9 @@ static void perf_pmu__parse_cleanup(void)
                for (i = 0; i < perf_pmu_events_list_num; i++) {
                        p = perf_pmu_events_list + i;
-                        free(p->symbol);
+                        zfree(&p->symbol);
                }
-                free(perf_pmu_events_list);
+                zfree(&perf_pmu_events_list);
-                perf_pmu_events_list = NULL;
                perf_pmu_events_list_num = 0;
        }
 }
@@ -1504,35 +1505,41 @@ static void perf_pmu__parse_init(void)
        struct perf_pmu_alias *alias;
        int len = 0;
-        pmu = perf_pmu__find("cpu");
+        pmu = NULL;
-        if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+        while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+                list_for_each_entry(alias, &pmu->aliases, list) {
+                        if (strchr(alias->name, '-'))
+                                len++;
+                        len++;
+                }
+        }
+        if (len == 0) {
                perf_pmu_events_list_num = -1;
                return;
        }
-        list_for_each_entry(alias, &pmu->aliases, list) {
-                if (strchr(alias->name, '-'))
-                        len++;
-                len++;
-        }
        perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
        if (!perf_pmu_events_list)
                return;
        perf_pmu_events_list_num = len;
        len = 0;
-        list_for_each_entry(alias, &pmu->aliases, list) {
+        pmu = NULL;
-                struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+        while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-                char *tmp = strchr(alias->name, '-');
+                list_for_each_entry(alias, &pmu->aliases, list) {
+                        struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
-                if (tmp != NULL) {
+                        char *tmp = strchr(alias->name, '-');
-                        SET_SYMBOL(strndup(alias->name, tmp - alias->name),
-                                        PMU_EVENT_SYMBOL_PREFIX);
+                        if (tmp != NULL) {
-                        p++;
+                                SET_SYMBOL(strndup(alias->name, tmp - alias->name),
-                        SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+                                                PMU_EVENT_SYMBOL_PREFIX);
-                        len += 2;
+                                p++;
-                } else {
+                                SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
-                        SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+                                len += 2;
-                        len++;
+                        } else {
+                                SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+                                len++;
+                        }
                }
        }
        qsort(perf_pmu_events_list, len,
@@ -1563,7 +1570,7 @@ perf_pmu__parse_check(const char *name)
        r = bsearch(&p, perf_pmu_events_list,
                        (size_t) perf_pmu_events_list_num,
                        sizeof(struct perf_pmu_event_symbol), comp_pmu);
-        free(p.symbol);
+        zfree(&p.symbol);
        return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
@@ -1710,8 +1717,8 @@ static void parse_events_print_error(struct parse_events_error *err,
                fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
                if (err->help)
                        fprintf(stderr, "\n%s\n", err->help);
-                free(err->str);
+                zfree(&err->str);
-                free(err->help);
+                zfree(&err->help);
        }
        fprintf(stderr, "Run 'perf list' for a list of valid events\n");
@@ -2013,17 +2020,14 @@ static bool is_event_supported(u8 type, unsigned config)
                .config = config,
                .disabled = 1,
        };
-        struct {
+        struct thread_map *tmap = thread_map__new_by_tid(0);
-                struct thread_map map;
-                int threads[1];
+        if (tmap == NULL)
-        } tmap = {
+                return false;
-                .map.nr  = 1,
-                .threads = { 0 },
-        };
        evsel = perf_evsel__new(&attr);
        if (evsel) {
-                open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+                open_return = perf_evsel__open(evsel, NULL, tmap);
                ret = open_return >= 0;
                if (open_return == -EACCES) {
@@ -2035,7 +2039,7 @@ static bool is_event_supported(u8 type, unsigned config)
                         *
                         */
                        evsel->attr.exclude_kernel = 1;
-                        ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+                        ret = perf_evsel__open(evsel, NULL, tmap) >= 0;
                }
                perf_evsel__delete(evsel);
        }
@@ -2314,24 +2318,20 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
        return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
 }
-static int new_term(struct parse_events_term **_term, int type_val,
+static int new_term(struct parse_events_term **_term,
-                    int type_term, char *config,
+                    struct parse_events_term *temp,
-                    char *str, u64 num, int err_term, int err_val)
+                    char *str, u64 num)
 {
        struct parse_events_term *term;
-        term = zalloc(sizeof(*term));
+        term = malloc(sizeof(*term));
        if (!term)
                return -ENOMEM;
+        *term = *temp;
        INIT_LIST_HEAD(&term->list);
-        term->type_val  = type_val;
-        term->type_term = type_term;
-        term->config = config;
-        term->err_term = err_term;
-        term->err_val  = err_val;
-        switch (type_val) {
+        switch (term->type_val) {
        case PARSE_EVENTS__TERM_TYPE_NUM:
                term->val.num = num;
                break;
@@ -2349,15 +2349,22 @@ static int new_term(struct parse_events_term **_term, int type_val,
 int parse_events_term__num(struct parse_events_term **term,
                           int type_term, char *config, u64 num,
+                           bool no_value,
                           void *loc_term_, void *loc_val_)
 {
        YYLTYPE *loc_term = loc_term_;
        YYLTYPE *loc_val = loc_val_;
-        return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
+        struct parse_events_term temp = {
-                        config, NULL, num,
+                .type_val  = PARSE_EVENTS__TERM_TYPE_NUM,
-                        loc_term ? loc_term->first_column : 0,
+                .type_term = type_term,
-                        loc_val ? loc_val->first_column : 0);
+                .config    = config,
+                .no_value  = no_value,
+                .err_term  = loc_term ? loc_term->first_column : 0,
+                .err_val   = loc_val  ? loc_val->first_column  : 0,
+        };
+        return new_term(term, &temp, NULL, num);
 }
 int parse_events_term__str(struct parse_events_term **term,
@@ -2367,37 +2374,45 @@ int parse_events_term__str(struct parse_events_term **term,
        YYLTYPE *loc_term = loc_term_;
        YYLTYPE *loc_val = loc_val_;
-        return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
+        struct parse_events_term temp = {
-                        config, str, 0,
+                .type_val  = PARSE_EVENTS__TERM_TYPE_STR,
-                        loc_term ? loc_term->first_column : 0,
+                .type_term = type_term,
-                        loc_val ? loc_val->first_column : 0);
+                .config    = config,
+                .err_term  = loc_term ? loc_term->first_column : 0,
+                .err_val   = loc_val  ? loc_val->first_column  : 0,
+        };
+        return new_term(term, &temp, str, 0);
 }
 int parse_events_term__sym_hw(struct parse_events_term **term,
                              char *config, unsigned idx)
 {
        struct event_symbol *sym;
+        struct parse_events_term temp = {
+                .type_val  = PARSE_EVENTS__TERM_TYPE_STR,
+                .type_term = PARSE_EVENTS__TERM_TYPE_USER,
+                .config    = config ?: (char *) "event",
+        };
        BUG_ON(idx >= PERF_COUNT_HW_MAX);
        sym = &event_symbols_hw[idx];
-        if (config)
+        return new_term(term, &temp, (char *) sym->symbol, 0);
-                return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-                                PARSE_EVENTS__TERM_TYPE_USER, config,
-                                (char *) sym->symbol, 0, 0, 0);
-        else
-                return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
-                                PARSE_EVENTS__TERM_TYPE_USER,
-                                (char *) "event", (char *) sym->symbol,
-                                0, 0, 0);
 }
 int parse_events_term__clone(struct parse_events_term **new,
                             struct parse_events_term *term)
 {
-        return new_term(new, term->type_val, term->type_term, term->config,
+        struct parse_events_term temp = {
-                        term->val.str, term->val.num,
+                .type_val  = term->type_val,
-                        term->err_term, term->err_val);
+                .type_term = term->type_term,
+                .config    = term->config,
+                .err_term  = term->err_term,
+                .err_val   = term->err_val,
+        };
+        return new_term(new, &temp, term->val.str, term->val.num);
 }
 void parse_events_terms__purge(struct list_head *terms)
@@ -2406,7 +2421,7 @@ void parse_events_terms__purge(struct list_head *terms)
        list_for_each_entry_safe(term, h, terms, list) {
                if (term->array.nr_ranges)
-                        free(term->array.ranges);
+                        zfree(&term->array.ranges);
                list_del_init(&term->list);
                free(term);
        }
@@ -2422,7 +2437,7 @@ void parse_events_terms__delete(struct list_head *terms)
 void parse_events__clear_array(struct parse_events_array *a)
 {
-        free(a->ranges);
+        zfree(&a->ranges);
 }
 void parse_events_evlist_error(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index da246a3ddb69..1af6a267c21b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -94,6 +94,7 @@ struct parse_events_term {
        int type_term;
        struct list_head list;
        bool used;
+        bool no_value;
        /* error string indexes for within parsed string */
        int err_term;
@@ -122,6 +123,7 @@ void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
                           int type_term, char *config, u64 num,
+                           bool novalue,
                           void *loc_term, void *loc_val);
 int parse_events_term__str(struct parse_events_term **term,
                           int type_term, char *config, char *str,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 879115f93edc..30f018ea1370 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -12,9 +12,13 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include "util.h"
+#include "pmu.h"
+#include "debug.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
+void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg);
 #define ABORT_ON(val) \
 do { \
        if (val) \
@@ -236,15 +240,34 @@ PE_KERNEL_PMU_EVENT sep_dc
        struct list_head *head;
        struct parse_events_term *term;
        struct list_head *list;
+        struct perf_pmu *pmu = NULL;
+        int ok = 0;
-        ALLOC_LIST(head);
+        /* Add it for all PMUs that support the alias */
-        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, 1, &@1, NULL));
-        list_add_tail(&term->list, head);
        ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
+        while ((pmu = perf_pmu__scan(pmu)) != NULL) {
-        parse_events_terms__delete(head);
+                struct perf_pmu_alias *alias;
+                list_for_each_entry(alias, &pmu->aliases, list) {
+                        if (!strcasecmp(alias->name, $1)) {
+                                ALLOC_LIST(head);
+                                ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+                                        $1, 1, false, &@1, NULL));
+                                list_add_tail(&term->list, head);
+                                if (!parse_events_add_pmu(data, list,
+                                                  pmu->name, head)) {
+                                        pr_debug("%s -> %s/%s/\n", $1,
+                                                 pmu->name, alias->str);
+                                        ok++;
+                                }
+                                parse_events_terms__delete(head);
+                        }
+                }
+        }
+        if (!ok)
+                YYABORT;
        $$ = list;
 }
 |
@@ -259,7 +282,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
        ALLOC_LIST(head);
        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        &pmu_name, 1, &@1, NULL));
+                                        &pmu_name, 1, false, &@1, NULL));
        list_add_tail(&term->list, head);
        ALLOC_LIST(list);
@@ -525,7 +548,7 @@ PE_NAME '=' PE_VALUE
        struct parse_events_term *term;
        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, $3, &@1, &@3));
+                                        $1, $3, false, &@1, &@3));
        $$ = term;
 }
 |
@@ -543,7 +566,7 @@ PE_NAME
        struct parse_events_term *term;
        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, 1, &@1, NULL));
+                                        $1, 1, true, &@1, NULL));
        $$ = term;
 }
 |
@@ -568,7 +591,7 @@ PE_TERM '=' PE_VALUE
 {
        struct parse_events_term *term;
-        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
+        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
        $$ = term;
 }
 |
@@ -576,7 +599,7 @@ PE_TERM
 {
        struct parse_events_term *term;
-        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
+        ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
        $$ = term;
 }
 |
@@ -597,7 +620,7 @@ PE_NAME array '=' PE_VALUE
        struct parse_events_term *term;
        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-                                        $1, $4, &@1, &@4));
+                                        $1, $4, false, &@1, &@4));
        term->array = $2;
        $$ = term;
 }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index dc6ccaa4e927..12f84dd2ac5d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -94,32 +94,10 @@ static int pmu_format(const char *name, struct list_head *format)
        return 0;
 }
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+static int convert_scale(const char *scale, char **end, double *sval)
 {
-        struct stat st;
-        ssize_t sret;
-        char scale[128];
-        int fd, ret = -1;
-        char path[PATH_MAX];
        char *lc;
+        int ret = 0;
-        snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
-        fd = open(path, O_RDONLY);
-        if (fd == -1)
-                return -1;
-        if (fstat(fd, &st) < 0)
-                goto error;
-        sret = read(fd, scale, sizeof(scale)-1);
-        if (sret < 0)
-                goto error;
-        if (scale[sret - 1] == '\n')
-                scale[sret - 1] = '\0';
-        else
-                scale[sret] = '\0';
        /*
         * save current locale
@@ -134,7 +112,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
        lc = strdup(lc);
        if (!lc) {
                ret = -ENOMEM;
-                goto error;
+                goto out;
        }
        /*
@@ -144,14 +122,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
         */
        setlocale(LC_NUMERIC, "C");
-        alias->scale = strtod(scale, NULL);
+        *sval = strtod(scale, end);
+out:
        /* restore locale */
        setlocale(LC_NUMERIC, lc);
        free(lc);
+        return ret;
+}
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+        struct stat st;
+        ssize_t sret;
+        char scale[128];
+        int fd, ret = -1;
+        char path[PATH_MAX];
-        ret = 0;
+        snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                return -1;
+        if (fstat(fd, &st) < 0)
+                goto error;
+        sret = read(fd, scale, sizeof(scale)-1);
+        if (sret < 0)
+                goto error;
+        if (scale[sret - 1] == '\n')
+                scale[sret - 1] = '\0';
+        else
+                scale[sret] = '\0';
+        ret = convert_scale(scale, NULL, &alias->scale);
 error:
        close(fd);
        return ret;
@@ -223,11 +229,13 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 }
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
-                                 char *desc, char *val, char *long_desc,
+                                 char *desc, char *val,
-                                 char *topic)
+                                 char *long_desc, char *topic,
+                                 char *unit, char *perpkg)
 {
        struct perf_pmu_alias *alias;
        int ret;
+        int num;
        alias = malloc(sizeof(*alias));
        if (!alias)
@@ -261,6 +269,13 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
        alias->long_desc = long_desc ? strdup(long_desc) :
                                desc ? strdup(desc) : NULL;
        alias->topic = topic ? strdup(topic) : NULL;
+        if (unit) {
+                if (convert_scale(unit, &unit, &alias->scale) < 0)
+                        return -1;
+                snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
+        }
+        alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
+        alias->str = strdup(val);
        list_add_tail(&alias->list, list);
@@ -278,7 +293,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
        buf[ret] = 0;
-        return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL);
+        return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
+                                     NULL);
 }
 static inline bool pmu_alias_info_file(char *name)
@@ -498,7 +514,7 @@ char * __weak get_cpuid_str(void)
 * to the current running CPU. Then, add all PMU events from that table
 * as aliases.
 */
-static void pmu_add_cpu_aliases(struct list_head *head)
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 {
        int i;
        struct pmu_events_map *map;
@@ -534,14 +550,21 @@ static void pmu_add_cpu_aliases(struct list_head *head)
         */
        i = 0;
        while (1) {
+                const char *pname;
                pe = &map->table[i++];
                if (!pe->name)
                        break;
+                pname = pe->pmu ? pe->pmu : "cpu";
+                if (strncmp(pname, name, strlen(pname)))
+                        continue;
                /* need type casts to override 'const' */
                __perf_pmu__new_alias(head, NULL, (char *)pe->name,
                                (char *)pe->desc, (char *)pe->event,
-                                (char *)pe->long_desc, (char *)pe->topic);
+                                (char *)pe->long_desc, (char *)pe->topic,
+                                (char *)pe->unit, (char *)pe->perpkg);
        }
 out:
@@ -569,15 +592,16 @@ static struct perf_pmu *pmu_lookup(const char *name)
        if (pmu_format(name, &format))
                return NULL;
-        if (pmu_aliases(name, &aliases))
+        /*
+         * Check the type first to avoid unnecessary work.
+         */
+        if (pmu_type(name, &type))
                return NULL;
-        if (!strcmp(name, "cpu"))
+        if (pmu_aliases(name, &aliases))
-                pmu_add_cpu_aliases(&aliases);
-        if (pmu_type(name, &type))
                return NULL;
+        pmu_add_cpu_aliases(&aliases, name);
        pmu = zalloc(sizeof(*pmu));
        if (!pmu)
                return NULL;
@@ -721,7 +745,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
                }
        }
-        if (verbose)
+        if (verbose > 0)
                printf("Required parameter '%s' not specified\n", term->config);
        return -1;
@@ -779,7 +803,7 @@ static int pmu_config_term(struct list_head *formats,
        format = pmu_find_format(formats, term->config);
        if (!format) {
-                if (verbose)
+                if (verbose > 0)
                        printf("Invalid event/parameter '%s'\n", term->config);
                if (err) {
                        char *pmu_term = pmu_formats_string(formats);
@@ -810,11 +834,20 @@ static int pmu_config_term(struct list_head *formats,
         * Either directly use a numeric term, or try to translate string terms
         * using event parameters.
         */
-        if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+        if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) {
+                if (term->no_value &&
+                    bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) {
+                        if (err) {
+                                err->idx = term->err_val;
+                                err->str = strdup("no value assigned for term");
+                        }
+                        return -EINVAL;
+                }
                val = term->val.num;
-        else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
+        } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
                if (strcmp(term->val.str, "?")) {
-                        if (verbose) {
+                        if (verbose > 0) {
                                pr_info("Invalid sysfs entry %s=%s\n",
                                                term->config, term->val.str);
                        }
@@ -921,12 +954,12 @@ static int check_info_data(struct perf_pmu_alias *alias,
         * define unit, scale and snapshot, fail
         * if there's more than one.
         */
-        if ((info->unit && alias->unit) ||
+        if ((info->unit && alias->unit[0]) ||
            (info->scale && alias->scale) ||
            (info->snapshot && alias->snapshot))
                return -EINVAL;
-        if (alias->unit)
+        if (alias->unit[0])
                info->unit = alias->unit;
        if (alias->scale)
@@ -1065,6 +1098,8 @@ struct sevent {
        char *name;
        char *desc;
        char *topic;
+        char *str;
+        char *pmu;
 };
 static int cmp_sevent(const void *a, const void *b)
@@ -1161,6 +1196,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
                        aliases[j].desc = long_desc ? alias->long_desc :
                                                alias->desc;
                        aliases[j].topic = alias->topic;
+                        aliases[j].str = alias->str;
+                        aliases[j].pmu = pmu->name;
                        j++;
                }
                if (pmu->selectable &&
@@ -1175,6 +1212,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
        len = j;
        qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
        for (j = 0; j < len; j++) {
+                /* Skip duplicates */
+                if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name))
+                        continue;
                if (name_only) {
                        printf("%s ", aliases[j].name);
                        continue;
@@ -1192,6 +1232,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
                        printf("%*s", 8, "[");
                        wordwrap(aliases[j].desc, 8, columns, 0);
                        printf("]\n");
+                        if (verbose > 0)
+                                printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
                } else
                        printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
                printed++;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 25712034c815..00852ddc7741 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -43,6 +43,7 @@ struct perf_pmu_alias {
        char *desc;
        char *long_desc;
        char *topic;
+        char *str;
        struct list_head terms; /* HEAD struct parse_events_term -> list */
        struct list_head list;  /* ELEM */
        char unit[UNIT_MAX_LEN+1];
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6a6f44dd594b..28fb62c32678 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -594,7 +594,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
        pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
                 tp->module ? : "kernel");
-        dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+        dinfo = debuginfo_cache__open(tp->module, verbose <= 0);
        if (dinfo)
                ret = debuginfo__find_probe_point(dinfo,
                                                 (unsigned long)addr, pp);
@@ -2061,7 +2061,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
                                          bool is_kprobe)
 {
        struct symbol *sym = NULL;
-        struct map *map;
+        struct map *map = NULL;
        u64 addr = tp->address;
        int ret = -ENOENT;
@@ -3023,20 +3023,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
        tev->nargs = pev->nargs;
        tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
-        if (!tev->args) {
+        if (!tev->args)
-                err = -ENOMEM;
                goto errout;
-        }
        for (i = 0; i < tev->nargs; i++)
                copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]);
        return 1;
 errout:
-        if (*tevs) {
+        clear_probe_trace_events(*tevs, 1);
-                clear_probe_trace_events(*tevs, 1);
+        *tevs = NULL;
-                *tevs = NULL;
-        }
        return err;
 }
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 0d9d6e0803b8..57cd268d4275 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -464,7 +464,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                /* Verify it is a data structure  */
                tag = dwarf_tag(&type);
                if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
-                        pr_warning("%s is not a data structure nor an union.\n",
+                        pr_warning("%s is not a data structure nor a union.\n",
                                   varname);
                        return -EINVAL;
                }
@@ -479,7 +479,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
        } else {
                /* Verify it is a data structure  */
                if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
-                        pr_warning("%s is not a data structure nor an union.\n",
+                        pr_warning("%s is not a data structure nor a union.\n",
                                   varname);
                        return -EINVAL;
                }
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 6516e220c247..82d28c67e0f3 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
 libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
 libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
 CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e55a132f69b7..dff043a29589 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -217,6 +217,7 @@ static void define_event_symbols(struct event_format *event,
                                       cur_field_name);
                break;
        case PRINT_HEX:
+        case PRINT_HEX_STR:
                define_event_symbols(event, ev_name, args->hex.field);
                define_event_symbols(event, ev_name, args->hex.size);
                break;
@@ -309,10 +310,10 @@ static SV *perl_process_callchain(struct perf_sample *sample,
                if (node->map) {
                        struct map *map = node->map;
                        const char *dsoname = "[unknown]";
-                        if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+                        if (map && map->dso) {
                                if (symbol_conf.show_kernel_path && map->dso->long_name)
                                        dsoname = map->dso->long_name;
-                                else if (map->dso->name)
+                                else
                                        dsoname = map->dso->name;
                        }
                        if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
@@ -350,8 +351,10 @@ static void perl_process_tracepoint(struct perf_sample *sample,
        if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                return;
-        if (!event)
+        if (!event) {
-                die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+                pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+                return;
+        }
        pid = raw_field_value(event, "common_pid", data);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 089438da1f7f..783326cfbaa6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -236,6 +236,7 @@ static void define_event_symbols(struct event_format *event,
                              cur_field_name);
                break;
        case PRINT_HEX:
+        case PRINT_HEX_STR:
                define_event_symbols(event, ev_name, args->hex.field);
                define_event_symbols(event, ev_name, args->hex.size);
                break;
@@ -368,10 +369,10 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
                if (node->map) {
                        struct map *map = node->map;
                        const char *dsoname = "[unknown]";
-                        if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+                        if (map && map->dso) {
                                if (symbol_conf.show_kernel_path && map->dso->long_name)
                                        dsoname = map->dso->long_name;
-                                else if (map->dso->name)
+                                else
                                        dsoname = map->dso->name;
                        }
                        pydict_set_item_string_decref(pyelem, "dso",
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201048a0..1dd617d116b5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -932,7 +932,7 @@ static void branch_stack__printf(struct perf_sample *sample)
                printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
                        i, e->from, e->to,
-                        e->flags.cycles,
+                        (unsigned short)e->flags.cycles,
                        e->flags.mispred ? "M" : " ",
                        e->flags.predicted ? "P" : " ",
                        e->flags.abort ? "A" : " ",
@@ -1191,7 +1191,7 @@ static int
        u64 sample_type = evsel->attr.sample_type;
        u64 read_format = evsel->attr.read_format;
-        /* Standard sample delievery. */
+        /* Standard sample delivery. */
        if (!(sample_type & PERF_SAMPLE_READ))
                return tool->sample(tool, event, sample, evsel, machine);
@@ -1901,7 +1901,7 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
                                     const char *symbol_name, u64 addr)
 {
        char *bracket;
-        enum map_type i;
+        int i;
        struct ref_reloc_sym *ref;
        ref = zalloc(sizeof(struct ref_reloc_sym));
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index c8680984d2d6..af415febbc46 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,8 +1,15 @@
 #!/usr/bin/python2
-from distutils.core import setup, Extension
 from os import getenv
+cc = getenv("CC")
+if cc == "clang":
+    from _sysconfigdata import build_time_vars
+    from re import sub
+    build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"])
+from distutils.core import setup, Extension
 from distutils.command.build_ext   import build_ext   as _build_ext
 from distutils.command.install_lib import install_lib as _install_lib
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index df622f4e301e..0ff622288d24 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -151,7 +151,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
        if (!dso_l || !dso_r)
                return cmp_null(dso_r, dso_l);
-        if (verbose) {
+        if (verbose > 0) {
                dso_name_l = dso_l->long_name;
                dso_name_r = dso_r->long_name;
        } else {
@@ -172,8 +172,8 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
                                     size_t size, unsigned int width)
 {
        if (map && map->dso) {
-                const char *dso_name = !verbose ? map->dso->short_name :
+                const char *dso_name = verbose > 0 ? map->dso->long_name :
-                        map->dso->long_name;
+                        map->dso->short_name;
                return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
        }
@@ -261,7 +261,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 {
        size_t ret = 0;
-        if (verbose) {
+        if (verbose > 0) {
                char o = map ? dso__symtab_origin(map->dso) : '!';
                ret += repsep_snprintf(bf, size, "%-#*llx %c ",
                                       BITS_PER_LONG / 4 + 2, ip, o);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7aff317fc7c4..796c847e2f00 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -108,7 +108,7 @@ struct hist_entry {
                /*
                 * Since perf diff only supports the stdio output, TUI
                 * fields are only accessed from perf report (or perf
-                 * top).  So make it an union to reduce memory usage.
+                 * top).  So make it a union to reduce memory usage.
                 */
                struct hist_entry_diff  diff;
                struct /* for TUI */ {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 39345c2ddfc2..0d51334a9b46 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -344,7 +344,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
        for (i = 0; i < 3; i++)
                update_stats(&ps->res_stats[i], count[i]);
-        if (verbose) {
+        if (verbose > 0) {
                fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
                        perf_evsel__name(counter), count[0], count[1], count[2]);
        }
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index bcae659b6546..efb53772e0ec 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
                len = strfilter_node__sprint_pt(node->l, buf);
                if (len < 0)
                        return len;
+                __fallthrough;
        case '!':
                if (buf) {
                        *(buf + len++) = *node->p;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d8dfaf64b32e..bddca519dd58 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -21,6 +21,8 @@ s64 perf_atoll(const char *str)
                case 'b': case 'B':
                        if (*p)
                                goto out_err;
+                        __fallthrough;
                case '\0':
                        return length;
                default:
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index adbc6c02c3aa..4e59ddeb4eda 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -213,7 +213,7 @@ static bool want_demangle(bool is_kernel_sym)
 static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
-        int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
+        int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS;
        char *demangled = NULL;
        /*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dc93940de351..70e389bc4af7 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1460,9 +1460,11 @@ int dso__load(struct dso *dso, struct map *map)
         * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
         */
        if (!dso->has_build_id &&
-            is_regular_file(dso->long_name) &&
+            is_regular_file(dso->long_name)) {
-            filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+            __symbol__join_symfs(name, PATH_MAX, dso->long_name);
+            if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0)
                dso__set_build_id(dso, build_id);
+        }
        /*
         * Iterate over candidate debug images.
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 7c6b33e8e2d2..63694e174e5c 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -21,7 +21,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
        unsigned long offset;
        size_t length;
-        if (sym && sym->name) {
+        if (sym) {
                length = fprintf(fp, "%s", sym->name);
                if (al && print_offsets) {
                        if (al->addr < sym->end)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f9eab200fd75..7c3fcc538a70 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -93,7 +93,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 {
        DIR *proc;
        int max_threads = 32, items, i;
-        char path[256];
+        char path[NAME_MAX + 1 + 6];
        struct dirent *dirent, **namelist = NULL;
        struct thread_map *threads = thread_map__alloc(max_threads);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d995743cb673..e7d60d05596d 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -42,7 +42,7 @@
 #include "evsel.h"
 #include "debug.h"
-#define VERSION "0.5"
+#define VERSION "0.6"
 static int output_fd;
@@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
        return false;
 }
+#define for_each_event(dir, dent, tps)                          \
+        while ((dent = readdir(dir)))                           \
+                if (dent->d_type == DT_DIR &&                   \
+                    (strcmp(dent->d_name, ".")) &&              \
+                    (strcmp(dent->d_name, "..")))               \
 static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 {
        struct dirent *dent;
@@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
                return -errno;
        }
-        while ((dent = readdir(dir))) {
+        for_each_event(dir, dent, tps) {
-                if (dent->d_type != DT_DIR ||
+                if (!name_in_tp_list(dent->d_name, tps))
-                    strcmp(dent->d_name, ".") == 0 ||
-                    strcmp(dent->d_name, "..") == 0 ||
-                    !name_in_tp_list(dent->d_name, tps))
                        continue;
                if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
                        err = -ENOMEM;
                        goto out;
@@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
        }
        rewinddir(dir);
-        while ((dent = readdir(dir))) {
+        for_each_event(dir, dent, tps) {
-                if (dent->d_type != DT_DIR ||
+                if (!name_in_tp_list(dent->d_name, tps))
-                    strcmp(dent->d_name, ".") == 0 ||
-                    strcmp(dent->d_name, "..") == 0 ||
-                    !name_in_tp_list(dent->d_name, tps))
                        continue;
                if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
                        err = -ENOMEM;
                        goto out;
@@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps)
                goto out;
        }
-        while ((dent = readdir(dir))) {
+        for_each_event(dir, dent, tps) {
-                if (dent->d_type != DT_DIR ||
+                if (strcmp(dent->d_name, "ftrace") == 0 ||
-                    strcmp(dent->d_name, ".") == 0 ||
-                    strcmp(dent->d_name, "..") == 0 ||
-                    strcmp(dent->d_name, "ftrace") == 0 ||
                    !system_in_tp_list(dent->d_name, tps))
                        continue;
                count++;
        }
@@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps)
        }
        rewinddir(dir);
-        while ((dent = readdir(dir))) {
+        for_each_event(dir, dent, tps) {
-                if (dent->d_type != DT_DIR ||
+                if (strcmp(dent->d_name, "ftrace") == 0 ||
-                    strcmp(dent->d_name, ".") == 0 ||
-                    strcmp(dent->d_name, "..") == 0 ||
-                    strcmp(dent->d_name, "ftrace") == 0 ||
                    !system_in_tp_list(dent->d_name, tps))
                        continue;
                if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
                        err = -ENOMEM;
                        goto out;
@@ -379,6 +377,34 @@ out:
        return err;
 }
+static int record_saved_cmdline(void)
+{
+        unsigned int size;
+        char *path;
+        struct stat st;
+        int ret, err = 0;
+        path = get_tracing_file("saved_cmdlines");
+        if (!path) {
+                pr_debug("can't get tracing/saved_cmdline");
+                return -ENOMEM;
+        }
+        ret = stat(path, &st);
+        if (ret < 0) {
+                /* not found */
+                size = 0;
+                if (write(output_fd, &size, 8) != 8)
+                        err = -EIO;
+                goto out;
+        }
+        err = record_file(path, 8);
+out:
+        put_tracing_file(path);
+        return err;
+}
 static void
 put_tracepoints_path(struct tracepoint_path *tps)
 {
@@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
        if (err)
                goto out;
        err = record_ftrace_printk();
+        if (err)
+                goto out;
+        err = record_saved_cmdline();
 out:
        /*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 33b52eaa39db..de0078e21408 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -160,6 +160,23 @@ void parse_ftrace_printk(struct pevent *pevent,
        }
 }
+void parse_saved_cmdline(struct pevent *pevent,
+                         char *file, unsigned int size __maybe_unused)
+{
+        char *comm;
+        char *line;
+        char *next = NULL;
+        int pid;
+        line = strtok_r(file, "\n", &next);
+        while (line) {
+                sscanf(line, "%d %ms", &pid, &comm);
+                pevent_register_comm(pevent, comm, pid);
+                free(comm);
+                line = strtok_r(NULL, "\n", &next);
+        }
+}
 int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
 {
        return pevent_parse_event(pevent, buf, size, "ftrace");
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b67a0ccf5ab9..27420159bf69 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -260,39 +260,53 @@ static int read_header_files(struct pevent *pevent)
 static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
+        int ret;
        char *buf;
        buf = malloc(size);
-        if (buf == NULL)
+        if (buf == NULL) {
+                pr_debug("memory allocation failure\n");
                return -1;
+        }
-        if (do_read(buf, size) < 0) {
+        ret = do_read(buf, size);
-                free(buf);
+        if (ret < 0) {
-                return -1;
+                pr_debug("error reading ftrace file.\n");
+                goto out;
        }
-        parse_ftrace_file(pevent, buf, size);
+        ret = parse_ftrace_file(pevent, buf, size);
+        if (ret < 0)
+                pr_debug("error parsing ftrace file.\n");
+out:
        free(buf);
-        return 0;
+        return ret;
 }
 static int read_event_file(struct pevent *pevent, char *sys,
                            unsigned long long size)
 {
+        int ret;
        char *buf;
        buf = malloc(size);
-        if (buf == NULL)
+        if (buf == NULL) {
+                pr_debug("memory allocation failure\n");
                return -1;
+        }
-        if (do_read(buf, size) < 0) {
+        ret = do_read(buf, size);
+        if (ret < 0) {
                free(buf);
-                return -1;
+                goto out;
        }
-        parse_event_file(pevent, buf, size, sys);
+        ret = parse_event_file(pevent, buf, size, sys);
+        if (ret < 0)
+                pr_debug("error parsing event file.\n");
+out:
        free(buf);
-        return 0;
+        return ret;
 }
 static int read_ftrace_files(struct pevent *pevent)
@@ -341,6 +355,36 @@ static int read_event_files(struct pevent *pevent)
        return 0;
 }
+static int read_saved_cmdline(struct pevent *pevent)
+{
+        unsigned long long size;
+        char *buf;
+        int ret;
+        /* it can have 0 size */
+        size = read8(pevent);
+        if (!size)
+                return 0;
+        buf = malloc(size + 1);
+        if (buf == NULL) {
+                pr_debug("memory allocation failure\n");
+                return -1;
+        }
+        ret = do_read(buf, size);
+        if (ret < 0) {
+                pr_debug("error reading saved cmdlines\n");
+                goto out;
+        }
+        parse_saved_cmdline(pevent, buf, size);
+        ret = 0;
+out:
+        free(buf);
+        return ret;
+}
 ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
        char buf[BUFSIZ];
@@ -379,10 +423,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
                return -1;
        if (show_version)
                printf("version = %s\n", version);
-        free(version);
-        if (do_read(buf, 1) < 0)
+        if (do_read(buf, 1) < 0) {
+                free(version);
                return -1;
+        }
        file_bigendian = buf[0];
        host_bigendian = bigendian();
@@ -423,6 +468,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
        err = read_ftrace_printk(pevent);
        if (err)
                goto out;
+        if (atof(version) >= 0.6) {
+                err = read_saved_cmdline(pevent);
+                if (err)
+                        goto out;
+        }
        size = trace_data_size;
        repipe = false;
@@ -438,5 +488,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 out:
        if (pevent)
                trace_event__cleanup(tevent);
+        free(version);
        return size;
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b0af9c81bb0d..1fbc044f9eb0 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6fec84dff3f7..bfb9b7987692 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -35,6 +35,7 @@
 #include "util.h"
 #include "debug.h"
 #include "asm/bug.h"
+#include "dso.h"
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -297,15 +298,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
        int fd;
        u64 ofs = dso->data.debug_frame_offset;
+        /* debug_frame can reside in:
+         *  - dso
+         *  - debug pointed by symsrc_filename
+         *  - gnu_debuglink, which doesn't necessary
+         *    has to be pointed by symsrc_filename
+         */
        if (ofs == 0) {
                fd = dso__data_get_fd(dso, machine);
-                if (fd < 0)
+                if (fd >= 0) {
-                        return -EINVAL;
+                        ofs = elf_section_offset(fd, ".debug_frame");
+                        dso__data_put_fd(dso);
+                }
+                if (ofs <= 0) {
+                        fd = open(dso->symsrc_filename, O_RDONLY);
+                        if (fd >= 0) {
+                                ofs = elf_section_offset(fd, ".debug_frame");
+                                close(fd);
+                        }
+                }
+                if (ofs <= 0) {
+                        char *debuglink = malloc(PATH_MAX);
+                        int ret = 0;
+                        ret = dso__read_binary_type_filename(
+                                dso, DSO_BINARY_TYPE__DEBUGLINK,
+                                machine->root_dir, debuglink, PATH_MAX);
+                        if (!ret) {
+                                fd = open(debuglink, O_RDONLY);
+                                if (fd >= 0) {
+                                        ofs = elf_section_offset(fd,
+                                                        ".debug_frame");
+                                        close(fd);
+                                }
+                        }
+                        if (ofs > 0) {
+                                if (dso->symsrc_filename != NULL) {
+                                        pr_warning(
+                                                "%s: overwrite symsrc(%s,%s)\n",
+                                                        __func__,
+                                                        dso->symsrc_filename,
+                                                        debuglink);
+                                        free(dso->symsrc_filename);
+                                }
+                                dso->symsrc_filename = debuglink;
+                        } else {
+                                free(debuglink);
+                        }
+                }
-                /* 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;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9ddd98827d12..d8b45cea54d0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -85,7 +85,7 @@ int mkdir_p(char *path, mode_t mode)
        return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
-int rm_rf(char *path)
+int rm_rf(const char *path)
 {
        DIR *dir;
        int ret = 0;
@@ -789,3 +789,16 @@ int is_printable_array(char *p, unsigned int len)
        }
        return 1;
 }
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+        char unit[4] = "BKMG";
+        int i = 0;
+        while (((n / 1024) > 1) && (i < 3)) {
+                n /= 1024;
+                i++;
+        }
+        return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1d639e38aa82..c74708da8571 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -209,7 +209,7 @@ static inline int sane_case(int x, int high)
 }
 int mkdir_p(char *path, mode_t mode);
-int rm_rf(char *path);
+int rm_rf(const char *path);
 struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
@@ -363,4 +363,5 @@ int is_printable_array(char *p, unsigned int len);
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
 #endif /* GIT_COMPAT_UTIL_H */
author	Daniel Vetter <daniel.vetter@ffwll.ch>	2017-03-14 10:07:33 -0400
committer	Daniel Vetter <daniel.vetter@ffwll.ch>	2017-03-14 10:07:33 -0400
commit	b70366e5d31788650b2a5cec5cd13ea80ac7e44a (patch)
tree	d972ffd190111d699200448494fda333d28b2486 /tools/perf
parent	f42e181935d5e5670c87d31ae48063a495bbacae (diff)
parent	db6ccf23e8ba40fc2e8914ec9c0eb950df71d9fe (diff)