Merge airlied/drm-next into drm-misc-next

Just catching up with upstream.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

261 files changed, 16709 insertions, 1966 deletions

diff --git a/tools/perf/Build b/tools/perf/Build
index bd8eeb60533c..b48ca40fccf9 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -50,6 +50,6 @@ libperf-y += util/
 libperf-y += arch/
 libperf-y += ui/
 libperf-y += scripts/
-libperf-y += trace/beauty/
+libperf-$(CONFIG_AUDIT) += trace/beauty/
 
 gtk-y += ui/gtk/
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 098cfb9ca8f0..db11478e30b4 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -192,7 +192,7 @@ do-install-man: man
 #               $(INSTALL) -m 644 $(DOC_MAN5) $(DESTDIR)$(man5dir); \
 #               $(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
 
-install-man: check-man-tools man
+install-man: check-man-tools man do-install-man
 
 ifdef missing_tools
   DO_INSTALL_MAN = $(warning Please install $(missing_tools) to have the man pages installed)
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4b6cdbf8f935..76971d2e4164 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -104,9 +104,9 @@ system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
 in transaction, respectively.
 
 While it is possible to create scripts to analyze the data, an alternative
-approach is available to export the data to a postgresql database.  Refer to
-script export-to-postgresql.py for more details, and to script
-call-graph-from-postgresql.py for an example of using the database.
+approach is available to export the data to a sqlite or postgresql database.
+Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
+and to script call-graph-from-sql.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
 unpack the raw data for power events and PTWRITE.
@@ -873,7 +873,7 @@ amended to take the number of elements as a parameter.
 
         $ cat ~/.perfconfig
         [intel-pt]
-                mispred-all
+                mispred-all = on
 
         $ perf record -e intel_pt//u ./sort 3000
         Bubble sorting array of 3000 elements
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index a89273d8e744..c635eab6af54 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -43,6 +43,10 @@ OPTIONS
 --quiet::
         Do not show any message.  (Suppress -v)
 
+-n::
+--show-nr-samples::
+        Show the number of samples for each symbol
+
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
@@ -88,6 +92,8 @@ OPTIONS
 --asm-raw::
         Show raw instruction encoding of assembly instructions.
 
+--show-total-period:: Show a column with the sum of periods.
+
 --source::
         Interleave source code with assembly code. Enabled by default,
         disable with --no-source.
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 058064db39d2..84681007f80f 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -61,6 +61,11 @@ OPTIONS
 --verbose::
         Be more verbose.
 
+--target-ns=PID:
+        Obtain mount namespace information from the target pid.  This is
+        used when creating a uprobe for a process that resides in a
+        different mount namespace from the perf(1) utility.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 73496320fca3..4be08a1e3f8d 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
 --ldload::
         Specify desired latency for loads event.
 
+-p::
+--phys-data::
+        Record/Report sample physical addresses
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 165c2b1d4317..d7e4869905f1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -130,6 +130,11 @@ OPTIONS
 --max-probes=NUM::
         Set the maximum number of probe points for an event. Default is 128.
 
+--target-ns=PID:
+        Obtain mount namespace information from the target pid.  This is
+        used when creating a uprobe for a process that resides in a
+        different mount namespace from the perf(1) utility.
+
 -x::
 --exec=PATH::
         Specify path to the executable or shared library file for user
@@ -264,6 +269,15 @@ Add probes at malloc() function on libc
 
  ./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc
 
+Add a uprobe to a target process running in a different mount namespace
+
+ ./perf probe --target-ns <target pid> -x /lib64/libc.so.6 malloc
+
+Add a USDT probe to a target process running in a different mount namespace
+
+ ./perf probe --target-ns <target pid> -x /usr/lib/jvm/java-1.8.0-openjdk-1.8.0.121-0.b13.el7_3.x86_64/jre/lib/amd64/server/libjvm.so %sdt_hotspot:thread__sleep__end
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b0e9e921d534..e397453e5a46 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -249,7 +249,10 @@ OPTIONS
 
 -d::
 --data::
-        Record the sample addresses.
+        Record the sample virtual addresses.
+
+--phys-data::
+        Record the sample physical addresses.
 
 -T::
 --timestamp::
@@ -332,6 +335,7 @@ following filters are defined:
         - no_tx: only when the target is not in a hardware transaction
         - abort_tx: only when the target is a hardware transaction abort
         - cond: conditional branches
+        - save_type: save branch type during sampling in case binary is not available later
 
 +
 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa84617181e..383a98d992ed 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
         - mem: type of memory access for the data at the time of the sample
         - snoop: type of snoop (if any) for the data at the time of the sample
         - dcacheline: the cacheline the data address is on at the time of the sample
+        - phys_daddr: physical address of data being executed on at the time of sample
 
         And the default sort keys are changed to local_weight, mem, sym, dso,
         symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796be96e..18dfcfa38454 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
         srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth.
+        callindent, insn, insnlen, synth, phys_addr.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 698076313606..c37d61682dfb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -41,13 +41,13 @@ report::
 
         - a symbolically formed event like 'pmu/param1=0x3,param2/' where
           param1 and param2 are defined as formats for the PMU in
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
         - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
           where M, N, K are numbers (in decimal, hex, octal format).
           Acceptable values for each of 'config', 'config1' and 'config2'
           parameters are defined by corresponding entries in
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
 -i::
 --no-inherit::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index e71d63843f45..d864ea6fd367 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -237,6 +237,10 @@ Default is to monitor all CPUS.
 --hierarchy::
         Enable hierarchy output.
 
+--force::
+        Don't do ownership validation.
+
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index c1e3288a2dfb..d53bea6bd571 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -37,7 +37,7 @@ OPTIONS
 --expr::
 --event::
         List of syscalls and other perf events (tracepoints, HW cache events,
-        etc) to show.
+        etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
         See 'perf list' for a complete list of events.
         Prefixing with ! shows all syscalls but the ones specified.  You may
         need to escape it.
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index de8b39dda7b8..e90c59c6d815 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -398,6 +398,11 @@ struct auxtrace_error_event {
         char msg[MAX_AUXTRACE_ERROR_MSG];
 };
 
+        PERF_RECORD_HEADER_FEATURE              = 80,
+
+Describes a header feature. These are records used in pipe-mode that
+contain information that otherwise would be in perf.data file's header.
+
 Event types
 
 Define the event attributes with their IDs.
@@ -422,8 +427,9 @@ struct perf_pipe_file_header {
 };
 
 The information about attrs, data, and event_types is instead in the
-synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and
-PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode.
+synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
+PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
+that are generated by perf record in pipe-mode.
 
 
 References:
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a29da46d180f..627b7cada144 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,34 +1,8 @@
 tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
 tools/scripts
 tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
 tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
@@ -42,52 +16,3 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-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/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/stat.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index bdf0e87f9b29..63f534a0902f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -35,7 +35,7 @@ ifeq ($(SRCARCH),x86)
   ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
-    LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
+    LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma
     $(call detected,CONFIG_X86_64)
   else
     LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
@@ -103,8 +103,12 @@ ifdef LIBDW_DIR
   LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
   LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+DWARFLIBS := -ldw
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+  DWARFLIBS += -lelf -lebl -ldl -lz -llzma -lbz2
+endif
 FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS)
 
 # for linking with debug library, run like:
 # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
@@ -144,7 +148,7 @@ ifndef DEBUG
 endif
 
 ifeq ($(DEBUG),0)
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
@@ -180,7 +184,7 @@ ifdef PYTHON_CONFIG
   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)
+  ifeq ($(CC_NO_CLANG), 1)
     PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   endif
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
@@ -330,6 +334,11 @@ ifeq ($(feature-sched_getcpu), 1)
   CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
 endif
 
+ifeq ($(feature-setns), 1)
+  CFLAGS += -DHAVE_SETNS_SUPPORT
+  $(call detected,CONFIG_SETNS)
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -360,10 +369,6 @@ ifndef NO_LIBELF
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
-      DWARFLIBS := -ldw
-      ifeq ($(findstring -static,${LDFLAGS}),-static)
-        DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
-      endif
       EXTLIBS += ${DWARFLIBS}
       $(call detected,CONFIG_DWARF)
     endif # PERF_HAVE_DWARF_REGS
@@ -500,6 +505,10 @@ ifndef NO_LOCAL_LIBUNWIND
   EXTLIBS += $(LIBUNWIND_LIBS)
   LDFLAGS += $(LIBUNWIND_LIBS)
 endif
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+  # gcc -static links libgcc_eh which contans piece of libunwind
+  LIBUNWIND_LDFLAGS += -Wl,--allow-multiple-definition
+endif
 
 ifndef NO_LIBUNWIND
   CFLAGS  += -DHAVE_LIBUNWIND_SUPPORT
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5008f51a08a2..91ef44bfaf3e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -33,6 +33,11 @@ include ../scripts/utilities.mak
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
 #
+# Define EXCLUDE_EXTLIBS=-lmylib to exclude libmylib from the auto-generated
+# EXTLIBS.
+#
+# Define EXTRA_PERFLIBS to pass extra libraries to PERFLIBS.
+#
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
 #
 # Define WERROR=0 to disable treating any warnings as errors.
@@ -159,8 +164,8 @@ LN      = ln -f
 MKDIR   = mkdir
 FIND    = find
 INSTALL = install
-FLEX    = flex
-BISON   = bison
+FLEX    ?= flex
+BISON   ?= bison
 STRIP   = strip
 AWK     = awk
 
@@ -235,7 +240,7 @@ endif
 ifeq ($(FEATURES_DUMP),)
 FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
 else
-FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+FEATURE_DUMP_EXPORT := $(realpath $(FEATURES_DUMP))
 endif
 
 export prefix bindir sharedir sysconfdir DESTDIR
@@ -274,7 +279,13 @@ LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
 LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
-LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
+#
+# The static build has no dynsym table, so this does not work for
+# static build. Looks like linker starts to scream about that now
+# (in Fedora 26) so we need to switch it off for static build.
+DYNAMIC_LIST_LDFLAGS               = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = $(if $(findstring -static,$(LDFLAGS)),,$(DYNAMIC_LIST_LDFLAGS))
 
 LIBAPI = $(API_PATH)libapi.a
 export LIBAPI
@@ -352,7 +363,8 @@ ifdef ASCIIDOC8
   export ASCIIDOC8
 endif
 
-LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
+EXTLIBS := $(call filter-out,$(EXCLUDE_EXTLIBS),$(EXTLIBS))
+LIBS = -Wl,--whole-archive $(PERFLIBS) $(EXTRA_PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ifeq ($(USE_CLANG), 1)
   CLANGLIBS_LIST = AST Basic CodeGen Driver Frontend Lex Tooling Edit Sema Analysis Parse Serialization
@@ -375,6 +387,60 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+beauty_outdir := $(OUTPUT)trace/beauty/generated
+beauty_ioctl_outdir := $(beauty_outdir)/ioctl
+drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
+drm_hdr_dir := $(srctree)/tools/include/uapi/drm
+drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
+
+$(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
+        $(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
+
+pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
+asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+
+$(pkey_alloc_access_rights_array): $(asm_generic_hdr_dir)/mman-common.h $(pkey_alloc_access_rights_tbl)
+        $(Q)$(SHELL) '$(pkey_alloc_access_rights_tbl)' $(asm_generic_hdr_dir) > $@
+
+sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c
+sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound
+sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+
+$(sndrv_ctl_ioctl_array): $(sndrv_ctl_hdr_dir)/asound.h $(sndrv_ctl_ioctl_tbl)
+        $(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(sndrv_ctl_hdr_dir) > $@
+
+sndrv_pcm_ioctl_array := $(beauty_ioctl_outdir)/sndrv_pcm_ioctl_array.c
+sndrv_pcm_hdr_dir := $(srctree)/tools/include/uapi/sound
+sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+
+$(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
+        $(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@
+
+kvm_ioctl_array := $(beauty_ioctl_outdir)/kvm_ioctl_array.c
+kvm_hdr_dir := $(srctree)/tools/include/uapi/linux
+kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
+
+$(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
+        $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
+
+vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
+vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
+vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+
+$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
+        $(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@
+
+perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c
+perf_hdr_dir := $(srctree)/tools/include/uapi/linux
+perf_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/perf_ioctl.sh
+
+$(perf_ioctl_array): $(perf_hdr_dir)/perf_event.h $(perf_ioctl_tbl)
+        $(Q)$(SHELL) '$(perf_ioctl_tbl)' $(perf_hdr_dir) > $@
+
 all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
@@ -469,7 +535,13 @@ endif
 __build-dir = $(subst $(OUTPUT),,$(dir $@))
 build-dir   = $(if $(__build-dir),$(__build-dir),.)
 
-prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders
+prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \
+        $(pkey_alloc_access_rights_array) \
+        $(sndrv_pcm_ioctl_array) \
+        $(sndrv_ctl_ioctl_array) \
+        $(kvm_ioctl_array) \
+        $(vhost_virtio_ioctl_array) \
+        $(perf_ioctl_array)
 
 $(OUTPUT)%.o: %.c prepare FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -512,7 +584,7 @@ $(LIBJVMTI_IN): FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti
 
 $(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN)
-        $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< -lelf -lrt
+        $(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $<
 endif
 
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
@@ -703,7 +775,11 @@ install-tests: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
-                $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+                $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+                $(INSTALL) tests/shell/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell'; \
+                $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'; \
+                $(INSTALL) tests/shell/lib/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/lib'
 
 install-bin: install-tools install-tests install-traceevent-plugins
 
@@ -734,7 +810,14 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
         $(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)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
-                $(OUTPUT)pmu-events/pmu-events.c
+                $(OUTPUT)pmu-events/pmu-events.c \
+                $(OUTPUT)$(drm_ioctl_array) \
+                $(OUTPUT)$(pkey_alloc_access_rights_array) \
+                $(OUTPUT)$(sndrv_ctl_ioctl_array) \
+                $(OUTPUT)$(sndrv_pcm_ioctl_array) \
+                $(OUTPUT)$(kvm_ioctl_array) \
+                $(OUTPUT)$(vhost_virtio_ioctl_array) \
+                $(OUTPUT)$(perf_ioctl_array)
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
 
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 7ce3d1a25133..fbfc055d3f4d 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -266,6 +266,32 @@ static u64 cs_etm_get_config(struct auxtrace_record *itr)
         return config;
 }
 
+#ifndef BIT
+#define BIT(N) (1UL << (N))
+#endif
+
+static u64 cs_etmv4_get_config(struct auxtrace_record *itr)
+{
+        u64 config = 0;
+        u64 config_opts = 0;
+
+        /*
+         * The perf event variable config bits represent both
+         * the command line options and register programming
+         * bits in ETMv3/PTM. For ETMv4 we must remap options
+         * to real bits
+         */
+        config_opts = cs_etm_get_config(itr);
+        if (config_opts & BIT(ETM_OPT_CYCACC))
+                config |= BIT(ETM4_CFG_BIT_CYCACC);
+        if (config_opts & BIT(ETM_OPT_TS))
+                config |= BIT(ETM4_CFG_BIT_TS);
+        if (config_opts & BIT(ETM_OPT_RETSTK))
+                config |= BIT(ETM4_CFG_BIT_RETSTK);
+
+        return config;
+}
+
 static size_t
 cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
                       struct perf_evlist *evlist __maybe_unused)
@@ -363,7 +389,7 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
                 magic = __perf_cs_etmv4_magic;
                 /* Get trace configuration register */
                 info->priv[*offset + CS_ETMV4_TRCCONFIGR] =
-                                                cs_etm_get_config(itr);
+                                                cs_etmv4_get_config(itr);
                 /* Get traceID from the framework */
                 info->priv[*offset + CS_ETMV4_TRCTRACEIDR] =
                                                 coresight_get_trace_id(cpu);
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index bf9a2594572c..9c4e23d8c8ce 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -126,7 +126,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
         struct rb_node *tmp;
         int i = 0;
 
-        map = get_target_map(pev->target, pev->uprobes);
+        map = get_target_map(pev->target, pev->nsi, pev->uprobes);
         if (!map || map__load(map) < 0)
                 return;
 
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 6c9211b18ec0..9a628a24c5c9 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -20,7 +20,7 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 $(header): $(sys)/syscall_64.tbl $(systbl)
         @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
         (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \
-        || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true
+        || echo "Warning: Kernel ABI header at 'tools/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'" >&2 )) || true
         $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
 
 clean::
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index c1625f256df3..d84b72063a30 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -76,3 +76,49 @@ static struct ins x86__instructions[] = {
         { .name = "xbeginq",    .ops = &jump_ops, },
         { .name = "retq",       .ops = &ret_ops,  },
 };
+
+static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
+                              const char *ins2)
+{
+        if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp"))
+                return false;
+
+        if (arch->model == 0x1e) {
+                /* Nehalem */
+                if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+                     strstr(ins1, "test")) {
+                        return true;
+                }
+        } else {
+                /* Newer platform */
+                if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+                     strstr(ins1, "test") ||
+                     strstr(ins1, "add") ||
+                     strstr(ins1, "sub") ||
+                     strstr(ins1, "and") ||
+                     strstr(ins1, "inc") ||
+                     strstr(ins1, "dec")) {
+                        return true;
+                }
+        }
+
+        return false;
+}
+
+static int x86__cpuid_parse(struct arch *arch, char *cpuid)
+{
+        unsigned int family, model, stepping;
+        int ret;
+
+        /*
+         * cpuid = "GenuineIntel,family,model,stepping"
+         */
+        ret = sscanf(cpuid, "%*[^,],%u,%u,%u", &family, &model, &stepping);
+        if (ret == 3) {
+                arch->family = family;
+                arch->model = model;
+                return 0;
+        }
+
+        return -1;
+}
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index b48de2f5813c..4e0b806a7a0f 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -1,11 +1,14 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
+#include <linux/compiler.h>
+struct test;
+
 /* Tests */
-int test__rdpmc(int subtest);
-int test__perf_time_to_tsc(int subtest);
-int test__insn_x86(int subtest);
-int test__intel_cqm_count_nmi_context(int subtest);
+int test__rdpmc(struct test *test __maybe_unused, int subtest);
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
+int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 08d9b2bc185c..b3860586a0c2 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -171,7 +171,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64)
  * verbose (-v) option to see all the instructions and whether or not they
  * decoded successfuly.
  */
-int test__insn_x86(int subtest __maybe_unused)
+int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret = 0;
 
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index f9713a71d77e..57f86b6e7d6f 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -36,7 +36,7 @@ static pid_t spawn(void)
  * the last read counter value to avoid triggering a WARN_ON_ONCE() in
  * smp_call_function_many() caused by sending IPIs from NMI context.
  */
-int test__intel_cqm_count_nmi_context(int subtest __maybe_unused)
+int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evlist *evlist = NULL;
         struct perf_evsel *evsel = NULL;
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index e3ae9cff2b67..5dd7efb192ce 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -37,7 +37,7 @@
  * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
  * supported then then the test passes but " (not supported)" is printed.
  */
-int test__perf_time_to_tsc(int subtest __maybe_unused)
+int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 500cf96db979..17fec30a0b31 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -154,7 +154,7 @@ out_close:
         return 0;
 }
 
-int test__rdpmc(int subtest __maybe_unused)
+int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int status = 0;
         int wret = 0;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 9535be57033f..db0ba8caf5a2 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -701,6 +701,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                                 perf_evsel__set_sample_bit(switch_evsel, TID);
                                 perf_evsel__set_sample_bit(switch_evsel, TIME);
                                 perf_evsel__set_sample_bit(switch_evsel, CPU);
+                                perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
 
                                 opts->record_switch_events = false;
                                 ptr->have_sched_switch = 3;
@@ -752,6 +753,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                 tracking_evsel->attr.freq = 0;
                 tracking_evsel->attr.sample_period = 1;
 
+                tracking_evsel->no_aux_samples = true;
                 if (need_immediate)
                         tracking_evsel->immediate = true;
 
@@ -761,6 +763,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                         /* And the CPU for switch events */
                         perf_evsel__set_sample_bit(tracking_evsel, CPU);
                 }
+                perf_evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
         }
 
         /*
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 7a5dc7e5c577..c38373195c4a 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -177,14 +177,11 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
          */
         process_branch_stack(sample->branch_stack, al, sample);
 
-        sample->period = 1;
-        sample->weight = 1;
-
         he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
         if (he == NULL)
                 return -ENOMEM;
 
-        ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+        ret = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
         hists__inc_nr_samples(hists, true);
         return ret;
 }
@@ -397,6 +394,8 @@ int cmd_annotate(int argc, const char **argv)
                         .namespaces = perf_event__process_namespaces,
                         .attr   = perf_event__process_attr,
                         .build_id = perf_event__process_build_id,
+                        .tracing_data   = perf_event__process_tracing_data,
+                        .feature        = perf_event__process_feature,
                         .ordered_events = true,
                         .ordering_requires_timestamps = true,
                 },
@@ -404,7 +403,7 @@ int cmd_annotate(int argc, const char **argv)
         struct perf_data_file file = {
                 .mode  = PERF_DATA_MODE_READ,
         };
-        const struct option options[] = {
+        struct option options[] = {
         OPT_STRING('i', "input", &input_name, "file",
                     "input file name"),
         OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
@@ -446,13 +445,20 @@ int cmd_annotate(int argc, const char **argv)
                     "Show event group information together"),
         OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
                     "Show a column with the sum of periods"),
+        OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
+                    "Show a column with the number of samples"),
         OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
                              "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
                              stdio__config_color, "always"),
         OPT_END()
         };
-        int ret = hists__init();
+        int ret;
+
+        set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
+        set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);
+
 
+        ret = hists__init();
         if (ret < 0)
                 return ret;
 
@@ -468,6 +474,11 @@ int cmd_annotate(int argc, const char **argv)
                 annotate.sym_hist_filter = argv[0];
         }
 
+        if (symbol_conf.show_nr_samples && annotate.use_gtk) {
+                pr_err("--show-nr-samples is not available in --gtk mode at this time\n");
+                return ret;
+        }
+
         if (quiet)
                 perf_quiet_option();
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 9eba7f1add1f..e3eb6240ced0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -14,6 +14,7 @@
 #include <unistd.h>
 #include "builtin.h"
 #include "perf.h"
+#include "namespaces.h"
 #include "util/cache.h"
 #include "util/debug.h"
 #include "util/header.h"
@@ -165,33 +166,41 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
         return 0;
 }
 
-static int build_id_cache__add_file(const char *filename)
+static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi)
 {
         char sbuild_id[SBUILD_ID_SIZE];
         u8 build_id[BUILD_ID_SIZE];
         int err;
+        struct nscookie nsc;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-        err = build_id_cache__add_s(sbuild_id, filename,
+        err = build_id_cache__add_s(sbuild_id, filename, nsi,
                                     false, false);
         pr_debug("Adding %s %s: %s\n", sbuild_id, filename,
                  err ? "FAIL" : "Ok");
         return err;
 }
 
-static int build_id_cache__remove_file(const char *filename)
+static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi)
 {
         u8 build_id[BUILD_ID_SIZE];
         char sbuild_id[SBUILD_ID_SIZE];
+        struct nscookie nsc;
 
         int err;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
@@ -204,13 +213,13 @@ static int build_id_cache__remove_file(const char *filename)
         return err;
 }
 
-static int build_id_cache__purge_path(const char *pathname)
+static int build_id_cache__purge_path(const char *pathname, struct nsinfo *nsi)
 {
         struct strlist *list;
         struct str_node *pos;
         int err;
 
-        err = build_id_cache__list_build_ids(pathname, &list);
+        err = build_id_cache__list_build_ids(pathname, nsi, &list);
         if (err)
                 goto out;
 
@@ -234,7 +243,7 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
         char filename[PATH_MAX];
         u8 build_id[BUILD_ID_SIZE];
 
-        if (dso__build_id_filename(dso, filename, sizeof(filename)) &&
+        if (dso__build_id_filename(dso, filename, sizeof(filename), false) &&
             filename__read_build_id(filename, build_id,
                                     sizeof(build_id)) != sizeof(build_id)) {
                 if (errno == ENOENT)
@@ -256,24 +265,30 @@ static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *f
         return 0;
 }
 
-static int build_id_cache__update_file(const char *filename)
+static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 {
         u8 build_id[BUILD_ID_SIZE];
         char sbuild_id[SBUILD_ID_SIZE];
+        struct nscookie nsc;
 
-        int err = 0;
+        int err;
 
-        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = filename__read_build_id(filename, &build_id, sizeof(build_id));
+        nsinfo__mountns_exit(&nsc);
+        if (err < 0) {
                 pr_debug("Couldn't read a build-id in %s\n", filename);
                 return -1;
         }
+        err = 0;
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
         if (build_id_cache__cached(sbuild_id))
                 err = build_id_cache__remove_s(sbuild_id);
 
         if (!err)
-                err = build_id_cache__add_s(sbuild_id, filename, false, false);
+                err = build_id_cache__add_s(sbuild_id, filename, nsi, false,
+                                            false);
 
         pr_debug("Updating %s %s: %s\n", sbuild_id, filename,
                  err ? "FAIL" : "Ok");
@@ -286,6 +301,7 @@ int cmd_buildid_cache(int argc, const char **argv)
         struct strlist *list;
         struct str_node *pos;
         int ret = 0;
+        int ns_id = -1;
         bool force = false;
         char const *add_name_list_str = NULL,
                    *remove_name_list_str = NULL,
@@ -299,6 +315,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 .mode  = PERF_DATA_MODE_READ,
         };
         struct perf_session *session = NULL;
+        struct nsinfo *nsi = NULL;
 
         const struct option buildid_cache_options[] = {
         OPT_STRING('a', "add", &add_name_list_str,
@@ -315,6 +332,7 @@ int cmd_buildid_cache(int argc, const char **argv)
         OPT_STRING('u', "update", &update_name_list_str, "file list",
                     "file(s) to update"),
         OPT_INCR('v', "verbose", &verbose, "be more verbose"),
+        OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"),
         OPT_END()
         };
         const char * const buildid_cache_usage[] = {
@@ -330,6 +348,9 @@ int cmd_buildid_cache(int argc, const char **argv)
                      !missing_filename && !update_name_list_str))
                 usage_with_options(buildid_cache_usage, buildid_cache_options);
 
+        if (ns_id > 0)
+                nsi = nsinfo__new(ns_id);
+
         if (missing_filename) {
                 file.path = missing_filename;
                 file.force = force;
@@ -348,7 +369,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(add_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__add_file(pos->s)) {
+                                if (build_id_cache__add_file(pos->s, nsi)) {
                                         if (errno == EEXIST) {
                                                 pr_debug("%s already in the cache\n",
                                                          pos->s);
@@ -366,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(remove_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__remove_file(pos->s)) {
+                                if (build_id_cache__remove_file(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -384,7 +405,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(purge_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__purge_path(pos->s)) {
+                                if (build_id_cache__purge_path(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -405,7 +426,7 @@ int cmd_buildid_cache(int argc, const char **argv)
                 list = strlist__new(update_name_list_str, NULL);
                 if (list) {
                         strlist__for_each_entry(pos, list)
-                                if (build_id_cache__update_file(pos->s)) {
+                                if (build_id_cache__update_file(pos->s, nsi)) {
                                         if (errno == ENOENT) {
                                                 pr_debug("%s wasn't in the cache\n",
                                                          pos->s);
@@ -424,6 +445,7 @@ int cmd_buildid_cache(int argc, const char **argv)
 
 out:
         perf_session__delete(session);
+        nsinfo__zput(nsi);
 
         return ret;
 }
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index ece45582a48d..a1d82e33282c 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -13,6 +13,7 @@
 #include "util/util.h"
 #include "util/debug.h"
 #include "util/config.h"
+#include <linux/string.h>
 
 static bool use_system_config, use_user_config;
 
@@ -58,7 +59,7 @@ static int set_config(struct perf_config_set *set, const char *file_name,
                 fprintf(fp, "[%s]\n", section->name);
 
                 perf_config_items__for_each_entry(&section->items, item) {
-                        if (!use_system_config && section->from_system_config)
+                        if (!use_system_config && item->from_system_config)
                                 continue;
                         if (item->value)
                                 fprintf(fp, "\t%s = %s\n",
@@ -79,7 +80,7 @@ static int show_spec_config(struct perf_config_set *set, const char *var)
                 return -1;
 
         perf_config_items__for_each_entry(&set->sections, section) {
-                if (prefixcmp(var, section->name) != 0)
+                if (!strstarts(var, section->name))
                         continue;
 
                 perf_config_items__for_each_entry(&section->items, item) {
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 0adb5f82335a..46cd8490baf4 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -69,7 +69,7 @@ static int cmd_data_convert(int argc, const char **argv)
         };
 
 #ifndef HAVE_LIBBABELTRACE_SUPPORT
-        pr_err("No conversion support compiled in.\n");
+        pr_err("No conversion support compiled in. perf should be compiled with environment variables LIBBABELTRACE=1 and LIBBABELTRACE_DIR=/path/to/libbabeltrace/\n");
         return -1;
 #endif
 
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index dd26c62c9893..25a42acabee1 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -381,7 +381,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
 {
         struct perf_ftrace *ftrace = cb;
 
-        if (prefixcmp(var, "ftrace."))
+        if (!strstarts(var, "ftrace."))
                 return 0;
 
         if (strcmp(var, "ftrace.tracer"))
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 530a7f2fa0f3..dbe4e4153bcf 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -90,7 +90,7 @@ static int check_emacsclient_version(void)
          */
         finish_command(&ec_process);
 
-        if (prefixcmp(buffer.buf, "emacsclient")) {
+        if (!strstarts(buffer.buf, "emacsclient")) {
                 fprintf(stderr, "Failed to parse emacsclient version.\n");
                 goto out;
         }
@@ -283,7 +283,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
                 add_man_viewer(value);
                 return 0;
         }
-        if (!prefixcmp(var, "man."))
+        if (!strstarts(var, "man."))
                 return add_man_viewer_info(var, value);
 
         return 0;
@@ -313,7 +313,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
         if (!perf_cmd)
                 return "perf";
-        else if (!prefixcmp(perf_cmd, "perf"))
+        else if (!strstarts(perf_cmd, "perf"))
                 return perf_cmd;
 
         return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index ea8db38eedd1..2b8032908fb2 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -770,6 +770,7 @@ int cmd_inject(int argc, const char **argv)
                         .finished_round = perf_event__repipe_oe_synth,
                         .build_id       = perf_event__repipe_op2_synth,
                         .id_index       = perf_event__repipe_op2_synth,
+                        .feature        = perf_event__repipe_op2_synth,
                 },
                 .input_name  = "-",
                 .samples = LIST_HEAD_INIT(inject.samples),
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a1497c516d85..24ee68ecdd42 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -627,7 +627,6 @@ static const struct {
         { "GFP_HIGHUSER_MOVABLE",       "HUM" },
         { "GFP_HIGHUSER",               "HU" },
         { "GFP_USER",                   "U" },
-        { "GFP_TEMPORARY",              "TMP" },
         { "GFP_KERNEL_ACCOUNT",         "KAC" },
         { "GFP_KERNEL",                 "K" },
         { "GFP_NOFS",                   "NF" },
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c0290793..0f15634ef82c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -23,6 +23,7 @@ struct perf_mem {
         bool                    hide_unresolved;
         bool                    dump_raw;
         bool                    force;
+        bool                    phys_addr;
         int                     operation;
         const char              *cpu_list;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
         rec_argv[i++] = "-d";
 
+        if (mem->phys_addr)
+                rec_argv[i++] = "--phys-data";
+
         for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
                 if (!perf_mem_events[j].record)
                         continue;
@@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool,
         if (al.map != NULL)
                 al.map->dso->hit = 1;
 
-        if (symbol_conf.field_sep) {
-                fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
-                      "%s0x%"PRIx64"%s%s:%s\n";
+        if (mem->phys_addr) {
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+                              "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+                              "%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
+
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->phys_addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
         } else {
-                fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
-                      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
-                symbol_conf.field_sep = " ";
-        }
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+                              "%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
 
-        printf(fmt,
-                sample->pid,
-                symbol_conf.field_sep,
-                sample->tid,
-                symbol_conf.field_sep,
-                sample->ip,
-                symbol_conf.field_sep,
-                sample->addr,
-                symbol_conf.field_sep,
-                sample->weight,
-                symbol_conf.field_sep,
-                sample->data_src,
-                symbol_conf.field_sep,
-                al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
-                al.sym ? al.sym->name : "???");
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
+        }
 out_put:
         addr_location__put(&al);
         return 0;
@@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem)
         if (ret < 0)
                 goto out_delete;
 
-        printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        if (mem->phys_addr)
+                printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        else
+                printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
         ret = perf_session__process_events(session);
 
@@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
          * there is no weight (cost) associated with stores, so don't print
          * the column
          */
-        if (!(mem->operation & MEM_OPERATION_LOAD))
-                rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-                                "dso_daddr,tlb,locked";
+        if (!(mem->operation & MEM_OPERATION_LOAD)) {
+                if (mem->phys_addr)
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked,phys_daddr";
+                else
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked";
+        } else if (mem->phys_addr)
+                rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+                                "dso_daddr,snoop,tlb,locked,phys_daddr";
 
         for (j = 1; j < argc; j++, i++)
                 rep_argv[i] = argv[j];
@@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv)
                    "separator for columns, no spaces will be added"
                    " between columns '.' is reserved."),
         OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+        OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
         OPT_END()
         };
         const char *const mem_subcommands[] = { "record", "report", NULL };
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index cf9f9e9c2fc0..c0065923a525 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -58,6 +58,7 @@ static struct {
         struct line_range line_range;
         char *target;
         struct strfilter *filter;
+        struct nsinfo *nsi;
 } params;
 
 /* Parse an event definition. Note that any error must die. */
@@ -80,6 +81,9 @@ static int parse_probe_event(const char *str)
                 params.target_used = true;
         }
 
+        if (params.nsi)
+                pev->nsi = nsinfo__get(params.nsi);
+
         /* Parse a perf-probe command into event */
         ret = parse_perf_probe_command(str, pev);
         pr_debug("%d arguments\n", pev->nargs);
@@ -189,7 +193,7 @@ static int opt_set_target(const struct option *opt, const char *str,
 
                 /* Expand given path to absolute path, except for modulename */
                 if (params.uprobes || strchr(str, '/')) {
-                        tmp = realpath(str, NULL);
+                        tmp = nsinfo__realpath(str, params.nsi);
                         if (!tmp) {
                                 pr_warning("Failed to get the absolute path of %s: %m\n", str);
                                 return ret;
@@ -208,6 +212,34 @@ static int opt_set_target(const struct option *opt, const char *str,
         return ret;
 }
 
+static int opt_set_target_ns(const struct option *opt __maybe_unused,
+                             const char *str, int unset __maybe_unused)
+{
+        int ret = -ENOENT;
+        pid_t ns_pid;
+        struct nsinfo *nsip;
+
+        if (str) {
+                errno = 0;
+                ns_pid = (pid_t)strtol(str, NULL, 10);
+                if (errno != 0) {
+                        ret = -errno;
+                        pr_warning("Failed to parse %s as a pid: %s\n", str,
+                                   strerror(errno));
+                        return ret;
+                }
+                nsip = nsinfo__new(ns_pid);
+                if (nsip && nsip->need_setns)
+                        params.nsi = nsinfo__get(nsip);
+                nsinfo__put(nsip);
+
+                ret = 0;
+        }
+
+        return ret;
+}
+
+
 /* Command option callbacks */
 
 #ifdef HAVE_DWARF_SUPPORT
@@ -299,6 +331,7 @@ static void cleanup_params(void)
         line_range__clear(&params.line_range);
         free(params.target);
         strfilter__delete(params.filter);
+        nsinfo__put(params.nsi);
         memset(&params, 0, sizeof(params));
 }
 
@@ -383,7 +416,7 @@ static int del_perf_probe_caches(struct strfilter *filter)
         }
 
         strlist__for_each_entry(nd, bidlist) {
-                cache = probe_cache__new(nd->s);
+                cache = probe_cache__new(nd->s, NULL);
                 if (!cache)
                         continue;
                 if (probe_cache__filter_purge(cache, filter) < 0 ||
@@ -554,6 +587,8 @@ __cmd_probe(int argc, const char **argv)
         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_CALLBACK(0, "target-ns", NULL, "pid",
+                     "target pid for namespace contexts", opt_set_target_ns),
         OPT_END()
         };
         int ret;
@@ -634,15 +669,15 @@ __cmd_probe(int argc, const char **argv)
                         pr_err_with_code("  Error: Failed to show event list.", ret);
                 return ret;
         case 'F':
-                ret = show_available_funcs(params.target, params.filter,
-                                        params.uprobes);
+                ret = show_available_funcs(params.target, params.nsi,
+                                           params.filter, params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show functions.", ret);
                 return ret;
 #ifdef HAVE_DWARF_SUPPORT
         case 'L':
                 ret = show_line_range(&params.line_range, params.target,
-                                      params.uprobes);
+                                      params.nsi, params.uprobes);
                 if (ret < 0)
                         pr_err_with_code("  Error: Failed to show lines.", ret);
                 return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 17a14bcce34a..56f8142ff97f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -799,6 +799,13 @@ static int record__synthesize(struct record *rec, bool tail)
                 return 0;
 
         if (file->is_pipe) {
+                err = perf_event__synthesize_features(
+                        tool, session, rec->evlist, process_synthesized_event);
+                if (err < 0) {
+                        pr_err("Couldn't synthesize features.\n");
+                        return err;
+                }
+
                 err = perf_event__synthesize_attrs(tool, session,
                                                    process_synthesized_event);
                 if (err < 0) {
@@ -1597,6 +1604,8 @@ static struct option __record_options[] = {
         OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
                     "per thread counts"),
         OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+        OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+                    "Record the sample physical addresses"),
         OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
         OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
                         &record.opts.sample_time_set,
@@ -1821,7 +1830,7 @@ int cmd_record(int argc, const char **argv)
                 record.opts.tail_synthesize = true;
 
         if (rec->evlist->nr_entries == 0 &&
-            perf_evlist__add_default(rec->evlist) < 0) {
+            __perf_evlist__add_default(rec->evlist, !record.opts.no_samples) < 0) {
                 pr_err("Not enough memory for event selector list\n");
                 goto out;
         }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 79a33eb1a10d..f9dff652dcbd 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -38,6 +38,7 @@
 #include "util/time-utils.h"
 #include "util/auxtrace.h"
 #include "util/units.h"
+#include "util/branch.h"
 
 #include <dlfcn.h>
 #include <errno.h>
@@ -73,6 +74,7 @@ struct report {
         u64                     queue_size;
         int                     socket_filter;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+        struct branch_type_stat brtype_stat;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
@@ -113,43 +115,60 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
         struct report *rep = arg;
         struct hist_entry *he = iter->he;
         struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
         struct mem_info *mi;
         struct branch_info *bi;
 
         if (!ui__has_annotation())
                 return 0;
 
-        hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
+        hist__account_cycles(sample->branch_stack, al, sample,
                              rep->nonany_branch_mode);
 
         if (sort__mode == SORT_MODE__BRANCH) {
                 bi = he->branch_info;
-                err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
+                err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
                 if (err)
                         goto out;
 
-                err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
+                err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
 
         } else if (rep->mem_mode) {
                 mi = he->mem_info;
-                err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+                err = addr_map_symbol__inc_samples(&mi->daddr, sample, evsel->idx);
                 if (err)
                         goto out;
 
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+                err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
 
         } else if (symbol_conf.cumulate_callchain) {
                 if (single)
-                        err = hist_entry__inc_addr_samples(he, evsel->idx,
+                        err = hist_entry__inc_addr_samples(he, sample, evsel->idx,
                                                            al->addr);
         } else {
-                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+                err = hist_entry__inc_addr_samples(he, sample, evsel->idx, al->addr);
         }
 
 out:
         return err;
 }
 
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+                                      struct addr_location *al __maybe_unused,
+                                      bool single __maybe_unused,
+                                      void *arg)
+{
+        struct hist_entry *he = iter->he;
+        struct report *rep = arg;
+        struct branch_info *bi;
+
+        bi = he->branch_info;
+        branch_type_count(&rep->brtype_stat, &bi->flags,
+                          bi->from.addr, bi->to.addr);
+
+        return 0;
+}
+
 static int process_sample_event(struct perf_tool *tool,
                                 union perf_event *event,
                                 struct perf_sample *sample,
@@ -188,6 +207,8 @@ static int process_sample_event(struct perf_tool *tool,
                  */
                 if (!sample->branch_stack)
                         goto out_put;
+
+                iter.add_entry_cb = hist_iter__branch_callback;
                 iter.ops = &hist_iter_branch;
         } else if (rep->mem_mode) {
                 iter.ops = &hist_iter_mem;
@@ -220,7 +241,7 @@ static int process_read_event(struct perf_tool *tool,
                 const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
                 int err = perf_read_values_add_value(&rep->show_threads_values,
                                            event->read.pid, event->read.tid,
-                                           event->read.id,
+                                           evsel->idx,
                                            name,
                                            event->read.value);
 
@@ -228,10 +249,6 @@ static int process_read_event(struct perf_tool *tool,
                         return err;
         }
 
-        dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-                    evsel ? perf_evsel__name(evsel) : "FAIL",
-                    event->read.value);
-
         return 0;
 }
 
@@ -258,10 +275,11 @@ static int report__setup_sample_type(struct report *rep)
                                     "'perf record' without -g?\n");
                         return -EINVAL;
                 }
-                if (symbol_conf.use_callchain) {
-                        ui__error("Selected -g or --branch-history but no "
-                                  "callchain data. Did\n"
-                                  "you call 'perf record' without -g?\n");
+                if (symbol_conf.use_callchain &&
+                        !symbol_conf.show_branchflag_count) {
+                        ui__error("Selected -g or --branch-history.\n"
+                                  "But no callchain or branch data.\n"
+                                  "Did you call 'perf record' without -g or -b?\n");
                         return -1;
                 }
         } else if (!callchain_param.enabled &&
@@ -396,7 +414,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
                 hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
                 hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-                               symbol_conf.use_callchain);
+                               symbol_conf.use_callchain ||
+                               symbol_conf.show_branchflag_count);
                 fprintf(stdout, "\n\n");
         }
 
@@ -410,6 +429,9 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
                 perf_read_values_destroy(&rep->show_threads_values);
         }
 
+        if (sort__mode == SORT_MODE__BRANCH)
+                branch_type_stat_display(stdout, &rep->brtype_stat);
+
         return 0;
 }
 
@@ -718,6 +740,7 @@ int cmd_report(int argc, const char **argv)
                         .id_index        = perf_event__process_id_index,
                         .auxtrace_info   = perf_event__process_auxtrace_info,
                         .auxtrace        = perf_event__process_auxtrace,
+                        .feature         = perf_event__process_feature,
                         .ordered_events  = true,
                         .ordering_requires_timestamps = true,
                 },
@@ -943,6 +966,8 @@ repeat:
         if (has_br_stack && branch_call_mode)
                 symbol_conf.show_branchflag_count = true;
 
+        memset(&report.brtype_stat, 0, sizeof(struct branch_type_stat));
+
         /*
          * Branch mode is a tristate:
          * -1 means default, so decide based on the file having branch data.
@@ -988,6 +1013,10 @@ repeat:
         /* Force tty output for header output and per-thread stat. */
         if (report.header || report.header_only || report.show_threads)
                 use_browser = 0;
+        if (report.header || report.header_only)
+                report.tool.show_feat_hdr = SHOW_FEAT_HEADER;
+        if (report.show_full_info)
+                report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
 
         if (strcmp(input_name, "-") != 0)
                 setup_browser(true);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 83cdc0a61fd6..3d4c3b5e1868 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -87,6 +87,7 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKINSN     = 1U << 23,
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
+        PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
 };
 
 struct output_option {
@@ -119,6 +120,7 @@ struct output_option {
         {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
         {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
         {.str = "synth", .field = PERF_OUTPUT_SYNTH},
+        {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 };
 
 enum {
@@ -175,7 +177,8 @@ static struct {
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+                              PERF_OUTPUT_PHYS_ADDR,
 
                 .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
@@ -382,6 +385,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_IREGS))
                 return -EINVAL;
 
+        if (PRINT_FIELD(PHYS_ADDR) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+                                        PERF_OUTPUT_PHYS_ADDR))
+                return -EINVAL;
+
         return 0;
 }
 
@@ -1446,6 +1454,9 @@ static void process_event(struct perf_script *script,
         if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
                 print_sample_bpf_output(sample);
         print_insn(sample, attr, thread, machine);
+
+        if (PRINT_FIELD(PHYS_ADDR))
+                printf("%16" PRIx64, sample->phys_addr);
         printf("\n");
 }
 
@@ -2199,16 +2210,11 @@ static struct script_desc *script_desc__findnew(const char *name)
 
         s = script_desc__new(name);
         if (!s)
-                goto out_delete_desc;
+                return NULL;
 
         script_desc__add(s);
 
         return s;
-
-out_delete_desc:
-        script_desc__delete(s);
-
-        return NULL;
 }
 
 static const char *ends_with(const char *str, const char *suffix)
@@ -2682,6 +2688,7 @@ int cmd_script(int argc, const char **argv)
                         .attr            = process_attr,
                         .event_update   = perf_event__process_event_update,
                         .tracing_data    = perf_event__process_tracing_data,
+                        .feature         = perf_event__process_feature,
                         .build_id        = perf_event__process_build_id,
                         .id_index        = perf_event__process_id_index,
                         .auxtrace_info   = perf_event__process_auxtrace_info,
@@ -2733,7 +2740,7 @@ int cmd_script(int argc, const char **argv)
                      "Valid types: hw,sw,trace,raw,synth. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
                      "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
                      parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
@@ -2972,10 +2979,13 @@ int cmd_script(int argc, const char **argv)
                 return -1;
 
         if (header || header_only) {
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER;
                 perf_session__fprintf_info(session, stdout, show_full_info);
                 if (header_only)
                         goto out_delete;
         }
+        if (show_full_info)
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
 
         if (symbol__init(&session->header.env) < 0)
                 goto out_delete;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 48ac53b199fc..69523ed55894 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -213,10 +213,20 @@ static void perf_stat__reset_stats(void)
 static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
         struct perf_event_attr *attr = &evsel->attr;
+        struct perf_evsel *leader = evsel->leader;
 
-        if (stat_config.scale)
+        if (stat_config.scale) {
                 attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
+        }
+
+        /*
+         * The event is part of non trivial group, let's enable
+         * the group read (for leader) and ID retrieval for all
+         * members.
+         */
+        if (leader->nr_members > 1)
+                attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;
 
         attr->inherit = !no_inherit;
 
@@ -333,13 +343,21 @@ static int read_counter(struct perf_evsel *counter)
                         struct perf_counts_values *count;
 
                         count = perf_counts(counter->counts, cpu, thread);
-                        if (perf_evsel__read(counter, cpu, thread, count)) {
+
+                        /*
+                         * The leader's group read loads data into its group members
+                         * (via perf_evsel__read_counter) and sets threir count->loaded.
+                         */
+                        if (!count->loaded &&
+                            perf_evsel__read_counter(counter, cpu, thread)) {
                                 counter->counts->scaled = -1;
                                 perf_counts(counter->counts, cpu, thread)->ena = 0;
                                 perf_counts(counter->counts, cpu, thread)->run = 0;
                                 return -1;
                         }
 
+                        count->loaded = false;
+
                         if (STAT_RECORD) {
                                 if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
                                         pr_err("failed to write stat event\n");
@@ -559,6 +577,11 @@ static int store_counter_ids(struct perf_evsel *counter)
         return __store_counter_ids(counter, cpus, threads);
 }
 
+static bool perf_evsel__should_store_id(struct perf_evsel *counter)
+{
+        return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
         int interval = stat_config.interval;
@@ -631,7 +654,8 @@ try_again:
                 if (l > unit_width)
                         unit_width = l;
 
-                if (STAT_RECORD && store_counter_ids(counter))
+                if (perf_evsel__should_store_id(counter) &&
+                    store_counter_ids(counter))
                         return -1;
         }
 
@@ -683,7 +707,7 @@ try_again:
                                 process_interval();
                         }
                 }
-                wait(&status);
+                waitpid(child_pid, &status, 0);
 
                 if (workload_exec_errno) {
                         const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
@@ -1233,7 +1257,7 @@ static bool collect_data(struct perf_evsel *counter,
         if (counter->merged_stat)
                 return false;
         cb(counter, data, true);
-        if (!no_merge)
+        if (!no_merge && counter->auto_merge_stats)
                 collect_all_aliases(counter, cb, data);
         return true;
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6052376634c0..ee954bde7e3e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
                 return err;
         }
 
-        err = symbol__disassemble(sym, map, NULL, 0, NULL);
+        err = symbol__disassemble(sym, map, NULL, 0, NULL, NULL);
         if (err == 0) {
 out_assign:
                 top->sym_filter_entry = he;
@@ -183,6 +183,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip)
 
 static void perf_top__record_precise_ip(struct perf_top *top,
                                         struct hist_entry *he,
+                                        struct perf_sample *sample,
                                         int counter, u64 ip)
 {
         struct annotation *notes;
@@ -199,7 +200,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
         if (pthread_mutex_trylock(&notes->lock))
                 return;
 
-        err = hist_entry__inc_addr_samples(he, counter, ip);
+        err = hist_entry__inc_addr_samples(he, sample, counter, ip);
 
         pthread_mutex_unlock(&notes->lock);
 
@@ -586,6 +587,13 @@ static void *display_thread_tui(void *arg)
                 .refresh        = top->delay_secs,
         };
 
+        /* In order to read symbols from other namespaces perf to  needs to call
+         * setns(2).  This isn't permitted if the struct_fs has multiple users.
+         * unshare(2) the fs so that we may continue to setns into namespaces
+         * that we're observing.
+         */
+        unshare(CLONE_FS);
+
         perf_top__sort_new_samples(top);
 
         /*
@@ -627,6 +635,13 @@ static void *display_thread(void *arg)
         struct perf_top *top = arg;
         int delay_msecs, c;
 
+        /* In order to read symbols from other namespaces perf to  needs to call
+         * setns(2).  This isn't permitted if the struct_fs has multiple users.
+         * unshare(2) the fs so that we may continue to setns into namespaces
+         * that we're observing.
+         */
+        unshare(CLONE_FS);
+
         display_setup_sig();
         pthread__unblock_sigwinch();
 repeat:
@@ -671,7 +686,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
         struct perf_evsel *evsel = iter->evsel;
 
         if (perf_hpp_list.sym && single)
-                perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
+                perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr);
 
         hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
                      !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
@@ -1205,6 +1220,7 @@ int cmd_top(int argc, const char **argv)
                     "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
                     "Show entries in a hierarchy"),
+        OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
         OPT_END()
         };
         const char * const top_usage[] = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 4b2a5d298197..771ddab94bb0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -64,6 +64,10 @@
 # define O_CLOEXEC              02000000
 #endif
 
+#ifndef F_LINUX_SPECIFIC_BASE
+# define F_LINUX_SPECIFIC_BASE  1024
+#endif
+
 struct trace {
         struct perf_tool        tool;
         struct syscalltbl       *sctbl;
@@ -279,34 +283,21 @@ out_delete:
         ({ struct syscall_tp *fields = evsel->priv; \
            fields->name.pointer(&fields->name, sample); })
 
-struct strarray {
-        int         offset;
-        int         nr_entries;
-        const char **entries;
-};
+size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val)
+{
+        int idx = val - sa->offset;
 
-#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
-        .nr_entries = ARRAY_SIZE(array), \
-        .entries = array, \
-}
+        if (idx < 0 || idx >= sa->nr_entries)
+                return scnprintf(bf, size, intfmt, val);
 
-#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
-        .offset     = off, \
-        .nr_entries = ARRAY_SIZE(array), \
-        .entries = array, \
+        return scnprintf(bf, size, "%s", sa->entries[idx]);
 }
 
 static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
                                                 const char *intfmt,
                                                 struct syscall_arg *arg)
 {
-        struct strarray *sa = arg->parm;
-        int idx = arg->val - sa->offset;
-
-        if (idx < 0 || idx >= sa->nr_entries)
-                return scnprintf(bf, size, intfmt, arg->val);
-
-        return scnprintf(bf, size, "%s", sa->entries[idx]);
+        return strarray__scnprintf(arg->parm, bf, size, intfmt, arg->val);
 }
 
 static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
@@ -317,24 +308,35 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
 
 #define SCA_STRARRAY syscall_arg__scnprintf_strarray
 
-#if defined(__i386__) || defined(__x86_64__)
-/*
- * FIXME: Make this available to all arches as soon as the ioctl beautifier
- *        gets rewritten to support all arches.
- */
-static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
-                                                 struct syscall_arg *arg)
-{
-        return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
+struct strarrays {
+        int             nr_entries;
+        struct strarray **entries;
+};
+
+#define DEFINE_STRARRAYS(array) struct strarrays strarrays__##array = { \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
 }
 
-#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
-#endif /* defined(__i386__) || defined(__x86_64__) */
+size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size,
+                                        struct syscall_arg *arg)
+{
+        struct strarrays *sas = arg->parm;
+        int i;
 
-static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
-                                        struct syscall_arg *arg);
+        for (i = 0; i < sas->nr_entries; ++i) {
+                struct strarray *sa = sas->entries[i];
+                int idx = arg->val - sa->offset;
 
-#define SCA_FD syscall_arg__scnprintf_fd
+                if (idx >= 0 && idx < sa->nr_entries) {
+                        if (sa->entries[idx] == NULL)
+                                break;
+                        return scnprintf(bf, size, "%s", sa->entries[idx]);
+                }
+        }
+
+        return scnprintf(bf, size, "%d", arg->val);
+}
 
 #ifndef AT_FDCWD
 #define AT_FDCWD        -100
@@ -358,21 +360,20 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 
 #define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
 
-static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
-                                         struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg)
 {
         return scnprintf(bf, size, "%#lx", arg->val);
 }
 
-#define SCA_HEX syscall_arg__scnprintf_hex
-
-static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
-                                         struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg)
 {
         return scnprintf(bf, size, "%d", arg->val);
 }
 
-#define SCA_INT syscall_arg__scnprintf_int
+size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return scnprintf(bf, size, "%ld", arg->val);
+}
 
 static const char *bpf_cmd[] = {
         "MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
@@ -407,12 +408,27 @@ static DEFINE_STRARRAY(whences);
 
 static const char *fcntl_cmds[] = {
         "DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
-        "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
-        "F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
-        "F_GETOWNER_UIDS",
+        "SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "GETLK64",
+        "SETLK64", "SETLKW64", "SETOWN_EX", "GETOWN_EX",
+        "GETOWNER_UIDS",
 };
 static DEFINE_STRARRAY(fcntl_cmds);
 
+static const char *fcntl_linux_specific_cmds[] = {
+        "SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
+        "SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
+        "GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
+};
+
+static DEFINE_STRARRAY_OFFSET(fcntl_linux_specific_cmds, F_LINUX_SPECIFIC_BASE);
+
+static struct strarray *fcntl_cmds_arrays[] = {
+        &strarray__fcntl_cmds,
+        &strarray__fcntl_linux_specific_cmds,
+};
+
+static DEFINE_STRARRAYS(fcntl_cmds_arrays);
+
 static const char *rlimit_resources[] = {
         "CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
         "MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
@@ -495,33 +511,6 @@ static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
 
 #define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
 
-#if defined(__i386__) || defined(__x86_64__)
-/*
- * FIXME: Make this available to all arches.
- */
-#define TCGETS          0x5401
-
-static const char *tioctls[] = {
-        "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
-        "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
-        "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
-        "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
-        "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
-        "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
-        "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
-        "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
-        "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
-        "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
-        "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
-        [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
-        "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
-        "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
-        "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
-};
-
-static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
-#endif /* defined(__i386__) || defined(__x86_64__) */
-
 #ifndef GRND_NONBLOCK
 #define GRND_NONBLOCK   0x0001
 #endif
@@ -552,9 +541,9 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 #define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags
 
-#define STRARRAY(arg, name, array) \
-          .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
-          .arg_parm      = { [arg] = &strarray__##array, }
+#define STRARRAY(name, array) \
+          { .scnprintf  = SCA_STRARRAY, \
+            .parm       = &strarray__##array, }
 
 #include "trace/beauty/eventfd.c"
 #include "trace/beauty/flock.c"
@@ -571,242 +560,219 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 #include "trace/beauty/socket_type.c"
 #include "trace/beauty/waitid_options.c"
 
+struct syscall_arg_fmt {
+        size_t     (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+        void       *parm;
+        const char *name;
+        bool       show_zero;
+};
+
 static struct syscall_fmt {
         const char *name;
         const char *alias;
-        size_t     (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
-        void       *arg_parm[6];
-        bool       errmsg;
+        struct syscall_arg_fmt arg[6];
+        u8         nr_args;
         bool       errpid;
         bool       timeout;
         bool       hexret;
 } syscall_fmts[] = {
-        { .name     = "access",     .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_ACCMODE,  /* mode */ }, },
-        { .name     = "arch_prctl", .errmsg = true, .alias = "prctl", },
-        { .name     = "bpf",        .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
+        { .name     = "access",
+          .arg = { [1] = { .scnprintf = SCA_ACCMODE,  /* mode */ }, }, },
+        { .name     = "arch_prctl", .alias = "prctl", },
+        { .name     = "bpf",
+          .arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
         { .name     = "brk",        .hexret = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
-        { .name     = "chdir",      .errmsg = true, },
-        { .name     = "chmod",      .errmsg = true, },
-        { .name     = "chroot",     .errmsg = true, },
-        { .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
-        { .name     = "clone",      .errpid = true, },
-        { .name     = "close",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
-        { .name     = "connect",    .errmsg = true, },
-        { .name     = "creat",      .errmsg = true, },
-        { .name     = "dup",        .errmsg = true, },
-        { .name     = "dup2",       .errmsg = true, },
-        { .name     = "dup3",       .errmsg = true, },
-        { .name     = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
-        { .name     = "eventfd2",   .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
-        { .name     = "faccessat",  .errmsg = true, },
-        { .name     = "fadvise64",  .errmsg = true, },
-        { .name     = "fallocate",  .errmsg = true, },
-        { .name     = "fchdir",     .errmsg = true, },
-        { .name     = "fchmod",     .errmsg = true, },
-        { .name     = "fchmodat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "fchown",     .errmsg = true, },
-        { .name     = "fchownat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "fcntl",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
-          .arg_parm      = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
-        { .name     = "fdatasync",  .errmsg = true, },
-        { .name     = "flock",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
-        { .name     = "fsetxattr",  .errmsg = true, },
-        { .name     = "fstat",      .errmsg = true, .alias = "newfstat", },
-        { .name     = "fstatat",    .errmsg = true, .alias = "newfstatat", },
-        { .name     = "fstatfs",    .errmsg = true, },
-        { .name     = "fsync",    .errmsg = true, },
-        { .name     = "ftruncate", .errmsg = true, },
-        { .name     = "futex",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
-        { .name     = "futimesat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "getdents",   .errmsg = true, },
-        { .name     = "getdents64", .errmsg = true, },
-        { .name     = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* brk */ }, }, },
+        { .name     = "clock_gettime",
+          .arg = { [0] = STRARRAY(clk_id, clockid), }, },
+        { .name     = "clone",      .errpid = true, .nr_args = 5,
+          .arg = { [0] = { .name = "flags",         .scnprintf = SCA_CLONE_FLAGS, },
+                   [1] = { .name = "child_stack",   .scnprintf = SCA_HEX, },
+                   [2] = { .name = "parent_tidptr", .scnprintf = SCA_HEX, },
+                   [3] = { .name = "child_tidptr",  .scnprintf = SCA_HEX, },
+                   [4] = { .name = "tls",           .scnprintf = SCA_HEX, }, }, },
+        { .name     = "close",
+          .arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
+        { .name     = "epoll_ctl",
+          .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
+        { .name     = "eventfd2",
+          .arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, },
+        { .name     = "fchmodat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "fchownat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "fcntl",
+          .arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */
+                           .parm      = &strarrays__fcntl_cmds_arrays,
+                           .show_zero = true, },
+                   [2] = { .scnprintf =  SCA_FCNTL_ARG, /* arg */ }, }, },
+        { .name     = "flock",
+          .arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
+        { .name     = "fstat", .alias = "newfstat", },
+        { .name     = "fstatat", .alias = "newfstatat", },
+        { .name     = "futex",
+          .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ }, }, },
+        { .name     = "futimesat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "getitimer",
+          .arg = { [0] = STRARRAY(which, itimers), }, },
         { .name     = "getpid",     .errpid = true, },
         { .name     = "getpgid",    .errpid = true, },
         { .name     = "getppid",    .errpid = true, },
-        { .name     = "getrandom",  .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
-        { .name     = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-        { .name     = "getxattr",   .errmsg = true, },
-        { .name     = "inotify_add_watch",          .errmsg = true, },
-        { .name     = "ioctl",      .errmsg = true,
-          .arg_scnprintf = {
+        { .name     = "getrandom",
+          .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
+        { .name     = "getrlimit",
+          .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "ioctl",
+          .arg = {
 #if defined(__i386__) || defined(__x86_64__)
 /*
  * FIXME: Make this available to all arches.
  */
-                             [1] = SCA_STRHEXARRAY, /* cmd */
-                             [2] = SCA_HEX, /* arg */ },
-          .arg_parm      = { [1] = &strarray__tioctls, /* cmd */ }, },
+                   [1] = { .scnprintf = SCA_IOCTL_CMD, /* cmd */ },
+                   [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #else
-                             [2] = SCA_HEX, /* arg */ }, },
+                   [2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
 #endif
-        { .name     = "keyctl",     .errmsg = true, STRARRAY(0, option, keyctl_options), },
-        { .name     = "kill",       .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "lchown",    .errmsg = true, },
-        { .name     = "lgetxattr",  .errmsg = true, },
-        { .name     = "linkat",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "listxattr",  .errmsg = true, },
-        { .name     = "llistxattr", .errmsg = true, },
-        { .name     = "lremovexattr",  .errmsg = true, },
-        { .name     = "lseek",      .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
-          .arg_parm      = { [2] = &strarray__whences, /* whence */ }, },
-        { .name     = "lsetxattr",  .errmsg = true, },
-        { .name     = "lstat",      .errmsg = true, .alias = "newlstat", },
-        { .name     = "lsxattr",    .errmsg = true, },
-        { .name     = "madvise",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX,      /* start */
-                             [2] = SCA_MADV_BHV, /* behavior */ }, },
-        { .name     = "mkdir",    .errmsg = true, },
-        { .name     = "mkdirat",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "mknod",      .errmsg = true, },
-        { .name     = "mknodat",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
-        { .name     = "mlock",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "mlockall",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
+        { .name     = "keyctl",
+          .arg = { [0] = STRARRAY(option, keyctl_options), }, },
+        { .name     = "kill",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "linkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "lseek",
+          .arg = { [2] = STRARRAY(whence, whences), }, },
+        { .name     = "lstat", .alias = "newlstat", },
+        { .name     = "madvise",
+          .arg = { [0] = { .scnprintf = SCA_HEX,      /* start */ },
+                   [2] = { .scnprintf = SCA_MADV_BHV, /* behavior */ }, }, },
+        { .name     = "mkdirat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "mknodat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
+        { .name     = "mlock",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "mlockall",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
         { .name     = "mmap",       .hexret = true,
 /* The standard mmap maps to old_mmap on s390x */
 #if defined(__s390x__)
         .alias = "old_mmap",
 #endif
-          .arg_scnprintf = { [0] = SCA_HEX,       /* addr */
-                             [2] = SCA_MMAP_PROT, /* prot */
-                             [3] = SCA_MMAP_FLAGS, /* flags */ }, },
-        { .name     = "mprotect",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* start */
-                             [2] = SCA_MMAP_PROT, /* prot */ }, },
-        { .name     = "mq_unlink", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* u_name */ }, },
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* addr */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ },
+                   [3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ }, }, },
+        { .name     = "mprotect",
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* start */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ }, }, },
+        { .name     = "mq_unlink",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* u_name */ }, }, },
         { .name     = "mremap",     .hexret = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */
-                             [3] = SCA_MREMAP_FLAGS, /* flags */
-                             [4] = SCA_HEX, /* new_addr */ }, },
-        { .name     = "munlock",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "munmap",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
-        { .name     = "name_to_handle_at", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "newfstatat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "open",       .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "open_by_handle_at", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-                             [2] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "openat",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
-                             [2] = SCA_OPEN_FLAGS, /* flags */ }, },
-        { .name     = "perf_event_open", .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_INT, /* cpu */
-                             [3] = SCA_FD,  /* group_fd */
-                             [4] = SCA_PERF_FLAGS,  /* flags */ }, },
-        { .name     = "pipe2",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
-        { .name     = "poll",       .errmsg = true, .timeout = true, },
-        { .name     = "ppoll",      .errmsg = true, .timeout = true, },
-        { .name     = "pread",      .errmsg = true, .alias = "pread64", },
-        { .name     = "preadv",     .errmsg = true, .alias = "pread", },
-        { .name     = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
-        { .name     = "pwrite",     .errmsg = true, .alias = "pwrite64", },
-        { .name     = "pwritev",    .errmsg = true, },
-        { .name     = "read",       .errmsg = true, },
-        { .name     = "readlink",   .errmsg = true, },
-        { .name     = "readlinkat", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "readv",      .errmsg = true, },
-        { .name     = "recvfrom",   .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "recvmmsg",   .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "recvmsg",    .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "removexattr", .errmsg = true, },
-        { .name     = "renameat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "rmdir",    .errmsg = true, },
-        { .name     = "rt_sigaction", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
-        { .name     = "rt_sigqueueinfo", .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "rt_tgsigqueueinfo", .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "sched_getattr",        .errmsg = true, },
-        { .name     = "sched_setattr",        .errmsg = true, },
-        { .name     = "sched_setscheduler",   .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
-        { .name     = "seccomp", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */
-                             [1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
-        { .name     = "select",     .errmsg = true, .timeout = true, },
-        { .name     = "sendmmsg",    .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "sendmsg",    .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
-        { .name     = "sendto",     .errmsg = true,
-          .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
+          .arg = { [0] = { .scnprintf = SCA_HEX,          /* addr */ },
+                   [3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ },
+                   [4] = { .scnprintf = SCA_HEX,          /* new_addr */ }, }, },
+        { .name     = "munlock",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "munmap",
+          .arg = { [0] = { .scnprintf = SCA_HEX, /* addr */ }, }, },
+        { .name     = "name_to_handle_at",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "newfstatat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "open",
+          .arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "open_by_handle_at",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,       /* dfd */ },
+                   [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "openat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,       /* dfd */ },
+                   [2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
+        { .name     = "perf_event_open",
+          .arg = { [2] = { .scnprintf = SCA_INT,        /* cpu */ },
+                   [3] = { .scnprintf = SCA_FD,         /* group_fd */ },
+                   [4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
+        { .name     = "pipe2",
+          .arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, },
+        { .name     = "pkey_alloc",
+          .arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS,   /* access_rights */ }, }, },
+        { .name     = "pkey_free",
+          .arg = { [0] = { .scnprintf = SCA_INT,        /* key */ }, }, },
+        { .name     = "pkey_mprotect",
+          .arg = { [0] = { .scnprintf = SCA_HEX,        /* start */ },
+                   [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ },
+                   [3] = { .scnprintf = SCA_INT,        /* pkey */ }, }, },
+        { .name     = "poll", .timeout = true, },
+        { .name     = "ppoll", .timeout = true, },
+        { .name     = "pread", .alias = "pread64", },
+        { .name     = "preadv", .alias = "pread", },
+        { .name     = "prlimit64",
+          .arg = { [1] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "pwrite", .alias = "pwrite64", },
+        { .name     = "readlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "recvfrom",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "recvmmsg",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "recvmsg",
+          .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "renameat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "rt_sigaction",
+          .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "rt_sigprocmask",
+          .arg = { [0] = STRARRAY(how, sighow), }, },
+        { .name     = "rt_sigqueueinfo",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "rt_tgsigqueueinfo",
+          .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "sched_setscheduler",
+          .arg = { [1] = { .scnprintf = SCA_SCHED_POLICY, /* policy */ }, }, },
+        { .name     = "seccomp",
+          .arg = { [0] = { .scnprintf = SCA_SECCOMP_OP,    /* op */ },
+                   [1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, },
+        { .name     = "select", .timeout = true, },
+        { .name     = "sendmmsg",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "sendmsg",
+          .arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
+        { .name     = "sendto",
+          .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
         { .name     = "set_tid_address", .errpid = true, },
-        { .name     = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
-        { .name     = "setpgid",    .errmsg = true, },
-        { .name     = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
-        { .name     = "setxattr",   .errmsg = true, },
-        { .name     = "shutdown",   .errmsg = true, },
-        { .name     = "socket",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
-                             [1] = SCA_SK_TYPE, /* type */ },
-          .arg_parm      = { [0] = &strarray__socket_families, /* family */ }, },
-        { .name     = "socketpair", .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
-                             [1] = SCA_SK_TYPE, /* type */ },
-          .arg_parm      = { [0] = &strarray__socket_families, /* family */ }, },
-        { .name     = "stat",       .errmsg = true, .alias = "newstat", },
-        { .name     = "statfs",     .errmsg = true, },
-        { .name     = "statx",      .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* flags */
-                             [2] = SCA_STATX_FLAGS, /* flags */
-                             [3] = SCA_STATX_MASK, /* mask */ }, },
-        { .name     = "swapoff",    .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
-        { .name     = "swapon",     .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
-        { .name     = "symlinkat",  .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "tgkill",     .errmsg = true,
-          .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "tkill",      .errmsg = true,
-          .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
-        { .name     = "truncate",   .errmsg = true, },
-        { .name     = "uname",      .errmsg = true, .alias = "newuname", },
-        { .name     = "unlinkat",   .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
-        { .name     = "utime",  .errmsg = true, },
-        { .name     = "utimensat",  .errmsg = true,
-          .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
-        { .name     = "utimes",  .errmsg = true, },
-        { .name     = "vmsplice",  .errmsg = true, },
+        { .name     = "setitimer",
+          .arg = { [0] = STRARRAY(which, itimers), }, },
+        { .name     = "setrlimit",
+          .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+        { .name     = "socket",
+          .arg = { [0] = STRARRAY(family, socket_families),
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+        { .name     = "socketpair",
+          .arg = { [0] = STRARRAY(family, socket_families),
+                   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+        { .name     = "stat", .alias = "newstat", },
+        { .name     = "statx",
+          .arg = { [0] = { .scnprintf = SCA_FDAT,        /* fdat */ },
+                   [2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } ,
+                   [3] = { .scnprintf = SCA_STATX_MASK,  /* mask */ }, }, },
+        { .name     = "swapoff",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
+        { .name     = "swapon",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
+        { .name     = "symlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "tgkill",
+          .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "tkill",
+          .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
+        { .name     = "uname", .alias = "newuname", },
+        { .name     = "unlinkat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+        { .name     = "utimensat",
+          .arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, },
         { .name     = "wait4",      .errpid = true,
-          .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
+          .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
         { .name     = "waitid",     .errpid = true,
-          .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
-        { .name     = "write",      .errmsg = true, },
-        { .name     = "writev",     .errmsg = true, },
+          .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
 };
 
 static int syscall_fmt__cmp(const void *name, const void *fmtp)
@@ -828,8 +794,7 @@ struct syscall {
         const char          *name;
         bool                is_exit;
         struct syscall_fmt  *fmt;
-        size_t              (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
-        void                **arg_parm;
+        struct syscall_arg_fmt *arg_fmt;
 };
 
 /*
@@ -859,6 +824,8 @@ static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
  * filename.ptr: The filename char pointer that will be vfs_getname'd
  * filename.entry_str_pos: Where to insert the string translated from
  *                         filename.ptr by the vfs_getname tracepoint/kprobe.
+ * ret_scnprintf: syscall args may set this to a different syscall return
+ *                formatter, for instance, fcntl may return fds, file flags, etc.
  */
 struct thread_trace {
         u64               entry_time;
@@ -867,6 +834,7 @@ struct thread_trace {
         unsigned long     pfmaj, pfmin;
         char              *entry_str;
         double            runtime_ms;
+        size_t            (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
         struct {
                 unsigned long ptr;
                 short int     entry_str_pos;
@@ -917,6 +885,15 @@ fail:
         return NULL;
 }
 
+
+void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
+                                    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg))
+{
+        struct thread_trace *ttrace = thread__priv(arg->thread);
+
+        ttrace->ret_scnprintf = ret_scnprintf;
+}
+
 #define TRACE_PFMAJ             (1 << 0)
 #define TRACE_PFMIN             (1 << 1)
 
@@ -996,8 +973,7 @@ static const char *thread__fd_path(struct thread *thread, int fd,
         return ttrace->paths.table[fd];
 }
 
-static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
-                                        struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
 {
         int fd = arg->val;
         size_t printed = scnprintf(bf, size, "%d", fd);
@@ -1162,32 +1138,46 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
         return err;
 }
 
+static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
+{
+        int idx;
+
+        if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
+                nr_args = sc->fmt->nr_args;
+
+        sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
+        if (sc->arg_fmt == NULL)
+                return -1;
+
+        for (idx = 0; idx < nr_args; ++idx) {
+                if (sc->fmt)
+                        sc->arg_fmt[idx] = sc->fmt->arg[idx];
+        }
+
+        sc->nr_args = nr_args;
+        return 0;
+}
+
 static int syscall__set_arg_fmts(struct syscall *sc)
 {
         struct format_field *field;
         int idx = 0, len;
 
-        sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
-        if (sc->arg_scnprintf == NULL)
-                return -1;
-
-        if (sc->fmt)
-                sc->arg_parm = sc->fmt->arg_parm;
+        for (field = sc->args; field; field = field->next, ++idx) {
+                if (sc->fmt && sc->fmt->arg[idx].scnprintf)
+                        continue;
 
-        for (field = sc->args; field; field = field->next) {
-                if (sc->fmt && sc->fmt->arg_scnprintf[idx])
-                        sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
-                else if (strcmp(field->type, "const char *") == 0 &&
+                if (strcmp(field->type, "const char *") == 0 &&
                          (strcmp(field->name, "filename") == 0 ||
                           strcmp(field->name, "path") == 0 ||
                           strcmp(field->name, "pathname") == 0))
-                        sc->arg_scnprintf[idx] = SCA_FILENAME;
+                        sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
                 else if (field->flags & FIELD_IS_POINTER)
-                        sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
+                        sc->arg_fmt[idx].scnprintf = syscall_arg__scnprintf_hex;
                 else if (strcmp(field->type, "pid_t") == 0)
-                        sc->arg_scnprintf[idx] = SCA_PID;
+                        sc->arg_fmt[idx].scnprintf = SCA_PID;
                 else if (strcmp(field->type, "umode_t") == 0)
-                        sc->arg_scnprintf[idx] = SCA_MODE_T;
+                        sc->arg_fmt[idx].scnprintf = SCA_MODE_T;
                 else if ((strcmp(field->type, "int") == 0 ||
                           strcmp(field->type, "unsigned int") == 0 ||
                           strcmp(field->type, "long") == 0) &&
@@ -1200,9 +1190,8 @@ static int syscall__set_arg_fmts(struct syscall *sc)
                          * 23 unsigned int
                          * 7 unsigned long
                          */
-                        sc->arg_scnprintf[idx] = SCA_FD;
+                        sc->arg_fmt[idx].scnprintf = SCA_FD;
                 }
-                ++idx;
         }
 
         return 0;
@@ -1247,11 +1236,13 @@ static int trace__read_syscall_info(struct trace *trace, int id)
                 sc->tp_format = trace_event__tp_format("syscalls", tp_name);
         }
 
+        if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
+                return -1;
+
         if (IS_ERR(sc->tp_format))
                 return -1;
 
         sc->args = sc->tp_format->format.fields;
-        sc->nr_args = sc->tp_format->format.nr_fields;
         /*
          * We need to check and discard the first variable '__syscall_nr'
          * or 'nr' that mean the syscall number. It is needless here.
@@ -1270,6 +1261,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 static int trace__validate_ev_qualifier(struct trace *trace)
 {
         int err = 0, i;
+        size_t nr_allocated;
         struct str_node *pos;
 
         trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
@@ -1283,13 +1275,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
                 goto out;
         }
 
+        nr_allocated = trace->ev_qualifier_ids.nr;
         i = 0;
 
         strlist__for_each_entry(pos, trace->ev_qualifier) {
                 const char *sc = pos->s;
-                int id = syscalltbl__id(trace->sctbl, sc);
+                int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
 
                 if (id < 0) {
+                        id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
+                        if (id >= 0)
+                                goto matches;
+
                         if (err == 0) {
                                 fputs("Error:\tInvalid syscall ", trace->output);
                                 err = -EINVAL;
@@ -1299,13 +1296,37 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
                         fputs(sc, trace->output);
                 }
-
+matches:
                 trace->ev_qualifier_ids.entries[i++] = id;
+                if (match_next == -1)
+                        continue;
+
+                while (1) {
+                        id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
+                        if (id < 0)
+                                break;
+                        if (nr_allocated == trace->ev_qualifier_ids.nr) {
+                                void *entries;
+
+                                nr_allocated += 8;
+                                entries = realloc(trace->ev_qualifier_ids.entries,
+                                                  nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
+                                if (entries == NULL) {
+                                        err = -ENOMEM;
+                                        fputs("\nError:\t Not enough memory for parsing\n", trace->output);
+                                        goto out_free;
+                                }
+                                trace->ev_qualifier_ids.entries = entries;
+                        }
+                        trace->ev_qualifier_ids.nr++;
+                        trace->ev_qualifier_ids.entries[i++] = id;
+                }
         }
 
         if (err < 0) {
                 fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
                       "\nHint:\tand: 'man syscalls'\n", trace->output);
+out_free:
                 zfree(&trace->ev_qualifier_ids.entries);
                 trace->ev_qualifier_ids.nr = 0;
         }
@@ -1321,33 +1342,68 @@ out:
  * variable to read it. Most notably this avoids extended load instructions
  * on unaligned addresses
  */
+unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx)
+{
+        unsigned long val;
+        unsigned char *p = arg->args + sizeof(unsigned long) * idx;
+
+        memcpy(&val, p, sizeof(val));
+        return val;
+}
+
+static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
+                                      struct syscall_arg *arg)
+{
+        if (sc->arg_fmt && sc->arg_fmt[arg->idx].name)
+                return scnprintf(bf, size, "%s: ", sc->arg_fmt[arg->idx].name);
+
+        return scnprintf(bf, size, "arg%d: ", arg->idx);
+}
+
+static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
+                                     struct syscall_arg *arg, unsigned long val)
+{
+        if (sc->arg_fmt && sc->arg_fmt[arg->idx].scnprintf) {
+                arg->val = val;
+                if (sc->arg_fmt[arg->idx].parm)
+                        arg->parm = sc->arg_fmt[arg->idx].parm;
+                return sc->arg_fmt[arg->idx].scnprintf(bf, size, arg);
+        }
+        return scnprintf(bf, size, "%ld", val);
+}
 
 static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                                       unsigned char *args, struct trace *trace,
                                       struct thread *thread)
 {
         size_t printed = 0;
-        unsigned char *p;
         unsigned long val;
+        u8 bit = 1;
+        struct syscall_arg arg = {
+                .args   = args,
+                .idx    = 0,
+                .mask   = 0,
+                .trace  = trace,
+                .thread = thread,
+        };
+        struct thread_trace *ttrace = thread__priv(thread);
+
+        /*
+         * Things like fcntl will set this in its 'cmd' formatter to pick the
+         * right formatter for the return value (an fd? file flags?), which is
+         * not needed for syscalls that always return a given type, say an fd.
+         */
+        ttrace->ret_scnprintf = NULL;
 
         if (sc->args != NULL) {
                 struct format_field *field;
-                u8 bit = 1;
-                struct syscall_arg arg = {
-                        .idx    = 0,
-                        .mask   = 0,
-                        .trace  = trace,
-                        .thread = thread,
-                };
 
                 for (field = sc->args; field;
                      field = field->next, ++arg.idx, bit <<= 1) {
                         if (arg.mask & bit)
                                 continue;
 
-                        /* special care for unaligned accesses */
-                        p = args + sizeof(unsigned long) * arg.idx;
-                        memcpy(&val, p, sizeof(val));
+                        val = syscall_arg__val(&arg, arg.idx);
 
                         /*
                          * Suppress this argument if its value is zero and
@@ -1355,23 +1411,16 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                          * strarray for it.
                          */
                         if (val == 0 &&
-                            !(sc->arg_scnprintf &&
-                              sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
-                              sc->arg_parm[arg.idx]))
+                            !(sc->arg_fmt &&
+                              (sc->arg_fmt[arg.idx].show_zero ||
+                               sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAY ||
+                               sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAYS) &&
+                              sc->arg_fmt[arg.idx].parm))
                                 continue;
 
                         printed += scnprintf(bf + printed, size - printed,
                                              "%s%s: ", printed ? ", " : "", field->name);
-                        if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
-                                arg.val = val;
-                                if (sc->arg_parm)
-                                        arg.parm = sc->arg_parm[arg.idx];
-                                printed += sc->arg_scnprintf[arg.idx](bf + printed,
-                                                                      size - printed, &arg);
-                        } else {
-                                printed += scnprintf(bf + printed, size - printed,
-                                                     "%ld", val);
-                        }
+                        printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
                 }
         } else if (IS_ERR(sc->tp_format)) {
                 /*
@@ -1379,16 +1428,17 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                  * may end up not having any args, like with gettid(), so only
                  * print the raw args when we didn't manage to read it.
                  */
-                int i = 0;
-
-                while (i < 6) {
-                        /* special care for unaligned accesses */
-                        p = args + sizeof(unsigned long) * i;
-                        memcpy(&val, p, sizeof(val));
-                        printed += scnprintf(bf + printed, size - printed,
-                                             "%sarg%d: %ld",
-                                             printed ? ", " : "", i, val);
-                        ++i;
+                while (arg.idx < sc->nr_args) {
+                        if (arg.mask & bit)
+                                goto next_arg;
+                        val = syscall_arg__val(&arg, arg.idx);
+                        if (printed)
+                                printed += scnprintf(bf + printed, size - printed, ", ");
+                        printed += syscall__scnprintf_name(sc, bf + printed, size - printed, &arg);
+                        printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
+next_arg:
+                        ++arg.idx;
+                        bit <<= 1;
                 }
         }
 
@@ -1635,17 +1685,31 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
         }
 
         if (sc->fmt == NULL) {
+                if (ret < 0)
+                        goto errno_print;
 signed_print:
                 fprintf(trace->output, ") = %ld", ret);
-        } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
+        } else if (ret < 0) {
+errno_print: {
                 char bf[STRERR_BUFSIZE];
                 const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
                            *e = audit_errno_to_name(-ret);
 
                 fprintf(trace->output, ") = -1 %s %s", e, emsg);
+        }
         } else if (ret == 0 && sc->fmt->timeout)
                 fprintf(trace->output, ") = 0 Timeout");
-        else if (sc->fmt->hexret)
+        else if (ttrace->ret_scnprintf) {
+                char bf[1024];
+                struct syscall_arg arg = {
+                        .val    = ret,
+                        .thread = thread,
+                        .trace  = trace,
+                };
+                ttrace->ret_scnprintf(bf, sizeof(bf), &arg);
+                ttrace->ret_scnprintf = NULL;
+                fprintf(trace->output, ") = %s", bf);
+        } else if (sc->fmt->hexret)
                 fprintf(trace->output, ") = %#lx", ret);
         else if (sc->fmt->errpid) {
                 struct thread *child = machine__find_thread(trace->host, ret, ret);
@@ -2171,6 +2235,30 @@ out_enomem:
         goto out;
 }
 
+static int trace__set_filter_loop_pids(struct trace *trace)
+{
+        unsigned int nr = 1;
+        pid_t pids[32] = {
+                getpid(),
+        };
+        struct thread *thread = machine__find_thread(trace->host, pids[0], pids[0]);
+
+        while (thread && nr < ARRAY_SIZE(pids)) {
+                struct thread *parent = machine__find_thread(trace->host, thread->ppid, thread->ppid);
+
+                if (parent == NULL)
+                        break;
+
+                if (!strcmp(thread__comm_str(parent), "sshd")) {
+                        pids[nr++] = parent->tid;
+                        break;
+                }
+                thread = parent;
+        }
+
+        return perf_evlist__set_filter_pids(trace->evlist, nr, pids);
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
         struct perf_evlist *evlist = trace->evlist;
@@ -2294,7 +2382,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         if (trace->filter_pids.nr > 0)
                 err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
         else if (thread_map__pid(evlist->threads, 0) == -1)
-                err = perf_evlist__set_filter_pid(evlist, getpid());
+                err = trace__set_filter_loop_pids(trace);
 
         if (err < 0)
                 goto out_error_mem;
@@ -2756,7 +2844,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
         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;
+        int len = strlen(str) + 1, err = -1, list, idx;
         char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
         char group_name[PATH_MAX];
 
@@ -2773,7 +2861,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
                         *sep = '\0';
 
                 list = 0;
-                if (syscalltbl__id(trace->sctbl, s) >= 0) {
+                if (syscalltbl__id(trace->sctbl, s) >= 0 ||
+                    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
                         list = 1;
                 } else {
                         path__join(group_name, sizeof(group_name), strace_groups_dir, s);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 83fe2202382e..932fda54b8a6 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -1,9 +1,15 @@
 #!/bin/sh
 
 HEADERS='
+include/uapi/drm/drm.h
+include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/kvm.h
 include/uapi/linux/perf_event.h
+include/uapi/linux/sched.h
 include/uapi/linux/stat.h
+include/uapi/linux/vhost.h
+include/uapi/sound/asound.h
 include/linux/hash.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
@@ -16,6 +22,7 @@ arch/x86/include/uapi/asm/perf_regs.h
 arch/x86/include/uapi/asm/kvm.h
 arch/x86/include/uapi/asm/kvm_perf.h
 arch/x86/include/uapi/asm/svm.h
+arch/x86/include/uapi/asm/unistd.h
 arch/x86/include/uapi/asm/vmx.h
 arch/powerpc/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm.h
@@ -29,12 +36,13 @@ include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/asm-generic/bitops/fls64.h
 include/linux/coresight-pmu.h
+include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
 '
 
 check () {
   file=$1
-  opts=
+  opts="--ignore-blank-lines --ignore-space-change"
 
   shift
   while [ -n "$*" ]; do
@@ -45,7 +53,7 @@ check () {
   cmd="diff $opts ../$file ../../$file > /dev/null"
 
   test -f ../../$file &&
-  eval $cmd || echo "Warning: $file differs from kernel" >&2
+  eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
 }
 
 
@@ -55,7 +63,7 @@ for i in $HEADERS; do
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check arch/x86/lib/memset_64.S        -B -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check include/uapi/asm-generic/mman.h -B -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
-check include/uapi/linux/mman.h       -B -I "^#include <\(uapi/\)*asm/mman.h>"
+check arch/x86/lib/memcpy_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check arch/x86/lib/memset_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
+check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
+check include/uapi/linux/mman.h       -I "^#include <\(uapi/\)*asm/mman.h>"
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index e4b717e9eb6c..c11f0c76e90c 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -9,16 +9,6 @@
 #include <linux/perf_event.h>
 #include <asm/barrier.h>
 
-#if defined(__i386__)
-#define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    {"model name"}
-#endif
-
-#if defined(__x86_64__)
-#define cpu_relax()     asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC    {"model name"}
-#endif
-
 #ifdef __powerpc__
 #define CPUINFO_PROC    {"cpu"}
 #endif
@@ -43,19 +33,10 @@
 #define CPUINFO_PROC    {"cpu model"}
 #endif
 
-#ifdef __ia64__
-#define cpu_relax()     asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC    {"model name"}
-#endif
-
 #ifdef __arm__
 #define CPUINFO_PROC    {"model name", "Processor"}
 #endif
 
-#ifdef __aarch64__
-#define cpu_relax()     asm volatile("yield" ::: "memory")
-#endif
-
 #ifdef __mips__
 #define CPUINFO_PROC    {"cpu model"}
 #endif
@@ -72,13 +53,8 @@
 #define CPUINFO_PROC    {"core ID"}
 #endif
 
-#ifdef __tile__
-#define cpu_relax()     asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    {"model name"}
-#endif
-
-#ifndef cpu_relax
-#define cpu_relax() barrier()
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC    { "model name", }
 #endif
 
 static inline int
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 628a5e412cb1..2f19e03c5c40 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -89,7 +89,7 @@ struct pager_config {
 static int pager_command_config(const char *var, const char *value, void *data)
 {
         struct pager_config *c = data;
-        if (!prefixcmp(var, "pager.") && !strcmp(var + 6, c->cmd))
+        if (strstarts(var, "pager.") && !strcmp(var + 6, c->cmd))
                 c->val = perf_config_bool(var, value);
         return 0;
 }
@@ -108,9 +108,9 @@ static int check_pager_config(const char *cmd)
 static int browser_command_config(const char *var, const char *value, void *data)
 {
         struct pager_config *c = data;
-        if (!prefixcmp(var, "tui.") && !strcmp(var + 4, c->cmd))
+        if (strstarts(var, "tui.") && !strcmp(var + 4, c->cmd))
                 c->val = perf_config_bool(var, value);
-        if (!prefixcmp(var, "gtk.") && !strcmp(var + 4, c->cmd))
+        if (strstarts(var, "gtk.") && !strcmp(var + 4, c->cmd))
                 c->val = perf_config_bool(var, value) ? 2 : 0;
         return 0;
 }
@@ -192,7 +192,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                 /*
                  * Check remaining flags.
                  */
-                if (!prefixcmp(cmd, CMD_EXEC_PATH)) {
+                if (strstarts(cmd, CMD_EXEC_PATH)) {
                         cmd += strlen(CMD_EXEC_PATH);
                         if (*cmd == '=')
                                 set_argv_exec_path(cmd + 1);
@@ -229,7 +229,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
                                 *envchanged = 1;
                         (*argv)++;
                         (*argc)--;
-                } else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
+                } else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
                         tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
                         fprintf(stderr, "dir: %s\n", tracing_path);
                         if (envchanged)
@@ -467,17 +467,23 @@ int main(int argc, const char **argv)
          *  - cannot execute it externally (since it would just do
          *    the same thing over again)
          *
-         * So we just directly call the internal command handler, and
-         * die if that one cannot handle it.
+         * So we just directly call the internal command handler. If that one
+         * fails to handle this, then maybe we just run a renamed perf binary
+         * that contains a dash in its name. To handle this scenario, we just
+         * fall through and ignore the "xxxx" part of the command string.
          */
-        if (!prefixcmp(cmd, "perf-")) {
+        if (strstarts(cmd, "perf-")) {
                 cmd += 5;
                 argv[0] = cmd;
                 handle_internal_command(argc, argv);
-                fprintf(stderr, "cannot handle %s internally", cmd);
-                goto out;
+                /*
+                 * If the command is handled, the above function does not
+                 * return undo changes and fall through in such a case.
+                 */
+                cmd -= 5;
+                argv[0] = cmd;
         }
-        if (!prefixcmp(cmd, "trace")) {
+        if (strstarts(cmd, "trace")) {
 #ifdef HAVE_LIBAUDIT_SUPPORT
                 setup_path();
                 argv[0] = "trace";
@@ -495,7 +501,7 @@ int main(int argc, const char **argv)
         commit_pager_choice();
 
         if (argc > 0) {
-                if (!prefixcmp(argv[0], "--"))
+                if (strstarts(argv[0], "--"))
                         argv[0] += 2;
         } else {
                 /* The user didn't specify a command; give them help */
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 806c216a1078..dc442ba21bf6 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -7,6 +7,7 @@
 #include <linux/perf_event.h>
 
 extern bool test_attr__enabled;
+void test_attr__ready(void);
 void test_attr__init(void);
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
                      int fd, int group_fd, unsigned long flags);
@@ -42,6 +43,7 @@ struct record_opts {
         bool         no_samples;
         bool         raw_samples;
         bool         sample_address;
+        bool         sample_phys_addr;
         bool         sample_weight;
         bool         sample_time;
         bool         sample_time_set;
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
index 1408ade0d773..c2ee3e4417fe 100644
--- a/tools/perf/pmu-events/README
+++ b/tools/perf/pmu-events/README
@@ -85,10 +85,6 @@ users to specify events by their name:
 
 where 'pm_1plus_ppc_cmpl' is a Power8 PMU event.
 
-In case of errors when processing files in the tools/perf/pmu-events/arch
-directory, 'jevents' tries to create an empty mapping file to allow the perf
-build to succeed even if the PMU event aliases cannot be used.
-
 However some errors in processing may cause the perf build to fail.
 
 Mapfile format
diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
index e925baa0c30b..a0f3a11ca19f 100644
--- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv
+++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv
@@ -13,9 +13,13 @@
 #
 
 # Power8 entries
-004b0000,1,power8.json,core
-004b0201,1,power8.json,core
-004c0000,1,power8.json,core
-004d0000,1,power8.json,core
-004d0100,1,power8.json,core
-004d0200,1,power8.json,core
+004b0000,1,power8,core
+004b0201,1,power8,core
+004c0000,1,power8,core
+004d0000,1,power8,core
+004d0100,1,power8,core
+004d0200,1,power8,core
+004c0100,1,power8,core
+004e0100,1,power9,core
+004e0200,1,power9,core
+004e1200,1,power9,core
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
new file mode 100644
index 000000000000..18f6645f2897
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
@@ -0,0 +1,137 @@
+[
+  {,
+    "EventCode": "0x300F4",
+    "EventName": "PM_THRD_CONC_RUN_INST",
+    "BriefDescription": "PPC Instructions Finished by this thread when all threads in the core had the run-latch set"
+  },
+  {,
+    "EventCode": "0x1E056",
+    "EventName": "PM_CMPLU_STALL_FLUSH_ANY_THREAD",
+    "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because any of the 4 threads in the same core suffered a flush, which blocks completion"
+  },
+  {,
+    "EventCode": "0x4D016",
+    "EventName": "PM_CMPLU_STALL_FXLONG",
+    "BriefDescription": "Completion stall due to a long latency scalar fixed point instruction (division, square root)"
+  },
+  {,
+    "EventCode": "0x2D016",
+    "EventName": "PM_CMPLU_STALL_FXU",
+    "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes"
+  },
+  {,
+    "EventCode": "0x1D15C",
+    "EventName": "PM_MRK_DTLB_MISS_1G",
+    "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x4D12A",
+    "EventName": "PM_MRK_DATA_FROM_RL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x1003C",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3",
+    "BriefDescription": "Completion stall by Dcache miss which resolved in L2/L3"
+  },
+  {,
+    "EventCode": "0x4C014",
+    "EventName": "PM_CMPLU_STALL_LMQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed in the L1 and the LMQ was unable to accept this load miss request because it was full"
+  },
+  {,
+    "EventCode": "0x14048",
+    "EventName": "PM_INST_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4D014",
+    "EventName": "PM_CMPLU_STALL_LOAD_FINISH",
+    "BriefDescription": "Finish stall because the NTF instruction was a load instruction with all its dependencies satisfied just going through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x2404A",
+    "EventName": "PM_INST_FROM_RL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1404A",
+    "EventName": "PM_INST_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x401EA",
+    "EventName": "PM_THRESH_EXC_128",
+    "BriefDescription": "Threshold counter exceeded a value of 128"
+  },
+  {,
+    "EventCode": "0x400F6",
+    "EventName": "PM_BR_MPRED_CMPL",
+    "BriefDescription": "Number of Branch Mispredicts"
+  },
+  {,
+    "EventCode": "0x2F140",
+    "EventName": "PM_MRK_DPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x101E6",
+    "EventName": "PM_THRESH_EXC_4096",
+    "BriefDescription": "Threshold counter exceed a count of 4096"
+  },
+  {,
+    "EventCode": "0x3D156",
+    "EventName": "PM_MRK_DTLB_MISS_64K",
+    "BriefDescription": "Marked Data TLB Miss page size 64K"
+  },
+  {,
+    "EventCode": "0x4C15E",
+    "EventName": "PM_MRK_DTLB_MISS_16M",
+    "BriefDescription": "Marked Data TLB Miss page size 16M"
+  },
+  {,
+    "EventCode": "0x2D15E",
+    "EventName": "PM_MRK_DTLB_MISS_16G",
+    "BriefDescription": "Marked Data TLB Miss page size 16G"
+  },
+  {,
+    "EventCode": "0x3F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4C016",
+    "EventName": "PM_CMPLU_STALL_DMISS_L2L3_CONFLICT",
+    "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 with a conflict"
+  },
+  {,
+    "EventCode": "0x2C01A",
+    "EventName": "PM_CMPLU_STALL_LHS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that hit on an older store and it was waiting for store data"
+  },
+  {,
+    "EventCode": "0x401E4",
+    "EventName": "PM_MRK_DTLB_MISS",
+    "BriefDescription": "Marked dtlb miss"
+  },
+  {,
+    "EventCode": "0x24046",
+    "EventName": "PM_INST_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1002A",
+    "EventName": "PM_CMPLU_STALL_LARX",
+    "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied"
+  },
+  {,
+    "EventCode": "0x3006C",
+    "EventName": "PM_RUN_CYC_SMT2_MODE",
+    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT2 mode"
+  },
+  {,
+    "EventCode": "0x1C058",
+    "EventName": "PM_DTLB_MISS_16G",
+    "BriefDescription": "Data TLB Miss page size 16G"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
new file mode 100644
index 000000000000..8a83bca26552
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/floating-point.json
@@ -0,0 +1,32 @@
+[
+  {,
+    "EventCode": "0x1415A",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with load hit store conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x10058",
+    "EventName": "PM_MEM_LOC_THRESH_IFU",
+    "BriefDescription": "Local Memory above threshold for IFU speculation control"
+  },
+  {,
+    "EventCode": "0x2D028",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x30012",
+    "EventName": "PM_FLUSH_COMPLETION",
+    "BriefDescription": "The instruction that was next to complete did not complete because it suffered a flush"
+  },
+  {,
+    "EventCode": "0x2D154",
+    "EventName": "PM_MRK_DERAT_MISS_64K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 64K"
+  },
+  {,
+    "EventCode": "0x4016E",
+    "EventName": "PM_THRESH_NOT_MET",
+    "BriefDescription": "Threshold counter did not meet threshold"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
new file mode 100644
index 000000000000..c63a919eda98
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -0,0 +1,372 @@
+[
+  {,
+    "EventCode": "0x3E15C",
+    "EventName": "PM_MRK_L2_TM_ST_ABORT_SISTER",
+    "BriefDescription": "TM marked store abort for this thread"
+  },
+  {,
+    "EventCode": "0x25044",
+    "EventName": "PM_IPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x101E8",
+    "EventName": "PM_THRESH_EXC_256",
+    "BriefDescription": "Threshold counter exceed a count of 256"
+  },
+  {,
+    "EventCode": "0x4504E",
+    "EventName": "PM_IPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1006A",
+    "EventName": "PM_NTC_ISSUE_HELD_DARQ_FULL",
+    "BriefDescription": "The NTC instruction is being held at dispatch because there are no slots in the DARQ for it"
+  },
+  {,
+    "EventCode": "0x4E016",
+    "EventName": "PM_CMPLU_STALL_LSAQ_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a load or store that was held in LSAQ because an older instruction from SRQ or LRQ won arbitration to the LSU pipe when this instruction tried to launch"
+  },
+  {,
+    "EventCode": "0x1001A",
+    "EventName": "PM_LSU_SRQ_FULL_CYC",
+    "BriefDescription": "Cycles in which the Store Queue is full on all 4 slices. This is event is not per thread. All the threads will see the same count for this core resource"
+  },
+  {,
+    "EventCode": "0x1E15E",
+    "EventName": "PM_MRK_L2_TM_REQ_ABORT",
+    "BriefDescription": "TM abort"
+  },
+  {,
+    "EventCode": "0x34052",
+    "EventName": "PM_INST_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x20114",
+    "EventName": "PM_MRK_L2_RC_DISP",
+    "BriefDescription": "Marked Instruction RC dispatched in L2"
+  },
+  {,
+    "EventCode": "0x4C044",
+    "EventName": "PM_DATA_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1C044",
+    "EventName": "PM_DATA_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x44050",
+    "EventName": "PM_INST_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x30154",
+    "EventName": "PM_MRK_FAB_RSP_DCLAIM",
+    "BriefDescription": "Marked store had to do a dclaim"
+  },
+  {,
+    "EventCode": "0x30014",
+    "EventName": "PM_CMPLU_STALL_STORE_FIN_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a store waiting for a slot in the store finish pipe. This means the instruction is ready to finish but there are instructions ahead of it, using the finish pipe"
+  },
+  {,
+    "EventCode": "0x3E054",
+    "EventName": "PM_LD_MISS_L1",
+    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+  },
+  {,
+    "EventCode": "0x2E01A",
+    "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT",
+    "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete"
+  },
+  {,
+    "EventCode": "0x2D01C",
+    "EventName": "PM_CMPLU_STALL_STCX",
+    "BriefDescription": "Finish stall because the NTF instruction was a stcx waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x2C010",
+    "EventName": "PM_CMPLU_STALL_LSU",
+    "BriefDescription": "Completion stall by LSU instruction"
+  },
+  {,
+    "EventCode": "0x2C042",
+    "EventName": "PM_DATA_FROM_L3_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state due to a demand load"
+  },
+  {,
+    "EventCode": "0x4E012",
+    "EventName": "PM_CMPLU_STALL_MTFPSCR",
+    "BriefDescription": "Completion stall because the ISU is updating the register and notifying the Effective Address Table (EAT)"
+  },
+  {,
+    "EventCode": "0x100F2",
+    "EventName": "PM_1PLUS_PPC_CMPL",
+    "BriefDescription": "1 or more ppc insts finished"
+  },
+  {,
+    "EventCode": "0x3001C",
+    "EventName": "PM_LSU_REJECT_LMQ_FULL",
+    "BriefDescription": "LSU Reject due to LMQ full (up to 4 per cycles)"
+  },
+  {,
+    "EventCode": "0x15046",
+    "EventName": "PM_IPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1015E",
+    "EventName": "PM_MRK_FAB_RSP_RD_T_INTV",
+    "BriefDescription": "Sampled Read got a T intervention"
+  },
+  {,
+    "EventCode": "0x101EC",
+    "EventName": "PM_THRESH_MET",
+    "BriefDescription": "threshold exceeded"
+  },
+  {,
+    "EventCode": "0x10020",
+    "EventName": "PM_PMC4_REWIND",
+    "BriefDescription": "PMC4 Rewind Event"
+  },
+  {,
+    "EventCode": "0x301EA",
+    "EventName": "PM_THRESH_EXC_1024",
+    "BriefDescription": "Threshold counter exceeded a value of 1024"
+  },
+  {,
+    "EventCode": "0x34056",
+    "EventName": "PM_CMPLU_STALL_LSU_MFSPR",
+    "BriefDescription": "Finish stall because the NTF instruction was a mfspr instruction targeting an LSU SPR and it was waiting for the register data to be returned"
+  },
+  {,
+    "EventCode": "0x44056",
+    "EventName": "PM_VECTOR_ST_CMPL",
+    "BriefDescription": "Number of vector store instructions completed"
+  },
+  {,
+    "EventCode": "0x2C124",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x4C12A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3C056",
+    "EventName": "PM_DTLB_MISS_64K",
+    "BriefDescription": "Data TLB Miss page size 64K"
+  },
+  {,
+    "EventCode": "0x30060",
+    "EventName": "PM_TM_TRANS_RUN_INST",
+    "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)"
+  },
+  {,
+    "EventCode": "0x2C014",
+    "EventName": "PM_CMPLU_STALL_STORE_FINISH",
+    "BriefDescription": "Finish stall because the NTF instruction was a store with all its dependencies met, just waiting to go through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x3515A",
+    "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE_CYC",
+    "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x34050",
+    "EventName": "PM_INST_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x3015E",
+    "EventName": "PM_MRK_FAB_RSP_CLAIM_RTY",
+    "BriefDescription": "Sampled store did a rwitm and got a rty"
+  },
+  {,
+    "EventCode": "0x0",
+    "EventName": "PM_SUSPENDED",
+    "BriefDescription": "Counter OFF"
+  },
+  {,
+    "EventCode": "0x10010",
+    "EventName": "PM_PMC4_OVERFLOW",
+    "BriefDescription": "Overflow from counter 4"
+  },
+  {,
+    "EventCode": "0x3E04A",
+    "EventName": "PM_DPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2F152",
+    "EventName": "PM_MRK_FAB_RSP_DCLAIM_CYC",
+    "BriefDescription": "cycles L2 RC took for a dclaim"
+  },
+  {,
+    "EventCode": "0x10004",
+    "EventName": "PM_CMPLU_STALL_LRQ_OTHER",
+    "BriefDescription": "Finish stall due to LRQ miscellaneous reasons, lost arbitration to LMQ slot, bank collisions, set prediction cleanup, set prediction multihit and others"
+  },
+  {,
+    "EventCode": "0x4F150",
+    "EventName": "PM_MRK_FAB_RSP_RWITM_CYC",
+    "BriefDescription": "cycles L2 RC took for a rwitm"
+  },
+  {,
+    "EventCode": "0x4E042",
+    "EventName": "PM_DPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F054",
+    "EventName": "PM_TLB_HIT",
+    "BriefDescription": "Number of times the TLB had the data required by the instruction. Applies to both HPT and RPT"
+  },
+  {,
+    "EventCode": "0x2C01E",
+    "EventName": "PM_CMPLU_STALL_SYNC_PMU_INT",
+    "BriefDescription": "Cycles in which the NTC instruction is waiting for a synchronous PMU interrupt"
+  },
+  {,
+    "EventCode": "0x24050",
+    "EventName": "PM_IOPS_CMPL",
+    "BriefDescription": "Internal Operations completed"
+  },
+  {,
+    "EventCode": "0x1515C",
+    "EventName": "PM_SYNC_MRK_BR_MPRED",
+    "BriefDescription": "Marked Branch mispredict that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x300FA",
+    "EventName": "PM_INST_FROM_L3MISS",
+    "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet"
+  },
+  {,
+    "EventCode": "0x15044",
+    "EventName": "PM_IPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x15152",
+    "EventName": "PM_SYNC_MRK_BR_LINK",
+    "BriefDescription": "Marked Branch and link branch that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x1E050",
+    "EventName": "PM_CMPLU_STALL_TEND",
+    "BriefDescription": "Finish stall because the NTF instruction was a tend instruction awaiting response from L2"
+  },
+  {,
+    "EventCode": "0x1013E",
+    "EventName": "PM_MRK_LD_MISS_EXPOSED_CYC",
+    "BriefDescription": "Marked Load exposed Miss (use edge detect to count #)"
+  },
+  {,
+    "EventCode": "0x25042",
+    "EventName": "PM_IPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x14054",
+    "EventName": "PM_INST_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x4015E",
+    "EventName": "PM_MRK_FAB_RSP_RD_RTY",
+    "BriefDescription": "Sampled L2 reads retry count"
+  },
+  {,
+    "EventCode": "0x45048",
+    "EventName": "PM_IPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x44052",
+    "EventName": "PM_INST_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x30026",
+    "EventName": "PM_CMPLU_STALL_STORE_DATA",
+    "BriefDescription": "Finish stall because the next to finish instruction was a store waiting on data"
+  },
+  {,
+    "EventCode": "0x301E6",
+    "EventName": "PM_MRK_DERAT_MISS",
+    "BriefDescription": "Erat Miss (TLB Access) All page sizes"
+  },
+  {,
+    "EventCode": "0x24154",
+    "EventName": "PM_THRESH_ACC",
+    "BriefDescription": "This event increments every time the threshold event counter ticks. Thresholding must be enabled (via MMCRA) and the thresholding start event must occur for this counter to increment. It will stop incrementing when the thresholding stop event occurs or when thresholding is disabled, until the next time a configured thresholding start event occurs."
+  },
+  {,
+    "EventCode": "0x2015E",
+    "EventName": "PM_MRK_FAB_RSP_RWITM_RTY",
+    "BriefDescription": "Sampled store did a rwitm and got a rty"
+  },
+  {,
+    "EventCode": "0x200FA",
+    "EventName": "PM_BR_TAKEN_CMPL",
+    "BriefDescription": "New event for Branch Taken"
+  },
+  {,
+    "EventCode": "0x35044",
+    "EventName": "PM_IPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4C010",
+    "EventName": "PM_CMPLU_STALL_STORE_PIPE_ARB",
+    "BriefDescription": "Finish stall because the NTF instruction was a store waiting for the next relaunch opportunity after an internal reject. This means the instruction is ready to relaunch and tried once but lost arbitration"
+  },
+  {,
+    "EventCode": "0x4C01C",
+    "EventName": "PM_CMPLU_STALL_ST_FWD",
+    "BriefDescription": "Completion stall due to store forward"
+  },
+  {,
+    "EventCode": "0x3515C",
+    "EventName": "PM_MRK_DATA_FROM_RL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x2D14C",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x40116",
+    "EventName": "PM_MRK_LARX_FIN",
+    "BriefDescription": "Larx finished"
+  },
+  {,
+    "EventCode": "0x4C056",
+    "EventName": "PM_DTLB_MISS_16M",
+    "BriefDescription": "Data TLB Miss page size 16M"
+  },
+  {,
+    "EventCode": "0x1003A",
+    "EventName": "PM_CMPLU_STALL_LSU_FIN",
+    "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish"
+  },
+  {,
+    "EventCode": "0x3012A",
+    "EventName": "PM_MRK_L2_RC_DONE",
+    "BriefDescription": "Marked RC done"
+  },
+  {,
+    "EventCode": "0x45044",
+    "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
new file mode 100644
index 000000000000..b9df54fb37e3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
@@ -0,0 +1,647 @@
+[
+  {,
+    "EventCode": "0x3C052",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for a demand load"
+  },
+  {,
+    "EventCode": "0x3013E",
+    "EventName": "PM_MRK_STALL_CMPLU_CYC",
+    "BriefDescription": "Number of cycles the marked instruction is experiencing a stall while it is next to complete (NTC)"
+  },
+  {,
+    "EventCode": "0x4F056",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3MISS",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from beyond the core's L3 data cache. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x24158",
+    "EventName": "PM_MRK_INST",
+    "BriefDescription": "An instruction was marked. Includes both Random Instruction Sampling (RIS) at decode time and Random Event Sampling (RES) at the time the configured event happens"
+  },
+  {,
+    "EventCode": "0x1E046",
+    "EventName": "PM_DPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3C04A",
+    "EventName": "PM_DATA_FROM_RMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C01C",
+    "EventName": "PM_CMPLU_STALL_DMISS_REMOTE",
+    "BriefDescription": "Completion stall by Dcache miss which resolved from remote chip (cache or memory)"
+  },
+  {,
+    "EventCode": "0x44040",
+    "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with dispatch conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x2E050",
+    "EventName": "PM_DARQ0_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7,8, or 9 DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x2D02E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L2 data cache. This implies that a level 4 PWC access was not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x3F05E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x2E01E",
+    "EventName": "PM_CMPLU_STALL_NTC_FLUSH",
+    "BriefDescription": "Completion stall due to ntc flush"
+  },
+  {,
+    "EventCode": "0x1F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x20130",
+    "EventName": "PM_MRK_INST_DECODED",
+    "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only"
+  },
+  {,
+    "EventCode": "0x3F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D058",
+    "EventName": "PM_VECTOR_FLOP_CMPL",
+    "BriefDescription": "Vector FP instruction completed"
+  },
+  {,
+    "EventCode": "0x14040",
+    "EventName": "PM_INST_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 without conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4404E",
+    "EventName": "PM_INST_FROM_L3MISS_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L3 due to a instruction fetch"
+  },
+  {,
+    "EventCode": "0x3003A",
+    "EventName": "PM_CMPLU_STALL_EXCEPTION",
+    "BriefDescription": "Cycles in which the NTC instruction is not allowed to complete because it was interrupted by ANY exception, which has to be serviced before the instruction can complete"
+  },
+  {,
+    "EventCode": "0x4F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3E044",
+    "EventName": "PM_DPTEG_FROM_L31_ECO_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x300F6",
+    "EventName": "PM_L1_DCACHE_RELOAD_VALID",
+    "BriefDescription": "DL1 reloaded due to Demand Load"
+  },
+  {,
+    "EventCode": "0x1415E",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS_CYC",
+    "BriefDescription": "Duration in cycles to reload from a location other than the local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x1E052",
+    "EventName": "PM_CMPLU_STALL_SLB",
+    "BriefDescription": "Finish stall because the NTF instruction was awaiting L2 response for an SLB"
+  },
+  {,
+    "EventCode": "0x4404C",
+    "EventName": "PM_INST_FROM_DMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group (Distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3000E",
+    "EventName": "PM_FXU_1PLUS_BUSY",
+    "BriefDescription": "At least one of the 4 FXU units is busy"
+  },
+  {,
+    "EventCode": "0x2C048",
+    "EventName": "PM_DATA_FROM_LMEM",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a demand load"
+  },
+  {,
+    "EventCode": "0x3000A",
+    "EventName": "PM_CMPLU_STALL_PM",
+    "BriefDescription": "Finish stall because the NTF instruction was issued to the Permute execution pipe and waiting to finish. Includes permute and decimal fixed point instructions (128 bit BCD arithmetic) + a few 128 bit fixpoint add/subtract instructions with carry. Not qualified by vector or multicycle"
+  },
+  {,
+    "EventCode": "0x1504E",
+    "EventName": "PM_IPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1C052",
+    "EventName": "PM_DATA_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for a demand load"
+  },
+  {,
+    "EventCode": "0x30008",
+    "EventName": "PM_DISP_STARVED",
+    "BriefDescription": "Dispatched Starved"
+  },
+  {,
+    "EventCode": "0x14042",
+    "EventName": "PM_INST_FROM_L2",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4000C",
+    "EventName": "PM_FREQ_UP",
+    "BriefDescription": "Power Management: Above Threshold A"
+  },
+  {,
+    "EventCode": "0x3C050",
+    "EventName": "PM_DATA_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0x25040",
+    "EventName": "PM_IPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x10132",
+    "EventName": "PM_MRK_INST_ISSUED",
+    "BriefDescription": "Marked instruction issued"
+  },
+  {,
+    "EventCode": "0x1C046",
+    "EventName": "PM_DATA_FROM_L31_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C044",
+    "EventName": "PM_DATA_FROM_L31_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C04A",
+    "EventName": "PM_DATA_FROM_RL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on the same Node or Group ( Remote) due to a demand load"
+  },
+  {,
+    "EventCode": "0x24044",
+    "EventName": "PM_INST_FROM_L31_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4C050",
+    "EventName": "PM_DATA_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for a demand load"
+  },
+  {,
+    "EventCode": "0x2C052",
+    "EventName": "PM_DATA_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for a demand load"
+  },
+  {,
+    "EventCode": "0x2F148",
+    "EventName": "PM_MRK_DPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D01A",
+    "EventName": "PM_CMPLU_STALL_EIEIO",
+    "BriefDescription": "Finish stall because the NTF instruction is an EIEIO waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x4F14E",
+    "EventName": "PM_MRK_DPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F05A",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L3 data cache. This is the deepest level of PWC possible for a translation"
+  },
+  {,
+    "EventCode": "0x1F05A",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from the core's L2 data cache. This is the deepest level of PWC possible for a translation"
+  },
+  {,
+    "EventCode": "0x30068",
+    "EventName": "PM_L1_ICACHE_RELOADED_PREF",
+    "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)"
+  },
+  {,
+    "EventCode": "0x4C04A",
+    "EventName": "PM_DATA_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x400FE",
+    "EventName": "PM_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a demand load"
+  },
+  {,
+    "EventCode": "0x3F058",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x4D142",
+    "EventName": "PM_MRK_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x30050",
+    "EventName": "PM_SYS_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was system pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x30028",
+    "EventName": "PM_CMPLU_STALL_SPEC_FINISH",
+    "BriefDescription": "Finish stall while waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC"
+  },
+  {,
+    "EventCode": "0x400F4",
+    "EventName": "PM_RUN_PURR",
+    "BriefDescription": "Run_PURR"
+  },
+  {,
+    "EventCode": "0x3404C",
+    "EventName": "PM_INST_FROM_DL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3D05A",
+    "EventName": "PM_NTC_ISSUE_HELD_OTHER",
+    "BriefDescription": "The NTC instruction is being held at dispatch during regular pipeline cycles, or because the VSU is busy with multi-cycle instructions, or because of a write-back collision with VSU"
+  },
+  {,
+    "EventCode": "0x2E048",
+    "EventName": "PM_DPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2D02A",
+    "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x1F05C",
+    "EventName": "PM_RADIX_PWC_L3_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 3 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x4D04A",
+    "EventName": "PM_DARQ0_0_3_ENTRIES",
+    "BriefDescription": "Cycles in which 3 or less DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x1404C",
+    "EventName": "PM_INST_FROM_LL4",
+    "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's L4 cache due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x200FD",
+    "EventName": "PM_L1_ICACHE_MISS",
+    "BriefDescription": "Demand iCache Miss"
+  },
+  {,
+    "EventCode": "0x34040",
+    "EventName": "PM_INST_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 with load hit store conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x20138",
+    "EventName": "PM_MRK_ST_NEST",
+    "BriefDescription": "Marked store sent to nest"
+  },
+  {,
+    "EventCode": "0x44048",
+    "EventName": "PM_INST_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x35046",
+    "EventName": "PM_IPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4C04E",
+    "EventName": "PM_DATA_FROM_L3MISS_MOD",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a demand load"
+  },
+  {,
+    "EventCode": "0x401E0",
+    "EventName": "PM_MRK_INST_CMPL",
+    "BriefDescription": "marked instruction completed"
+  },
+  {,
+    "EventCode": "0x2C128",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x34044",
+    "EventName": "PM_INST_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4E018",
+    "EventName": "PM_CMPLU_STALL_NTC_DISP_FIN",
+    "BriefDescription": "Finish stall because the NTF instruction was one that must finish at dispatch."
+  },
+  {,
+    "EventCode": "0x2E05E",
+    "EventName": "PM_LMQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the LMQ has no pending load misses for this thread"
+  },
+  {,
+    "EventCode": "0x4C122",
+    "EventName": "PM_DARQ1_0_3_ENTRIES",
+    "BriefDescription": "Cycles in which 3 or fewer DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x4F058",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x14046",
+    "EventName": "PM_INST_FROM_L31_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3012C",
+    "EventName": "PM_MRK_ST_FWD",
+    "BriefDescription": "Marked st forwards"
+  },
+  {,
+    "EventCode": "0x101E0",
+    "EventName": "PM_MRK_INST_DISP",
+    "BriefDescription": "The thread has dispatched a randomly sampled marked instruction"
+  },
+  {,
+    "EventCode": "0x1D058",
+    "EventName": "PM_DARQ0_10_12_ENTRIES",
+    "BriefDescription": "Cycles in which 10 or more DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x300FE",
+    "EventName": "PM_DATA_FROM_L3MISS",
+    "BriefDescription": "Demand LD - L3 Miss (not L2 hit and not L3 hit)"
+  },
+  {,
+    "EventCode": "0x30006",
+    "EventName": "PM_CMPLU_STALL_OTHER_CMPL",
+    "BriefDescription": "Instructions the core completed while this tread was stalled"
+  },
+  {,
+    "EventCode": "0x1005C",
+    "EventName": "PM_CMPLU_STALL_DP",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by NOT vector"
+  },
+  {,
+    "EventCode": "0x1E042",
+    "EventName": "PM_DPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1016E",
+    "EventName": "PM_MRK_BR_CMPL",
+    "BriefDescription": "Branch Instruction completed"
+  },
+  {,
+    "EventCode": "0x2013A",
+    "EventName": "PM_MRK_BRU_FIN",
+    "BriefDescription": "bru marked instr finish"
+  },
+  {,
+    "EventCode": "0x4F05E",
+    "EventName": "PM_RADIX_PWC_L3_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 3 page walk cache from beyond the core's L3 data cache. This implies that a level 4 PWC access was not necessary for this translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x400FC",
+    "EventName": "PM_ITLB_MISS",
+    "BriefDescription": "ITLB Reloaded. Counts 1 per ITLB miss for HPT but multiple for radix depending on number of levels traveresed"
+  },
+  {,
+    "EventCode": "0x2D024",
+    "EventName": "PM_RADIX_PWC_L2_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB but hit on both the first and second levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x3F056",
+    "EventName": "PM_RADIX_PWC_L3_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB but hit on the first, second, and third levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x4E014",
+    "EventName": "PM_TM_TX_PASS_RUN_INST",
+    "BriefDescription": "Run instructions spent in successful transactions"
+  },
+  {,
+    "EventCode": "0x1E044",
+    "EventName": "PM_DPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D05A",
+    "EventName": "PM_NON_MATH_FLOP_CMPL",
+    "BriefDescription": "Non FLOP operation completed"
+  },
+  {,
+    "EventCode": "0x101E2",
+    "EventName": "PM_MRK_BR_TAKEN_CMPL",
+    "BriefDescription": "Marked Branch Taken completed"
+  },
+  {,
+    "EventCode": "0x3E158",
+    "EventName": "PM_MRK_STCX_FAIL",
+    "BriefDescription": "marked stcx failed"
+  },
+  {,
+    "EventCode": "0x1C048",
+    "EventName": "PM_DATA_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1C054",
+    "EventName": "PM_DATA_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for a demand load"
+  },
+  {,
+    "EventCode": "0x4405E",
+    "EventName": "PM_DARQ_STORE_REJECT",
+    "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry but It was rejected. Divide by PM_DARQ_STORE_XMIT to get reject ratio"
+  },
+  {,
+    "EventCode": "0x1C042",
+    "EventName": "PM_DATA_FROM_L2",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a demand load"
+  },
+  {,
+    "EventCode": "0x1D14C",
+    "EventName": "PM_MRK_DATA_FROM_LL4",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a marked load"
+  },
+  {,
+    "EventCode": "0x1006C",
+    "EventName": "PM_RUN_CYC_ST_MODE",
+    "BriefDescription": "Cycles run latch is set and core is in ST mode"
+  },
+  {,
+    "EventCode": "0x3C044",
+    "EventName": "PM_DATA_FROM_L31_ECO_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's ECO L3 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x4C052",
+    "EventName": "PM_DATA_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for a demand load"
+  },
+  {,
+    "EventCode": "0x20050",
+    "EventName": "PM_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope and data sourced across this scope was group pump for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x1F150",
+    "EventName": "PM_MRK_ST_L2DISP_TO_CMPL_CYC",
+    "BriefDescription": "cycles from L2 rc disp to l2 rc completion"
+  },
+  {,
+    "EventCode": "0x4505A",
+    "EventName": "PM_SP_FLOP_CMPL",
+    "BriefDescription": "SP instruction completed"
+  },
+  {,
+    "EventCode": "0x4000A",
+    "EventName": "PM_ISQ_36_44_ENTRIES",
+    "BriefDescription": "Cycles in which 36 or more Issue Queue entries are in use. This is a shared event, not per thread. There are 44 issue queue entries across 4 slices in the whole core"
+  },
+  {,
+    "EventCode": "0x2C12E",
+    "EventName": "PM_MRK_DATA_FROM_LL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from the local chip's L4 cache due to a marked load"
+  },
+  {,
+    "EventCode": "0x2C058",
+    "EventName": "PM_MEM_PREF",
+    "BriefDescription": "Memory prefetch for this thread. Includes L4"
+  },
+  {,
+    "EventCode": "0x40012",
+    "EventName": "PM_L1_ICACHE_RELOADED_ALL",
+    "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch"
+  },
+  {,
+    "EventCode": "0x4003C",
+    "EventName": "PM_DISP_HELD_SYNC_HOLD",
+    "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline"
+  },
+  {,
+    "EventCode": "0x3003C",
+    "EventName": "PM_CMPLU_STALL_NESTED_TEND",
+    "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay"
+  },
+  {,
+    "EventCode": "0x3D05C",
+    "EventName": "PM_DISP_HELD_HB_FULL",
+    "BriefDescription": "Dispatch held due to History Buffer full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
+  },
+  {,
+    "EventCode": "0x30052",
+    "EventName": "PM_SYS_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (system) mispredicted. Either the original scope was too small (Chip/Group) or the original scope was System and it should have been smaller. Counts for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x2E044",
+    "EventName": "PM_DPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x34048",
+    "EventName": "PM_INST_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x45042",
+    "EventName": "PM_IPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x15042",
+    "EventName": "PM_IPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1C05E",
+    "EventName": "PM_MEM_LOC_THRESH_LSU_MED",
+    "BriefDescription": "Local memory above threshold for data prefetch"
+  },
+  {,
+    "EventCode": "0x40134",
+    "EventName": "PM_MRK_INST_TIMEO",
+    "BriefDescription": "marked Instruction finish timeout (instruction lost)"
+  },
+  {,
+    "EventCode": "0x1002C",
+    "EventName": "PM_L1_DCACHE_RELOADED_ALL",
+    "BriefDescription": "L1 data cache reloaded for demand. If MMCR1[16] is 1, prefetches will be included as well"
+  },
+  {,
+    "EventCode": "0x30130",
+    "EventName": "PM_MRK_INST_FIN",
+    "BriefDescription": "marked instruction finished"
+  },
+  {,
+    "EventCode": "0x1F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3504E",
+    "EventName": "PM_DARQ0_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x30064",
+    "EventName": "PM_DARQ_STORE_XMIT",
+    "BriefDescription": "The DARQ attempted to transmit a store into an LSAQ or SRQ entry. Includes rejects. Not qualified by thread, so it includes counts for the whole core"
+  },
+  {,
+    "EventCode": "0x45046",
+    "EventName": "PM_IPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x2C016",
+    "EventName": "PM_CMPLU_STALL_PASTE",
+    "BriefDescription": "Finish stall because the NTF instruction was a paste waiting for response from L2"
+  },
+  {,
+    "EventCode": "0x24156",
+    "EventName": "PM_MRK_STCX_FIN",
+    "BriefDescription": "Number of marked stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed"
+  },
+  {,
+    "EventCode": "0x15150",
+    "EventName": "PM_SYNC_MRK_PROBE_NOP",
+    "BriefDescription": "Marked probeNops which can cause synchronous interrupts"
+  },
+  {,
+    "EventCode": "0x301E4",
+    "EventName": "PM_MRK_BR_MPRED_CMPL",
+    "BriefDescription": "Marked Branch Mispredicted"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
new file mode 100644
index 000000000000..9960d1c0dd44
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
@@ -0,0 +1,132 @@
+[
+  {,
+    "EventCode": "0x3006E",
+    "EventName": "PM_NEST_REF_CLK",
+    "BriefDescription": "Multiply by 4 to obtain the number of PB cycles"
+  },
+  {,
+    "EventCode": "0x20010",
+    "EventName": "PM_PMC1_OVERFLOW",
+    "BriefDescription": "Overflow from counter 1"
+  },
+  {,
+    "EventCode": "0x2005A",
+    "EventName": "PM_DARQ1_7_9_ENTRIES",
+    "BriefDescription": "Cycles in which 7 to 9 DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x3C048",
+    "EventName": "PM_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x10008",
+    "EventName": "PM_RUN_SPURR",
+    "BriefDescription": "Run SPURR"
+  },
+  {,
+    "EventCode": "0x200F6",
+    "EventName": "PM_LSU_DERAT_MISS",
+    "BriefDescription": "DERAT Reloaded due to a DERAT miss"
+  },
+  {,
+    "EventCode": "0x4C048",
+    "EventName": "PM_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x1D15E",
+    "EventName": "PM_MRK_RUN_CYC",
+    "BriefDescription": "Run cycles in which a marked instruction is in the pipeline"
+  },
+  {,
+    "EventCode": "0x4003E",
+    "EventName": "PM_LD_CMPL",
+    "BriefDescription": "count of Loads completed"
+  },
+  {,
+    "EventCode": "0x2D156",
+    "EventName": "PM_MRK_DTLB_MISS_4K",
+    "BriefDescription": "Marked Data TLB Miss page size 4k"
+  },
+  {,
+    "EventCode": "0x4C042",
+    "EventName": "PM_DATA_FROM_L3",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load"
+  },
+  {,
+    "EventCode": "0x4D02C",
+    "EventName": "PM_PMC1_REWIND",
+    "BriefDescription": ""
+  },
+  {,
+    "EventCode": "0x15158",
+    "EventName": "PM_SYNC_MRK_L2HIT",
+    "BriefDescription": "Marked L2 Hits that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x3404A",
+    "EventName": "PM_INST_FROM_RMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x301E2",
+    "EventName": "PM_MRK_ST_CMPL",
+    "BriefDescription": "Marked store completed and sent to nest"
+  },
+  {,
+    "EventCode": "0x1C050",
+    "EventName": "PM_DATA_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0x4C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_OTHER",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with dispatch conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x2E05C",
+    "EventName": "PM_LSU_REJECT_ERAT_MISS",
+    "BriefDescription": "LSU Reject due to ERAT (up to 4 per cycles)"
+  },
+  {,
+    "EventCode": "0x1000A",
+    "EventName": "PM_PMC3_REWIND",
+    "BriefDescription": "PMC3 rewind event. A rewind happens when a speculative event (such as latency or CPI stack) is selected on PMC3 and the stall reason or reload source did not match the one programmed in PMC3. When this occurs, the count in PMC3 will not change."
+  },
+  {,
+    "EventCode": "0x3C058",
+    "EventName": "PM_LARX_FIN",
+    "BriefDescription": "Larx finished"
+  },
+  {,
+    "EventCode": "0x1C040",
+    "EventName": "PM_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x2C040",
+    "EventName": "PM_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state due to a demand load"
+  },
+  {,
+    "EventCode": "0x2E05A",
+    "EventName": "PM_LRQ_REJECT",
+    "BriefDescription": "Internal LSU reject from LRQ. Rejects cause the load to go back to LRQ, but it stays contained within the LSU once it gets issued. This event counts the number of times the LRQ attempts to relaunch an instruction after a reject. Any load can suffer multiple rejects"
+  },
+  {,
+    "EventCode": "0x2C05C",
+    "EventName": "PM_INST_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for an instruction fetch (demand only)"
+  },
+  {,
+    "EventCode": "0x4D056",
+    "EventName": "PM_NON_FMA_FLOP_CMPL",
+    "BriefDescription": "Non FMA instruction completed"
+  },
+  {,
+    "EventCode": "0x3E050",
+    "EventName": "PM_DARQ1_4_6_ENTRIES",
+    "BriefDescription": "Cycles in which 4, 5, or 6 DARQ1 entries (out of 12) are in use"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
new file mode 100644
index 000000000000..54cc3be00fc2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -0,0 +1,2392 @@
+[
+  {,
+    "EventCode": "0x3084",
+    "EventName": "PM_ISU1_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0xF880",
+    "EventName": "PM_SNOOP_TLBIE",
+    "BriefDescription": "TLBIE snoop"
+  },
+  {,
+    "EventCode": "0x4088",
+    "EventName": "PM_IC_DEMAND_REQ",
+    "BriefDescription": "Demand Instruction fetch request"
+  },
+  {,
+    "EventCode": "0x20A4",
+    "EventName": "PM_TM_TRESUME",
+    "BriefDescription": "TM resume instruction completed"
+  },
+  {,
+    "EventCode": "0x40008",
+    "EventName": "PM_SRQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the SRQ has at least one (out of four) empty slice"
+  },
+  {,
+    "EventCode": "0x20064",
+    "EventName": "PM_IERAT_RELOAD_4K",
+    "BriefDescription": "IERAT reloaded (after a miss) for 4K pages"
+  },
+  {,
+    "EventCode": "0x260B4",
+    "EventName": "PM_L3_P2_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 2 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x20006",
+    "EventName": "PM_DISP_HELD_ISSQ_FULL",
+    "BriefDescription": "Dispatch held due to Issue q full. Includes issue queue and branch queue"
+  },
+  {,
+    "EventCode": "0x201E4",
+    "EventName": "PM_MRK_DATA_FROM_L3MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x4E044",
+    "EventName": "PM_DPTEG_FROM_L31_ECO_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40B8",
+    "EventName": "PM_BR_MPRED_TAKEN_CR",
+    "BriefDescription": "A Conditional Branch that resolved to taken was mispredicted as not taken (due to the BHT Direction Prediction)."
+  },
+  {,
+    "EventCode": "0xF8AC",
+    "EventName": "PM_DC_DEALLOC_NO_CONF",
+    "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)"
+  },
+  {,
+    "EventCode": "0xD090",
+    "EventName": "PM_LS0_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x40BC",
+    "EventName": "PM_THRD_PRIO_0_1_CYC",
+    "BriefDescription": "Cycles thread running at priority level 0 or 1"
+  },
+  {,
+    "EventCode": "0x2084",
+    "EventName": "PM_FLUSH_HB_RESTORE_CYC",
+    "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush.  History buffer recovery"
+  },
+  {,
+    "EventCode": "0x4F054",
+    "EventName": "PM_RADIX_PWC_MISS",
+    "BriefDescription": "A radix translation attempt missed in the TLB and all levels of page walk cache."
+  },
+  {,
+    "EventCode": "0x24048",
+    "EventName": "PM_INST_FROM_LMEM",
+    "BriefDescription": "The processor's Instruction cache was reloaded from the local chip's Memory due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0xD8B4",
+    "EventName": "PM_LSU0_LRQ_S0_VALID_CYC",
+    "BriefDescription": "Slot 0 of LRQ valid"
+  },
+  {,
+    "EventCode": "0x2E052",
+    "EventName": "PM_TM_PASSED",
+    "BriefDescription": "Number of TM transactions that passed"
+  },
+  {,
+    "EventCode": "0xD1A0",
+    "EventName": "PM_MRK_LSU_FLUSH_LHS",
+    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
+  },
+  {,
+    "EventCode": "0xF088",
+    "EventName": "PM_LSU0_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x360B2",
+    "EventName": "PM_L3_GRP_GUESS_WRONG_LOW",
+    "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low"
+  },
+  {,
+    "EventCode": "0x168A6",
+    "EventName": "PM_TM_CAM_OVERFLOW",
+    "BriefDescription": "L3 TM cam overflow during L2 co of SC"
+  },
+  {,
+    "EventCode": "0xE8B0",
+    "EventName": "PM_TEND_PEND_CYC",
+    "BriefDescription": "TEND latency per thread"
+  },
+  {,
+    "EventCode": "0x4884",
+    "EventName": "PM_IBUF_FULL_CYC",
+    "BriefDescription": "Cycles No room in ibuff"
+  },
+  {,
+    "EventCode": "0xD08C",
+    "EventName": "PM_LSU2_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region. This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])"
+  },
+  {,
+    "EventCode": "0x300F8",
+    "EventName": "PM_TB_BIT_TRANS",
+    "BriefDescription": "timebase event"
+  },
+  {,
+    "EventCode": "0x3C040",
+    "EventName": "PM_DATA_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0xE0BC",
+    "EventName": "PM_LS0_PTE_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 0"
+  },
+  {,
+    "EventCode": "0x3884",
+    "EventName": "PM_ISU3_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x460A6",
+    "EventName": "PM_RD_FORMING_SC",
+    "BriefDescription": "Read forming SC"
+  },
+  {,
+    "EventCode": "0x468A0",
+    "EventName": "PM_L3_PF_OFF_CHIP_MEM",
+    "BriefDescription": "L3 PF from Off chip memory"
+  },
+  {,
+    "EventCode": "0x268AA",
+    "EventName": "PM_L3_P1_LCO_DATA",
+    "BriefDescription": "LCO sent with data port 1"
+  },
+  {,
+    "EventCode": "0xE894",
+    "EventName": "PM_LSU1_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x5888",
+    "EventName": "PM_IC_INVALIDATE",
+    "BriefDescription": "Ic line invalidated"
+  },
+  {,
+    "EventCode": "0x2890",
+    "EventName": "PM_DISP_CLB_HELD_TLBIE",
+    "BriefDescription": "Dispatch Hold: Due to TLBIE"
+  },
+  {,
+    "EventCode": "0x1001C",
+    "EventName": "PM_CMPLU_STALL_THRD",
+    "BriefDescription": "Completion Stalled because the thread was blocked"
+  },
+  {,
+    "EventCode": "0x368A6",
+    "EventName": "PM_SNP_TM_HIT_T",
+    "BriefDescription": "Snp TM sthit T/Tn/Te"
+  },
+  {,
+    "EventCode": "0x3001A",
+    "EventName": "PM_DATA_TABLEWALK_CYC",
+    "BriefDescription": "Data Tablewalk Cycles.  Could be 1 or 2 active tablewalks. Includes data prefetches."
+  },
+  {,
+    "EventCode": "0xD894",
+    "EventName": "PM_LS3_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x35158",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xF0B4",
+    "EventName": "PM_DC_PREF_CONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch"
+  },
+  {,
+    "EventCode": "0xF894",
+    "EventName": "PM_LSU3_L1_CAM_CANCEL",
+    "BriefDescription": "ls3 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0x2888",
+    "EventName": "PM_FLUSH_DISP_TLBIE",
+    "BriefDescription": "Dispatch Flush: TLBIE"
+  },
+  {,
+    "EventCode": "0xD1A4",
+    "EventName": "PM_MRK_LSU_FLUSH_SAO",
+    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
+  },
+  {,
+    "EventCode": "0x4E11E",
+    "EventName": "PM_MRK_DATA_FROM_DMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x5894",
+    "EventName": "PM_LWSYNC",
+    "BriefDescription": "Lwsync instruction decoded and transferred"
+  },
+  {,
+    "EventCode": "0x14156",
+    "EventName": "PM_MRK_DATA_FROM_L2_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x468A6",
+    "EventName": "PM_RD_CLEARING_SC",
+    "BriefDescription": "Read clearing SC"
+  },
+  {,
+    "EventCode": "0x50A0",
+    "EventName": "PM_HWSYNC",
+    "BriefDescription": "Hwsync instruction decoded and transferred"
+  },
+  {,
+    "EventCode": "0x168B0",
+    "EventName": "PM_L3_P1_NODE_PUMP",
+    "BriefDescription": "L3 PF sent with nodal scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0xD0BC",
+    "EventName": "PM_LSU0_1_LRQF_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LRQF is full.  LRQF is the queue that holds loads between finish and completion.  If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ"
+  },
+  {,
+    "EventCode": "0x2D148",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_LDHITST",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 with load hit store conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x460A8",
+    "EventName": "PM_SN_HIT",
+    "BriefDescription": "Any port snooper hit L3.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x360AA",
+    "EventName": "PM_L3_P0_CO_MEM",
+    "BriefDescription": "L3 CO to memory port 0 with or without data"
+  },
+  {,
+    "EventCode": "0xF0A4",
+    "EventName": "PM_DC_PREF_HW_ALLOC",
+    "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism"
+  },
+  {,
+    "EventCode": "0xF0BC",
+    "EventName": "PM_LS2_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0xD0AC",
+    "EventName": "PM_SRQ_SYNC_CYC",
+    "BriefDescription": "A sync is in the S2Q (edge detect to count)"
+  },
+  {,
+    "EventCode": "0x401E6",
+    "EventName": "PM_MRK_INST_FROM_L3MISS",
+    "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet"
+  },
+  {,
+    "EventCode": "0x26082",
+    "EventName": "PM_L2_IC_INV",
+    "BriefDescription": "I-cache Invalidates sent over the realod bus to the core"
+  },
+  {,
+    "EventCode": "0xC8AC",
+    "EventName": "PM_LSU_FLUSH_RELAUNCH_MISS",
+    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+  },
+  {,
+    "EventCode": "0x260A4",
+    "EventName": "PM_L3_LD_HIT",
+    "BriefDescription": "L3 Hits for demand LDs"
+  },
+  {,
+    "EventCode": "0xF0A0",
+    "EventName": "PM_DATA_STORE",
+    "BriefDescription": "All ops that drain from s2q to L2 containing data"
+  },
+  {,
+    "EventCode": "0x1D148",
+    "EventName": "PM_MRK_DATA_FROM_RMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x16088",
+    "EventName": "PM_L2_LOC_GUESS_CORRECT",
+    "BriefDescription": "L2 guess local (LNS) and guess was correct (ie data local)"
+  },
+  {,
+    "EventCode": "0x160A4",
+    "EventName": "PM_L3_HIT",
+    "BriefDescription": "L3 Hits (L2 miss hitting L3, including data/instrn/xlate)"
+  },
+  {,
+    "EventCode": "0xE09C",
+    "EventName": "PM_LSU0_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x168B4",
+    "EventName": "PM_L3_P1_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 1 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x268AC",
+    "EventName": "PM_L3_RD_USAGE",
+    "BriefDescription": "Rotating sample of 16 RD actives"
+  },
+  {,
+    "EventCode": "0x1415C",
+    "EventName": "PM_MRK_DATA_FROM_L3_MEPF_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 without dispatch conflicts hit on Mepf state due to a marked load"
+  },
+  {,
+    "EventCode": "0xE880",
+    "EventName": "PM_L1_SW_PREF",
+    "BriefDescription": "Software L1 Prefetches, including SW Transient Prefetches"
+  },
+  {,
+    "EventCode": "0x288C",
+    "EventName": "PM_DISP_CLB_HELD_BAL",
+    "BriefDescription": "Dispatch/CLB Hold: Balance Flush"
+  },
+  {,
+    "EventCode": "0x101EA",
+    "EventName": "PM_MRK_L1_RELOAD_VALID",
+    "BriefDescription": "Marked demand reload"
+  },
+  {,
+    "EventCode": "0x1D156",
+    "EventName": "PM_MRK_LD_MISS_L1_CYC",
+    "BriefDescription": "Marked ld latency"
+  },
+  {,
+    "EventCode": "0x4C01A",
+    "EventName": "PM_CMPLU_STALL_DMISS_L3MISS",
+    "BriefDescription": "Completion stall due to cache miss resolving missed the L3"
+  },
+  {,
+    "EventCode": "0x2006C",
+    "EventName": "PM_RUN_CYC_SMT4_MODE",
+    "BriefDescription": "Cycles in which this thread's run latch is set and the core is in SMT4 mode"
+  },
+  {,
+    "EventCode": "0x5088",
+    "EventName": "PM_DECODE_FUSION_OP_PRESERV",
+    "BriefDescription": "Destructive op operand preservation"
+  },
+  {,
+    "EventCode": "0x1D14E",
+    "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE_CYC",
+    "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x509C",
+    "EventName": "PM_FORCED_NOP",
+    "BriefDescription": "Instruction was forced to execute as a nop because it was found to behave like a nop (have no effect) at decode time"
+  },
+  {,
+    "EventCode": "0xC098",
+    "EventName": "PM_LS2_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x20058",
+    "EventName": "PM_DARQ1_10_12_ENTRIES",
+    "BriefDescription": "Cycles in which 10 or  more DARQ1 entries (out of 12) are in use"
+  },
+  {,
+    "EventCode": "0x360A6",
+    "EventName": "PM_SNP_TM_HIT_M",
+    "BriefDescription": "Snp TM st hit M/Mu"
+  },
+  {,
+    "EventCode": "0x5898",
+    "EventName": "PM_LINK_STACK_INVALID_PTR",
+    "BriefDescription": "It is most often caused by certain types of flush where the pointer is not available. Can result in the data in the link stack becoming unusable."
+  },
+  {,
+    "EventCode": "0x46088",
+    "EventName": "PM_L2_CHIP_PUMP",
+    "BriefDescription": "RC requests that were local (aka chip) pump attempts"
+  },
+  {,
+    "EventCode": "0x28A0",
+    "EventName": "PM_TM_TSUSPEND",
+    "BriefDescription": "TM suspend instruction completed"
+  },
+  {,
+    "EventCode": "0x20054",
+    "EventName": "PM_L1_PREF",
+    "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch"
+  },
+  {,
+    "EventCode": "0xF888",
+    "EventName": "PM_LSU1_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x4505E",
+    "EventName": "PM_FLOP_CMPL",
+    "BriefDescription": "Floating Point Operation Finished"
+  },
+  {,
+    "EventCode": "0x1D144",
+    "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x400FA",
+    "EventName": "PM_RUN_INST_CMPL",
+    "BriefDescription": "Run_Instructions"
+  },
+  {,
+    "EventCode": "0x15154",
+    "EventName": "PM_SYNC_MRK_L3MISS",
+    "BriefDescription": "Marked L3 misses that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0xE0B4",
+    "EventName": "PM_LS0_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x26884",
+    "EventName": "PM_DSIDE_MRU_TOUCH",
+    "BriefDescription": "D-side L2 MRU touch sent to L2"
+  },
+  {,
+    "EventCode": "0x30134",
+    "EventName": "PM_MRK_ST_CMPL_INT",
+    "BriefDescription": "marked store finished with intervention"
+  },
+  {,
+    "EventCode": "0xC0B8",
+    "EventName": "PM_LSU_FLUSH_SAO",
+    "BriefDescription": "A load-hit-load condition with Strong Address Ordering will have address compare disabled and flush"
+  },
+  {,
+    "EventCode": "0x50A8",
+    "EventName": "PM_EAT_FORCE_MISPRED",
+    "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT.  The EAT forces a mispredict in this case since there is no predicated target to validate.  This is a rare case that may occur when the EAT is full and a branch is issued"
+  },
+  {,
+    "EventCode": "0xC094",
+    "EventName": "PM_LS0_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0xF8BC",
+    "EventName": "PM_LS3_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x58B0",
+    "EventName": "PM_BTAC_GOOD_RESULT",
+    "BriefDescription": "BTAC predicts a taken branch and the BHT agrees, and the target address is correct"
+  },
+  {,
+    "EventCode": "0x1C04C",
+    "EventName": "PM_DATA_FROM_LL4",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's L4 cache due to a demand load"
+  },
+  {,
+    "EventCode": "0x3608E",
+    "EventName": "PM_TM_ST_CONF",
+    "BriefDescription": "TM Store (fav or non-fav) ran into conflict (failed)"
+  },
+  {,
+    "EventCode": "0xD998",
+    "EventName": "PM_MRK_LSU_FLUSH_EMSH",
+    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
+  },
+  {,
+    "EventCode": "0xF8A0",
+    "EventName": "PM_NON_DATA_STORE",
+    "BriefDescription": "All ops that drain from s2q to L2 and contain no data"
+  },
+  {,
+    "EventCode": "0x3F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40A0",
+    "EventName": "PM_BR_UNCOND",
+    "BriefDescription": "Unconditional Branch Completed. HW branch prediction was not used for this branch. This can be an I-form branch, a B-form branch with BO-field set to branch always, or a B-form branch which was covenrted to a Resolve."
+  },
+  {,
+    "EventCode": "0x1F056",
+    "EventName": "PM_RADIX_PWC_L1_HIT",
+    "BriefDescription": "A radix translation attempt missed in the TLB and only the first level page walk cache was a hit."
+  },
+  {,
+    "EventCode": "0xF8A8",
+    "EventName": "PM_DC_PREF_FUZZY_CONF",
+    "BriefDescription": "A demand load referenced a line in an active fuzzy prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software.Fuzzy stream confirm (out of order effects, or pf cant keep up)"
+  },
+  {,
+    "EventCode": "0xF8A4",
+    "EventName": "PM_DC_PREF_SW_ALLOC",
+    "BriefDescription": "Prefetch stream allocated by software prefetching"
+  },
+  {,
+    "EventCode": "0xE0A0",
+    "EventName": "PM_LSU2_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x2894",
+    "EventName": "PM_TM_OUTER_TEND",
+    "BriefDescription": "Completion time outer tend"
+  },
+  {,
+    "EventCode": "0xF098",
+    "EventName": "PM_XLATE_HPT_MODE",
+    "BriefDescription": "LSU reports every cycle the thread is in HPT translation mode (as opposed to radix mode)"
+  },
+  {,
+    "EventCode": "0x2C04E",
+    "EventName": "PM_LD_MISS_L1_FIN",
+    "BriefDescription": "Number of load instructions that finished with an L1 miss. Note that even if a load spans multiple slices this event will increment only once per load op."
+  },
+  {,
+    "EventCode": "0x30162",
+    "EventName": "PM_MRK_LSU_DERAT_MISS",
+    "BriefDescription": "Marked derat reload (miss) for any page size"
+  },
+  {,
+    "EventCode": "0x160A0",
+    "EventName": "PM_L3_PF_MISS_L3",
+    "BriefDescription": "L3 PF missed in L3"
+  },
+  {,
+    "EventCode": "0x1C04A",
+    "EventName": "PM_DATA_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0xD99C",
+    "EventName": "PM_MRK_LSU_FLUSH_UE",
+    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
+  },
+  {,
+    "EventCode": "0x268B0",
+    "EventName": "PM_L3_P1_GRP_PUMP",
+    "BriefDescription": "L3 PF sent with grp scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x30016",
+    "EventName": "PM_CMPLU_STALL_SRQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a store that was held in LSAQ because the SRQ was full"
+  },
+  {,
+    "EventCode": "0x40B4",
+    "EventName": "PM_BR_PRED_TA",
+    "BriefDescription": "Conditional Branch Completed that had its target address predicted. Only XL-form branches set this event.  This equal the sum of CCACHE, LSTACK, and PCACHE"
+  },
+  {,
+    "EventCode": "0x40AC",
+    "EventName": "PM_BR_MPRED_CCACHE",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Count Cache Target Prediction"
+  },
+  {,
+    "EventCode": "0x3688A",
+    "EventName": "PM_L2_RTY_LD",
+    "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
+  },
+  {,
+    "EventCode": "0xE08C",
+    "EventName": "PM_LSU0_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0xE088",
+    "EventName": "PM_LS2_ERAT_MISS_PREF",
+    "BriefDescription": "LS0 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0xF0A8",
+    "EventName": "PM_DC_PREF_CONF",
+    "BriefDescription": "A demand load referenced a line in an active prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software. Includes forwards and backwards streams"
+  },
+  {,
+    "EventCode": "0x16888",
+    "EventName": "PM_L2_LOC_GUESS_WRONG",
+    "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)"
+  },
+  {,
+    "EventCode": "0xE0A4",
+    "EventName": "PM_TMA_REQ_L2",
+    "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding"
+  },
+  {,
+    "EventCode": "0x5884",
+    "EventName": "PM_DECODE_LANES_NOT_AVAIL",
+    "BriefDescription": "Decode has something to transmit but dispatch lanes are not available"
+  },
+  {,
+    "EventCode": "0x3C042",
+    "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load"
+  },
+  {,
+    "EventCode": "0x168AA",
+    "EventName": "PM_L3_P1_LCO_NO_DATA",
+    "BriefDescription": "Dataless L3 LCO sent port 1"
+  },
+  {,
+    "EventCode": "0x3D140",
+    "EventName": "PM_MRK_DATA_FROM_L2_DISP_CONFLICT_OTHER_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0xC89C",
+    "EventName": "PM_LS1_LAUNCH_HELD_PREF",
+    "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle"
+  },
+  {,
+    "EventCode": "0x4894",
+    "EventName": "PM_IC_RELOAD_PRIVATE",
+    "BriefDescription": "Reloading line was brought in private for a specific thread.  Most lines are brought in shared for all eight threads.  If RA does not match then invalidates and then brings it shared to other thread. In P7 line brought in private , then line was invalidat"
+  },
+  {,
+    "EventCode": "0x1688E",
+    "EventName": "PM_TM_LD_CAUSED_FAIL",
+    "BriefDescription": "Non-TM Load caused any thread to fail"
+  },
+  {,
+    "EventCode": "0x26084",
+    "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x101E4",
+    "EventName": "PM_MRK_L1_ICACHE_MISS",
+    "BriefDescription": "sampled Instruction suffered an icache Miss"
+  },
+  {,
+    "EventCode": "0x20A0",
+    "EventName": "PM_TM_NESTED_TBEGIN",
+    "BriefDescription": "Completion Tm nested tbegin"
+  },
+  {,
+    "EventCode": "0x368AA",
+    "EventName": "PM_L3_P1_CO_MEM",
+    "BriefDescription": "L3 CO to memory port 1 with or without data"
+  },
+  {,
+    "EventCode": "0xC8A4",
+    "EventName": "PM_LSU3_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0xD9A4",
+    "EventName": "PM_MRK_LSU_FLUSH_LARX_STCX",
+    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+  },
+  {,
+    "EventCode": "0x4D012",
+    "EventName": "PM_PMC3_SAVED",
+    "BriefDescription": "PMC3 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0xE888",
+    "EventName": "PM_LS3_ERAT_MISS_PREF",
+    "BriefDescription": "LS1 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0x368B4",
+    "EventName": "PM_L3_RD0_BUSY",
+    "BriefDescription": "Lifetime, sample of RD machine 0 valid"
+  },
+  {,
+    "EventCode": "0x46080",
+    "EventName": "PM_L2_DISP_ALL_L2MISS",
+    "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0xF8B8",
+    "EventName": "PM_LS1_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x408C",
+    "EventName": "PM_L1_DEMAND_WRITE",
+    "BriefDescription": "Instruction Demand sectors written into IL1"
+  },
+  {,
+    "EventCode": "0x368A8",
+    "EventName": "PM_SN_INVL",
+    "BriefDescription": "Any port snooper detects a store to a line in the Sx state and invalidates the line.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x160B2",
+    "EventName": "PM_L3_LOC_GUESS_CORRECT",
+    "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only"
+  },
+  {,
+    "EventCode": "0x48B4",
+    "EventName": "PM_DECODE_FUSION_CONST_GEN",
+    "BriefDescription": "32-bit constant generation"
+  },
+  {,
+    "EventCode": "0x4D146",
+    "EventName": "PM_MRK_DATA_FROM_L21_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xE080",
+    "EventName": "PM_S2Q_FULL",
+    "BriefDescription": "Cycles during which the S2Q is full"
+  },
+  {,
+    "EventCode": "0x268B4",
+    "EventName": "PM_L3_P3_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 3 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0xD8B8",
+    "EventName": "PM_LSU0_LMQ_S0_VALID",
+    "BriefDescription": "Slot 0 of LMQ valid"
+  },
+  {,
+    "EventCode": "0x2098",
+    "EventName": "PM_TM_NESTED_TEND",
+    "BriefDescription": "Completion time nested tend"
+  },
+  {,
+    "EventCode": "0x36084",
+    "EventName": "PM_L2_RCST_DISP",
+    "BriefDescription": "All D-side store dispatch attempts for this thread"
+  },
+  {,
+    "EventCode": "0x368A0",
+    "EventName": "PM_L3_PF_OFF_CHIP_CACHE",
+    "BriefDescription": "L3 PF from Off chip cache"
+  },
+  {,
+    "EventCode": "0x20056",
+    "EventName": "PM_TAKEN_BR_MPRED_CMPL",
+    "BriefDescription": "Total number of taken branches that were incorrectly predicted as not-taken. This event counts branches completed and does not include speculative instructions"
+  },
+  {,
+    "EventCode": "0x4688A",
+    "EventName": "PM_L2_SYS_PUMP",
+    "BriefDescription": "RC requests that were system pump attempts"
+  },
+  {,
+    "EventCode": "0xE090",
+    "EventName": "PM_LSU2_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0x4001C",
+    "EventName": "PM_INST_IMC_MATCH_CMPL",
+    "BriefDescription": "IMC Match Count"
+  },
+  {,
+    "EventCode": "0x40A8",
+    "EventName": "PM_BR_PRED_LSTACK",
+    "BriefDescription": "Conditional Branch Completed  that used the Link Stack for Target Prediction"
+  },
+  {,
+    "EventCode": "0x268A2",
+    "EventName": "PM_L3_CI_MISS",
+    "BriefDescription": "L3 castins miss (total count)"
+  },
+  {,
+    "EventCode": "0x289C",
+    "EventName": "PM_TM_NON_FAV_TBEGIN",
+    "BriefDescription": "Dispatch time non favored tbegin"
+  },
+  {,
+    "EventCode": "0xF08C",
+    "EventName": "PM_LSU2_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x360A0",
+    "EventName": "PM_L3_PF_ON_CHIP_CACHE",
+    "BriefDescription": "L3 PF from On chip cache"
+  },
+  {,
+    "EventCode": "0x35152",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS_CYC",
+    "BriefDescription": "Duration in cycles to reload from a location other than the local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x160AC",
+    "EventName": "PM_L3_SN_USAGE",
+    "BriefDescription": "Rotating sample of 16 snoop valids"
+  },
+  {,
+    "EventCode": "0x16084",
+    "EventName": "PM_L2_RCLD_DISP",
+    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x1608C",
+    "EventName": "PM_RC0_BUSY",
+    "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x36082",
+    "EventName": "PM_L2_LD_DISP",
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
+  },
+  {,
+    "EventCode": "0xF8B0",
+    "EventName": "PM_L3_SW_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest"
+  },
+  {,
+    "EventCode": "0xF884",
+    "EventName": "PM_TABLEWALK_CYC_PREF",
+    "BriefDescription": "tablewalk qualified for pte  prefetches"
+  },
+  {,
+    "EventCode": "0x4D144",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x16884",
+    "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR",
+    "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x460A0",
+    "EventName": "PM_L3_PF_ON_CHIP_MEM",
+    "BriefDescription": "L3 PF from On chip memory"
+  },
+  {,
+    "EventCode": "0xF084",
+    "EventName": "PM_PTE_PREFETCH",
+    "BriefDescription": "PTE prefetches"
+  },
+  {,
+    "EventCode": "0x2D026",
+    "EventName": "PM_RADIX_PWC_L1_PDE_FROM_L2",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 1 page walk cache from the core's L2 data cache"
+  },
+  {,
+    "EventCode": "0x48B0",
+    "EventName": "PM_BR_MPRED_PCACHE",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to pattern cache prediction"
+  },
+  {,
+    "EventCode": "0x2C126",
+    "EventName": "PM_MRK_DATA_FROM_L2",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0xE0AC",
+    "EventName": "PM_TM_FAIL_TLBIE",
+    "BriefDescription": "Transaction failed because there was a TLBIE hit in the bloom filter"
+  },
+  {,
+    "EventCode": "0x260AA",
+    "EventName": "PM_L3_P0_LCO_DATA",
+    "BriefDescription": "LCO sent with data port 0"
+  },
+  {,
+    "EventCode": "0x4888",
+    "EventName": "PM_IC_PREF_REQ",
+    "BriefDescription": "Instruction prefetch requests"
+  },
+  {,
+    "EventCode": "0xC898",
+    "EventName": "PM_LS3_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x488C",
+    "EventName": "PM_IC_PREF_WRITE",
+    "BriefDescription": "Instruction prefetch written into IL1"
+  },
+  {,
+    "EventCode": "0xF89C",
+    "EventName": "PM_XLATE_MISS",
+    "BriefDescription": "The LSU requested a line from L2 for translation.  It may be satisfied from any source beyond L2.  Includes speculative instructions"
+  },
+  {,
+    "EventCode": "0x14158",
+    "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x35156",
+    "EventName": "PM_MRK_DATA_FROM_L31_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x268A6",
+    "EventName": "PM_TM_RST_SC",
+    "BriefDescription": "TM-snp rst RM SC"
+  },
+  {,
+    "EventCode": "0x468A4",
+    "EventName": "PM_L3_TRANS_PF",
+    "BriefDescription": "L3 Transient prefetch received from L2"
+  },
+  {,
+    "EventCode": "0x4094",
+    "EventName": "PM_IC_PREF_CANCEL_L2",
+    "BriefDescription": "L2 Squashed a demand or prefetch request"
+  },
+  {,
+    "EventCode": "0x48AC",
+    "EventName": "PM_BR_MPRED_LSTACK",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Link Stack Target Prediction"
+  },
+  {,
+    "EventCode": "0xE88C",
+    "EventName": "PM_LSU1_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0xC0B4",
+    "EventName": "PM_LSU_FLUSH_WRK_ARND",
+    "BriefDescription": "LSU workaround flush.  These flushes are setup with programmable scan only latches to perform various actions when the flush macro receives a trigger from the dbg macros. These actions include things like flushing the next op encountered for a particular thread or flushing the next op that is NTC op that is encountered on a particular slice. The kind of flush that the workaround is setup to perform is highly variable."
+  },
+  {,
+    "EventCode": "0x34054",
+    "EventName": "PM_PARTIAL_ST_FIN",
+    "BriefDescription": "Any store finished by an LSU slice"
+  },
+  {,
+    "EventCode": "0x5880",
+    "EventName": "PM_THRD_PRIO_6_7_CYC",
+    "BriefDescription": "Cycles thread running at priority level 6 or 7"
+  },
+  {,
+    "EventCode": "0x4898",
+    "EventName": "PM_IC_DEMAND_L2_BR_REDIRECT",
+    "BriefDescription": "L2 I cache demand request due to branch Mispredict ( 15 cycle path)"
+  },
+  {,
+    "EventCode": "0x4880",
+    "EventName": "PM_BANK_CONFLICT",
+    "BriefDescription": "Read blocked due to interleave conflict.  The ifar logic will detect an interleave conflict and kill the data that was read that cycle."
+  },
+  {,
+    "EventCode": "0x360B0",
+    "EventName": "PM_L3_P0_SYS_PUMP",
+    "BriefDescription": "L3 PF sent with sys scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x3006A",
+    "EventName": "PM_IERAT_RELOAD_64K",
+    "BriefDescription": "IERAT Reloaded (Miss) for a 64k page"
+  },
+  {,
+    "EventCode": "0xD8BC",
+    "EventName": "PM_LSU2_3_LRQF_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LRQF is full.  LRQF is the queue that holds loads between finish and completion.  If it fills up, instructions stay in LRQ until completion, potentially backing up the LRQ"
+  },
+  {,
+    "EventCode": "0x46086",
+    "EventName": "PM_L2_SN_M_RD_DONE",
+    "BriefDescription": "SNP dispatched for a read and was M (true M)"
+  },
+  {,
+    "EventCode": "0x40154",
+    "EventName": "PM_MRK_FAB_RSP_BKILL",
+    "BriefDescription": "Marked store had to do a bkill"
+  },
+  {,
+    "EventCode": "0xF094",
+    "EventName": "PM_LSU2_L1_CAM_CANCEL",
+    "BriefDescription": "ls2 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0x2D014",
+    "EventName": "PM_CMPLU_STALL_LRQ_FULL",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that was held in LSAQ (load-store address queue) because the LRQ (load-reorder queue) was full"
+  },
+  {,
+    "EventCode": "0x3E05E",
+    "EventName": "PM_L3_CO_MEPF",
+    "BriefDescription": "L3 castouts in Mepf state for this thread"
+  },
+  {,
+    "EventCode": "0x460A2",
+    "EventName": "PM_L3_LAT_CI_HIT",
+    "BriefDescription": "L3 Lateral Castins Hit"
+  },
+  {,
+    "EventCode": "0x3D14E",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3D15E",
+    "EventName": "PM_MULT_MRK",
+    "BriefDescription": "mult marked instr"
+  },
+  {,
+    "EventCode": "0x4084",
+    "EventName": "PM_EAT_FULL_CYC",
+    "BriefDescription": "Cycles No room in EAT"
+  },
+  {,
+    "EventCode": "0x5098",
+    "EventName": "PM_LINK_STACK_WRONG_ADD_PRED",
+    "BriefDescription": "Link stack predicts wrong address, because of link stack design limitation or software violating the coding conventions"
+  },
+  {,
+    "EventCode": "0x2C050",
+    "EventName": "PM_DATA_GRP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was group pump (prediction=correct) for a demand load"
+  },
+  {,
+    "EventCode": "0xC0A4",
+    "EventName": "PM_LSU2_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x58A0",
+    "EventName": "PM_LINK_STACK_CORRECT",
+    "BriefDescription": "Link stack predicts right address"
+  },
+  {,
+    "EventCode": "0x4C05A",
+    "EventName": "PM_DTLB_MISS_1G",
+    "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x36886",
+    "EventName": "PM_L2_SN_SX_I_DONE",
+    "BriefDescription": "SNP dispatched and went from Sx to Ix"
+  },
+  {,
+    "EventCode": "0x4E04A",
+    "EventName": "PM_DPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2C12C",
+    "EventName": "PM_MRK_DATA_FROM_DL4_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x2608E",
+    "EventName": "PM_TM_LD_CONF",
+    "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)"
+  },
+  {,
+    "EventCode": "0x4080",
+    "EventName": "PM_INST_FROM_L1",
+    "BriefDescription": "Instruction fetches from L1.  L1 instruction hit"
+  },
+  {,
+    "EventCode": "0xE898",
+    "EventName": "PM_LSU3_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x260A0",
+    "EventName": "PM_L3_CO_MEM",
+    "BriefDescription": "L3 CO to memory OR of port 0 and 1 (lossy = may undercount if two cresp come in the same cyc)"
+  },
+  {,
+    "EventCode": "0x16082",
+    "EventName": "PM_L2_CASTOUT_MOD",
+    "BriefDescription": "L2 Castouts - Modified (M,Mu,Me)"
+  },
+  {,
+    "EventCode": "0xC09C",
+    "EventName": "PM_LS0_LAUNCH_HELD_PREF",
+    "BriefDescription": "Number of times a load or store instruction was unable to launch/relaunch because a high priority prefetch used that relaunch cycle"
+  },
+  {,
+    "EventCode": "0xC8B8",
+    "EventName": "PM_LSU_FLUSH_LARX_STCX",
+    "BriefDescription": "A larx is flushed because an older larx has an LMQ reservation for the same thread.  A stcx is flushed because an older stcx is in the LMQ.  The flush happens when the older larx/stcx relaunches"
+  },
+  {,
+    "EventCode": "0x260A6",
+    "EventName": "PM_NON_TM_RST_SC",
+    "BriefDescription": "Non-TM snp rst TM SC"
+  },
+  {,
+    "EventCode": "0x3608A",
+    "EventName": "PM_L2_RTY_ST",
+    "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
+  },
+  {,
+    "EventCode": "0x24040",
+    "EventName": "PM_INST_FROM_L2_MEPF",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x209C",
+    "EventName": "PM_TM_FAV_TBEGIN",
+    "BriefDescription": "Dispatch time Favored tbegin"
+  },
+  {,
+    "EventCode": "0x2D01E",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_ISSQ",
+    "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full"
+  },
+  {,
+    "EventCode": "0x50A4",
+    "EventName": "PM_FLUSH_MPRED",
+    "BriefDescription": "Branch mispredict flushes.  Includes target and address misprecition"
+  },
+  {,
+    "EventCode": "0x508C",
+    "EventName": "PM_SHL_CREATED",
+    "BriefDescription": "Store-Hit-Load Table Entry Created"
+  },
+  {,
+    "EventCode": "0x1504C",
+    "EventName": "PM_IPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x268A4",
+    "EventName": "PM_L3_LD_MISS",
+    "BriefDescription": "L3 Misses for demand LDs"
+  },
+  {,
+    "EventCode": "0x26088",
+    "EventName": "PM_L2_GRP_GUESS_CORRECT",
+    "BriefDescription": "L2 guess grp (GS or NNS) and guess was correct (data intra-group AND ^on-chip)"
+  },
+  {,
+    "EventCode": "0xD088",
+    "EventName": "PM_LSU0_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0xE8B4",
+    "EventName": "PM_LS1_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x1688C",
+    "EventName": "PM_RC_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each RC machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0x3F054",
+    "EventName": "PM_RADIX_PWC_L4_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 4 page walk cache from beyond the core's L3 data cache. This is the deepest level of PWC possible for a translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x2608A",
+    "EventName": "PM_ISIDE_DISP_FAIL_ADDR",
+    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x50B4",
+    "EventName": "PM_TAGE_CORRECT_TAKEN_CMPL",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.  Counted at completion for taken branches only"
+  },
+  {,
+    "EventCode": "0x2090",
+    "EventName": "PM_DISP_CLB_HELD_SB",
+    "BriefDescription": "Dispatch/CLB Hold: Scoreboard"
+  },
+  {,
+    "EventCode": "0xE0B0",
+    "EventName": "PM_TM_FAIL_NON_TX_CONFLICT",
+    "BriefDescription": "Non transactional conflict from LSU, gets reported to TEXASR"
+  },
+  {,
+    "EventCode": "0xD198",
+    "EventName": "PM_MRK_LSU_FLUSH_ATOMIC",
+    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
+  },
+  {,
+    "EventCode": "0x201E0",
+    "EventName": "PM_MRK_DATA_FROM_MEMORY",
+    "BriefDescription": "The processor's data cache was reloaded from a memory location including L4 from local remote or distant due to a marked load"
+  },
+  {,
+    "EventCode": "0x368A2",
+    "EventName": "PM_L3_L2_CO_MISS",
+    "BriefDescription": "L2 CO miss"
+  },
+  {,
+    "EventCode": "0x3608C",
+    "EventName": "PM_CO0_BUSY",
+    "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x2C122",
+    "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x35154",
+    "EventName": "PM_MRK_DATA_FROM_L3_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 due to a marked load"
+  },
+  {,
+    "EventCode": "0x1D140",
+    "EventName": "PM_MRK_DATA_FROM_L31_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x4404A",
+    "EventName": "PM_INST_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's Instruction cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x28AC",
+    "EventName": "PM_TM_FAIL_SELF",
+    "BriefDescription": "TM aborted because a self-induced conflict occurred in Suspended state, due to one of the following: a store to a storage location that was previously accessed transactionally; a dcbf, dcbi, or icbi specify- ing a block that was previously accessed transactionally; a dcbst specifying a block that was previously written transactionally; or a tlbie that specifies a translation that was pre- viously used transactionally"
+  },
+  {,
+    "EventCode": "0x45056",
+    "EventName": "PM_SCALAR_FLOP_CMPL",
+    "BriefDescription": "Scalar flop operation completed"
+  },
+  {,
+    "EventCode": "0x16092",
+    "EventName": "PM_L2_LD_MISS_128B",
+    "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)"
+  },
+  {,
+    "EventCode": "0x2E014",
+    "EventName": "PM_STCX_FIN",
+    "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed"
+  },
+  {,
+    "EventCode": "0xE0B8",
+    "EventName": "PM_LS2_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x2094",
+    "EventName": "PM_TM_OUTER_TBEGIN",
+    "BriefDescription": "Completion time outer tbegin"
+  },
+  {,
+    "EventCode": "0x160B4",
+    "EventName": "PM_L3_P0_LCO_RTY",
+    "BriefDescription": "L3 initiated LCO received retry on port 0 (can try 4 times)"
+  },
+  {,
+    "EventCode": "0x36892",
+    "EventName": "PM_DSIDE_OTHER_64B_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory that was for hpc_read64, (RC had to fetch other 64B of a line from MC) i.e., number of times RC had to go to memory to get 'missing' 64B"
+  },
+  {,
+    "EventCode": "0x20A8",
+    "EventName": "PM_TM_FAIL_FOOTPRINT_OVERFLOW",
+    "BriefDescription": "TM aborted because the tracking limit for transactional storage accesses was exceeded.. Asynchronous"
+  },
+  {,
+    "EventCode": "0x30018",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL",
+    "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
+  },
+  {,
+    "EventCode": "0xC894",
+    "EventName": "PM_LS1_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x360A2",
+    "EventName": "PM_L3_L2_CO_HIT",
+    "BriefDescription": "L2 CO hits"
+  },
+  {,
+    "EventCode": "0x36092",
+    "EventName": "PM_DSIDE_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an D-side fetch where data came EXCLUSIVELY from memory (excluding hpcread64 accesses), i.e., total memory accesses by RCs"
+  },
+  {,
+    "EventCode": "0x10138",
+    "EventName": "PM_MRK_BR_2PATH",
+    "BriefDescription": "marked branches which are not strongly biased"
+  },
+  {,
+    "EventCode": "0x2884",
+    "EventName": "PM_ISYNC",
+    "BriefDescription": "Isync completion count per thread"
+  },
+  {,
+    "EventCode": "0x16882",
+    "EventName": "PM_L2_CASTOUT_SHR",
+    "BriefDescription": "L2 Castouts - Shared (Tx,Sx)"
+  },
+  {,
+    "EventCode": "0xD884",
+    "EventName": "PM_LSU3_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x26092",
+    "EventName": "PM_L2_LD_MISS_64B",
+    "BriefDescription": "All successful D-side load dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B(i.e., M=1)"
+  },
+  {,
+    "EventCode": "0x26080",
+    "EventName": "PM_L2_LD_MISS",
+    "BriefDescription": "All successful D-Side Load dispatches that were an L2 miss for this thread"
+  },
+  {,
+    "EventCode": "0x3D14C",
+    "EventName": "PM_MRK_DATA_FROM_DMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x100FA",
+    "EventName": "PM_ANY_THRD_RUN_CYC",
+    "BriefDescription": "Cycles in which at least one thread has the run latch set"
+  },
+  {,
+    "EventCode": "0x2C12A",
+    "EventName": "PM_MRK_DATA_FROM_RMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from another chip's memory on the same Node or Group ( Remote) due to a marked load"
+  },
+  {,
+    "EventCode": "0x25048",
+    "EventName": "PM_IPTEG_FROM_LMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD8A8",
+    "EventName": "PM_ISLB_MISS",
+    "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
+  },
+  {,
+    "EventCode": "0xD19C",
+    "EventName": "PM_MRK_LSU_FLUSH_RELAUNCH_MISS",
+    "BriefDescription": "If a load that has already returned data and has to relaunch for any reason then gets a miss (erat, setp, data cache), it will often be flushed at relaunch time because the data might be inconsistent"
+  },
+  {,
+    "EventCode": "0x260A2",
+    "EventName": "PM_L3_CI_HIT",
+    "BriefDescription": "L3 Castins Hit (total count)"
+  },
+  {,
+    "EventCode": "0x44054",
+    "EventName": "PM_VECTOR_LD_CMPL",
+    "BriefDescription": "Number of vector load instructions completed"
+  },
+  {,
+    "EventCode": "0x1E05C",
+    "EventName": "PM_CMPLU_STALL_NESTED_TBEGIN",
+    "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tbegin. This is a short delay, and it includes ROT"
+  },
+  {,
+    "EventCode": "0x1608E",
+    "EventName": "PM_ST_CAUSED_FAIL",
+    "BriefDescription": "Non-TM Store caused any thread to fail"
+  },
+  {,
+    "EventCode": "0x3080",
+    "EventName": "PM_ISU0_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x1515A",
+    "EventName": "PM_SYNC_MRK_L2MISS",
+    "BriefDescription": "Marked L2 Miss that can throw a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x26892",
+    "EventName": "PM_L2_ST_MISS_64B",
+    "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 64B (i.e., M=1)"
+  },
+  {,
+    "EventCode": "0x2688C",
+    "EventName": "PM_CO_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each CO machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0xD084",
+    "EventName": "PM_LSU2_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x48B8",
+    "EventName": "PM_BR_MPRED_TAKEN_TA",
+    "BriefDescription": "Conditional Branch Completed that was Mispredicted due to the Target Address Prediction from the Count Cache or Link Stack.  Only XL-form branches that resolved Taken set this event."
+  },
+  {,
+    "EventCode": "0x50B0",
+    "EventName": "PM_BTAC_BAD_RESULT",
+    "BriefDescription": "BTAC thinks branch will be taken but it is either predicted not-taken by the BHT, or the target address is wrong (less common).  In both cases, a redirect will happen"
+  },
+  {,
+    "EventCode": "0xD888",
+    "EventName": "PM_LSU1_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0x58B4",
+    "EventName": "PM_TAGE_CORRECT",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.   Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0x3688C",
+    "EventName": "PM_SN_USAGE",
+    "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
+  },
+  {,
+    "EventCode": "0x46084",
+    "EventName": "PM_L2_RCST_DISP_FAIL_OTHER",
+    "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision"
+  },
+  {,
+    "EventCode": "0xF0AC",
+    "EventName": "PM_DC_PREF_STRIDED_CONF",
+    "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
+  },
+  {,
+    "EventCode": "0x45054",
+    "EventName": "PM_FMA_CMPL",
+    "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. "
+  },
+  {,
+    "EventCode": "0x5090",
+    "EventName": "PM_SHL_ST_DISABLE",
+    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Disabled (entry was disabled due to the entry shown to not prevent the flush)"
+  },
+  {,
+    "EventCode": "0x201E8",
+    "EventName": "PM_THRESH_EXC_512",
+    "BriefDescription": "Threshold counter exceeded a value of 512"
+  },
+  {,
+    "EventCode": "0x5084",
+    "EventName": "PM_DECODE_FUSION_EXT_ADD",
+    "BriefDescription": "32-bit extended addition"
+  },
+  {,
+    "EventCode": "0x36080",
+    "EventName": "PM_L2_INST",
+    "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
+  },
+  {,
+    "EventCode": "0x3504C",
+    "EventName": "PM_IPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD890",
+    "EventName": "PM_LS1_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x1688A",
+    "EventName": "PM_ISIDE_DISP",
+    "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x468AA",
+    "EventName": "PM_L3_P1_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 (LCO) port 1 with or without data"
+  },
+  {,
+    "EventCode": "0x28B0",
+    "EventName": "PM_DISP_HELD_TBEGIN",
+    "BriefDescription": "This outer tbegin transaction cannot be dispatched until the previous tend instruction completes"
+  },
+  {,
+    "EventCode": "0xE8A0",
+    "EventName": "PM_LSU3_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x2C05E",
+    "EventName": "PM_INST_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for an instruction fetch (demand only)"
+  },
+  {,
+    "EventCode": "0xC8BC",
+    "EventName": "PM_STCX_SUCCESS_CMPL",
+    "BriefDescription": "Number of stcx instructions that completed successfully"
+  },
+  {,
+    "EventCode": "0xE098",
+    "EventName": "PM_LSU2_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x44044",
+    "EventName": "PM_INST_FROM_L31_ECO_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x16886",
+    "EventName": "PM_CO_DISP_FAIL",
+    "BriefDescription": "CO dispatch failed due to all CO machines being busy"
+  },
+  {,
+    "EventCode": "0x3D146",
+    "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x16892",
+    "EventName": "PM_L2_ST_MISS_128B",
+    "BriefDescription": "All successful D-side store dispatches that were an L2 miss (NOT Sx,Tx,Mx) for this thread and the RC calculated the request should be for 128B (i.e., M=0)"
+  },
+  {,
+    "EventCode": "0x26890",
+    "EventName": "PM_ISIDE_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an I-side fetch where data came from memory"
+  },
+  {,
+    "EventCode": "0xD094",
+    "EventName": "PM_LS2_DC_COLLISIONS",
+    "BriefDescription": "Read-write data cache collisions"
+  },
+  {,
+    "EventCode": "0x3C05E",
+    "EventName": "PM_MEM_RWITM",
+    "BriefDescription": "Memory Read With Intent to Modify for this thread"
+  },
+  {,
+    "EventCode": "0x26882",
+    "EventName": "PM_L2_DC_INV",
+    "BriefDescription": "D-cache invalidates sent over the reload bus to the core"
+  },
+  {,
+    "EventCode": "0xC090",
+    "EventName": "PM_LSU_STCX",
+    "BriefDescription": "STCX sent to nest, i.e. total"
+  },
+  {,
+    "EventCode": "0xD080",
+    "EventName": "PM_LSU0_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0x2C120",
+    "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x36086",
+    "EventName": "PM_L2_RC_ST_DONE",
+    "BriefDescription": "RC did store to line that was Tx or Sx"
+  },
+  {,
+    "EventCode": "0xE8AC",
+    "EventName": "PM_TM_FAIL_TX_CONFLICT",
+    "BriefDescription": "Transactional conflict from LSU, gets reported to TEXASR"
+  },
+  {,
+    "EventCode": "0x48A8",
+    "EventName": "PM_DECODE_FUSION_LD_ST_DISP",
+    "BriefDescription": "32-bit displacement D-form and 16-bit displacement X-form"
+  },
+  {,
+    "EventCode": "0x3D144",
+    "EventName": "PM_MRK_DATA_FROM_L2_MEPF_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x44046",
+    "EventName": "PM_INST_FROM_L21_MOD",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x40B0",
+    "EventName": "PM_BR_PRED_TAKEN_CR",
+    "BriefDescription": "Conditional Branch that had its direction predicted. I-form branches do not set this event.  In addition, B-form branches which do not use the BHT do not set this event - these are branches with BO-field set to 'always taken' and branches"
+  },
+  {,
+    "EventCode": "0x15040",
+    "EventName": "PM_IPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xD9A0",
+    "EventName": "PM_MRK_LSU_FLUSH_LHL_SHL",
+    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
+  },
+  {,
+    "EventCode": "0x35042",
+    "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request"
+  },
+  {,
+    "EventCode": "0xF898",
+    "EventName": "PM_XLATE_RADIX_MODE",
+    "BriefDescription": "LSU reports every cycle the thread is in radix translation mode (as opposed to HPT mode)"
+  },
+  {,
+    "EventCode": "0x2D142",
+    "EventName": "PM_MRK_DATA_FROM_L3_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x160B0",
+    "EventName": "PM_L3_P0_NODE_PUMP",
+    "BriefDescription": "L3 PF sent with nodal scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0xD88C",
+    "EventName": "PM_LSU3_LDMX_FIN",
+    "BriefDescription": "New P9 instruction LDMX. The definition of this new PMU event is (from the ldmx RFC02491):  The thread has executed an ldmx instruction that accessed a doubleword that contains an effective address within an enabled section of the Load Monitored region.  This event, therefore, should not occur if the FSCR has disabled the load monitored facility (FSCR[52]) or disabled the EBB facility (FSCR[56])."
+  },
+  {,
+    "EventCode": "0x36882",
+    "EventName": "PM_L2_LD_HIT",
+    "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x168AC",
+    "EventName": "PM_L3_CI_USAGE",
+    "BriefDescription": "Rotating sample of 16 CI or CO actives"
+  },
+  {,
+    "EventCode": "0x20134",
+    "EventName": "PM_MRK_FXU_FIN",
+    "BriefDescription": "fxu marked instr finish"
+  },
+  {,
+    "EventCode": "0x4608E",
+    "EventName": "PM_TM_CAP_OVERFLOW",
+    "BriefDescription": "TM Footprint Capacity Overflow"
+  },
+  {,
+    "EventCode": "0x4F05C",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from beyond the core's L3 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x40014",
+    "EventName": "PM_PROBE_NOP_DISP",
+    "BriefDescription": "ProbeNops dispatched"
+  },
+  {,
+    "EventCode": "0x58A8",
+    "EventName": "PM_DECODE_HOLD_ICT_FULL",
+    "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use.  This means the ICT is full for this thread"
+  },
+  {,
+    "EventCode": "0x10052",
+    "EventName": "PM_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x2505E",
+    "EventName": "PM_BACK_BR_CMPL",
+    "BriefDescription": "Branch instruction completed with a target address less than current instruction address"
+  },
+  {,
+    "EventCode": "0x2688A",
+    "EventName": "PM_ISIDE_DISP_FAIL_OTHER",
+    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)"
+  },
+  {,
+    "EventCode": "0x2001A",
+    "EventName": "PM_NTC_ALL_FIN",
+    "BriefDescription": "Cycles after all instructions have finished to group completed"
+  },
+  {,
+    "EventCode": "0x3005A",
+    "EventName": "PM_ISQ_0_8_ENTRIES",
+    "BriefDescription": "Cycles in which 8 or less Issue Queue entries are in use. This is a shared event, not per thread"
+  },
+  {,
+    "EventCode": "0x3515E",
+    "EventName": "PM_MRK_BACK_BR_CMPL",
+    "BriefDescription": "Marked branch instruction completed with a target address less than current instruction address"
+  },
+  {,
+    "EventCode": "0xF890",
+    "EventName": "PM_LSU1_L1_CAM_CANCEL",
+    "BriefDescription": "ls1 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0xE884",
+    "EventName": "PM_LS1_ERAT_MISS_PREF",
+    "BriefDescription": "LS1 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0xE89C",
+    "EventName": "PM_LSU1_TM_L1_MISS",
+    "BriefDescription": "Load tm L1 miss"
+  },
+  {,
+    "EventCode": "0x28A8",
+    "EventName": "PM_TM_FAIL_CONF_NON_TM",
+    "BriefDescription": "TM aborted because a conflict occurred with a non-transactional access by another processor"
+  },
+  {,
+    "EventCode": "0x16890",
+    "EventName": "PM_L1PF_L2MEMACC",
+    "BriefDescription": "Valid when first beat of data comes in for an L1PF where data came from memory"
+  },
+  {,
+    "EventCode": "0x4504C",
+    "EventName": "PM_IPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1002E",
+    "EventName": "PM_LMQ_MERGE",
+    "BriefDescription": "A demand miss collides with a prefetch for the same line"
+  },
+  {,
+    "EventCode": "0x160B6",
+    "EventName": "PM_L3_WI0_BUSY",
+    "BriefDescription": "Rotating sample of 8 WI valid"
+  },
+  {,
+    "EventCode": "0x368AC",
+    "EventName": "PM_L3_CO0_BUSY",
+    "BriefDescription": "Lifetime, sample of CO machine 0 valid"
+  },
+  {,
+    "EventCode": "0x2E040",
+    "EventName": "PM_DPTEG_FROM_L2_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1D152",
+    "EventName": "PM_MRK_DATA_FROM_DL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x46880",
+    "EventName": "PM_ISIDE_MRU_TOUCH",
+    "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread"
+  },
+  {,
+    "EventCode": "0x1C05C",
+    "EventName": "PM_DTLB_MISS_2M",
+    "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
+  },
+  {,
+    "EventCode": "0x50B8",
+    "EventName": "PM_TAGE_OVERRIDE_WRONG",
+    "BriefDescription": "The TAGE overrode BHT direction prediction but it was incorrect.  Counted at completion for taken branches only"
+  },
+  {,
+    "EventCode": "0x160AE",
+    "EventName": "PM_L3_P0_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 0, every retry counted"
+  },
+  {,
+    "EventCode": "0x268B2",
+    "EventName": "PM_L3_LOC_GUESS_WRONG",
+    "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low"
+  },
+  {,
+    "EventCode": "0x36088",
+    "EventName": "PM_L2_SYS_GUESS_CORRECT",
+    "BriefDescription": "L2 guess system (VGS or RNS) and guess was correct (ie data beyond-group)"
+  },
+  {,
+    "EventCode": "0x589C",
+    "EventName": "PM_PTESYNC",
+    "BriefDescription": "ptesync instruction counted when the instruction is decoded and transmitted"
+  },
+  {,
+    "EventCode": "0x26086",
+    "EventName": "PM_CO_TM_SC_FOOTPRINT",
+    "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus"
+  },
+  {,
+    "EventCode": "0x1E05A",
+    "EventName": "PM_CMPLU_STALL_ANY_SYNC",
+    "BriefDescription": "Cycles in which the NTC sync instruction (isync, lwsync or hwsync) is not allowed to complete"
+  },
+  {,
+    "EventCode": "0xF090",
+    "EventName": "PM_LSU0_L1_CAM_CANCEL",
+    "BriefDescription": "ls0 l1 tm cam cancel"
+  },
+  {,
+    "EventCode": "0xC0A8",
+    "EventName": "PM_LSU_FLUSH_CI",
+    "BriefDescription": "Load was not issued to LSU as a cache inhibited (non-cacheable) load but it was later determined to be cache inhibited"
+  },
+  {,
+    "EventCode": "0x20AC",
+    "EventName": "PM_TM_FAIL_CONF_TM",
+    "BriefDescription": "TM aborted because a conflict occurred with another transaction."
+  },
+  {,
+    "EventCode": "0x588C",
+    "EventName": "PM_SHL_ST_DEP_CREATED",
+    "BriefDescription": "Store-Hit-Load Table Read Hit with entry Enabled"
+  },
+  {,
+    "EventCode": "0x360AC",
+    "EventName": "PM_L3_SN0_BUSY",
+    "BriefDescription": "Lifetime, sample of snooper machine 0 valid"
+  },
+  {,
+    "EventCode": "0x3005C",
+    "EventName": "PM_BFU_BUSY",
+    "BriefDescription": "Cycles in which all 4 Binary Floating Point units are busy. The BFU is running at capacity"
+  },
+  {,
+    "EventCode": "0x48A0",
+    "EventName": "PM_BR_PRED_PCACHE",
+    "BriefDescription": "Conditional branch completed that used pattern cache prediction"
+  },
+  {,
+    "EventCode": "0x26880",
+    "EventName": "PM_L2_ST_MISS",
+    "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread"
+  },
+  {,
+    "EventCode": "0xF8B4",
+    "EventName": "PM_DC_PREF_XCONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch"
+  },
+  {,
+    "EventCode": "0x35048",
+    "EventName": "PM_IPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x260A8",
+    "EventName": "PM_L3_PF_HIT_L3",
+    "BriefDescription": "L3 PF hit in L3 (abandoned)"
+  },
+  {,
+    "EventCode": "0x360B4",
+    "EventName": "PM_L3_PF0_BUSY",
+    "BriefDescription": "Lifetime, sample of PF machine 0 valid"
+  },
+  {,
+    "EventCode": "0xC0B0",
+    "EventName": "PM_LSU_FLUSH_UE",
+    "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
+  },
+  {,
+    "EventCode": "0x4013A",
+    "EventName": "PM_MRK_IC_MISS",
+    "BriefDescription": "Marked instruction experienced I cache miss"
+  },
+  {,
+    "EventCode": "0x2088",
+    "EventName": "PM_FLUSH_DISP_SB",
+    "BriefDescription": "Dispatch Flush: Scoreboard"
+  },
+  {,
+    "EventCode": "0x401E8",
+    "EventName": "PM_MRK_DATA_FROM_L2MISS",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a marked load"
+  },
+  {,
+    "EventCode": "0x3688E",
+    "EventName": "PM_TM_ST_CAUSED_FAIL",
+    "BriefDescription": "TM Store (fav or non-fav) caused another thread to fail"
+  },
+  {,
+    "EventCode": "0x460B2",
+    "EventName": "PM_L3_SYS_GUESS_WRONG",
+    "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high"
+  },
+  {,
+    "EventCode": "0x58B8",
+    "EventName": "PM_TAGE_OVERRIDE_WRONG_SPEC",
+    "BriefDescription": "The TAGE overrode BHT direction prediction and it was correct.   Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0xE890",
+    "EventName": "PM_LSU3_ERAT_HIT",
+    "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
+  },
+  {,
+    "EventCode": "0x2898",
+    "EventName": "PM_TM_TABORT_TRECLAIM",
+    "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim"
+  },
+  {,
+    "EventCode": "0x4C054",
+    "EventName": "PM_DERAT_MISS_16G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G"
+  },
+  {,
+    "EventCode": "0x268A0",
+    "EventName": "PM_L3_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)"
+  },
+  {,
+    "EventCode": "0x5080",
+    "EventName": "PM_THRD_PRIO_4_5_CYC",
+    "BriefDescription": "Cycles thread running at priority level 4 or 5"
+  },
+  {,
+    "EventCode": "0x2505C",
+    "EventName": "PM_VSU_FIN",
+    "BriefDescription": "VSU instruction finished. Up to 4 per cycle"
+  },
+  {,
+    "EventCode": "0x40A4",
+    "EventName": "PM_BR_PRED_CCACHE",
+    "BriefDescription": "Conditional Branch Completed that used the Count Cache for Target Prediction"
+  },
+  {,
+    "EventCode": "0x2E04A",
+    "EventName": "PM_DPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D12E",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xC8B4",
+    "EventName": "PM_LSU_FLUSH_LHL_SHL",
+    "BriefDescription": "The instruction was flushed because of a sequential load/store consistency.  If a load or store hits on an older load that has either been snooped (for loads) or has stale data (for stores)."
+  },
+  {,
+    "EventCode": "0x58A4",
+    "EventName": "PM_FLUSH_LSU",
+    "BriefDescription": "LSU flushes.  Includes all lsu flushes"
+  },
+  {,
+    "EventCode": "0x1D150",
+    "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0xC8A0",
+    "EventName": "PM_LSU1_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x48BC",
+    "EventName": "PM_THRD_PRIO_2_3_CYC",
+    "BriefDescription": "Cycles thread running at priority level 2 or 3"
+  },
+  {,
+    "EventCode": "0x10134",
+    "EventName": "PM_MRK_ST_DONE_L2",
+    "BriefDescription": "marked store completed in L2 ( RC machine done)"
+  },
+  {,
+    "EventCode": "0x368B2",
+    "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
+    "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high"
+  },
+  {,
+    "EventCode": "0xE8BC",
+    "EventName": "PM_LS1_PTE_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on table 1"
+  },
+  {,
+    "EventCode": "0x1F152",
+    "EventName": "PM_MRK_FAB_RSP_BKILL_CYC",
+    "BriefDescription": "cycles L2 RC took for a bkill"
+  },
+  {,
+    "EventCode": "0x4C124",
+    "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT_CYC",
+    "BriefDescription": "Duration in cycles to reload from local core's L3 without conflict due to a marked load"
+  },
+  {,
+    "EventCode": "0x2F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x26888",
+    "EventName": "PM_L2_GRP_GUESS_WRONG",
+    "BriefDescription": "L2 guess grp (GS or NNS) and guess was not correct (ie data on-chip OR beyond-group)"
+  },
+  {,
+    "EventCode": "0x368AE",
+    "EventName": "PM_L3_P1_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
+  },
+  {,
+    "EventCode": "0xC0AC",
+    "EventName": "PM_LSU_FLUSH_EMSH",
+    "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
+  },
+  {,
+    "EventCode": "0x260B2",
+    "EventName": "PM_L3_SYS_GUESS_CORRECT",
+    "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)"
+  },
+  {,
+    "EventCode": "0x1D146",
+    "EventName": "PM_MRK_DATA_FROM_MEMORY_CYC",
+    "BriefDescription": "Duration in cycles to reload from a memory location including L4 from local remote or distant due to a marked load"
+  },
+  {,
+    "EventCode": "0xE094",
+    "EventName": "PM_LSU0_TM_L1_HIT",
+    "BriefDescription": "Load tm hit in L1"
+  },
+  {,
+    "EventCode": "0x46888",
+    "EventName": "PM_L2_GROUP_PUMP",
+    "BriefDescription": "RC requests that were on group (aka nodel) pump attempts"
+  },
+  {,
+    "EventCode": "0xF0B0",
+    "EventName": "PM_L3_LD_PREF",
+    "BriefDescription": "L3 load prefetch, sourced from a hardware or software stream, was sent to the nest"
+  },
+  {,
+    "EventCode": "0x16080",
+    "EventName": "PM_L2_LD",
+    "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)"
+  },
+  {,
+    "EventCode": "0x4505C",
+    "EventName": "PM_MATH_FLOP_CMPL",
+    "BriefDescription": "Math flop instruction completed"
+  },
+  {,
+    "EventCode": "0x368B0",
+    "EventName": "PM_L3_P1_SYS_PUMP",
+    "BriefDescription": "L3 PF sent with sys scope port 1, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x1F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2000C",
+    "EventName": "PM_THRD_ALL_RUN_CYC",
+    "BriefDescription": "Cycles in which all the threads have the run latch set"
+  },
+  {,
+    "EventCode": "0xC0BC",
+    "EventName": "PM_LSU_FLUSH_OTHER",
+    "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)"
+  },
+  {,
+    "EventCode": "0x5094",
+    "EventName": "PM_IC_MISS_ICBI",
+    "BriefDescription": "threaded version, IC Misses where we got EA dir hit but no sector valids were on. ICBI took line out"
+  },
+  {,
+    "EventCode": "0xC8A8",
+    "EventName": "PM_LSU_FLUSH_ATOMIC",
+    "BriefDescription": "Quad-word loads (lq) are considered atomic because they always span at least 2 slices.  If a snoop or store from another thread changes the data the load is accessing between the 2 or 3 pieces of the lq instruction, the lq will be flushed"
+  },
+  {,
+    "EventCode": "0x1E04E",
+    "EventName": "PM_DPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D05E",
+    "EventName": "PM_BR_CMPL",
+    "BriefDescription": "Any Branch instruction completed"
+  },
+  {,
+    "EventCode": "0x260B0",
+    "EventName": "PM_L3_P0_GRP_PUMP",
+    "BriefDescription": "L3 PF sent with grp scope port 0, counts even retried requests"
+  },
+  {,
+    "EventCode": "0x30132",
+    "EventName": "PM_MRK_VSU_FIN",
+    "BriefDescription": "VSU marked instr finish"
+  },
+  {,
+    "EventCode": "0x2D120",
+    "EventName": "PM_MRK_DATA_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
+  },
+  {,
+    "EventCode": "0x1E048",
+    "EventName": "PM_DPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x16086",
+    "EventName": "PM_L2_SN_M_WR_DONE",
+    "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)"
+  },
+  {,
+    "EventCode": "0x489C",
+    "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL",
+    "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
+  },
+  {,
+    "EventCode": "0xF0B8",
+    "EventName": "PM_LS0_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0x20132",
+    "EventName": "PM_MRK_DFU_FIN",
+    "BriefDescription": "Decimal Unit marked Instruction Finish"
+  },
+  {,
+    "EventCode": "0x160A6",
+    "EventName": "PM_TM_SC_CO",
+    "BriefDescription": "L3 castout TM SC line"
+  },
+  {,
+    "EventCode": "0xC8B0",
+    "EventName": "PM_LSU_FLUSH_LHS",
+    "BriefDescription": "Effective Address alias flush : no EA match but Real Address match.  If the data has not yet been returned for this load, the instruction will just be rejected, but if it has returned data, it will be flushed"
+  },
+  {,
+    "EventCode": "0x3F150",
+    "EventName": "PM_MRK_ST_DRAIN_TO_L2DISP_CYC",
+    "BriefDescription": "cycles to drain st from core to L2"
+  },
+  {,
+    "EventCode": "0x168A4",
+    "EventName": "PM_L3_MISS",
+    "BriefDescription": "L3 Misses (L2 miss also missing L3, including data/instrn/xlate)"
+  },
+  {,
+    "EventCode": "0xF080",
+    "EventName": "PM_LSU_STCX_FAIL",
+    "BriefDescription": ""
+  },
+  {,
+    "EventCode": "0x30038",
+    "EventName": "PM_CMPLU_STALL_DMISS_LMEM",
+    "BriefDescription": "Completion stall due to cache miss that resolves in local memory"
+  },
+  {,
+    "EventCode": "0x28A4",
+    "EventName": "PM_MRK_TEND_FAIL",
+    "BriefDescription": "Nested or not nested tend failed for a marked tend instruction"
+  },
+  {,
+    "EventCode": "0x100FC",
+    "EventName": "PM_LD_REF_L1",
+    "BriefDescription": "All L1 D cache load references counted at finish, gated by reject"
+  },
+  {,
+    "EventCode": "0xC0A0",
+    "EventName": "PM_LSU0_FALSE_LHS",
+    "BriefDescription": "False LHS match detected"
+  },
+  {,
+    "EventCode": "0x468A8",
+    "EventName": "PM_SN_MISS",
+    "BriefDescription": "Any port snooper L3 miss or collision.  Up to 4 can happen in a cycle but we only count 1"
+  },
+  {,
+    "EventCode": "0x36888",
+    "EventName": "PM_L2_SYS_GUESS_WRONG",
+    "BriefDescription": "L2 guess system (VGS or RNS) and guess was not correct (ie data ^beyond-group)"
+  },
+  {,
+    "EventCode": "0x2080",
+    "EventName": "PM_EE_OFF_EXT_INT",
+    "BriefDescription": "CyclesMSR[EE] is off and external interrupts are active"
+  },
+  {,
+    "EventCode": "0xE8B8",
+    "EventName": "PM_LS3_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
+    "EventCode": "0x2688E",
+    "EventName": "PM_TM_FAV_CAUSED_FAIL",
+    "BriefDescription": "TM Load (fav) caused another thread to fail"
+  },
+  {,
+    "EventCode": "0x16090",
+    "EventName": "PM_SN0_BUSY",
+    "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)"
+  },
+  {,
+    "EventCode": "0x360AE",
+    "EventName": "PM_L3_P0_CO_RTY",
+    "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted"
+  },
+  {,
+    "EventCode": "0x168A8",
+    "EventName": "PM_L3_WI_USAGE",
+    "BriefDescription": "Lifetime, sample of Write Inject machine 0 valid"
+  },
+  {,
+    "EventCode": "0x468A2",
+    "EventName": "PM_L3_LAT_CI_MISS",
+    "BriefDescription": "L3 Lateral Castins Miss"
+  },
+  {,
+    "EventCode": "0x4090",
+    "EventName": "PM_IC_PREF_CANCEL_PAGE",
+    "BriefDescription": "Prefetch Canceled due to page boundary"
+  },
+  {,
+    "EventCode": "0xF09C",
+    "EventName": "PM_SLB_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when a tablewalk is pending on this thread on the SLB table"
+  },
+  {,
+    "EventCode": "0x460AA",
+    "EventName": "PM_L3_P0_CO_L31",
+    "BriefDescription": "L3 CO to L3.1 (LCO) port 0 with or without data"
+  },
+  {,
+    "EventCode": "0x2880",
+    "EventName": "PM_FLUSH_DISP",
+    "BriefDescription": "Dispatch flush"
+  },
+  {,
+    "EventCode": "0x168AE",
+    "EventName": "PM_L3_P1_PF_RTY",
+    "BriefDescription": "L3 PF received retry port 1, every retry counted"
+  },
+  {,
+    "EventCode": "0x46082",
+    "EventName": "PM_L2_ST_DISP",
+    "BriefDescription": "All successful D-side store dispatches for this thread "
+  },
+  {,
+    "EventCode": "0x4609E",
+    "EventName": "PM_L2_INST_MISS",
+    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
+  },
+  {,
+    "EventCode": "0xE084",
+    "EventName": "PM_LS0_ERAT_MISS_PREF",
+    "BriefDescription": "LS0 Erat miss due to prefetch"
+  },
+  {,
+    "EventCode": "0x409C",
+    "EventName": "PM_BR_PRED",
+    "BriefDescription": "Conditional Branch Executed in which the HW predicted the Direction or Target.  Includes taken and not taken and is counted at execution time"
+  },
+  {,
+    "EventCode": "0x2D144",
+    "EventName": "PM_MRK_DATA_FROM_L31_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x360A4",
+    "EventName": "PM_L3_CO_LCO",
+    "BriefDescription": "Total L3 COs occurred on LCO L3.1 (good cresp, may end up in mem on a retry)"
+  },
+  {,
+    "EventCode": "0x4890",
+    "EventName": "PM_IC_PREF_CANCEL_HIT",
+    "BriefDescription": "Prefetch Canceled due to icache hit"
+  },
+  {,
+    "EventCode": "0x268A8",
+    "EventName": "PM_RD_HIT_PF",
+    "BriefDescription": "RD machine hit L3 PF machine"
+  },
+  {,
+    "EventCode": "0x16880",
+    "EventName": "PM_L2_ST",
+    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
+  },
+  {,
+    "EventCode": "0x4098",
+    "EventName": "PM_IC_DEMAND_L2_BHT_REDIRECT",
+    "BriefDescription": "L2 I cache demand request due to BHT redirect, branch redirect ( 2 bubbles 3 cycles)"
+  },
+  {,
+    "EventCode": "0xD0B4",
+    "EventName": "PM_LSU0_SRQ_S0_VALID_CYC",
+    "BriefDescription": "Slot 0 of SRQ valid"
+  },
+  {,
+    "EventCode": "0x160AA",
+    "EventName": "PM_L3_P0_LCO_NO_DATA",
+    "BriefDescription": "Dataless L3 LCO sent port 0"
+  },
+  {,
+    "EventCode": "0x208C",
+    "EventName": "PM_CLB_HELD",
+    "BriefDescription": "CLB (control logic block - indicates quadword fetch block) Hold: Any Reason"
+  },
+  {,
+    "EventCode": "0xF88C",
+    "EventName": "PM_LSU3_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0x200F2",
+    "EventName": "PM_INST_DISP",
+    "BriefDescription": "# PPC Dispatched"
+  },
+  {,
+    "EventCode": "0x4E05E",
+    "EventName": "PM_TM_OUTER_TBEGIN_DISP",
+    "BriefDescription": "Number of outer tbegin instructions dispatched. The dispatch unit determines whether the tbegin instruction is outer or nested. This is a speculative count, which includes flushed instructions"
+  },
+  {,
+    "EventCode": "0x2D018",
+    "EventName": "PM_CMPLU_STALL_EXEC_UNIT",
+    "BriefDescription": "Completion stall due to execution units (FXU/VSU/CRU)"
+  },
+  {,
+    "EventCode": "0x20B0",
+    "EventName": "PM_LSU_FLUSH_NEXT",
+    "BriefDescription": "LSU flush next reported at flush time.  Sometimes these also come with an exception"
+  },
+  {,
+    "EventCode": "0x3880",
+    "EventName": "PM_ISU2_ISS_HOLD_ALL",
+    "BriefDescription": "All ISU rejects"
+  },
+  {,
+    "EventCode": "0x46882",
+    "EventName": "PM_L2_ST_HIT",
+    "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
+  },
+  {,
+    "EventCode": "0x360A8",
+    "EventName": "PM_L3_CO",
+    "BriefDescription": "L3 castout occurring (does not include casthrough or log writes (cinj/dmaw))"
+  },
+  {,
+    "EventCode": "0x368A4",
+    "EventName": "PM_L3_CINJ",
+    "BriefDescription": "L3 castin of cache inject"
+  },
+  {,
+    "EventCode": "0xC890",
+    "EventName": "PM_LSU_NCST",
+    "BriefDescription": "Asserts when a i=1 store op is sent to the nest. No record of issue pipe (LS0/LS1) is maintained so this is for both pipes. Probably don't need separate LS0 and LS1"
+  },
+  {,
+    "EventCode": "0xD880",
+    "EventName": "PM_LSU1_SET_MPRED",
+    "BriefDescription": "Set prediction(set-p) miss.  The entry was not found in the Set prediction table"
+  },
+  {,
+    "EventCode": "0xD0B8",
+    "EventName": "PM_LSU_LMQ_FULL_CYC",
+    "BriefDescription": "Counts the number of cycles the LMQ is full"
+  },
+  {,
+    "EventCode": "0x168B2",
+    "EventName": "PM_L3_GRP_GUESS_CORRECT",
+    "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)"
+  },
+  {,
+    "EventCode": "0x48A4",
+    "EventName": "PM_STOP_FETCH_PENDING_CYC",
+    "BriefDescription": "Fetching is stopped due to an incoming instruction that will result in a flush"
+  },
+  {,
+    "EventCode": "0x36884",
+    "EventName": "PM_L2_RCST_DISP_FAIL_ADDR",
+    "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ"
+  },
+  {,
+    "EventCode": "0x260AC",
+    "EventName": "PM_L3_PF_USAGE",
+    "BriefDescription": "Rotating sample of 32 PF actives"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
new file mode 100644
index 000000000000..bc2db636dabf
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -0,0 +1,552 @@
+[
+  {,
+    "EventCode": "0x4D04C",
+    "EventName": "PM_DFU_BUSY",
+    "BriefDescription": "Cycles in which all 4 Decimal Floating Point units are busy. The DFU is running at capacity"
+  },
+  {,
+    "EventCode": "0x100F6",
+    "EventName": "PM_IERAT_RELOAD",
+    "BriefDescription": "Number of I-ERAT reloads"
+  },
+  {,
+    "EventCode": "0x201E2",
+    "EventName": "PM_MRK_LD_MISS_L1",
+    "BriefDescription": "Marked DL1 Demand Miss counted at exec time. Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
+  },
+  {,
+    "EventCode": "0x40010",
+    "EventName": "PM_PMC3_OVERFLOW",
+    "BriefDescription": "Overflow from counter 3"
+  },
+  {,
+    "EventCode": "0x1005A",
+    "EventName": "PM_CMPLU_STALL_DFLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a multi-cycle instruction issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Qualified by multicycle"
+  },
+  {,
+    "EventCode": "0x4D140",
+    "EventName": "PM_MRK_DATA_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "The processor's data cache was reloaded either shared or modified data from another core's L2/L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1E040",
+    "EventName": "PM_DPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x24052",
+    "EventName": "PM_FXU_IDLE",
+    "BriefDescription": "Cycles in which FXU0, FXU1, FXU2, and FXU3 are all idle"
+  },
+  {,
+    "EventCode": "0x1E054",
+    "EventName": "PM_CMPLU_STALL",
+    "BriefDescription": "Nothing completed and ICT not empty"
+  },
+  {,
+    "EventCode": "0x2",
+    "EventName": "PM_INST_CMPL",
+    "BriefDescription": "Number of PowerPC Instructions that completed."
+  },
+  {,
+    "EventCode": "0x3D058",
+    "EventName": "PM_VSU_DP_FSQRT_FDIV",
+    "BriefDescription": "vector versions of fdiv,fsqrt"
+  },
+  {,
+    "EventCode": "0x10006",
+    "EventName": "PM_DISP_HELD",
+    "BriefDescription": "Dispatch Held"
+  },
+  {,
+    "EventCode": "0x3D154",
+    "EventName": "PM_MRK_DERAT_MISS_16M",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M"
+  },
+  {,
+    "EventCode": "0x200F8",
+    "EventName": "PM_EXT_INT",
+    "BriefDescription": "external interrupt"
+  },
+  {,
+    "EventCode": "0x20008",
+    "EventName": "PM_ICT_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the ICT is completely empty. No itags are assigned to any thread"
+  },
+  {,
+    "EventCode": "0x4F146",
+    "EventName": "PM_MRK_DPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10056",
+    "EventName": "PM_MEM_READ",
+    "BriefDescription": "Reads from Memory from this thread (includes data/inst/xlate/l1prefetch/inst prefetch). Includes L4"
+  },
+  {,
+    "EventCode": "0x3C04C",
+    "EventName": "PM_DATA_FROM_DL4",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's L4 on a different Node or Group (Distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x4E046",
+    "EventName": "PM_DPTEG_FROM_L21_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E016",
+    "EventName": "PM_NTC_ISSUE_HELD_ARB",
+    "BriefDescription": "The NTC instruction is being held at dispatch because it lost arbitration onto the issue pipe to another instruction (from the same thread or a different thread)"
+  },
+  {,
+    "EventCode": "0x15156",
+    "EventName": "PM_SYNC_MRK_FX_DIVIDE",
+    "BriefDescription": "Marked fixed point divide that can cause a synchronous interrupt"
+  },
+  {,
+    "EventCode": "0x1C056",
+    "EventName": "PM_DERAT_MISS_4K",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 4K"
+  },
+  {,
+    "EventCode": "0x2F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10024",
+    "EventName": "PM_PMC5_OVERFLOW",
+    "BriefDescription": "Overflow from counter 5"
+  },
+  {,
+    "EventCode": "0x2C018",
+    "EventName": "PM_CMPLU_STALL_DMISS_L21_L31",
+    "BriefDescription": "Completion stall by Dcache miss which resolved on chip ( excluding local L2/L3)"
+  },
+  {,
+    "EventCode": "0x4006A",
+    "EventName": "PM_IERAT_RELOAD_16M",
+    "BriefDescription": "IERAT Reloaded (Miss) for a 16M page"
+  },
+  {,
+    "EventCode": "0x4E010",
+    "EventName": "PM_ICT_NOSLOT_IC_L3MISS",
+    "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache"
+  },
+  {,
+    "EventCode": "0x4D01C",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_SYNC",
+    "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch"
+  },
+  {,
+    "EventCode": "0x2D01A",
+    "EventName": "PM_ICT_NOSLOT_IC_MISS",
+    "BriefDescription": "Ict empty for this thread due to Icache Miss"
+  },
+  {,
+    "EventCode": "0x3D152",
+    "EventName": "PM_MRK_DERAT_MISS_1G",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x4F14A",
+    "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x30058",
+    "EventName": "PM_TLBIE_FIN",
+    "BriefDescription": "tlbie finished"
+  },
+  {,
+    "EventCode": "0x100F8",
+    "EventName": "PM_ICT_NOSLOT_CYC",
+    "BriefDescription": "Number of cycles the ICT has no itags assigned to this thread"
+  },
+  {,
+    "EventCode": "0x3E042",
+    "EventName": "PM_DPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F140",
+    "EventName": "PM_MRK_DPTEG_FROM_L2_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2C05A",
+    "EventName": "PM_DERAT_MISS_1G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x1F058",
+    "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2",
+    "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation"
+  },
+  {,
+    "EventCode": "0x1D14A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x10050",
+    "EventName": "PM_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x45058",
+    "EventName": "PM_IC_MISS_CMPL",
+    "BriefDescription": "Non-speculative icache miss, counted at completion"
+  },
+  {,
+    "EventCode": "0x2D150",
+    "EventName": "PM_MRK_DERAT_MISS_4K",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 4K"
+  },
+  {,
+    "EventCode": "0x34058",
+    "EventName": "PM_ICT_NOSLOT_BR_MPRED_ICMISS",
+    "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred"
+  },
+  {,
+    "EventCode": "0x10022",
+    "EventName": "PM_PMC2_SAVED",
+    "BriefDescription": "PMC2 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0x2000A",
+    "EventName": "PM_HV_CYC",
+    "BriefDescription": "Cycles in which msr_hv is high. Note that this event does not take msr_pr into consideration"
+  },
+  {,
+    "EventCode": "0x1F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x300FC",
+    "EventName": "PM_DTLB_MISS",
+    "BriefDescription": "Data PTEG reload"
+  },
+  {,
+    "EventCode": "0x2D152",
+    "EventName": "PM_MRK_DERAT_MISS_2M",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x2C046",
+    "EventName": "PM_DATA_FROM_RL2L3_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x20052",
+    "EventName": "PM_GRP_PUMP_MPRED",
+    "BriefDescription": "Final Pump Scope (Group) ended up either larger or smaller than Initial Pump Scope for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x3F05A",
+    "EventName": "PM_RADIX_PWC_L2_PDE_FROM_L3",
+    "BriefDescription": "A Page Directory Entry was reloaded to a level 2 page walk cache from the core's L3 data cache"
+  },
+  {,
+    "EventCode": "0x1E04A",
+    "EventName": "PM_DPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10064",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN",
+    "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch"
+  },
+  {,
+    "EventCode": "0x2E046",
+    "EventName": "PM_DPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E042",
+    "EventName": "PM_DPTEG_FROM_L3_MEPF",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2D012",
+    "EventName": "PM_CMPLU_STALL_DFU",
+    "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle"
+  },
+  {,
+    "EventCode": "0x4C04C",
+    "EventName": "PM_DATA_FROM_DMEM",
+    "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load"
+  },
+  {,
+    "EventCode": "0x30022",
+    "EventName": "PM_PMC4_SAVED",
+    "BriefDescription": "PMC4 Rewind Value saved (matched condition)"
+  },
+  {,
+    "EventCode": "0x200F4",
+    "EventName": "PM_RUN_CYC",
+    "BriefDescription": "Run_cycles"
+  },
+  {,
+    "EventCode": "0x400F2",
+    "EventName": "PM_1PLUS_PPC_DISP",
+    "BriefDescription": "Cycles at least one Instr Dispatched"
+  },
+  {,
+    "EventCode": "0x3D148",
+    "EventName": "PM_MRK_DATA_FROM_L21_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x2F146",
+    "EventName": "PM_MRK_DPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4E01A",
+    "EventName": "PM_ICT_NOSLOT_DISP_HELD",
+    "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason"
+  },
+  {,
+    "EventCode": "0x401EC",
+    "EventName": "PM_THRESH_EXC_2048",
+    "BriefDescription": "Threshold counter exceeded a value of 2048"
+  },
+  {,
+    "EventCode": "0x35150",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3E052",
+    "EventName": "PM_ICT_NOSLOT_IC_L3",
+    "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3"
+  },
+  {,
+    "EventCode": "0x2405A",
+    "EventName": "PM_NTC_FIN",
+    "BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. This event is used to account for cycles in which work is being completed in the CPI stack"
+  },
+  {,
+    "EventCode": "0x40052",
+    "EventName": "PM_PUMP_MPRED",
+    "BriefDescription": "Pump misprediction. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x30056",
+    "EventName": "PM_TM_ABORTS",
+    "BriefDescription": "Number of TM transactions aborted"
+  },
+  {,
+    "EventCode": "0x2404C",
+    "EventName": "PM_INST_FROM_MEMORY",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1C05A",
+    "EventName": "PM_DERAT_MISS_2M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
+  },
+  {,
+    "EventCode": "0x30024",
+    "EventName": "PM_PMC6_OVERFLOW",
+    "BriefDescription": "Overflow from counter 6"
+  },
+  {,
+    "EventCode": "0x10068",
+    "EventName": "PM_BRU_FIN",
+    "BriefDescription": "Branch Instruction Finished"
+  },
+  {,
+    "EventCode": "0x30020",
+    "EventName": "PM_PMC2_REWIND",
+    "BriefDescription": "PMC2 Rewind Event (did not match condition)"
+  },
+  {,
+    "EventCode": "0x40064",
+    "EventName": "PM_DUMMY2_REMOVE_ME",
+    "BriefDescription": "Space holder for LS_PC_RELOAD_RA"
+  },
+  {,
+    "EventCode": "0x3F148",
+    "EventName": "PM_MRK_DPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D01E",
+    "EventName": "PM_ICT_NOSLOT_BR_MPRED",
+    "BriefDescription": "Ict empty for this thread due to branch mispred"
+  },
+  {,
+    "EventCode": "0x3405E",
+    "EventName": "PM_IFETCH_THROTTLE",
+    "BriefDescription": "Cycles in which Instruction fetch throttle was active."
+  },
+  {,
+    "EventCode": "0x1F148",
+    "EventName": "PM_MRK_DPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3E046",
+    "EventName": "PM_DPTEG_FROM_L21_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another core's L2 on the same chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2F144",
+    "EventName": "PM_MRK_DPTEG_FROM_L31_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4C15C",
+    "EventName": "PM_MRK_DERAT_MISS_16G",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G"
+  },
+  {,
+    "EventCode": "0x14052",
+    "EventName": "PM_INST_GRP_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0xD0A8",
+    "EventName": "PM_DSLB_MISS",
+    "BriefDescription": "Data SLB Miss - Total of all segment sizes"
+  },
+  {,
+    "EventCode": "0x4C058",
+    "EventName": "PM_MEM_CO",
+    "BriefDescription": "Memory castouts from this thread"
+  },
+  {,
+    "EventCode": "0x40004",
+    "EventName": "PM_FXU_FIN",
+    "BriefDescription": "The fixed point unit Unit finished an instruction. Instructions that finish may not necessary complete."
+  },
+  {,
+    "EventCode": "0x2C054",
+    "EventName": "PM_DERAT_MISS_64K",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K"
+  },
+  {,
+    "EventCode": "0x10018",
+    "EventName": "PM_IC_DEMAND_CYC",
+    "BriefDescription": "Icache miss demand cycles"
+  },
+  {,
+    "EventCode": "0x3C054",
+    "EventName": "PM_DERAT_MISS_16M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M"
+  },
+  {,
+    "EventCode": "0x2D14E",
+    "EventName": "PM_MRK_DATA_FROM_L21_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x3405C",
+    "EventName": "PM_CMPLU_STALL_DPLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle"
+  },
+  {,
+    "EventCode": "0x4D052",
+    "EventName": "PM_2FLOP_CMPL",
+    "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg "
+  },
+  {,
+    "EventCode": "0x1F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L2",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40062",
+    "EventName": "PM_DUMMY1_REMOVE_ME",
+    "BriefDescription": "Space holder for L2_PC_PM_MK_LDST_SCOPE_PRED_STATUS"
+  },
+  {,
+    "EventCode": "0x4C012",
+    "EventName": "PM_CMPLU_STALL_ERAT_MISS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load or store that suffered a translation miss"
+  },
+  {,
+    "EventCode": "0x4D050",
+    "EventName": "PM_VSU_NON_FLOP_CMPL",
+    "BriefDescription": "Non FLOP operation completed"
+  },
+  {,
+    "EventCode": "0x2E012",
+    "EventName": "PM_TM_TX_PASS_RUN_CYC",
+    "BriefDescription": "cycles spent in successful transactions"
+  },
+  {,
+    "EventCode": "0x4D04E",
+    "EventName": "PM_VSU_FSQRT_FDIV",
+    "BriefDescription": "four flops operation (fdiv,fsqrt) Scalar Instructions only"
+  },
+  {,
+    "EventCode": "0x4C120",
+    "EventName": "PM_MRK_DATA_FROM_L2_MEPF",
+    "BriefDescription": "The processor's data cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to a marked load"
+  },
+  {,
+    "EventCode": "0x10062",
+    "EventName": "PM_LD_L3MISS_PEND_CYC",
+    "BriefDescription": "Cycles L3 miss was pending for this thread"
+  },
+  {,
+    "EventCode": "0x2F14C",
+    "EventName": "PM_MRK_DPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x14050",
+    "EventName": "PM_INST_CHIP_PUMP_CPRED",
+    "BriefDescription": "Initial and Final Pump Scope was chip pump (prediction=correct) for an instruction fetch"
+  },
+  {,
+    "EventCode": "0x2000E",
+    "EventName": "PM_FXU_BUSY",
+    "BriefDescription": "Cycles in which all 4 FXUs are busy. The FXU is running at capacity"
+  },
+  {,
+    "EventCode": "0x20066",
+    "EventName": "PM_TLB_MISS",
+    "BriefDescription": "TLB Miss (I + D)"
+  },
+  {,
+    "EventCode": "0x10054",
+    "EventName": "PM_PUMP_CPRED",
+    "BriefDescription": "Pump prediction correct. Counts across all types of pumps for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x4D124",
+    "EventName": "PM_MRK_DATA_FROM_L31_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x400F8",
+    "EventName": "PM_FLUSH",
+    "BriefDescription": "Flush (any type)"
+  },
+  {,
+    "EventCode": "0x30004",
+    "EventName": "PM_CMPLU_STALL_EMQ_FULL",
+    "BriefDescription": "Finish stall because the next to finish instruction suffered an ERAT miss and the EMQ was full"
+  },
+  {,
+    "EventCode": "0x1D154",
+    "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
new file mode 100644
index 000000000000..3ef8a10aac86
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -0,0 +1,122 @@
+[
+  {,
+    "EventCode": "0x20036",
+    "EventName": "PM_BR_2PATH",
+    "BriefDescription": "Branches that are not strongly biased"
+  },
+  {,
+    "EventCode": "0x40056",
+    "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH",
+    "BriefDescription": "Local memory above threshold for LSU medium"
+  },
+  {,
+    "EventCode": "0x2C056",
+    "EventName": "PM_DTLB_MISS_4K",
+    "BriefDescription": "Data TLB Miss page size 4k"
+  },
+  {,
+    "EventCode": "0x40118",
+    "EventName": "PM_MRK_DCACHE_RELOAD_INTV",
+    "BriefDescription": "Combined Intervention event"
+  },
+  {,
+    "EventCode": "0x4F148",
+    "EventName": "PM_MRK_DPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x301E8",
+    "EventName": "PM_THRESH_EXC_64",
+    "BriefDescription": "Threshold counter exceeded a value of 64"
+  },
+  {,
+    "EventCode": "0x4E04E",
+    "EventName": "PM_DPTEG_FROM_L3MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L3 due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x40050",
+    "EventName": "PM_SYS_PUMP_MPRED_RTY",
+    "BriefDescription": "Final Pump Scope (system) ended up larger than Initial Pump Scope (Chip/Group) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
+  },
+  {,
+    "EventCode": "0x1F14E",
+    "EventName": "PM_MRK_DPTEG_FROM_L2MISS",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a location other than the local core's L2 due to a marked data side request.. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4D018",
+    "EventName": "PM_CMPLU_STALL_BRU",
+    "BriefDescription": "Completion stall due to a Branch Unit"
+  },
+  {,
+    "EventCode": "0x45052",
+    "EventName": "PM_4FLOP_CMPL",
+    "BriefDescription": "4 FLOP instruction completed"
+  },
+  {,
+    "EventCode": "0x3D142",
+    "EventName": "PM_MRK_DATA_FROM_LMEM",
+    "BriefDescription": "The processor's data cache was reloaded from the local chip's Memory due to a marked load"
+  },
+  {,
+    "EventCode": "0x4C01E",
+    "EventName": "PM_CMPLU_STALL_CRYPTO",
+    "BriefDescription": "Finish stall because the NTF instruction was routed to the crypto execution pipe and was waiting to finish"
+  },
+  {,
+    "EventCode": "0x3000C",
+    "EventName": "PM_FREQ_DOWN",
+    "BriefDescription": "Power Management: Below Threshold B"
+  },
+  {,
+    "EventCode": "0x4D128",
+    "EventName": "PM_MRK_DATA_FROM_LMEM_CYC",
+    "BriefDescription": "Duration in cycles to reload from the local chip's Memory due to a marked load"
+  },
+  {,
+    "EventCode": "0x4D054",
+    "EventName": "PM_8FLOP_CMPL",
+    "BriefDescription": "8 FLOP instruction completed"
+  },
+  {,
+    "EventCode": "0x10026",
+    "EventName": "PM_TABLEWALK_CYC",
+    "BriefDescription": "Cycles when an instruction tablewalk is active"
+  },
+  {,
+    "EventCode": "0x2C012",
+    "EventName": "PM_CMPLU_STALL_DCACHE_MISS",
+    "BriefDescription": "Finish stall because the NTF instruction was a load that missed the L1 and was waiting for the data to return from the nest"
+  },
+  {,
+    "EventCode": "0x2E04C",
+    "EventName": "PM_DPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x3F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x4F142",
+    "EventName": "PM_MRK_DPTEG_FROM_L3",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x10060",
+    "EventName": "PM_TM_TRANS_RUN_CYC",
+    "BriefDescription": "run cycles in transactional state"
+  },
+  {,
+    "EventCode": "0x1E04C",
+    "EventName": "PM_DPTEG_FROM_LL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x45050",
+    "EventName": "PM_1FLOP_CMPL",
+    "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
new file mode 100644
index 000000000000..8c0f12024afa
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
@@ -0,0 +1,232 @@
+[
+  {,
+    "EventCode": "0x1E",
+    "EventName": "PM_CYC",
+    "BriefDescription": "Processor cycles"
+  },
+  {,
+    "EventCode": "0x30010",
+    "EventName": "PM_PMC2_OVERFLOW",
+    "BriefDescription": "Overflow from counter 2"
+  },
+  {,
+    "EventCode": "0x3C046",
+    "EventName": "PM_DATA_FROM_L21_SHR",
+    "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x4D05C",
+    "EventName": "PM_DP_QP_FLOP_CMPL",
+    "BriefDescription": "Double-Precion or Quad-Precision instruction completed"
+  },
+  {,
+    "EventCode": "0x4E04C",
+    "EventName": "PM_DPTEG_FROM_DMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x20016",
+    "EventName": "PM_ST_FIN",
+    "BriefDescription": "Store finish count. Includes speculative activity"
+  },
+  {,
+    "EventCode": "0x44042",
+    "EventName": "PM_INST_FROM_L3",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1504A",
+    "EventName": "PM_IPTEG_FROM_RL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x40132",
+    "EventName": "PM_MRK_LSU_FIN",
+    "BriefDescription": "lsu marked instr PPC finish"
+  },
+  {,
+    "EventCode": "0x3C05C",
+    "EventName": "PM_CMPLU_STALL_VFXU",
+    "BriefDescription": "Finish stall due to a vector fixed point instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes"
+  },
+  {,
+    "EventCode": "0x30066",
+    "EventName": "PM_LSU_FIN",
+    "BriefDescription": "LSU Finished a PPC instruction (up to 4 per cycle)"
+  },
+  {,
+    "EventCode": "0x2011C",
+    "EventName": "PM_MRK_NTC_CYC",
+    "BriefDescription": "Cycles during which the marked instruction is next to complete (completion is held up because the marked instruction hasn't completed yet)"
+  },
+  {,
+    "EventCode": "0x3E048",
+    "EventName": "PM_DPTEG_FROM_DL2L3_SHR",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x2E018",
+    "EventName": "PM_CMPLU_STALL_VFXLONG",
+    "BriefDescription": "Completion stall due to a long latency vector fixed point instruction (division, square root)"
+  },
+  {,
+    "EventCode": "0x1C04E",
+    "EventName": "PM_DATA_FROM_L2MISS_MOD",
+    "BriefDescription": "The processor's data cache was reloaded from a location other than the local core's L2 due to a demand load"
+  },
+  {,
+    "EventCode": "0x15048",
+    "EventName": "PM_IPTEG_FROM_ON_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on the same chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x34046",
+    "EventName": "PM_INST_FROM_L21_SHR",
+    "BriefDescription": "The processor's Instruction cache was reloaded with Shared (S) data from another core's L2 on the same chip due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x1E058",
+    "EventName": "PM_STCX_FAIL",
+    "BriefDescription": "stcx failed"
+  },
+  {,
+    "EventCode": "0x20112",
+    "EventName": "PM_MRK_NTF_FIN",
+    "BriefDescription": "Marked next to finish instruction finished"
+  },
+  {,
+    "EventCode": "0x300F0",
+    "EventName": "PM_ST_MISS_L1",
+    "BriefDescription": "Store Missed L1"
+  },
+  {,
+    "EventCode": "0x4C046",
+    "EventName": "PM_DATA_FROM_L21_MOD",
+    "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another core's L2 on the same chip due to a demand load"
+  },
+  {,
+    "EventCode": "0x2504A",
+    "EventName": "PM_IPTEG_FROM_RL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on the same Node or Group ( Remote) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x2003E",
+    "EventName": "PM_LSU_LMQ_SRQ_EMPTY_CYC",
+    "BriefDescription": "Cycles in which the LSU is empty for all threads (lmq and srq are completely empty)"
+  },
+  {,
+    "EventCode": "0x201E6",
+    "EventName": "PM_THRESH_EXC_32",
+    "BriefDescription": "Threshold counter exceeded a value of 32"
+  },
+  {,
+    "EventCode": "0x4405C",
+    "EventName": "PM_CMPLU_STALL_VDP",
+    "BriefDescription": "Finish stall because the NTF instruction was a vector instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Not qualified multicycle. Qualified by vector"
+  },
+  {,
+    "EventCode": "0x4D010",
+    "EventName": "PM_PMC1_SAVED",
+    "BriefDescription": "PMC1 Rewind Value saved"
+  },
+  {,
+    "EventCode": "0x200FE",
+    "EventName": "PM_DATA_FROM_L2MISS",
+    "BriefDescription": "Demand LD - L2 Miss (not L2 hit)"
+  },
+  {,
+    "EventCode": "0x2D14A",
+    "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD_CYC",
+    "BriefDescription": "Duration in cycles to reload with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x10028",
+    "EventName": "PM_STALL_END_ICT_EMPTY",
+    "BriefDescription": "The number a times the core transitioned from a stall to ICT-empty for this thread"
+  },
+  {,
+    "EventCode": "0x2504C",
+    "EventName": "PM_IPTEG_FROM_MEMORY",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from a memory location including L4 from local remote or distant due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x4504A",
+    "EventName": "PM_IPTEG_FROM_OFF_CHIP_CACHE",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x1404E",
+    "EventName": "PM_INST_FROM_L2MISS",
+    "BriefDescription": "The processor's Instruction cache was reloaded from a location other than the local core's L2 due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x34042",
+    "EventName": "PM_INST_FROM_L3_DISP_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 with dispatch conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x4E048",
+    "EventName": "PM_DPTEG_FROM_DL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x200F0",
+    "EventName": "PM_ST_CMPL",
+    "BriefDescription": "Stores completed from S2Q (2nd-level store queue)."
+  },
+  {,
+    "EventCode": "0x4E05C",
+    "EventName": "PM_LSU_REJECT_LHS",
+    "BriefDescription": "LSU Reject due to LHS (up to 4 per cycle)"
+  },
+  {,
+    "EventCode": "0x14044",
+    "EventName": "PM_INST_FROM_L3_NO_CONFLICT",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without conflict due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x3E04C",
+    "EventName": "PM_DPTEG_FROM_DL4",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
+  },
+  {,
+    "EventCode": "0x1F15E",
+    "EventName": "PM_MRK_PROBE_NOP_CMPL",
+    "BriefDescription": "Marked probeNops completed"
+  },
+  {,
+    "EventCode": "0x20018",
+    "EventName": "PM_ST_FWD",
+    "BriefDescription": "Store forwards that finished"
+  },
+  {,
+    "EventCode": "0x1D142",
+    "EventName": "PM_MRK_DATA_FROM_L31_ECO_SHR_CYC",
+    "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's ECO L3 on the same chip due to a marked load"
+  },
+  {,
+    "EventCode": "0x24042",
+    "EventName": "PM_INST_FROM_L3_MEPF",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 without dispatch conflicts hit on Mepf state. due to an instruction fetch (not prefetch)"
+  },
+  {,
+    "EventCode": "0x25046",
+    "EventName": "PM_IPTEG_FROM_RL2L3_MOD",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x3504A",
+    "EventName": "PM_IPTEG_FROM_RMEM",
+    "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a instruction side request"
+  },
+  {,
+    "EventCode": "0x3C05A",
+    "EventName": "PM_CMPLU_STALL_VDPLONG",
+    "BriefDescription": "Finish stall because the NTF instruction was a scalar multi-cycle instruction issued to the Double Precision execution pipe and waiting to finish. Includes binary floating point instructions in 32 and 64 bit binary floating point format. Qualified by NOT vector AND multicycle"
+  },
+  {,
+    "EventCode": "0x2E01C",
+    "EventName": "PM_CMPLU_STALL_TLBIE",
+    "BriefDescription": "Finish stall because the NTF instruction was a tlbie waiting for response from L2"
+  }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index d1a12e584c1b..4ea068366c3e 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -34,3 +34,4 @@ GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-2C,v2,westmereep-dp,core
 GenuineIntel-6-25,v2,westmereep-sp,core
 GenuineIntel-6-2F,v2,westmereex,core
+GenuineIntel-6-55,v1,skylakex,core
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
new file mode 100644
index 000000000000..b5bc742b6fbc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -0,0 +1,1672 @@
+[
+    {
+        "EventCode": "0x24",
+        "UMask": "0x21",
+        "BriefDescription": "Demand Data Read miss L2, no rejects",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
+        "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x22",
+        "BriefDescription": "RFO requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x24",
+        "BriefDescription": "L2 cache misses when fetching instructions",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x27",
+        "BriefDescription": "Demand requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
+        "PublicDescription": "Demand requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x38",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.PF_MISS",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x3f",
+        "BriefDescription": "All requests that miss L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.MISS",
+        "PublicDescription": "All requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x41",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x42",
+        "BriefDescription": "RFO requests that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0x44",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xd8",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.PF_HIT",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe1",
+        "BriefDescription": "Demand Data Read requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe2",
+        "BriefDescription": "RFO requests to L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe4",
+        "BriefDescription": "L2 code requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xe7",
+        "BriefDescription": "Demand requests to L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "PublicDescription": "Demand requests to L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xf8",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.ALL_PF",
+        "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x24",
+        "UMask": "0xff",
+        "BriefDescription": "All L2 requests",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "PublicDescription": "All L2 requests.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "UMask": "0x41",
+        "BriefDescription": "Core-originated cacheable demand requests missed L3",
+        "Counter": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "UMask": "0x4f",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
+        "Counter": "0,1,2,3",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "AnyThread": "1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x48",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "UMask": "0x1",
+        "BriefDescription": "L1D data line replacements",
+        "Counter": "0,1,2,3",
+        "EventName": "L1D.REPLACEMENT",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x2",
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle. ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x4",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x8",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x1",
+        "BriefDescription": "Demand Data Read requests sent to uncore",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x2",
+        "BriefDescription": "Cacheable and noncachaeble code read requests",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x4",
+        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x8",
+        "BriefDescription": "Demand and prefetch data reads",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x80",
+        "BriefDescription": "Any memory transaction that reached the SQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB2",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
+        "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x11",
+        "BriefDescription": "Retired load instructions that miss the STLB.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x12",
+        "BriefDescription": "Retired store instructions that miss the STLB.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "100003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x21",
+        "BriefDescription": "Retired load instructions with locked access.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x41",
+        "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x42",
+        "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "SampleAfterValue": "100003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x81",
+        "BriefDescription": "All retired load instructions.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD0",
+        "UMask": "0x82",
+        "BriefDescription": "All retired store instructions.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "SampleAfterValue": "2000003",
+        "L1_Hit_Indication": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
+        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. ",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x10",
+        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
+        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x20",
+        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. ",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD1",
+        "UMask": "0x40",
+        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. ",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
+        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
+        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD2",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
+        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x1",
+        "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x2",
+        "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x4",
+        "BriefDescription": "Retired load instructions whose data sources was remote HITM",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "Retired load instructions whose data sources was remote HITM.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD3",
+        "UMask": "0x8",
+        "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache",
+        "Data_LA": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xD4",
+        "UMask": "0x4",
+        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
+        "Data_LA": "1",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xF0",
+        "UMask": "0x40",
+        "BriefDescription": "L2 writebacks that access L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_TRANS.L2_WB",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF1",
+        "UMask": "0x1f",
+        "BriefDescription": "L2 cache lines filling L2",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_IN.ALL",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped ",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.USELESS_PREF",
+        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF2",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "L2_LINES_OUT.USELESS_HWPF",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xF4",
+        "UMask": "0x10",
+        "BriefDescription": "Number of cache line split locks sent to uncore.",
+        "Counter": "0,1,2,3",
+        "EventName": "SQ_MISC.SPLIT_LOCK",
+        "PublicDescription": "Counts the number of cache line split locks sent to the uncore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that have any response type.",
+        "MSRValue": "0x0000010001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
+        "MSRValue": "0x0000010002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
+        "MSRValue": "0x3f803c0002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that have any response type.",
+        "MSRValue": "0x0000010004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that hit in the L3.",
+        "MSRValue": "0x3f803c0004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
+        "MSRValue": "0x0000010010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
+        "MSRValue": "0x0000010020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
+        "MSRValue": "0x0000010080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
+        "MSRValue": "0x0000010100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.",
+        "MSRValue": "0x0000010400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.",
+        "MSRValue": "0x3f803c0400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that have any response type.",
+        "MSRValue": "0x0000010490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that have any response type.",
+        "MSRValue": "0x0000010120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
+        "MSRValue": "0x0000010491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
+        "MSRValue": "0x3f803c0491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
+        "MSRValue": "0x0000010122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "MSRValue": "0x01003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x04003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
+        "MSRValue": "0x08003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "tbd; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
+        "MSRValue": "0x10003c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
+        "MSRValue": "0x3f803c0122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3.; Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
new file mode 100644
index 000000000000..1c09a328df36
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
@@ -0,0 +1,88 @@
+[
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x1",
+        "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x2",
+        "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x4",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x8",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x10",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x20",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x40",
+        "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
+        "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC7",
+        "UMask": "0x80",
+        "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
+        "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "UMask": "0x1e",
+        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "Counter": "0,1,2,3",
+        "EventName": "FP_ASSIST.ANY",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
new file mode 100644
index 000000000000..40abc0852cd6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -0,0 +1,482 @@
+[
+    {
+        "EventCode": "0x79",
+        "UMask": "0x4",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MITE_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MITE_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_DSB_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x18",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x18",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x20",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x24",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x24",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
+        "UMask": "0x30",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x80",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_16B.IFDATA_STALL",
+        "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x1",
+        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_HIT",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x2",
+        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_MISS",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x83",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "Counter": "0,1,2,3",
+        "EventName": "ICACHE_64B.IFTAG_STALL",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "CounterMask": "4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "CounterMask": "3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0x9C",
+        "UMask": "0x1",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAB",
+        "UMask": "0x2",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
+        "Counter": "0,1,2,3",
+        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
+        "PEBS": "1",
+        "MSRValue": "0x11",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. ",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x12",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.L1I_MISS",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x13",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x14",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+        "PEBS": "1",
+        "MSRValue": "0x15",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. ",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x200206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400406",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x400806",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x401006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x402006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x404006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x408006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x410006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x420006",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x100206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+        "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC6",
+        "UMask": "0x1",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
+        "PEBS": "1",
+        "MSRValue": "0x300206",
+        "Counter": "0,1,2,3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+        "MSRIndex": "0x3F7",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
new file mode 100644
index 000000000000..ca22a22c1abd
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -0,0 +1,1396 @@
+[
+    {
+        "EventCode": "0x54",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_CONFLICT",
+        "PublicDescription": "Number of times a TSX line had a cache conflict.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_CAPACITY",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x54",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
+        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC2",
+        "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x4",
+        "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC3",
+        "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x8",
+        "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC4",
+        "PublicDescription": "RTM region detected inside HLE.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5d",
+        "UMask": "0x10",
+        "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region",
+        "Counter": "0,1,2,3",
+        "EventName": "TX_EXEC.MISC5",
+        "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x6",
+        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "CounterMask": "6",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB0",
+        "UMask": "0x10",
+        "BriefDescription": "Demand Data Read requests who miss L3 cache",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "UMask": "0x2",
+        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "Errata": "SKL089",
+        "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times an HLE execution started.",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.START",
+        "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times an HLE execution successfully committed",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.COMMIT",
+        "PublicDescription": "Number of times HLE commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED",
+        "PublicDescription": "Number of times HLE abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_MEM",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_TIMER",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.). ",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC8",
+        "UMask": "0x80",
+        "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
+        "Counter": "0,1,2,3",
+        "EventName": "HLE_RETIRED.ABORTED_EVENTS",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x1",
+        "BriefDescription": "Number of times an RTM execution started.",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.START",
+        "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x2",
+        "BriefDescription": "Number of times an RTM execution successfully committed",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.COMMIT",
+        "PublicDescription": "Number of times RTM commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x4",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED",
+        "PublicDescription": "Number of times RTM abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x8",
+        "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_MEM",
+        "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x10",
+        "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_TIMER",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x20",
+        "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x40",
+        "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC9",
+        "UMask": "0x80",
+        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
+        "Counter": "0,1,2,3",
+        "EventName": "RTM_RETIRED.ABORTED_EVENTS",
+        "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x4",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x8",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "50021",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x10",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "20011",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x20",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x40",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "2003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x80",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "1009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x100",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "503",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xCD",
+        "UMask": "0x1",
+        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "PEBS": "2",
+        "MSRValue": "0x200",
+        "Counter": "0,1,2,3",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+        "MSRIndex": "0x3F6",
+        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "TakenAlone": "1",
+        "SampleAfterValue": "101",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000001 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.",
+        "MSRValue": "0x3fbc000002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000002 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss in the L3.",
+        "MSRValue": "0x3fbc000004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000004 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000010 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000020 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000080 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000100 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.",
+        "MSRValue": "0x3fbc000400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000400 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000490 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000120 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.",
+        "MSRValue": "0x3fbc000491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000491 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.",
+        "MSRValue": "0x3fbc000122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
+        "MSRValue": "0x083fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
+        "MSRValue": "0x103fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
+        "MSRValue": "0x063fc00122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.",
+        "MSRValue": "0x063b800122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "Offcore": "1",
+        "EventCode": "0xB7, 0xBB",
+        "UMask": "0x1",
+        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "MSRValue": "0x0604000122 ",
+        "Counter": "0,1,2,3",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json
new file mode 100644
index 000000000000..70243b0b0586
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json
@@ -0,0 +1,72 @@
+[
+    {
+        "EventCode": "0x28",
+        "UMask": "0x7",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL0_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x18",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL1_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x20",
+        "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture).  This includes high current AVX 512-bit instructions.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "UMask": "0x40",
+        "BriefDescription": "Core cycles the core was throttled due to a pending power level request.",
+        "Counter": "0,1,2,3",
+        "EventName": "CORE_POWER.THROTTLE",
+        "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.",
+        "SampleAfterValue": "200003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCB",
+        "UMask": "0x1",
+        "BriefDescription": "Number of hardware interrupts received by the processor.",
+        "Counter": "0,1,2,3",
+        "EventName": "HW_INTERRUPTS.RECEIVED",
+        "PublicDescription": "Counts the number of hardware interruptions received by the processor.",
+        "SampleAfterValue": "203",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xFE",
+        "UMask": "0x2",
+        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventName": "IDI_MISC.WB_UPGRADE",
+        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xFE",
+        "UMask": "0x4",
+        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventName": "IDI_MISC.WB_DOWNGRADE",
+        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
new file mode 100644
index 000000000000..0895d1e52a4a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -0,0 +1,950 @@
+[
+    {
+        "EventCode": "0x00",
+        "UMask": "0x1",
+        "BriefDescription": "Instructions retired from execution.",
+        "Counter": "Fixed counter 1",
+        "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 1"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when the thread is not in halt state",
+        "Counter": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.THREAD",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x2",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "EventCode": "0x00",
+        "UMask": "0x3",
+        "BriefDescription": "Reference cycles when the core is not in halt state.",
+        "Counter": "Fixed counter 3",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "Fixed counter 3"
+    },
+    {
+        "EventCode": "0x03",
+        "UMask": "0x2",
+        "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x03",
+        "UMask": "0x8",
+        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x07",
+        "UMask": "0x1",
+        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
+        "Counter": "0,1,2,3",
+        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0D",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.",
+        "Counter": "0,1,2,3",
+        "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0x0E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x2",
+        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x0E",
+        "UMask": "0x20",
+        "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_ISSUED.SLOW_LEA",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x14",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "Counter": "0,1,2,3",
+        "EventName": "ARITH.DIVIDER_ACTIVE",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0x3C",
+        "UMask": "0x0",
+        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x3C",
+        "UMask": "0x2",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
+        "Counter": "0,1,2,3",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "2503",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x4C",
+        "UMask": "0x1",
+        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
+        "Counter": "0,1,2,3",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "Invert": "1",
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterMask": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x87",
+        "UMask": "0x1",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+        "Counter": "0,1,2,3",
+        "EventName": "ILD_STALL.LCP",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x20",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA1",
+        "UMask": "0x80",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA2",
+        "UMask": "0x1",
+        "BriefDescription": "Resource-related stall cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA2",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+        "Counter": "0,1,2,3",
+        "EventName": "RESOURCE_STALLS.SB",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x4",
+        "BriefDescription": "Total execution stalls.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x5",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "CounterMask": "5",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "CounterMask": "8",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0xc",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "CounterMask": "12",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "CounterMask": "16",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA3",
+        "UMask": "0x14",
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
+        "CounterMask": "20",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+        "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x4",
+        "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x8",
+        "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA6",
+        "UMask": "0x40",
+        "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.",
+        "Counter": "0,1,2,3",
+        "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.UOPS",
+        "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "CounterMask": "4",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Number of uops executed on the core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE",
+        "PublicDescription": "Number of uops executed from any thread.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterMask": "3",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xB1",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "CounterMask": "1",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xB1",
+        "UMask": "0x10",
+        "BriefDescription": "Counts the number of x87 uops dispatched.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_EXECUTED.X87",
+        "PublicDescription": "Counts the number of x87 uops executed.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x0",
+        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+        "Counter": "0,1,2,3",
+        "EventName": "INST_RETIRED.ANY_P",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC0",
+        "UMask": "0x1",
+        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
+        "PEBS": "2",
+        "Counter": "1",
+        "EventName": "INST_RETIRED.PREC_DIST",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "1"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC0",
+        "UMask": "0x1",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS instructions retired event.",
+        "PEBS": "2",
+        "Counter": "0,2,3",
+        "EventName": "INST_RETIRED.TOTAL_CYCLES_PS",
+        "CounterMask": "10",
+        "Errata": "SKL091, SKL044",
+        "PublicDescription": "Number of cycles using an always true condition applied to  PEBS instructions retired event. (inst_ret< 16)",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,2,3"
+    },
+    {
+        "EventCode": "0xC1",
+        "UMask": "0x3f",
+        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
+        "Counter": "0,1,2,3",
+        "EventName": "OTHER_ASSISTS.ANY",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Retirement slots used.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "Counts the retirement slots used.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles without actually retired uops.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "Invert": "1",
+        "EventCode": "0xC2",
+        "UMask": "0x2",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "Counter": "0,1,2,3",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "CounterMask": "10",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "UMask": "0x1",
+        "BriefDescription": "Number of machine clears (nukes) of any type. ",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "CounterMask": "1",
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC3",
+        "UMask": "0x4",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "Counter": "0,1,2,3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x0",
+        "BriefDescription": "All (macro) branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "Errata": "SKL091",
+        "PublicDescription": "Counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x1",
+        "BriefDescription": "Conditional branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x2",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x4",
+        "BriefDescription": "All (macro) branch instructions retired. ",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x8",
+        "BriefDescription": "Return instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts return instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x10",
+        "BriefDescription": "Not taken branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x20",
+        "BriefDescription": "Taken branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC4",
+        "UMask": "0x40",
+        "BriefDescription": "Far branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "Errata": "SKL091",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts far branch instructions retired.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x0",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x1",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x2",
+        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x4",
+        "BriefDescription": "Mispredicted macro branch instructions retired. ",
+        "PEBS": "2",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0xC5",
+        "UMask": "0x20",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+        "PEBS": "1",
+        "Counter": "0,1,2,3",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCC",
+        "UMask": "0x20",
+        "BriefDescription": "Increments whenever there is an update to the LBR array.",
+        "Counter": "0,1,2,3",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xE6",
+        "UMask": "0x1",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "Counter": "0,1,2,3",
+        "EventName": "BACLEARS.ANY",
+        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json
new file mode 100644
index 000000000000..9c7e5f8beee2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json
@@ -0,0 +1,172 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "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": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_channel_ppd %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "MetricName": "power_self_refresh %",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses",
+        "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",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "DRAM Page Activate commands sent due to a write request",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT.WR",
+        "PerPkg": "1",
+        "PublicDescription": "Counts DRAM Page Activate commands sent on this channel due to a write request to the iMC (Memory Controller).  Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS (Column Access Select) command.",
+        "UMask": "0x2",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "All DRAM CAS Commands issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts all CAS (Column Address Select) commands issued to DRAM per memory channel.  CAS commands are issued to specify the address to read or write on DRAM, so this event increments for every read and write. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.",
+        "UMask": "0xF",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_READ",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD_REG",
+        "PerPkg": "1",
+        "PublicDescription": "Counts CAS (Column Access Select) regular read commands issued to DRAM on a per channel basis.  CAS commands are issued to specify the address to read or write on DRAM, and this event increments for every regular read.  This event only counts regular reads and does not includes underfill reads due to partial write requests.  This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write)  is enabled or not.",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "DRAM Underfill Read CAS Commands issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis.  CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads.  Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request). ",
+        "UMask": "0x2",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "LLC_MISSES.MEM_WRITE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read Pending Queue Allocations",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_M_RPQ_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ).  This queue is used to schedule reads out to the memory controller and to track the requests.  Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC.  The requests deallocate after the read CAS command has been issued to DRAM.  This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ.    ",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read Pending Queue Occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_M_RPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries in the Read Pending Queue (RPQ) at each cycle.  This can then be used to calculate both the average occupancy of the queue (in conjunction with the number of cycles not empty) and the average latency in the queue (in conjunction with the number of allocations).  The RPQ is used to schedule reads out to the memory controller and to track the requests.  Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate from the RPQ after the CAS command has been issued to memory.",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write Pending Queue Allocations",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x20",
+        "EventName": "UNC_M_WPQ_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of writes requests allocated into the Write Pending Queue (WPQ).  The WPQ is used to schedule writes out to the memory controller and to track the requests.  Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (Memory Controller).  The write requests deallocate after being issued to DRAM.  Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC.",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write Pending Queue Occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x81",
+        "EventName": "UNC_M_WPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle.  This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations).  The WPQ is used to schedule writes out to the memory controller and to track the requests.",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json
new file mode 100644
index 000000000000..de6e70e552e2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json
@@ -0,0 +1,1156 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_CHA_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "config1=0x40e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "config1=0x40040e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "config1=0x40041e33",
+        "PerPkg": "1",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "config1=0x41833",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "config1=0x41a33",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x21",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x03",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "read requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0x0C",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from local home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "write requests from remote home agent",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UPI_DATA_BANDWIDTH_TX",
+        "PerPkg": "1",
+        "ScaleUnit": "7.11E-06Bytes",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "FCMask": "0x07",
+        "Filter": "ch_mask=0x1f",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "MetricName": "LLC_MISSES.PCIE_WRITE",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth writing at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 0",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "MetricName": "LLC_MISSES.PCIE_READ",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 1",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 2",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "PCI Express bandwidth reading at IIO, part 3",
+        "Counter": "0,1",
+        "EventCode": "0x83",
+        "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "ScaleUnit": "4Bytes",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x33",
+        "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops.  Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set.  For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them.  However, if only 1 CV bit is set the core my have modified the data.  If the transaction was an RFO, it would need to invalidate the lines.  This event can be filtered based on who triggered the initial snoop(s).",
+        "UMask": "0x42",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x33",
+        "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops.  Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set.  For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them.  However, if only 1 CV bit is set the core my have modified the data.  If the transaction was an RFO, it would need to invalidate the lines.  This event can be filtered based on who triggered the initial snoop(s).",
+        "UMask": "0x82",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x53",
+        "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP",
+        "PerPkg": "1",
+        "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x53",
+        "EventName": "UNC_CHA_DIR_LOOKUP.SNP",
+        "PerPkg": "1",
+        "PublicDescription": "Counts  transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x54",
+        "EventName": "UNC_CHA_DIR_UPDATE.HA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x54",
+        "EventName": "UNC_CHA_DIR_UPDATE.TOR",
+        "PerPkg": "1",
+        "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.",
+        "UMask": "0x02",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5F",
+        "EventName": "UNC_CHA_HITME_HIT.EX_RDS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state.  This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Normal priority reads issued to the memory controller from the CHA",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x59",
+        "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5B",
+        "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Number of times that an RFO hit in S state.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x39",
+        "EventName": "UNC_CHA_MISC.RFO_HIT_S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a  write) request hit a cacheline in the S (Shared) state.",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Local requests for exclusive ownership of a cache line  without receiving data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.",
+        "UMask": "0x10",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x50",
+        "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.",
+        "UMask": "0x20",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspCnflct* Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.",
+        "UMask": "0x40",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspI Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPI",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).",
+        "UMask": "0x01",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspIFwd Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states.  This is commonly returned with RFO (the Read for Ownership issued before a write) transactions.  The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward)  states.",
+        "UMask": "0x04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "RspSFwd Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy.  This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.",
+        "UMask": "0x08",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to it's home socket, and the cacheline was forwarded to the requestor socket.  This snoop response is only used in >= 4 socket systems.  It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to it's home socket to be written back to memory.",
+        "UMask": "0x20",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Rsp*WB Snoop Responses Received",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5C",
+        "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home.  This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured.  This reponse will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.",
+        "UMask": "0x10",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Clockticks of the IIO Traffic Controller",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_IIO_CLOCKTICKS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU ",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by  a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU ",
+        "Counter": "2,3",
+        "EventCode": "0xC0",
+        "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by  a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xC1",
+        "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is  made by IIO Part1 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x04",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x01",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x02",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x04",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x84",
+        "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3",
+        "FCMask": "0x07",
+        "PerPkg": "1",
+        "PortMask": "0x08",
+        "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to  any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.",
+        "UMask": "0x01",
+        "Unit": "IIO"
+    },
+    {
+        "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x22",
+        "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x24",
+        "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Messages sent direct to core (bypassing the CHA)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x23",
+        "EventName": "UNC_M2M_DIRECT2CORE_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads in which direct to core transaction were overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x25",
+        "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x28",
+        "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Cycles when direct to Intel UPI was disabled",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x27",
+        "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Messages sent direct to the Intel UPI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x26",
+        "EventName": "UNC_M2M_DIRECT2UPI_TAKEN",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x29",
+        "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x8",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state) ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2D",
+        "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data.  The data may be stored in any state in the local socket.",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from A to I",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to I (Invalid)",
+        "UMask": "0x20",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from A to S",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to S (Shared)",
+        "UMask": "0x40",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from/to Any state ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from I to A",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to A (SnoopAll)",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from I to S",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to S (Shared)",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from S to A",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to A (SnoopAll)",
+        "UMask": "0x10",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Multi-socket cacheline Directory update from S to I",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2E",
+        "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to I (Invalid)",
+        "UMask": "0x8",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Reads to iMC issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_M2M_IMC_READS.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). ",
+        "UMask": "0x4",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_M2M_IMC_READS.NORMAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).  It only counts  normal priority non-isochronous reads.",
+        "UMask": "0x1",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Writes to iMC issued",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x38",
+        "EventName": "UNC_M2M_IMC_WRITES.ALL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).",
+        "UMask": "0x10",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Partial Non-Isochronous writes to the iMC",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x38",
+        "EventName": "UNC_M2M_IMC_WRITES.PARTIAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller).  It only counts normal priority non-isochronous writes.",
+        "UMask": "0x2",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Prefecth requests that got turn into a demand request",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x56",
+        "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address.  Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Inserts into the Memory Controller Prefetch Queue",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x57",
+        "EventName": "UNC_M2M_PREFCAM_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the M2M (Mesh to Memory) recieves a prefetch request and inserts it into its outstanding prefetch queue.  Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "AD Ingress (from CMS) Queue Inserts",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M2M_RxC_AD_INSERTS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop).  This is generally used for reads, and ",
+        "Unit": "M2M"
+    },
+    {
+        "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x29",
+        "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN",
+        "PerPkg": "1",
+        "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)",
+        "Unit": "M3UPI"
+    },
+    {
+        "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_UPI_CLOCKTICKS",
+        "PerPkg": "1",
+        "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI).  This clock runs at1/8th the 'GT/s' speed of the UPI link.  For example, a  9.6GT/s  link will have a fixed Frequency of 1.2 Ghz.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Data Response packets that go direct to core",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x12",
+        "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C",
+        "PerPkg": "1",
+        "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.",
+        "UMask": "0x1",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Data Response packets that go direct to Intel UPI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x12",
+        "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U",
+        "PerPkg": "1",
+        "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .",
+        "UMask": "0x2",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_UPI_L1_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode.  L1 is a mode that totally shuts down the UPI link.  Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x25",
+        "EventName": "UNC_UPI_RxL0P_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x1",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer  (Receive Queue) and passed directly across the BGF and into the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x2",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs received which bypassed the Slot0 Recieve Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x31",
+        "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) whcih bypassed the slot2 RxQ buffer (Receive Queue)  and passed directly to the Egress.  This is a latency optimization, and should generally be the common case.  If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+        "UMask": "0x4",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Valid data FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts valid data FLITs  (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Null FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.",
+        "UMask": "0x27",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Protocol header and credit FLITs received from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x3",
+        "EventName": "UNC_UPI_RxL_FLITS.NON_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts protocol header and credit FLITs  (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.",
+        "UMask": "0x97",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x27",
+        "EventName": "UNC_UPI_TxL0P_POWER_CYCLES",
+        "PerPkg": "1",
+        "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "FLITs that bypassed the TxL Buffer",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x41",
+        "EventName": "UNC_UPI_TxL_BYPASSED",
+        "PerPkg": "1",
+        "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link.  However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR  mode, increasing latency to transfer out to the link.",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UPI_DATA_BANDWIDTH_TX",
+        "PerPkg": "1",
+        "ScaleUnit": "7.11E-06Bytes",
+        "UMask": "0x0F",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Null FLITs transmitted from any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.",
+        "UMask": "0x27",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Idle FLITs transmitted",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.IDLE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs).  Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.",
+        "UMask": "0x47",
+        "Unit": "UPI LL"
+    },
+    {
+        "BriefDescription": "Protocol header and credit FLITs transmitted across any slot",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_UPI_TxL_FLITS.NON_DATA",
+        "PerPkg": "1",
+        "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.",
+        "UMask": "0x97",
+        "Unit": "UPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
new file mode 100644
index 000000000000..70750dab7ead
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
@@ -0,0 +1,284 @@
+[
+    {
+        "EventCode": "0x08",
+        "UMask": "0x1",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x2",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x4",
+        "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x8",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts load misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0xe",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x08",
+        "UMask": "0x20",
+        "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x1",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x2",
+        "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk (4K page size). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x4",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk (2M and 4M page sizes). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x8",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0xe",
+        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture. ",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x49",
+        "UMask": "0x20",
+        "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x4F",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
+        "Counter": "0,1,2,3",
+        "EventName": "EPT.WALK_PENDING",
+        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x1",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x2",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x4",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts completed page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x8",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0xe",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake. ",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture. ",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x10",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.WALK_ACTIVE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
+        "UMask": "0x20",
+        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB_MISSES.STLB_HIT",
+        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAE",
+        "UMask": "0x1",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
+        "Counter": "0,1,2,3",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x1",
+        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.DTLB_THREAD",
+        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBD",
+        "UMask": "0x20",
+        "BriefDescription": "STLB flush attempts",
+        "Counter": "0,1,2,3",
+        "EventName": "TLB_FLUSH.STLB_ANY",
+        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
+        "SampleAfterValue": "100007",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index bd0aabb2bd0f..d51dc9ca8861 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -137,6 +137,8 @@ static struct field {
         { "AnyThread",  "any=" },
         { "EdgeDetect", "edge=" },
         { "SampleAfterValue", "period=" },
+        { "FCMask",     "fc_mask=" },
+        { "PortMask",   "ch_mask=" },
         { NULL, NULL }
 };
 
@@ -822,10 +824,6 @@ static int process_one_file(const char *fpath, const struct stat *sb,
  * PMU event tables (see struct pmu_events_map).
  *
  * Write out the PMU events tables and the mapping table to pmu-event.c.
- *
- * If unable to process the JSON or arch files, create an empty mapping
- * table so we can continue to build/use  perf even if we cannot use the
- * PMU event aliases.
  */
 int main(int argc, char *argv[])
 {
@@ -836,6 +834,7 @@ int main(int argc, char *argv[])
         const char *arch;
         const char *output_file;
         const char *start_dirname;
+        struct stat stbuf;
 
         prog = basename(argv[0]);
         if (argc < 4) {
@@ -857,11 +856,17 @@ int main(int argc, char *argv[])
                 return 2;
         }
 
+        sprintf(ldirname, "%s/%s", start_dirname, arch);
+
+        /* If architecture does not have any event lists, bail out */
+        if (stat(ldirname, &stbuf) < 0) {
+                pr_info("%s: Arch %s has no PMU event lists\n", prog, arch);
+                goto empty_map;
+        }
+
         /* Include pmu-events.h first */
         fprintf(eventsfp, "#include \"../../pmu-events/pmu-events.h\"\n");
 
-        sprintf(ldirname, "%s/%s", start_dirname, arch);
-
         /*
          * The mapfile allows multiple CPUids to point to the same JSON file,
          * so, not sure if there is a need for symlinks within the pmu-events
@@ -878,6 +883,9 @@ int main(int argc, char *argv[])
         if (rc && verbose) {
                 pr_info("%s: Error walking file tree %s\n", prog, ldirname);
                 goto empty_map;
+        } else if (rc < 0) {
+                /* Make build fail */
+                return 1;
         } else if (rc) {
                 goto empty_map;
         }
@@ -892,7 +900,8 @@ int main(int argc, char *argv[])
 
         if (process_mapfile(eventsfp, mapfile)) {
                 pr_info("%s: Error processing mapfile %s\n", prog, mapfile);
-                goto empty_map;
+                /* Make build fail */
+                return 1;
         }
 
         return 0;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 1d95009592eb..f6c84966e4f8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -57,6 +57,7 @@ try:
                 'ia64'  : audit.MACH_IA64,
                 'ppc'   : audit.MACH_PPC,
                 'ppc64' : audit.MACH_PPC64,
+                'ppc64le' : audit.MACH_PPC64LE,
                 's390'  : audit.MACH_S390,
                 's390x' : audit.MACH_S390X,
                 'i386'  : audit.MACH_X86,
diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-record b/tools/perf/scripts/python/bin/export-to-sqlite-record
new file mode 100644
index 000000000000..070204fd6d00
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-sqlite-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a sqlite3 database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-report b/tools/perf/scripts/python/bin/export-to-sqlite-report
new file mode 100644
index 000000000000..5ff6033e70ba
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-sqlite-report
@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a sqlite3 database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+        break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-sqlite-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/call-graph-from-postgresql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index e78fdc2a5a9d..b494a67a1c67 100644
--- a/tools/perf/scripts/python/call-graph-from-postgresql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -1,6 +1,6 @@
 #!/usr/bin/python2
-# call-graph-from-postgresql.py: create call-graph from postgresql database
-# Copyright (c) 2014, Intel Corporation.
+# call-graph-from-sql.py: create call-graph from sql database
+# Copyright (c) 2014-2017, Intel Corporation.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms and conditions of the GNU General Public License,
@@ -11,18 +11,19 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
 
-# To use this script you will need to have exported data using the
-# export-to-postgresql.py script.  Refer to that script for details.
+# To use this script you will need to have exported data using either the
+# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
+# scripts for details.
 #
-# Following on from the example in the export-to-postgresql.py script, a
+# Following on from the example in the export scripts, a
 # call-graph can be displayed for the pt_example database like this:
 #
-#       python tools/perf/scripts/python/call-graph-from-postgresql.py pt_example
+#       python tools/perf/scripts/python/call-graph-from-sql.py pt_example
 #
-# Note this script supports connecting to remote databases by setting hostname,
-# port, username, password, and dbname e.g.
+# Note that for PostgreSQL, this script supports connecting to remote databases
+# by setting hostname, port, username, password, and dbname e.g.
 #
-#       python tools/perf/scripts/python/call-graph-from-postgresql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+#       python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
 #
 # The result is a GUI window with a tree representing a context-sensitive
 # call-graph.  Expanding a couple of levels of the tree and adjusting column
@@ -160,7 +161,7 @@ class TreeItem():
                                   '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
                                   '( SELECT ip FROM call_paths where id = call_path_id ) '
                                   'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-                                  'ORDER BY call_path_id')
+                                  ' ORDER BY call_path_id')
                 if not ret:
                         raise Exception("Query failed: " + query.lastError().text())
                 last_call_path_id = 0
@@ -291,29 +292,40 @@ class MainWindow(QMainWindow):
 
 if __name__ == '__main__':
         if (len(sys.argv) < 2):
-                print >> sys.stderr, "Usage is: call-graph-from-postgresql.py <database name>"
+                print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
                 raise Exception("Too few arguments")
 
         dbname = sys.argv[1]
 
-        db = QSqlDatabase.addDatabase('QPSQL')
-
-        opts = dbname.split()
-        for opt in opts:
-                if '=' in opt:
-                        opt = opt.split('=')
-                        if opt[0] == 'hostname':
-                                db.setHostName(opt[1])
-                        elif opt[0] == 'port':
-                                db.setPort(int(opt[1]))
-                        elif opt[0] == 'username':
-                                db.setUserName(opt[1])
-                        elif opt[0] == 'password':
-                                db.setPassword(opt[1])
-                        elif opt[0] == 'dbname':
-                                dbname = opt[1]
-                else:
-                        dbname = opt
+        is_sqlite3 = False
+        try:
+                f = open(dbname)
+                if f.read(15) == "SQLite format 3":
+                        is_sqlite3 = True
+                f.close()
+        except:
+                pass
+
+        if is_sqlite3:
+                db = QSqlDatabase.addDatabase('QSQLITE')
+        else:
+                db = QSqlDatabase.addDatabase('QPSQL')
+                opts = dbname.split()
+                for opt in opts:
+                        if '=' in opt:
+                                opt = opt.split('=')
+                                if opt[0] == 'hostname':
+                                        db.setHostName(opt[1])
+                                elif opt[0] == 'port':
+                                        db.setPort(int(opt[1]))
+                                elif opt[0] == 'username':
+                                        db.setUserName(opt[1])
+                                elif opt[0] == 'password':
+                                        db.setPassword(opt[1])
+                                elif opt[0] == 'dbname':
+                                        dbname = opt[1]
+                        else:
+                                dbname = opt
 
         db.setDatabaseName(dbname)
         if not db.open():
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 7656ff8aa066..efcaf6cac2eb 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
 #       pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-postgresql.py.  Refer to that script for details.
+# call-graph-from-sql.py.  Refer to that script for details.
 #
 # Tables:
 #
@@ -340,7 +340,8 @@ if branches:
                 'to_sym_offset  bigint,'
                 'to_ip          bigint,'
                 'branch_type    integer,'
-                'in_tx          boolean)')
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
 else:
         do_query(query, 'CREATE TABLE samples ('
                 'id             bigint          NOT NULL,'
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
new file mode 100644
index 000000000000..f827bf77e9d2
--- /dev/null
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -0,0 +1,451 @@
+# export-to-sqlite.py: export perf data to a sqlite3 database
+# Copyright (c) 2017, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+import os
+import sys
+import struct
+import datetime
+
+# To use this script you will need to have installed package python-pyside which
+# provides LGPL-licensed Python bindings for Qt.  You will also need the package
+# libqt4-sql-sqlite for Qt sqlite3 support.
+#
+# An example of using this script with Intel PT:
+#
+#       $ perf record -e intel_pt//u ls
+#       $ perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
+#       2017-07-31 14:26:07.326913 Creating database...
+#       2017-07-31 14:26:07.538097 Writing records...
+#       2017-07-31 14:26:09.889292 Adding indexes
+#       2017-07-31 14:26:09.958746 Done
+#
+# To browse the database, sqlite3 can be used e.g.
+#
+#       $ sqlite3 pt_example
+#       sqlite> .header on
+#       sqlite> select * from samples_view where id < 10;
+#       sqlite> .mode column
+#       sqlite> select * from samples_view where id < 10;
+#       sqlite> .tables
+#       sqlite> .schema samples_view
+#       sqlite> .quit
+#
+# An example of using the database is provided by the script
+# call-graph-from-sql.py.  Refer to that script for details.
+#
+# The database structure is practically the same as created by the script
+# export-to-postgresql.py. Refer to that script for details.  A notable
+# difference is  the 'transaction' column of the 'samples' table which is
+# renamed 'transaction_' in sqlite because 'transaction' is a reserved word.
+
+from PySide.QtSql import *
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+# These perf imports are not used at present
+#from perf_trace_context import *
+#from Core import *
+
+perf_db_export_mode = True
+perf_db_export_calls = False
+perf_db_export_callchains = False
+
+def usage():
+        print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"
+        print >> sys.stderr, "where:    columns         'all' or 'branches'"
+        print >> sys.stderr, "          calls           'calls' => create calls and call_paths table"
+        print >> sys.stderr, "          callchains      'callchains' => create call_paths table"
+        raise Exception("Too few arguments")
+
+if (len(sys.argv) < 2):
+        usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+        columns = sys.argv[2]
+else:
+        columns = "all"
+
+if columns not in ("all", "branches"):
+        usage()
+
+branches = (columns == "branches")
+
+for i in range(3,len(sys.argv)):
+        if (sys.argv[i] == "calls"):
+                perf_db_export_calls = True
+        elif (sys.argv[i] == "callchains"):
+                perf_db_export_callchains = True
+        else:
+                usage()
+
+def do_query(q, s):
+        if (q.exec_(s)):
+                return
+        raise Exception("Query failed: " + q.lastError().text())
+
+def do_query_(q):
+        if (q.exec_()):
+                return
+        raise Exception("Query failed: " + q.lastError().text())
+
+print datetime.datetime.today(), "Creating database..."
+
+db_exists = False
+try:
+        f = open(dbname)
+        f.close()
+        db_exists = True
+except:
+        pass
+
+if db_exists:
+        raise Exception(dbname + " already exists")
+
+db = QSqlDatabase.addDatabase('QSQLITE')
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+
+do_query(query, 'PRAGMA journal_mode = OFF')
+do_query(query, 'BEGIN TRANSACTION')
+
+do_query(query, 'CREATE TABLE selected_events ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'name           varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'pid            integer,'
+                'root_dir       varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'machine_id     bigint,'
+                'process_id     bigint,'
+                'pid            integer,'
+                'tid            integer)')
+do_query(query, 'CREATE TABLE comms ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'comm           varchar(16))')
+do_query(query, 'CREATE TABLE comm_threads ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'comm_id        bigint,'
+                'thread_id      bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'machine_id     bigint,'
+                'short_name     varchar(256),'
+                'long_name      varchar(4096),'
+                'build_id       varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'dso_id         bigint,'
+                'sym_start      bigint,'
+                'sym_end        bigint,'
+                'binding        integer,'
+                'name           varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'name           varchar(80))')
+
+if branches:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
+else:
+        do_query(query, 'CREATE TABLE samples ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'evsel_id       bigint,'
+                'machine_id     bigint,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'dso_id         bigint,'
+                'symbol_id      bigint,'
+                'sym_offset     bigint,'
+                'ip             bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'to_dso_id      bigint,'
+                'to_symbol_id   bigint,'
+                'to_sym_offset  bigint,'
+                'to_ip          bigint,'
+                'period         bigint,'
+                'weight         bigint,'
+                'transaction_   bigint,'
+                'data_src       bigint,'
+                'branch_type    integer,'
+                'in_tx          boolean,'
+                'call_path_id   bigint)')
+
+if perf_db_export_calls or perf_db_export_callchains:
+        do_query(query, 'CREATE TABLE call_paths ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'parent_id      bigint,'
+                'symbol_id      bigint,'
+                'ip             bigint)')
+if perf_db_export_calls:
+        do_query(query, 'CREATE TABLE calls ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'thread_id      bigint,'
+                'comm_id        bigint,'
+                'call_path_id   bigint,'
+                'call_time      bigint,'
+                'return_time    bigint,'
+                'branch_count   bigint,'
+                'call_id        bigint,'
+                'return_id      bigint,'
+                'parent_call_path_id    bigint,'
+                'flags          integer)')
+
+# printf was added to sqlite in version 3.8.3
+sqlite_has_printf = False
+try:
+        do_query(query, 'SELECT printf("") FROM machines')
+        sqlite_has_printf = True
+except:
+        pass
+
+def emit_to_hex(x):
+        if sqlite_has_printf:
+                return 'printf("%x", ' + x + ')'
+        else:
+                return x
+
+do_query(query, 'CREATE VIEW machines_view AS '
+        'SELECT '
+                'id,'
+                'pid,'
+                'root_dir,'
+                'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest'
+        ' FROM machines')
+
+do_query(query, 'CREATE VIEW dsos_view AS '
+        'SELECT '
+                'id,'
+                'machine_id,'
+                '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+                'short_name,'
+                'long_name,'
+                'build_id'
+        ' FROM dsos')
+
+do_query(query, 'CREATE VIEW symbols_view AS '
+        'SELECT '
+                'id,'
+                'name,'
+                '(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,'
+                'dso_id,'
+                'sym_start,'
+                'sym_end,'
+                'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding'
+        ' FROM symbols')
+
+do_query(query, 'CREATE VIEW threads_view AS '
+        'SELECT '
+                'id,'
+                'machine_id,'
+                '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,'
+                'process_id,'
+                'pid,'
+                'tid'
+        ' FROM threads')
+
+do_query(query, 'CREATE VIEW comm_threads_view AS '
+        'SELECT '
+                'comm_id,'
+                '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                'thread_id,'
+                '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                '(SELECT tid FROM threads WHERE id = thread_id) AS tid'
+        ' FROM comm_threads')
+
+if perf_db_export_calls or perf_db_export_callchains:
+        do_query(query, 'CREATE VIEW call_paths_view AS '
+                'SELECT '
+                        'c.id,'
+                        + emit_to_hex('c.ip') + ' AS ip,'
+                        'c.symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,'
+                        '(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,'
+                        '(SELECT dso FROM symbols_view  WHERE id = c.symbol_id) AS dso_short_name,'
+                        'c.parent_id,'
+                        + emit_to_hex('p.ip') + ' AS parent_ip,'
+                        'p.symbol_id AS parent_symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,'
+                        '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,'
+                        '(SELECT dso FROM symbols_view  WHERE id = p.symbol_id) AS parent_dso_short_name'
+                ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id')
+if perf_db_export_calls:
+        do_query(query, 'CREATE VIEW calls_view AS '
+                'SELECT '
+                        'calls.id,'
+                        'thread_id,'
+                        '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                        '(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+                        '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                        'call_path_id,'
+                        + emit_to_hex('ip') + ' AS ip,'
+                        'symbol_id,'
+                        '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+                        'call_time,'
+                        'return_time,'
+                        'return_time - call_time AS elapsed_time,'
+                        'branch_count,'
+                        'call_id,'
+                        'return_id,'
+                        'CASE WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' ELSE \'\' END AS flags,'
+                        'parent_call_path_id'
+                ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+        'SELECT '
+                'id,'
+                'time,'
+                'cpu,'
+                '(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+                '(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+                '(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+                '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+                + emit_to_hex('ip') + ' AS ip_hex,'
+                '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+                'sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+                + emit_to_hex('to_ip') + ' AS to_ip_hex,'
+                '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+                'to_sym_offset,'
+                '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+                '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+                'in_tx'
+        ' FROM samples')
+
+do_query(query, 'END TRANSACTION')
+
+evsel_query = QSqlQuery(db)
+evsel_query.prepare("INSERT INTO selected_events VALUES (?, ?)")
+machine_query = QSqlQuery(db)
+machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)")
+thread_query = QSqlQuery(db)
+thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)")
+comm_query = QSqlQuery(db)
+comm_query.prepare("INSERT INTO comms VALUES (?, ?)")
+comm_thread_query = QSqlQuery(db)
+comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)")
+dso_query = QSqlQuery(db)
+dso_query.prepare("INSERT INTO dsos VALUES (?, ?, ?, ?, ?)")
+symbol_query = QSqlQuery(db)
+symbol_query.prepare("INSERT INTO symbols VALUES (?, ?, ?, ?, ?, ?)")
+branch_type_query = QSqlQuery(db)
+branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)")
+sample_query = QSqlQuery(db)
+if branches:
+        sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+else:
+        sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+if perf_db_export_calls or perf_db_export_callchains:
+        call_path_query = QSqlQuery(db)
+        call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)")
+if perf_db_export_calls:
+        call_query = QSqlQuery(db)
+        call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)")
+
+def trace_begin():
+        print datetime.datetime.today(), "Writing records..."
+        do_query(query, 'BEGIN TRANSACTION')
+        # id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+        evsel_table(0, "unknown")
+        machine_table(0, 0, "unknown")
+        thread_table(0, 0, 0, -1, -1)
+        comm_table(0, "unknown")
+        dso_table(0, 0, "unknown", "unknown", "")
+        symbol_table(0, 0, 0, 0, 0, "unknown")
+        sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+        if perf_db_export_calls or perf_db_export_callchains:
+                call_path_table(0, 0, 0, 0)
+
+unhandled_count = 0
+
+def trace_end():
+        do_query(query, 'END TRANSACTION')
+
+        print datetime.datetime.today(), "Adding indexes"
+        if perf_db_export_calls:
+                do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
+
+        if (unhandled_count):
+                print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+        print datetime.datetime.today(), "Done"
+
+def trace_unhandled(event_name, context, event_fields_dict):
+        global unhandled_count
+        unhandled_count += 1
+
+def sched__sched_switch(*x):
+        pass
+
+def bind_exec(q, n, x):
+        for xx in x[0:n]:
+                q.addBindValue(str(xx))
+        do_query_(q)
+
+def evsel_table(*x):
+        bind_exec(evsel_query, 2, x)
+
+def machine_table(*x):
+        bind_exec(machine_query, 3, x)
+
+def thread_table(*x):
+        bind_exec(thread_query, 5, x)
+
+def comm_table(*x):
+        bind_exec(comm_query, 2, x)
+
+def comm_thread_table(*x):
+        bind_exec(comm_thread_query, 3, x)
+
+def dso_table(*x):
+        bind_exec(dso_query, 5, x)
+
+def symbol_table(*x):
+        bind_exec(symbol_query, 6, x)
+
+def branch_type_table(*x):
+        bind_exec(branch_type_query, 2, x)
+
+def sample_table(*x):
+        if branches:
+                bind_exec(sample_query, 18, x)
+        else:
+                bind_exec(sample_query, 22, x)
+
+def call_path_table(*x):
+        bind_exec(call_path_query, 4, x)
+
+def call_return_table(*x):
+        bind_exec(call_query, 11, x)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 84222bdb8689..87bf3edb037c 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -34,6 +34,7 @@ perf-y += thread-map.o
 perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
+perf-y += mem.o
 perf-y += cpumap.o
 perf-y += stat.o
 perf-y += event_update.o
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0e77b2cf61ec..c9aafed7da15 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -36,6 +36,7 @@
 #define ENV "PERF_TEST_ATTR"
 
 static char *dir;
+static bool ready;
 
 void test_attr__init(void)
 {
@@ -67,6 +68,9 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
         FILE *file;
         char path[PATH_MAX];
 
+        if (!ready)
+                return 0;
+
         snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
                  attr->type, attr->config, fd);
 
@@ -136,7 +140,7 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 {
         int errno_saved = errno;
 
-        if (store_event(attr, pid, cpu, fd, group_fd, flags)) {
+        if ((fd != -1) && store_event(attr, pid, cpu, fd, group_fd, flags)) {
                 pr_err("test attr FAILED");
                 exit(128);
         }
@@ -144,6 +148,12 @@ void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
         errno = errno_saved;
 }
 
+void test_attr__ready(void)
+{
+        if (unlikely(test_attr__enabled) && !ready)
+                ready = true;
+}
+
 static int run_dir(const char *d, const char *perf)
 {
         char v[] = "-vvvvv";
@@ -159,7 +169,7 @@ static int run_dir(const char *d, const char *perf)
         return system(cmd);
 }
 
-int test__attr(int subtest __maybe_unused)
+int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct stat st;
         char path_perf[PATH_MAX];
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index cdf21a9d0c35..6bb50e82a3e3 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -9,6 +9,20 @@ import logging
 import shutil
 import ConfigParser
 
+def data_equal(a, b):
+    # Allow multiple values in assignment separated by '|'
+    a_list = a.split('|')
+    b_list = b.split('|')
+
+    for a_item in a_list:
+        for b_item in b_list:
+            if (a_item == b_item):
+                return True
+            elif (a_item == '*') or (b_item == '*'):
+                return True
+
+    return False
+
 class Fail(Exception):
     def __init__(self, test, msg):
         self.msg = msg
@@ -82,34 +96,25 @@ class Event(dict):
         self.add(base)
         self.add(data)
 
-    def compare_data(self, a, b):
-        # Allow multiple values in assignment separated by '|'
-        a_list = a.split('|')
-        b_list = b.split('|')
-
-        for a_item in a_list:
-            for b_item in b_list:
-                if (a_item == b_item):
-                    return True
-                elif (a_item == '*') or (b_item == '*'):
-                    return True
-
-        return False
-
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
             if not self.has_key(t) or not other.has_key(t):
                 return False
-            if not self.compare_data(self[t], other[t]):
+            if not data_equal(self[t], other[t]):
                 return False
         return True
 
+    def optional(self):
+        if self.has_key('optional') and self['optional'] == '1':
+            return True
+        return False
+
     def diff(self, other):
         for t in Event.terms:
             if not self.has_key(t) or not other.has_key(t):
                 continue
-            if not self.compare_data(self[t], other[t]):
+            if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
 
 # Test file description needs to have following sections:
@@ -218,9 +223,9 @@ class Test(object):
               self.perf, self.command, tempdir, self.args)
         ret = os.WEXITSTATUS(os.system(cmd))
 
-        log.info("  '%s' ret %d " % (cmd, ret))
+        log.info("  '%s' ret '%s', expected '%s'" % (cmd, str(ret), str(self.ret)))
 
-        if ret != int(self.ret):
+        if not data_equal(str(ret), str(self.ret)):
             raise Unsup(self)
 
     def compare(self, expect, result):
@@ -244,9 +249,12 @@ class Test(object):
             log.debug("    match: [%s] matches %s" % (exp_name, str(exp_list)))
 
             # we did not any matching event - fail
-            if (not exp_list):
-                exp_event.diff(res_event)
-                raise Fail(self, 'match failure');
+            if not exp_list:
+                if exp_event.optional():
+                    log.debug("    %s does not match, but is optional" % exp_name)
+                else:
+                    exp_event.diff(res_event)
+                    raise Fail(self, 'match failure');
 
             match[exp_name] = exp_list
 
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index 7e6d74946e04..31e0b1da830b 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -7,7 +7,7 @@ cpu=*
 type=0|1
 size=112
 config=0
-sample_period=4000
+sample_period=*
 sample_type=263
 read_format=0
 disabled=1
@@ -15,7 +15,7 @@ inherit=1
 pinned=0
 exclusive=0
 exclude_user=0
-exclude_kernel=0
+exclude_kernel=0|1
 exclude_hv=0
 exclude_idle=0
 mmap=1
@@ -25,7 +25,7 @@ inherit_stat=0
 enable_on_exec=1
 task=0
 watermark=0
-precise_ip=0
+precise_ip=0|1|2|3
 mmap_data=0
 sample_id_all=1
 exclude_host=0|1
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index f4cf148f14cb..4d0c2e42b64e 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -8,14 +8,14 @@ type=0
 size=112
 config=0
 sample_period=0
-sample_type=0
+sample_type=65536
 read_format=3
 disabled=1
 inherit=1
 pinned=0
 exclusive=0
 exclude_user=0
-exclude_kernel=0
+exclude_kernel=0|1
 exclude_hv=0
 exclude_idle=0
 mmap=0
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index d6a7e43f61b3..cb0a3138fa54 100644
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -C 0 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 cpu=0
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
index 55c0428370ca..85a23cf35ba1 100644
--- a/tools/perf/tests/attr/test-record-basic
+++ b/tools/perf/tests/attr/test-record-basic
@@ -1,5 +1,6 @@
 [config]
 command = record
 args    = kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
index 1421960ed4e9..81f839e2fad0 100644
--- a/tools/perf/tests/attr/test-record-branch-any
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -b kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
index 915c4df0e0c2..357421f4dfce 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
index 8708dbd4f373..dbc55f2ab845 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any_call kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=16
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
index 0d3607a6dcbe..a0824ff8e131 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-any_ret
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j any_ret kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=32
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
index f25526740cec..f34d6f120181 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-hv
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j hv kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
index e862dd179128..b86a35232248 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-ind_call
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j ind_call kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=64
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
index 182971e898f5..d3fbc5e1858a 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-k
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j k kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
index 83449ef9e687..a318f0dda173 100644
--- a/tools/perf/tests/attr/test-record-branch-filter-u
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -1,8 +1,8 @@
 [config]
 command = record
 args    = -j u kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=2311
 branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
index 2f841de56f6b..34f6cc577263 100644
--- a/tools/perf/tests/attr/test-record-count
+++ b/tools/perf/tests/attr/test-record-count
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -c 123 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=123
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
index 716e143b5291..a9cf2233b0ce 100644
--- a/tools/perf/tests/attr/test-record-data
+++ b/tools/perf/tests/attr/test-record-data
@@ -1,10 +1,9 @@
 [config]
 command = record
 args    = -d kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
-
 # sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
 # PERF_SAMPLE_ADDR | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC
 sample_type=33039
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
index 600d0f8f2583..bf4cb459f0d5 100644
--- a/tools/perf/tests/attr/test-record-freq
+++ b/tools/perf/tests/attr/test-record-freq
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -F 100 kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=100
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
index 853597a9a8f6..0b216e69760c 100644
--- a/tools/perf/tests/attr/test-record-graph-default
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -g kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
index d6f324ea578c..da2fa73bd0a2 100644
--- a/tools/perf/tests/attr/test-record-graph-dwarf
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -1,10 +1,12 @@
 [config]
 command = record
 args    = --call-graph dwarf -- kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_type=12583
+sample_type=45359
 exclude_callchain_user=1
 sample_stack_user=8192
 # TODO different for each arch, no support for that now
 sample_regs_user=*
+mmap_data=1
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
index 055e3bee7993..625d190bb798 100644
--- a/tools/perf/tests/attr/test-record-graph-fp
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = --call-graph fp kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=295
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index 57739cacdb2a..6e7961f6f7a5 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = --group -e cycles,instructions kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling
index 658f5d60c873..ef59afd6d635 100644
--- a/tools/perf/tests/attr/test-record-group-sampling
+++ b/tools/perf/tests/attr/test-record-group-sampling
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index c5548d054aff..87a222d014d8 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+ret     = 1
 
 [event-1:base-record]
 fd=1
diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-buffering
index f253b78cdbf2..aa3956d8fe20 100644
--- a/tools/perf/tests/attr/test-record-no-delay
+++ b/tools/perf/tests/attr/test-record-no-buffering
@@ -1,9 +1,9 @@
 [config]
 command = record
-args    = -D kill >/dev/null 2>&1
+args    = --no-buffering kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=263
 watermark=0
 wakeup_events=1
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 44edcb2edcd5..560943decb87 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -i kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_type=263
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
index d0141b2418b5..8eb73ab639e0 100644
--- a/tools/perf/tests/attr/test-record-no-samples
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -n kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=0
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
index 8abc5314fc52..69bc748f0f27 100644
--- a/tools/perf/tests/attr/test-record-period
+++ b/tools/perf/tests/attr/test-record-period
@@ -1,6 +1,7 @@
 [config]
 command = record
 args    = -c 100 -P kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
 sample_period=100
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
index 4a8ef25b5f49..a188a614a44c 100644
--- a/tools/perf/tests/attr/test-record-raw
+++ b/tools/perf/tests/attr/test-record-raw
@@ -1,7 +1,7 @@
 [config]
 command = record
 args    = -R kill >/dev/null 2>&1
+ret     = 1
 
 [event:base-record]
-sample_period=4000
 sample_type=1415
diff --git a/tools/perf/tests/attr/test-stat-C0 b/tools/perf/tests/attr/test-stat-C0
index aa835950751f..67717fe6a65d 100644
--- a/tools/perf/tests/attr/test-stat-C0
+++ b/tools/perf/tests/attr/test-stat-C0
@@ -4,6 +4,6 @@ args    = -e cycles -C 0 kill >/dev/null 2>&1
 ret     = 1
 
 [event:base-stat]
-# events are enabled by default when attached to cpu
-disabled=0
+# events are disabled by default when attached to cpu
+disabled=1
 enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
index 19270f54c96e..e911dbd4eb47 100644
--- a/tools/perf/tests/attr/test-stat-default
+++ b/tools/perf/tests/attr/test-stat-default
@@ -38,12 +38,14 @@ config=0
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
index 51426b87153b..b39270a08e74 100644
--- a/tools/perf/tests/attr/test-stat-detailed-1
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -39,12 +39,14 @@ config=0
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
index 8de5acc31c27..45f8e6ea34f8 100644
--- a/tools/perf/tests/attr/test-stat-detailed-2
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -39,12 +39,14 @@ config=0
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
@@ -108,6 +110,7 @@ config=65538
 fd=15
 type=3
 config=1
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
index 0a1f45bf7d79..30ae0fb7a3fd 100644
--- a/tools/perf/tests/attr/test-stat-detailed-3
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -39,12 +39,14 @@ config=0
 fd=6
 type=0
 config=7
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
 [event7:base-stat]
 fd=7
 type=0
 config=8
+optional=1
 
 # PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
 [event8:base-stat]
@@ -108,6 +110,7 @@ config=65538
 fd=15
 type=3
 config=1
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1I                <<  0  |
@@ -162,6 +165,7 @@ config=65540
 fd=21
 type=3
 config=512
+optional=1
 
 # PERF_TYPE_HW_CACHE,
 #  PERF_COUNT_HW_CACHE_L1D                <<  0  |
@@ -171,3 +175,4 @@ config=512
 fd=22
 type=3
 config=66048
+optional=1
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 50f6d7afee58..d233ad336463 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -75,7 +75,7 @@ static int do_test(struct perf_evlist *evlist, int mmap_pages,
 }
 
 
-int test__backward_ring_buffer(int subtest __maybe_unused)
+int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0;
         char pid[16], sbuf[STRERR_BUFSIZE];
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 9abe6c13090f..0d7c06584905 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -40,7 +40,7 @@ static int test_bitmap(const char *str)
         return ret;
 }
 
-int test__bitmap_print(int subtest __maybe_unused)
+int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
         TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 39bbb97cd30a..97937e1bc53a 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -164,7 +164,7 @@ static long long bp_count(int fd)
         return count;
 }
 
-int test__bp_signal(int subtest __maybe_unused)
+int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct sigaction sa;
         long long count1, count2, count3;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index 3b1ac6f31b15..61ecd8021f49 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -57,7 +57,7 @@ static long long bp_count(int fd)
 #define EXECUTIONS 10000
 #define THRESHOLD  100
 
-int test__bp_signal_overflow(int subtest __maybe_unused)
+int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_event_attr pe;
         struct sigaction sa;
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
index b4ebc75e25ae..43f1e16486f4 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -26,9 +26,11 @@ static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
         (void *) 6;
 
 SEC("func=null_lseek file->f_mode offset orig")
-int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode,
+int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
                          unsigned long offset, unsigned long orig)
 {
+        fmode_t f_mode = (fmode_t)_f_mode;
+
         if (err)
                 return 0;
         if (f_mode & FMODE_WRITE)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 5876da126b58..34c22cdf4d5d 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -124,16 +124,16 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         struct perf_evlist *evlist;
         int i, ret = TEST_FAIL, err = 0, count = 0;
 
-        struct parse_events_evlist parse_evlist;
+        struct parse_events_state parse_state;
         struct parse_events_error parse_error;
 
         bzero(&parse_error, sizeof(parse_error));
-        bzero(&parse_evlist, sizeof(parse_evlist));
-        parse_evlist.error = &parse_error;
-        INIT_LIST_HEAD(&parse_evlist.list);
+        bzero(&parse_state, sizeof(parse_state));
+        parse_state.error = &parse_error;
+        INIT_LIST_HEAD(&parse_state.list);
 
-        err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
-        if (err || list_empty(&parse_evlist.list)) {
+        err = parse_events_load_bpf_obj(&parse_state, &parse_state.list, obj, NULL);
+        if (err || list_empty(&parse_state.list)) {
                 pr_debug("Failed to add events selected by BPF\n");
                 return TEST_FAIL;
         }
@@ -155,8 +155,8 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
                 goto out_delete_evlist;
         }
 
-        perf_evlist__splice_list_tail(evlist, &parse_evlist.list);
-        evlist->nr_groups = parse_evlist.nr_groups;
+        perf_evlist__splice_list_tail(evlist, &parse_state.list);
+        evlist->nr_groups = parse_state.nr_groups;
 
         perf_evlist__config(evlist, &opts, NULL);
 
@@ -321,7 +321,7 @@ static int check_env(void)
         return 0;
 }
 
-int test__bpf(int i)
+int test__bpf(struct test *test __maybe_unused, int i)
 {
         int err;
 
@@ -351,7 +351,7 @@ const char *test__bpf_subtest_get_desc(int i __maybe_unused)
         return NULL;
 }
 
-int test__bpf(int i __maybe_unused)
+int test__bpf(struct test *test __maybe_unused, int i __maybe_unused)
 {
         pr_debug("Skip BPF test because BPF support is not compiled\n");
         return TEST_SKIP;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 3ccfd58a8c3c..377bea009163 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -6,7 +6,10 @@
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
+#include <sys/types.h>
+#include <dirent.h>
 #include <sys/wait.h>
+#include <sys/stat.h>
 #include "builtin.h"
 #include "hist.h"
 #include "intlist.h"
@@ -14,8 +17,10 @@
 #include "debug.h"
 #include "color.h"
 #include <subcmd/parse-options.h>
+#include "string2.h"
 #include "symbol.h"
 #include <linux/kernel.h>
+#include <subcmd/exec-cmd.h>
 
 static bool dont_fork;
 
@@ -43,6 +48,10 @@ static struct test generic_tests[] = {
                 .func = test__basic_mmap,
         },
         {
+                .desc = "Test data source output",
+                .func = test__mem,
+        },
+        {
                 .desc = "Parse event definition strings",
                 .func = test__parse_events,
         },
@@ -179,7 +188,7 @@ static struct test generic_tests[] = {
         },
         {
                 .desc = "Session topology",
-                .func = test_session_topology,
+                .func = test__session_topology,
         },
         {
                 .desc = "BPF filter",
@@ -325,7 +334,7 @@ static int run_test(struct test *test, int subtest)
                         }
                 }
 
-                err = test->func(subtest);
+                err = test->func(test, subtest);
                 if (!dont_fork)
                         exit(err);
         }
@@ -383,12 +392,143 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
         return err;
 }
 
+static const char *shell_test__description(char *description, size_t size,
+                                           const char *path, const char *name)
+{
+        FILE *fp;
+        char filename[PATH_MAX];
+
+        path__join(filename, sizeof(filename), path, name);
+        fp = fopen(filename, "r");
+        if (!fp)
+                return NULL;
+
+        description = fgets(description, size, fp);
+        fclose(fp);
+
+        return description ? trim(description + 1) : NULL;
+}
+
+#define for_each_shell_test(dir, ent)           \
+        while ((ent = readdir(dir)) != NULL)    \
+                if (ent->d_type == DT_REG && ent->d_name[0] != '.')
+
+static const char *shell_tests__dir(char *path, size_t size)
+{
+        const char *devel_dirs[] = { "./tools/perf/tests", "./tests", };
+        char *exec_path;
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
+                struct stat st;
+                if (!lstat(devel_dirs[i], &st)) {
+                        scnprintf(path, size, "%s/shell", devel_dirs[i]);
+                        if (!lstat(devel_dirs[i], &st))
+                                return path;
+                }
+        }
+
+        /* Then installed path. */
+        exec_path = get_argv_exec_path();
+        scnprintf(path, size, "%s/tests/shell", exec_path);
+        free(exec_path);
+        return path;
+}
+
+static int shell_tests__max_desc_width(void)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+        int width = 0;
+
+        if (path == NULL)
+                return -1;
+
+        dir = opendir(path);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                char bf[256];
+                const char *desc = shell_test__description(bf, sizeof(bf), path, ent->d_name);
+
+                if (desc) {
+                        int len = strlen(desc);
+
+                        if (width < len)
+                                width = len;
+                }
+        }
+
+        closedir(dir);
+        return width;
+}
+
+struct shell_test {
+        const char *dir;
+        const char *file;
+};
+
+static int shell_test__run(struct test *test, int subdir __maybe_unused)
+{
+        int err;
+        char script[PATH_MAX];
+        struct shell_test *st = test->priv;
+
+        path__join(script, sizeof(script), st->dir, st->file);
+
+        err = system(script);
+        if (!err)
+                return TEST_OK;
+
+        return WEXITSTATUS(err) == 2 ? TEST_SKIP : TEST_FAIL;
+}
+
+static int run_shell_tests(int argc, const char *argv[], int i, int width)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        struct shell_test st = {
+                .dir = shell_tests__dir(path_dir, sizeof(path_dir)),
+        };
+
+        if (st.dir == NULL)
+                return -1;
+
+        dir = opendir(st.dir);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                int curr = i++;
+                char desc[256];
+                struct test test = {
+                        .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name),
+                        .func = shell_test__run,
+                        .priv = &st,
+                };
+
+                if (!perf_test__matches(&test, curr, argc, argv))
+                        continue;
+
+                st.file = ent->d_name;
+                pr_info("%2d: %-*s:", i, width, test.desc);
+                test_and_print(&test, false, -1);
+        }
+
+        closedir(dir);
+        return 0;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
         struct test *t;
         unsigned int j;
         int i = 0;
-        int width = 0;
+        int width = shell_tests__max_desc_width();
 
         for_each_test(j, t) {
                 int len = strlen(t->desc);
@@ -455,6 +595,37 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
                 }
         }
 
+        return run_shell_tests(argc, argv, i, width);
+}
+
+static int perf_test__list_shell(int argc, const char **argv, int i)
+{
+        DIR *dir;
+        struct dirent *ent;
+        char path_dir[PATH_MAX];
+        const char *path = shell_tests__dir(path_dir, sizeof(path_dir));
+
+        if (path == NULL)
+                return -1;
+
+        dir = opendir(path);
+        if (!dir)
+                return -1;
+
+        for_each_shell_test(dir, ent) {
+                int curr = i++;
+                char bf[256];
+                struct test t = {
+                        .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name),
+                };
+
+                if (!perf_test__matches(&t, curr, argc, argv))
+                        continue;
+
+                pr_info("%2d: %s\n", i, t.desc);
+        }
+
+        closedir(dir);
         return 0;
 }
 
@@ -465,12 +636,17 @@ static int perf_test__list(int argc, const char **argv)
         int i = 0;
 
         for_each_test(j, t) {
-                if (argc > 1 && !strstr(t->desc, argv[1]))
+                int curr = i++;
+
+                if (!perf_test__matches(t, curr, argc, argv) ||
+                    (t->is_supported && !t->is_supported()))
                         continue;
 
-                pr_info("%2d: %s\n", ++i, t->desc);
+                pr_info("%2d: %s\n", i, t->desc);
         }
 
+        perf_test__list_shell(argc, argv, i);
+
         return 0;
 }
 
@@ -498,7 +674,7 @@ int cmd_test(int argc, const char **argv)
 
         argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
         if (argc >= 1 && !strcmp(argv[0], "list"))
-                return perf_test__list(argc, argv);
+                return perf_test__list(argc - 1, argv + 1);
 
         symbol_conf.priv_size = sizeof(int);
         symbol_conf.sort_by_name = true;
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
index c5bb2203f5a9..c60ec916f0f2 100644
--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -33,12 +33,12 @@ const char *test__clang_subtest_get_desc(int i)
 }
 
 #ifndef HAVE_LIBCLANGLLVM_SUPPORT
-int test__clang(int i __maybe_unused)
+int test__clang(struct test *test __maybe_unused, int i __maybe_unused)
 {
         return TEST_SKIP;
 }
 #else
-int test__clang(int i)
+int test__clang(struct test *test __maybe_unused, int i)
 {
         if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table))
                 return TEST_FAIL;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 94b7c7b02bde..466a462b26d1 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -237,6 +237,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
         thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
         if (!al.map || !al.map->dso) {
+                if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
+                        pr_debug("Hypervisor address can not be resolved - skipping\n");
+                        return 0;
+                }
+
                 pr_debug("thread__find_addr_map failed\n");
                 return -1;
         }
@@ -673,7 +678,7 @@ out_err:
         return err;
 }
 
-int test__code_reading(int subtest __maybe_unused)
+int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 4478773cdb97..199702252270 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -72,7 +72,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 }
 
 
-int test__cpu_map_synthesize(int subtest __maybe_unused)
+int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct cpu_map *cpus;
 
@@ -106,7 +106,7 @@ static int cpu_map_print(const char *str)
         return !strcmp(buf, str);
 }
 
-int test__cpu_map_print(int subtest __maybe_unused)
+int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
         TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 8f08df5861cb..30aead42d136 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -112,7 +112,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine)
         return fd;
 }
 
-int test__dso_data(int subtest __maybe_unused)
+int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         struct dso *dso;
@@ -247,7 +247,7 @@ static int set_fd_limit(int n)
         return setrlimit(RLIMIT_NOFILE, &rlim);
 }
 
-int test__dso_data_cache(int subtest __maybe_unused)
+int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
@@ -307,7 +307,7 @@ int test__dso_data_cache(int subtest __maybe_unused)
         return 0;
 }
 
-int test__dso_data_reopen(int subtest __maybe_unused)
+int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine machine;
         long nr_end, nr = open_files_cnt();
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 3e56d08f7995..9ba1d216a89f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -6,7 +6,7 @@
 #include "debug.h"
 #include "machine.h"
 #include "event.h"
-#include "unwind.h"
+#include "../util/unwind.h"
 #include "perf_regs.h"
 #include "map.h"
 #include "thread.h"
@@ -154,7 +154,7 @@ static noinline int krava_1(struct thread *thread)
         return krava_2(thread);
 }
 
-int test__dwarf_unwind(int subtest __maybe_unused)
+int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machine *machine;
         struct thread *thread;
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 634f20c631d8..b82b981c3259 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -213,7 +213,7 @@ out_err:
  * and checks that enabled and running times
  * match.
  */
-int test__event_times(int subtest __maybe_unused)
+int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err, ret = 0;
 
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index 63ecf21750eb..9484da2ec6b4 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -76,7 +76,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__event_update(int subtest __maybe_unused)
+int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evlist *evlist;
         struct perf_evsel *evsel;
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index d2bea6f780f8..d32759b6e38a 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -97,7 +97,7 @@ out_delete_evlist:
 #define perf_evsel__name_array_test(names) \
         __perf_evsel__name_array_test(names, ARRAY_SIZE(names))
 
-int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused)
+int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = 0, ret = 0;
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 1984b3bbfe15..5fc906d26c5c 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
         return ret;
 }
 
-int test__perf_evsel__tp_sched_test(int subtest __maybe_unused)
+int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
         int ret = 0;
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 6c6a3749aaf6..cb251bf523e7 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -13,7 +13,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2)
         return 0;
 }
 
-int test__expr(int subtest __maybe_unused)
+int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         const char *p;
         const char **other;
@@ -31,6 +31,11 @@ int test__expr(int subtest __maybe_unused)
         ret |= test(&ctx, "(BAR/2)%2", 1);
         ret |= test(&ctx, "1 - -4",  5);
         ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4",  5);
+        ret |= test(&ctx, "1-1 | 1", 1);
+        ret |= test(&ctx, "1-1 & 1", 0);
+        ret |= test(&ctx, "min(1,2) + 1", 2);
+        ret |= test(&ctx, "max(1,2) + 1", 3);
+        ret |= test(&ctx, "1+1 if 3*4 else 0", 2);
 
         if (ret)
                 return ret;
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index bc5982f42dc3..7d3a9e2ff897 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -26,7 +26,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
         return printed + fdarray__fprintf(fda, fp);
 }
 
-int test__fdarray__filter(int subtest __maybe_unused)
+int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(5, 5);
@@ -104,7 +104,7 @@ out:
         return err;
 }
 
-int test__fdarray__add(int subtest __maybe_unused)
+int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct fdarray *fda = fdarray__new(2, 2);
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index d549a9f2c41b..8d19c0200cb7 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -687,7 +687,7 @@ out:
         return err;
 }
 
-int test__hists_cumulate(int subtest __maybe_unused)
+int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index df9c91f49af1..755ca551b810 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -101,7 +101,7 @@ out:
         return TEST_FAIL;
 }
 
-int test__hists_filter(int subtest __maybe_unused)
+int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index a26cbb79e988..073c9c2856bc 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other)
         return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-int test__hists_link(int subtest __maybe_unused)
+int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         struct hists *hists, *first_hists;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 06e5080182d3..282d62eaebe2 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -573,7 +573,7 @@ out:
         return err;
 }
 
-int test__hists_output(int subtest __maybe_unused)
+int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = TEST_FAIL;
         struct machines machines;
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
index a5192f6a20d7..38f765767587 100644
--- a/tools/perf/tests/is_printable_array.c
+++ b/tools/perf/tests/is_printable_array.c
@@ -4,7 +4,7 @@
 #include "debug.h"
 #include "print_binary.h"
 
-int test__is_printable_array(int subtest __maybe_unused)
+int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
         char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 614e45a3c603..739428603b71 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -49,7 +49,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  * when an event is disabled but a dummy software event is not disabled.  If the
  * test passes %0 is returned, otherwise %-1 is returned.
  */
-int test__keep_tracking(int subtest __maybe_unused)
+int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .mmap_pages          = UINT_MAX,
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index 6cd9e5107f77..8b9d4ba06c0e 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -50,7 +50,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 #define M(path, c, e) \
         TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
-int test__kmod_path__parse(int subtest __maybe_unused)
+int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         /* path                alloc_name  alloc_ext   kmod  comp   name     ext */
         T("/xxxx/xxxx/x-x.ko", true      , true      , true, false, "[x_x]", NULL);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 482b5365e68d..5187b50dbafe 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -132,7 +132,7 @@ out:
         return ret;
 }
 
-int test__llvm(int subtest)
+int test__llvm(struct test *test __maybe_unused, int subtest)
 {
         int ret;
         void *obj_buf = NULL;
diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c
new file mode 100644
index 000000000000..21952e1e6e6d
--- /dev/null
+++ b/tools/perf/tests/mem.c
@@ -0,0 +1,56 @@
+#include "util/mem-events.h"
+#include "util/symbol.h"
+#include "linux/perf_event.h"
+#include "util/debug.h"
+#include "tests.h"
+#include <string.h>
+
+static int check(union perf_mem_data_src data_src,
+                  const char *string)
+{
+        char out[100];
+        char failure[100];
+        struct mem_info mi = { .data_src = data_src };
+
+        int n;
+
+        n = perf_mem__snp_scnprintf(out, sizeof out, &mi);
+        n += perf_mem__lvl_scnprintf(out + n, sizeof out - n, &mi);
+        snprintf(failure, sizeof failure, "unexpected %s", out);
+        TEST_ASSERT_VAL(failure, !strcmp(string, out));
+        return 0;
+}
+
+int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused)
+{
+        int ret = 0;
+        union perf_mem_data_src src;
+
+        memset(&src, 0, sizeof(src));
+
+        src.mem_lvl = PERF_MEM_LVL_HIT;
+        src.mem_lvl_num = 4;
+
+        ret |= check(src, "N/AL4 hit");
+
+        src.mem_remote = 1;
+
+        ret |= check(src, "N/ARemote L4 hit");
+
+        src.mem_lvl = PERF_MEM_LVL_MISS;
+        src.mem_lvl_num = PERF_MEM_LVLNUM_PMEM;
+        src.mem_remote = 0;
+
+        ret |= check(src, "N/APMEM miss");
+
+        src.mem_remote = 1;
+
+        ret |= check(src, "N/ARemote PMEM miss");
+
+        src.mem_snoopx = PERF_MEM_SNOOPX_FWD;
+        src.mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+
+        ret |= check(src , "FwdRemote RAM miss");
+
+        return ret;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 15c770856aac..bc8a70ee46d8 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -22,7 +22,7 @@
  * Then it checks if the number of syscalls reported as perf events by
  * the kernel corresponds to the number of syscalls made.
  */
-int test__basic_mmap(int subtest __maybe_unused)
+int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 6ea4d8a5d26b..f94a4196e7c9 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -221,7 +221,7 @@ static int mmap_events(synth_cb synth)
  *
  * by using all thread objects.
  */
-int test__mmap_thread_lookup(int subtest __maybe_unused)
+int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         /* perf_event__synthesize_threads synthesize */
         TEST_ASSERT_VAL("failed with sythesizing all",
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 1a74dd9fd067..9cf1c35f2ad0 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -16,7 +16,7 @@
 #include "debug.h"
 #include "stat.h"
 
-int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
+int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1, fd, cpu;
         struct cpu_map *cpus;
@@ -115,7 +115,7 @@ int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused)
 
         perf_evsel__free_counts(evsel);
 out_close_fd:
-        perf_evsel__close_fd(evsel, 1, threads->nr);
+        perf_evsel__close_fd(evsel);
 out_evsel_delete:
         perf_evsel__delete(evsel);
 out_thread_map_delete:
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 9788fac91095..b6ee1c41f45d 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -14,7 +14,7 @@
 #define AT_FDCWD       -100
 #endif
 
-int test__syscall_openat_tp_fields(int subtest __maybe_unused)
+int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index e44506e21ee7..9dc5c5d37553 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -10,7 +10,7 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__openat_syscall_event(int subtest __maybe_unused)
+int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1, fd;
         struct perf_evsel *evsel;
@@ -56,7 +56,7 @@ int test__openat_syscall_event(int subtest __maybe_unused)
 
         err = 0;
 out_close_fd:
-        perf_evsel__close_fd(evsel, 1, threads->nr);
+        perf_evsel__close_fd(evsel);
 out_evsel_delete:
         perf_evsel__delete(evsel);
 out_thread_map_delete:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 812a053d1941..0f0b025faa4b 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1810,7 +1810,7 @@ static int test_pmu_events(void)
         return ret;
 }
 
-int test__parse_events(int subtest __maybe_unused)
+int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret1, ret2 = 0;
 
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index c6207db09f12..91867dcc39f0 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -68,7 +68,7 @@ struct test_attr_event {
  *
  * Return: %0 on success, %-1 if the test fails.
  */
-int test__parse_no_sample_id_all(int subtest __maybe_unused)
+int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err;
 
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index 665ecc19671c..bf2517d6de70 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -27,7 +27,7 @@ static void the_hook(void *_hook_flags)
         *p = 0;
 }
 
-int test__perf_hooks(int subtest __maybe_unused)
+int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int hook_flags = 0;
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index d37cd9588cc0..19b650064b70 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -37,7 +37,7 @@ realloc:
         return cpu;
 }
 
-int test__PERF_RECORD(int subtest __maybe_unused)
+int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct record_opts opts = {
                 .target = {
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index a6d7aef30030..9f7f589f9c54 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -135,7 +135,7 @@ static struct list_head *test_terms_list(void)
         return &terms;
 }
 
-int test__pmu(int subtest __maybe_unused)
+int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char *format = test_format_dir_get();
         LIST_HEAD(formats);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index fa79509da535..598a7e058ad4 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -9,7 +9,7 @@
 
 extern int verbose;
 
-int test__python_use(int subtest __maybe_unused)
+int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char *cmd;
         int ret;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index bac5c3885b3b..c3858487159d 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -141,6 +141,9 @@ static bool samples_same(const struct perf_sample *s1,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                COMP(phys_addr);
+
         return true;
 }
 
@@ -206,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
                         .mask   = sample_regs,
                         .regs   = regs,
                 },
+                .phys_addr      = 113,
         };
         struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
         struct perf_sample sample_out;
@@ -292,7 +296,7 @@ out_free:
  * checks sample format bits separately and together.  If the test passes %0 is
  * returned, otherwise %-1 is returned.
  */
-int test__sample_parsing(int subtest __maybe_unused)
+int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
         u64 sample_type;
@@ -305,7 +309,7 @@ int test__sample_parsing(int subtest __maybe_unused)
          * were added.  Please actually update the test rather than just change
          * the condition below.
          */
-        if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+        if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) {
                 pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
                 return -1;
         }
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index 06eda675ae2c..a9903d9b8bc2 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -33,7 +33,7 @@ static int build_id_cache__add_file(const char *filename)
         }
 
         build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
-        err = build_id_cache__add_s(sbuild_id, filename, false, false);
+        err = build_id_cache__add_s(sbuild_id, filename, NULL, false, false);
         if (err < 0)
                 pr_debug("Failed to add build id cache of %s\n", filename);
         return err;
@@ -54,7 +54,7 @@ static char *get_self_path(void)
 static int search_cached_probe(const char *target,
                                const char *group, const char *event)
 {
-        struct probe_cache *cache = probe_cache__new(target);
+        struct probe_cache *cache = probe_cache__new(target, NULL);
         int ret = 0;
 
         if (!cache) {
@@ -71,7 +71,7 @@ static int search_cached_probe(const char *target,
         return ret;
 }
 
-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
         int ret = TEST_FAIL;
         char __tempdir[] = "./test-buildid-XXXXXX";
@@ -83,6 +83,8 @@ int test__sdt_event(int subtests __maybe_unused)
         }
         /* Note that buildid_dir must be an absolute path */
         tempdir = realpath(__tempdir, NULL);
+        if (tempdir == NULL)
+                goto error_rmdir;
 
         /* At first, scan itself */
         set_buildid_dir(tempdir);
@@ -100,14 +102,14 @@ int test__sdt_event(int subtests __maybe_unused)
 
 error_rmdir:
         /* Cleanup temporary buildid dir */
-        rm_rf(tempdir);
+        rm_rf(__tempdir);
 error:
         free(tempdir);
         free(myself);
         return ret;
 }
 #else
-int test__sdt_event(int subtests __maybe_unused)
+int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
 {
         pr_debug("Skip SDT event test because SDT support is not compiled\n");
         return TEST_SKIP;
diff --git a/tools/perf/tests/shell/lib/probe.sh b/tools/perf/tests/shell/lib/probe.sh
new file mode 100644
index 000000000000..6293cc660947
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe.sh
@@ -0,0 +1,6 @@
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+skip_if_no_perf_probe() {
+        perf probe 2>&1 | grep -q 'is not a perf-command' && return 2
+        return 0
+}
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
new file mode 100644
index 000000000000..30a950c9d407
--- /dev/null
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -0,0 +1,23 @@
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+perf probe -l 2>&1 | grep -q probe:vfs_getname
+had_vfs_getname=$?
+
+cleanup_probe_vfs_getname() {
+        if [ $had_vfs_getname -eq 1 ] ; then
+                perf probe -q -d probe:vfs_getname
+        fi
+}
+
+add_probe_vfs_getname() {
+        local verbose=$1
+        if [ $had_vfs_getname -eq 1 ] ; then
+                line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/')
+                perf probe $verbose "vfs_getname=getname_flags:${line} pathname=result->name:string"
+        fi
+}
+
+skip_if_no_debuginfo() {
+        add_probe_vfs_getname -v 2>&1 | egrep -q "^(Failed to find the path for kernel|Debuginfo-analysis is not supported)" && return 2
+        return 1
+}
diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh
new file mode 100755
index 000000000000..9b7635184dc2
--- /dev/null
+++ b/tools/perf/tests/shell/probe_vfs_getname.sh
@@ -0,0 +1,14 @@
+# Add vfs_getname probe to get syscall args filenames
+#
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
new file mode 100755
index 000000000000..ba29535b8580
--- /dev/null
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -0,0 +1,41 @@
+# Use vfs_getname probe to get syscall args filenames
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf record' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname probe in the generated
+# perf.data file, with the temp file name as the pathname argument.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+record_open_file() {
+        echo "Recording open file:"
+        perf record -o ${perfdata} -e probe:vfs_getname touch $file
+}
+
+perf_script_filenames() {
+        echo "Looking at perf.data file for vfs_getname records for the file we touched:"
+        perf script -i ${perfdata} | \
+        egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname: +\([[:xdigit:]]+\) +pathname=\"${file}\""
+}
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+        exit $err
+fi
+
+record_open_file && perf_script_filenames
+err=$?
+rm -f ${perfdata}
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
new file mode 100755
index 000000000000..462fc755092e
--- /dev/null
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -0,0 +1,43 @@
+# probe libc's inet_pton & backtrace it with ping
+
+# Installs a probe on libc's inet_pton function, that will use uprobes,
+# then use 'perf trace' on a ping to localhost asking for just one packet
+# with the a backtrace 3 levels deep, check that it is what we expect.
+# This needs no debuginfo package, all is done using the libc ELF symtab
+# and the CFI info in the binaries.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+trace_libc_inet_pton_backtrace() {
+        idx=0
+        expected[0]="PING.*bytes"
+        expected[1]="64 bytes from ::1.*"
+        expected[2]=".*ping statistics.*"
+        expected[3]=".*packets transmitted.*"
+        expected[4]="rtt min.*"
+        expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
+        expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+        expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+        expected[8]=".*\(.*/bin/ping.*\)$"
+
+        perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+                echo $line
+                echo "$line" | egrep -q "${expected[$idx]}"
+                if [ $? -ne 0 ] ; then
+                        printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+                        exit 1
+                fi
+                let idx+=1
+                [ $idx -eq 9 ] && break
+        done
+}
+
+skip_if_no_perf_probe && \
+perf probe -q /lib64/libc-*.so inet_pton && \
+trace_libc_inet_pton_backtrace
+err=$?
+rm -f ${file}
+perf probe -q -d probe_libc:inet_pton
+exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
new file mode 100755
index 000000000000..2e68c5f120da
--- /dev/null
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -0,0 +1,35 @@
+# Check open filename arg using perf trace + vfs_getname
+
+# Uses the 'perf test shell' library to add probe:vfs_getname to the system
+# then use it with 'perf trace' using 'touch' to write to a temp file, then
+# checks that that was captured by the vfs_getname was used by 'perf trace',
+# that already handles "probe:vfs_getname" if present, and used in the
+# "open" syscall "filename" argument beautifier.
+
+# Arnaldo Carvalho de Melo <acme@kernel.org>, 2017
+
+. $(dirname $0)/lib/probe.sh
+
+skip_if_no_perf_probe || exit 2
+
+. $(dirname $0)/lib/probe_vfs_getname.sh
+
+file=$(mktemp /tmp/temporary_file.XXXXX)
+
+trace_open_vfs_getname() {
+        perf trace -e open touch $file 2>&1 | \
+        egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+}
+
+
+add_probe_vfs_getname || skip_if_no_debuginfo
+err=$?
+if [ $err -ne 0 ] ; then
+        exit $err
+fi
+
+trace_open_vfs_getname
+err=$?
+rm -f ${file}
+cleanup_probe_vfs_getname
+exit $err
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 6a20ff2326bb..7f988a939036 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -45,7 +45,7 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat_config(int subtest __maybe_unused)
+int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_stat_config stat_config = {
                 .aggr_mode      = AGGR_CORE,
@@ -75,7 +75,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat(int subtest __maybe_unused)
+int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct perf_counts_values count;
 
@@ -101,7 +101,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__synthesize_stat_round(int subtest __maybe_unused)
+int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         TEST_ASSERT_VAL("failed to synthesize stat_config",
                 !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 828494db4a19..d88511f6072c 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -124,7 +124,7 @@ out_delete_evlist:
         return err;
 }
 
-int test__sw_clock_freq(int subtest __maybe_unused)
+int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int ret;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 65474fd80da7..2acd78555192 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -306,7 +306,7 @@ out_free_nodes:
  * evsel->system_wide and evsel->tracking flags (respectively) with other events
  * sometimes enabled or disabled.
  */
-int test__switch_tracking(int subtest __maybe_unused)
+int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         const char *sched_switch = "sched:sched_switch";
         struct switch_tracking switch_tracking = { .tids = NULL, };
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index cf00ebad2ef5..f0881d0dd9c9 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -32,7 +32,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
  * if the number of exit event reported by the kernel is 1 or not
  * in order to check the kernel returns correct number of event.
  */
-int test__task_exit(int subtest __maybe_unused)
+int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         union perf_event *event;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 577363809c9b..921412a6a880 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -28,77 +28,79 @@ enum {
 
 struct test {
         const char *desc;
-        int (*func)(int subtest);
+        int (*func)(struct test *test, int subtest);
         struct {
                 bool skip_if_fail;
                 int (*get_nr)(void);
                 const char *(*get_desc)(int subtest);
         } subtest;
         bool (*is_supported)(void);
+        void *priv;
 };
 
 /* Tests */
-int test__vmlinux_matches_kallsyms(int subtest);
-int test__openat_syscall_event(int subtest);
-int test__openat_syscall_event_on_all_cpus(int subtest);
-int test__basic_mmap(int subtest);
-int test__PERF_RECORD(int subtest);
-int test__perf_evsel__roundtrip_name_test(int subtest);
-int test__perf_evsel__tp_sched_test(int subtest);
-int test__syscall_openat_tp_fields(int subtest);
-int test__pmu(int subtest);
-int test__attr(int subtest);
-int test__dso_data(int subtest);
-int test__dso_data_cache(int subtest);
-int test__dso_data_reopen(int subtest);
-int test__parse_events(int subtest);
-int test__hists_link(int subtest);
-int test__python_use(int subtest);
-int test__bp_signal(int subtest);
-int test__bp_signal_overflow(int subtest);
-int test__task_exit(int subtest);
-int test__sw_clock_freq(int subtest);
-int test__code_reading(int subtest);
-int test__sample_parsing(int subtest);
-int test__keep_tracking(int subtest);
-int test__parse_no_sample_id_all(int subtest);
-int test__dwarf_unwind(int subtest);
-int test__expr(int subtest);
-int test__hists_filter(int subtest);
-int test__mmap_thread_lookup(int subtest);
-int test__thread_mg_share(int subtest);
-int test__hists_output(int subtest);
-int test__hists_cumulate(int subtest);
-int test__switch_tracking(int subtest);
-int test__fdarray__filter(int subtest);
-int test__fdarray__add(int subtest);
-int test__kmod_path__parse(int subtest);
-int test__thread_map(int subtest);
-int test__llvm(int subtest);
+int test__vmlinux_matches_kallsyms(struct test *test, int subtest);
+int test__openat_syscall_event(struct test *test, int subtest);
+int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest);
+int test__basic_mmap(struct test *test, int subtest);
+int test__PERF_RECORD(struct test *test, int subtest);
+int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest);
+int test__perf_evsel__tp_sched_test(struct test *test, int subtest);
+int test__syscall_openat_tp_fields(struct test *test, int subtest);
+int test__pmu(struct test *test, int subtest);
+int test__attr(struct test *test, int subtest);
+int test__dso_data(struct test *test, int subtest);
+int test__dso_data_cache(struct test *test, int subtest);
+int test__dso_data_reopen(struct test *test, int subtest);
+int test__parse_events(struct test *test, int subtest);
+int test__hists_link(struct test *test, int subtest);
+int test__python_use(struct test *test, int subtest);
+int test__bp_signal(struct test *test, int subtest);
+int test__bp_signal_overflow(struct test *test, int subtest);
+int test__task_exit(struct test *test, int subtest);
+int test__mem(struct test *test, int subtest);
+int test__sw_clock_freq(struct test *test, int subtest);
+int test__code_reading(struct test *test, int subtest);
+int test__sample_parsing(struct test *test, int subtest);
+int test__keep_tracking(struct test *test, int subtest);
+int test__parse_no_sample_id_all(struct test *test, int subtest);
+int test__dwarf_unwind(struct test *test, int subtest);
+int test__expr(struct test *test, int subtest);
+int test__hists_filter(struct test *test, int subtest);
+int test__mmap_thread_lookup(struct test *test, int subtest);
+int test__thread_mg_share(struct test *test, int subtest);
+int test__hists_output(struct test *test, int subtest);
+int test__hists_cumulate(struct test *test, int subtest);
+int test__switch_tracking(struct test *test, int subtest);
+int test__fdarray__filter(struct test *test, int subtest);
+int test__fdarray__add(struct test *test, int subtest);
+int test__kmod_path__parse(struct test *test, int subtest);
+int test__thread_map(struct test *test, int subtest);
+int test__llvm(struct test *test, int subtest);
 const char *test__llvm_subtest_get_desc(int subtest);
 int test__llvm_subtest_get_nr(void);
-int test__bpf(int subtest);
+int test__bpf(struct test *test, int subtest);
 const char *test__bpf_subtest_get_desc(int subtest);
 int test__bpf_subtest_get_nr(void);
-int test_session_topology(int subtest);
-int test__thread_map_synthesize(int subtest);
-int test__thread_map_remove(int subtest);
-int test__cpu_map_synthesize(int subtest);
-int test__synthesize_stat_config(int subtest);
-int test__synthesize_stat(int subtest);
-int test__synthesize_stat_round(int subtest);
-int test__event_update(int subtest);
-int test__event_times(int subtest);
-int test__backward_ring_buffer(int subtest);
-int test__cpu_map_print(int subtest);
-int test__sdt_event(int subtest);
-int test__is_printable_array(int subtest);
-int test__bitmap_print(int subtest);
-int test__perf_hooks(int subtest);
-int test__clang(int subtest);
+int test__session_topology(struct test *test, int subtest);
+int test__thread_map_synthesize(struct test *test, int subtest);
+int test__thread_map_remove(struct test *test, int subtest);
+int test__cpu_map_synthesize(struct test *test, int subtest);
+int test__synthesize_stat_config(struct test *test, int subtest);
+int test__synthesize_stat(struct test *test, int subtest);
+int test__synthesize_stat_round(struct test *test, int subtest);
+int test__event_update(struct test *test, int subtest);
+int test__event_times(struct test *test, int subtest);
+int test__backward_ring_buffer(struct test *test, int subtest);
+int test__cpu_map_print(struct test *test, int subtest);
+int test__sdt_event(struct test *test, int subtest);
+int test__is_printable_array(struct test *test, int subtest);
+int test__bitmap_print(struct test *test, int subtest);
+int test__perf_hooks(struct test *test, int subtest);
+int test__clang(struct test *test, 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);
+int test__unit_number__scnprint(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index a63d6945807b..b3423c744f46 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -9,7 +9,7 @@
 #define NAME    (const char *) "perf"
 #define NAMEUL  (unsigned long) NAME
 
-int test__thread_map(int subtest __maybe_unused)
+int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *map;
 
@@ -76,7 +76,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-int test__thread_map_synthesize(int subtest __maybe_unused)
+int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *threads;
 
@@ -95,7 +95,7 @@ int test__thread_map_synthesize(int subtest __maybe_unused)
         return 0;
 }
 
-int test__thread_map_remove(int subtest __maybe_unused)
+int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct thread_map *threads;
         char *str;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 76686dd6f5ec..b9c7f58db6c4 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -4,7 +4,7 @@
 #include "map.h"
 #include "debug.h"
 
-int test__thread_mg_share(int subtest __maybe_unused)
+int test__thread_mg_share(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         struct machines machines;
         struct machine *machine;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 803f893550d6..19b0561fd6f6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -86,7 +86,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
         return 0;
 }
 
-int test_session_topology(int subtest __maybe_unused)
+int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         char path[PATH_MAX];
         struct cpu_map *map;
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
index 44589de084b8..15cd1cf8c129 100644
--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -5,7 +5,7 @@
 #include "units.h"
 #include "debug.h"
 
-int test__unit_number__scnprint(int subtest __maybe_unused)
+int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused)
 {
         struct {
                 u64              n;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 8456175fc234..86cb8868f67f 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -11,7 +11,7 @@
 
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
-int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
+int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
         int err = -1;
         struct rb_node *nd;
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index be95ac6ce845..175d633c6b49 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -1 +1,7 @@
+libperf-y += clone.o
+libperf-y += fcntl.o
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
+libperf-y += ioctl.o
+endif
+libperf-y += pkey_alloc.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index cf50be3f17a4..4b58581a6053 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -1,13 +1,44 @@
 #ifndef _PERF_TRACE_BEAUTY_H
 #define _PERF_TRACE_BEAUTY_H
 
+#include <linux/kernel.h>
 #include <linux/types.h>
 
+struct strarray {
+        int         offset;
+        int         nr_entries;
+        const char **entries;
+};
+
+#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
+}
+
+#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
+        .offset     = off, \
+        .nr_entries = ARRAY_SIZE(array), \
+        .entries = array, \
+}
+
+size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+
 struct trace;
 struct thread;
 
+/**
+ * @val: value of syscall argument being formatted
+ * @args: All the args, use syscall_args__val(arg, nth) to access one
+ * @thread: tid state (maps, pid, tid, etc)
+ * @trace: 'perf trace' internals: all threads, etc
+ * @parm: private area, may be an strarray, for instance
+ * @idx: syscall arg idx (is this the first?)
+ * @mask: a syscall arg may mask another arg, see syscall_arg__scnprintf_futex_op
+ */
+
 struct syscall_arg {
         unsigned long val;
+        unsigned char *args;
         struct thread *thread;
         struct trace  *trace;
         void          *parm;
@@ -15,10 +46,53 @@ struct syscall_arg {
         u8            mask;
 };
 
+unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx);
+
+size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STRARRAYS syscall_arg__scnprintf_strarrays
+
+size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FD syscall_arg__scnprintf_fd
+
+size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_HEX syscall_arg__scnprintf_hex
+
+size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_INT syscall_arg__scnprintf_int
+
+size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_LONG syscall_arg__scnprintf_long
+
+size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PID syscall_arg__scnprintf_pid
+
+size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_CLONE_FLAGS syscall_arg__scnprintf_clone_flags
+
+size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FCNTL_CMD syscall_arg__scnprintf_fcntl_cmd
+
+size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FCNTL_ARG syscall_arg__scnprintf_fcntl_arg
+
+size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
+
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
+
+size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
 size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
 
+size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size);
+
+void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
+                                    size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg));
+
 #endif /* _PERF_TRACE_BEAUTY_H */
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
new file mode 100644
index 000000000000..d64d049ab991
--- /dev/null
+++ b/tools/perf/trace/beauty/clone.c
@@ -0,0 +1,75 @@
+/*
+ * trace/beauty/cone.c
+ *
+ *  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 "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <uapi/linux/sched.h>
+
+static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+        int printed = 0;
+
+#define P_FLAG(n) \
+        if (flags & CLONE_##n) { \
+                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+                flags &= ~CLONE_##n; \
+        }
+
+        P_FLAG(VM);
+        P_FLAG(FS);
+        P_FLAG(FILES);
+        P_FLAG(SIGHAND);
+        P_FLAG(PTRACE);
+        P_FLAG(VFORK);
+        P_FLAG(PARENT);
+        P_FLAG(THREAD);
+        P_FLAG(NEWNS);
+        P_FLAG(SYSVSEM);
+        P_FLAG(SETTLS);
+        P_FLAG(PARENT_SETTID);
+        P_FLAG(CHILD_CLEARTID);
+        P_FLAG(DETACHED);
+        P_FLAG(UNTRACED);
+        P_FLAG(CHILD_SETTID);
+        P_FLAG(NEWCGROUP);
+        P_FLAG(NEWUTS);
+        P_FLAG(NEWIPC);
+        P_FLAG(NEWUSER);
+        P_FLAG(NEWPID);
+        P_FLAG(NEWNET);
+        P_FLAG(IO);
+#undef P_FLAG
+
+        if (flags)
+                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+        return printed;
+}
+
+size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long flags = arg->val;
+        enum syscall_clone_args {
+                SCC_FLAGS         = (1 << 0),
+                SCC_CHILD_STACK   = (1 << 1),
+                SCC_PARENT_TIDPTR = (1 << 2),
+                SCC_CHILD_TIDPTR  = (1 << 3),
+                SCC_TLS           = (1 << 4),
+        };
+        if (!(flags & CLONE_PARENT_SETTID))
+                arg->mask |= SCC_PARENT_TIDPTR;
+
+        if (!(flags & (CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID)))
+                arg->mask |= SCC_CHILD_TIDPTR;
+
+        if (!(flags & CLONE_SETTLS))
+                arg->mask |= SCC_TLS;
+
+        return clone__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
new file mode 100755
index 000000000000..2149d3a98e42
--- /dev/null
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -0,0 +1,13 @@
+#!/bin/sh
+
+drm_header_dir=$1
+printf "#ifndef DRM_COMMAND_BASE\n"
+grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+printf "#endif\n"
+
+printf "static const char *drm_ioctl_cmds[] = {\n"
+grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+        sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[      ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/     [\2] = "\1",/g'
+grep "^#define DRM_I915_[A-Z_0-9]\+[     ]\+0x" $drm_header_dir/i915_drm.h | \
+        sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[       ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
new file mode 100644
index 000000000000..9e8900c13cb1
--- /dev/null
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -0,0 +1,100 @@
+/*
+ * trace/beauty/fcntl.c
+ *
+ *  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 "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <uapi/linux/fcntl.h>
+
+static size_t fcntl__scnprintf_getfd(unsigned long val, char *bf, size_t size)
+{
+        return scnprintf(bf, size, "%s", val ? "CLOEXEC" : "0");
+}
+
+static size_t syscall_arg__scnprintf_fcntl_getfd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return fcntl__scnprintf_getfd(arg->val, bf, size);
+}
+
+static size_t fcntl__scnprintf_getlease(unsigned long val, char *bf, size_t size)
+{
+        static const char *fcntl_setlease[] = { "RDLCK", "WRLCK", "UNLCK", };
+        static DEFINE_STRARRAY(fcntl_setlease);
+
+        return strarray__scnprintf(&strarray__fcntl_setlease, bf, size, "%x", val);
+}
+
+static size_t syscall_arg__scnprintf_fcntl_getlease(char *bf, size_t size, struct syscall_arg *arg)
+{
+        return fcntl__scnprintf_getlease(arg->val, bf, size);
+}
+
+size_t syscall_arg__scnprintf_fcntl_cmd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        if (arg->val == F_GETFL) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_open_flags);
+                goto mask_arg;
+        }
+        if (arg->val == F_GETFD) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getfd);
+                goto mask_arg;
+        }
+        if (arg->val == F_DUPFD_CLOEXEC || arg->val == F_DUPFD) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fd);
+                goto out;
+        }
+        if (arg->val == F_GETOWN) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_pid);
+                goto mask_arg;
+        }
+        if (arg->val == F_GETLEASE) {
+                syscall_arg__set_ret_scnprintf(arg, syscall_arg__scnprintf_fcntl_getlease);
+                goto mask_arg;
+        }
+        /*
+         * Some commands ignore the third fcntl argument, "arg", so mask it
+         */
+        if (arg->val == F_GET_SEALS ||
+            arg->val == F_GETSIG) {
+mask_arg:
+                arg->mask |= (1 << 2);
+        }
+out:
+        return syscall_arg__scnprintf_strarrays(bf, size, arg);
+}
+
+size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int cmd = syscall_arg__val(arg, 1);
+
+        if (cmd == F_DUPFD)
+                return syscall_arg__scnprintf_fd(bf, size, arg);
+
+        if (cmd == F_SETFD)
+                return fcntl__scnprintf_getfd(arg->val, bf, size);
+
+        if (cmd == F_SETFL)
+                return open__scnprintf_flags(arg->val, bf, size);
+
+        if (cmd == F_SETOWN)
+                return syscall_arg__scnprintf_pid(bf, size, arg);
+
+        if (cmd == F_SETLEASE)
+                return fcntl__scnprintf_getlease(arg->val, bf, size);
+        /*
+         * We still don't grab the contents of pointers on entry or exit,
+         * so just print them as hex numbers
+         */
+        if (cmd == F_SETLK || cmd == F_SETLKW || cmd == F_GETLK ||
+            cmd == F_OFD_SETLK || cmd == F_OFD_SETLKW || cmd == F_OFD_GETLK ||
+            cmd == F_GETOWN_EX || cmd == F_SETOWN_EX ||
+            cmd == F_GET_RW_HINT || cmd == F_SET_RW_HINT ||
+            cmd == F_GET_FILE_RW_HINT || cmd == F_SET_FILE_RW_HINT)
+                return syscall_arg__scnprintf_hex(bf, size, arg);
+
+        return syscall_arg__scnprintf_long(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
new file mode 100644
index 000000000000..1be3b4cf0827
--- /dev/null
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -0,0 +1,162 @@
+/*
+ * trace/beauty/ioctl.c
+ *
+ *  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 "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+
+/*
+ * FIXME: to support all arches we have to improve this, for
+ * now, to build on older systems without things like TIOCGEXCL,
+ * get it directly from our copy.
+ *
+ * Right now only x86 is being supported for beautifying ioctl args
+ * in 'perf trace', see tools/perf/trace/beauty/Build and builtin-trace.c
+ */
+#include <uapi/asm-generic/ioctls.h>
+
+static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
+{
+        static const char *ioctl_tty_cmd[] = {
+        "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+        "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL", "TIOCSCTTY",
+        "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI", "TIOCGWINSZ", "TIOCSWINSZ",
+        "TIOCMGET", "TIOCMBIS", "TIOCMBIC", "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR",
+        "FIONREAD", "TIOCLINUX", "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT",
+        "FIONBIO", "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP",
+        [_IOC_NR(TIOCSBRK)] = "TIOCSBRK", "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2",
+        "TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
+        "TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
+        "TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+        [_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
+        "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
+        "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
+        "TIOCMIWAIT", "TIOCGICOUNT", };
+        static DEFINE_STRARRAY(ioctl_tty_cmd);
+
+        if (nr < strarray__ioctl_tty_cmd.nr_entries && strarray__ioctl_tty_cmd.entries[nr] != NULL)
+                return scnprintf(bf, size, "%s", strarray__ioctl_tty_cmd.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'T', nr, dir);
+}
+
+static size_t ioctl__scnprintf_drm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/drm_ioctl_array.c"
+        static DEFINE_STRARRAY(drm_ioctl_cmds);
+
+        if (nr < strarray__drm_ioctl_cmds.nr_entries && strarray__drm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "DRM_%s", strarray__drm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'd', nr, dir);
+}
+
+static size_t ioctl__scnprintf_sndrv_pcm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/sndrv_pcm_ioctl_array.c"
+        static DEFINE_STRARRAY(sndrv_pcm_ioctl_cmds);
+
+        if (nr < strarray__sndrv_pcm_ioctl_cmds.nr_entries && strarray__sndrv_pcm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "SNDRV_PCM_%s", strarray__sndrv_pcm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'A', nr, dir);
+}
+
+static size_t ioctl__scnprintf_sndrv_ctl_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/sndrv_ctl_ioctl_array.c"
+        static DEFINE_STRARRAY(sndrv_ctl_ioctl_cmds);
+
+        if (nr < strarray__sndrv_ctl_ioctl_cmds.nr_entries && strarray__sndrv_ctl_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "SNDRV_CTL_%s", strarray__sndrv_ctl_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 'U', nr, dir);
+}
+
+static size_t ioctl__scnprintf_kvm_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/kvm_ioctl_array.c"
+        static DEFINE_STRARRAY(kvm_ioctl_cmds);
+
+        if (nr < strarray__kvm_ioctl_cmds.nr_entries && strarray__kvm_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "KVM_%s", strarray__kvm_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir);
+}
+
+static size_t ioctl__scnprintf_vhost_virtio_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c"
+        static DEFINE_STRARRAY(vhost_virtio_ioctl_cmds);
+        static DEFINE_STRARRAY(vhost_virtio_ioctl_read_cmds);
+        struct strarray *s = (dir & _IOC_READ) ? &strarray__vhost_virtio_ioctl_read_cmds : &strarray__vhost_virtio_ioctl_cmds;
+
+        if (nr < s->nr_entries && s->entries[nr] != NULL)
+                return scnprintf(bf, size, "VHOST_%s", s->entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAF, nr, dir);
+}
+
+static size_t ioctl__scnprintf_perf_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/perf_ioctl_array.c"
+        static DEFINE_STRARRAY(perf_ioctl_cmds);
+
+        if (nr < strarray__perf_ioctl_cmds.nr_entries && strarray__perf_ioctl_cmds.entries[nr] != NULL)
+                return scnprintf(bf, size, "PERF_%s", strarray__perf_ioctl_cmds.entries[nr]);
+
+        return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir);
+}
+
+static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size)
+{
+        int dir  = _IOC_DIR(cmd),
+            type = _IOC_TYPE(cmd),
+            nr   = _IOC_NR(cmd),
+            sz   = _IOC_SIZE(cmd);
+        int printed = 0;
+        static const struct ioctl_type {
+                int     type;
+                size_t  (*scnprintf)(int nr, int dir, char *bf, size_t size);
+        } ioctl_types[] = { /* Must be ordered by type */
+                              { .type   = '$', .scnprintf = ioctl__scnprintf_perf_cmd, },
+                ['A' - '$'] = { .type   = 'A', .scnprintf = ioctl__scnprintf_sndrv_pcm_cmd, },
+                ['T' - '$'] = { .type   = 'T', .scnprintf = ioctl__scnprintf_tty_cmd, },
+                ['U' - '$'] = { .type   = 'U', .scnprintf = ioctl__scnprintf_sndrv_ctl_cmd, },
+                ['d' - '$'] = { .type   = 'd', .scnprintf = ioctl__scnprintf_drm_cmd, },
+                [0xAE - '$'] = { .type  = 0xAE, .scnprintf = ioctl__scnprintf_kvm_cmd, },
+                [0xAF - '$'] = { .type  = 0xAF, .scnprintf = ioctl__scnprintf_vhost_virtio_cmd, },
+        };
+        const int nr_types = ARRAY_SIZE(ioctl_types);
+
+        if (type >= ioctl_types[0].type && type <= ioctl_types[nr_types - 1].type) {
+                const int index = type - ioctl_types[0].type;
+
+                if (ioctl_types[index].scnprintf != NULL)
+                        return ioctl_types[index].scnprintf(nr, dir, bf, size);
+        }
+
+        printed += scnprintf(bf + printed, size - printed, "%c", '(');
+
+        if (dir == _IOC_NONE) {
+                printed += scnprintf(bf + printed, size - printed, "%s", "NONE");
+        } else {
+                if (dir & _IOC_READ)
+                        printed += scnprintf(bf + printed, size - printed, "%s", "READ");
+                if (dir & _IOC_WRITE)
+                        printed += scnprintf(bf + printed, size - printed, "%s%s", dir & _IOC_READ ? "|" : "", "WRITE");
+        }
+
+        return printed + scnprintf(bf + printed, size - printed, ", %#x, %#x, %#x)", type, nr, sz);
+}
+
+size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long cmd = arg->val;
+
+        return ioctl__scnprintf_cmd(cmd, bf, size);
+}
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
new file mode 100755
index 000000000000..bd28817afced
--- /dev/null
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+kvm_header_dir=$1
+
+printf "static const char *kvm_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${kvm_header_dir}/kvm.h    | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index af1cfde6b97b..754558f9009d 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -34,6 +34,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 {
         int printed = 0, flags = arg->val;
 
+        if (flags & MAP_ANONYMOUS)
+                arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
+
 #define P_MMAP_FLAG(n) \
         if (flags & MAP_##n) { \
                 printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index f55a4597fc38..e359e041dc0e 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -14,13 +14,16 @@
 #define O_NOATIME       01000000
 #endif
 
-static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
-                                               struct syscall_arg *arg)
-{
-        int printed = 0, flags = arg->val;
+#ifndef O_TMPFILE
+#define O_TMPFILE       020000000
+#endif
 
-        if (!(flags & O_CREAT))
-                arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+#undef O_LARGEFILE
+#define O_LARGEFILE     00100000
+
+size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+        int printed = 0;
 
         if (flags == 0)
                 return scnprintf(bf, size, "RDONLY");
@@ -30,6 +33,7 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
                 flags &= ~O_##n; \
         }
 
+        P_FLAG(RDWR);
         P_FLAG(APPEND);
         P_FLAG(ASYNC);
         P_FLAG(CLOEXEC);
@@ -38,6 +42,8 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
         P_FLAG(DIRECTORY);
         P_FLAG(EXCL);
         P_FLAG(LARGEFILE);
+        P_FLAG(NOFOLLOW);
+        P_FLAG(TMPFILE);
         P_FLAG(NOATIME);
         P_FLAG(NOCTTY);
 #ifdef O_NONBLOCK
@@ -48,7 +54,6 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 #ifdef O_PATH
         P_FLAG(PATH);
 #endif
-        P_FLAG(RDWR);
 #ifdef O_DSYNC
         if ((flags & O_SYNC) == O_SYNC)
                 printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
@@ -68,4 +73,12 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
         return printed;
 }
 
-#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+        int flags = arg->val;
+
+        if (!(flags & O_CREAT))
+                arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+
+        return open__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
new file mode 100755
index 000000000000..faea4237c793
--- /dev/null
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *perf_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
+egrep $regex ${header_dir}/perf_event.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 07486ea65ae3..b6d419e16dcf 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,4 @@
-static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
+size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
         int pid = arg->val;
         struct trace *trace = arg->trace;
@@ -17,5 +17,3 @@ static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_a
 
         return printed;
 }
-
-#define SCA_PID syscall_arg__scnprintf_pid
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
new file mode 100644
index 000000000000..2ba784a3734a
--- /dev/null
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -0,0 +1,50 @@
+/*
+ * trace/beauty/pkey_alloc.c
+ *
+ *  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 "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <linux/log2.h>
+
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+        int i, printed = 0;
+
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+        static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+        if (access_rights == 0) {
+                const char *s = strarray__pkey_alloc_access_rights.entries[0];
+                if (s)
+                        return scnprintf(bf, size, "%s", s);
+                return scnprintf(bf, size, "%d", 0);
+        }
+
+        for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
+                int bit = 1 << (i - 1);
+
+                if (!(access_rights & bit))
+                        continue;
+
+                if (printed != 0)
+                        printed += scnprintf(bf + printed, size - printed, "|");
+
+                if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
+                        printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+                else
+                        printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
+        }
+
+        return printed;
+}
+
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long cmd = arg->val;
+
+        return pkey_alloc__scnprintf_access_rights(cmd, bf, size);
+}
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
new file mode 100755
index 000000000000..62e51a02b839
--- /dev/null
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *pkey_alloc_access_rights[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
+egrep $regex ${header_dir}/mman-common.h        | \
+        sed -r "s/$regex/\2 \2 \1/g"    | \
+        sort | xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
new file mode 100755
index 000000000000..aad5ab130539
--- /dev/null
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+sound_header_dir=$1
+
+printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+        sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
new file mode 100755
index 000000000000..b7e9ef6b2f55
--- /dev/null
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+
+sound_header_dir=$1
+
+printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+        sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
new file mode 100755
index 000000000000..76f1de697787
--- /dev/null
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+
+vhost_virtio_header_dir=$1
+
+printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
+
+printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
+regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
+egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 83874b0e266c..d0c2007c307b 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -8,6 +8,7 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/string.h>
 #include <stdlib.h>
 #include <sys/ttydefaults.h>
 #include "browser.h"
@@ -563,7 +564,7 @@ static int ui_browser__color_config(const char *var, const char *value,
         int i;
 
         /* same dir for all commands */
-        if (prefixcmp(var, "colors.") != 0)
+        if (!strstarts(var, "colors.") != 0)
                 return 0;
 
         for (i = 0; ui_browser__colorsets[i].name != NULL; ++i) {
@@ -738,6 +739,35 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
                 __ui_browser__line_arrow_down(browser, column, start, end);
 }
 
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+                            unsigned int row, bool arrow_down)
+{
+        unsigned int end_row;
+
+        if (row >= browser->top_idx)
+                end_row = row - browser->top_idx;
+        else
+                return;
+
+        SLsmg_set_char_set(1);
+
+        if (arrow_down) {
+                ui_browser__gotorc(browser, end_row, column - 1);
+                SLsmg_write_char(SLSMG_ULCORN_CHAR);
+                ui_browser__gotorc(browser, end_row, column);
+                SLsmg_draw_hline(2);
+                ui_browser__gotorc(browser, end_row + 1, column - 1);
+                SLsmg_write_char(SLSMG_LTEE_CHAR);
+        } else {
+                ui_browser__gotorc(browser, end_row, column - 1);
+                SLsmg_write_char(SLSMG_LTEE_CHAR);
+                ui_browser__gotorc(browser, end_row, column);
+                SLsmg_draw_hline(2);
+        }
+
+        SLsmg_set_char_set(0);
+}
+
 void ui_browser__init(void)
 {
         int i = 0;
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index be3b70eb5fca..a12eff75638b 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -43,6 +43,8 @@ void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...);
 void ui_browser__write_graph(struct ui_browser *browser, int graph);
 void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
                               u64 start, u64 end);
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+                            unsigned int row, bool arrow_down);
 void __ui_browser__show_title(struct ui_browser *browser, const char *title);
 void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *browser, const char *title,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 27f41f28dcb4..786fecaf578e 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -9,14 +9,16 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/config.h"
+#include "../../util/evlist.h"
 #include <inttypes.h>
 #include <pthread.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <sys/ttydefaults.h>
 
 struct disasm_line_samples {
-        double          percent;
-        u64             nr;
+        double                percent;
+        struct sym_hist_entry he;
 };
 
 #define IPC_WIDTH 6
@@ -40,6 +42,7 @@ static struct annotate_browser_opt {
              jump_arrows,
              show_linenr,
              show_nr_jumps,
+             show_nr_samples,
              show_total_period;
 } annotate_browser__opts = {
         .use_offset     = true,
@@ -108,11 +111,12 @@ static int annotate_browser__set_jumps_percent_color(struct annotate_browser *br
 
 static int annotate_browser__pcnt_width(struct annotate_browser *ab)
 {
-        int w = 7 * ab->nr_events;
+        return (annotate_browser__opts.show_total_period ? 12 : 7) * ab->nr_events;
+}
 
-        if (ab->have_cycles)
-                w += IPC_WIDTH + CYCLES_WIDTH;
-        return w;
+static int annotate_browser__cycles_width(struct annotate_browser *ab)
+{
+        return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0;
 }
 
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
@@ -125,7 +129,8 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                              (!current_entry || (browser->use_navkeypressed &&
                                                  !browser->navkeypressed)));
         int width = browser->width, printed;
-        int i, pcnt_width = annotate_browser__pcnt_width(ab);
+        int i, pcnt_width = annotate_browser__pcnt_width(ab),
+               cycles_width = annotate_browser__cycles_width(ab);
         double percent_max = 0.0;
         char bf[256];
         bool show_title = false;
@@ -149,8 +154,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                                                 bdl->samples[i].percent,
                                                 current_entry);
                         if (annotate_browser__opts.show_total_period) {
+                                ui_browser__printf(browser, "%11" PRIu64 " ",
+                                                   bdl->samples[i].he.period);
+                        } else if (annotate_browser__opts.show_nr_samples) {
                                 ui_browser__printf(browser, "%6" PRIu64 " ",
-                                                   bdl->samples[i].nr);
+                                                   bdl->samples[i].he.nr_samples);
                         } else {
                                 ui_browser__printf(browser, "%6.2f ",
                                                    bdl->samples[i].percent);
@@ -160,9 +168,12 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 ui_browser__set_percent_color(browser, 0, current_entry);
 
                 if (!show_title)
-                        ui_browser__write_nstring(browser, " ", 7 * ab->nr_events);
-                else
-                        ui_browser__printf(browser, "%*s", 7, "Percent");
+                        ui_browser__write_nstring(browser, " ", pcnt_width);
+                else {
+                        ui_browser__printf(browser, "%*s", pcnt_width,
+                                           annotate_browser__opts.show_total_period ? "Period" :
+                                           annotate_browser__opts.show_nr_samples ? "Samples" : "Percent");
+                }
         }
         if (ab->have_cycles) {
                 if (dl->ipc)
@@ -188,7 +199,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 width += 1;
 
         if (!*dl->line)
-                ui_browser__write_nstring(browser, " ", width - pcnt_width);
+                ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width);
         else if (dl->offset == -1) {
                 if (dl->line_nr && annotate_browser__opts.show_linenr)
                         printed = scnprintf(bf, sizeof(bf), "%-*d ",
@@ -197,7 +208,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                         printed = scnprintf(bf, sizeof(bf), "%*s  ",
                                     ab->addr_width, " ");
                 ui_browser__write_nstring(browser, bf, printed);
-                ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width + 1);
+                ui_browser__write_nstring(browser, dl->line, width - printed - pcnt_width - cycles_width + 1);
         } else {
                 u64 addr = dl->offset;
                 int color = -1;
@@ -254,7 +265,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
                 }
 
                 disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
-                ui_browser__write_nstring(browser, bf, width - pcnt_width - 3 - printed);
+                ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed);
         }
 
         if (current_entry)
@@ -272,6 +283,25 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
         return true;
 }
 
+static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
+{
+        struct disasm_line *pos = list_prev_entry(cursor, node);
+        const char *name;
+
+        if (!pos)
+                return false;
+
+        if (ins__is_lock(&pos->ins))
+                name = pos->ops.locked.ins.name;
+        else
+                name = pos->ins.name;
+
+        if (!name || !cursor->ins.name)
+                return false;
+
+        return ins__is_fused(ab->arch, name, cursor->ins.name);
+}
+
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
         struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
@@ -307,6 +337,13 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
         ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
         __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
                                  from, to);
+
+        if (is_fused(ab, cursor)) {
+                ui_browser__mark_fused(browser,
+                                       pcnt_width + 3 + ab->addr_width,
+                                       from - 1,
+                                       to > from ? true : false);
+        }
 }
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
@@ -422,14 +459,14 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
                 next = disasm__get_next_ip_line(&notes->src->source, pos);
 
                 for (i = 0; i < browser->nr_events; i++) {
-                        u64 nr_samples;
+                        struct sym_hist_entry sample;
 
                         bpos->samples[i].percent = disasm__calc_percent(notes,
                                                 evsel->idx + i,
                                                 pos->offset,
                                                 next ? next->offset : len,
-                                                &path, &nr_samples);
-                        bpos->samples[i].nr = nr_samples;
+                                                &path, &sample);
+                        bpos->samples[i].he = sample;
 
                         if (max_percent < bpos->samples[i].percent)
                                 max_percent = bpos->samples[i].percent;
@@ -792,13 +829,14 @@ static int annotate_browser__run(struct annotate_browser *browser,
                 "q/ESC/CTRL+C  Exit\n\n"
                 "ENTER         Go to target\n"
                 "ESC           Exit\n"
-                "H             Cycle thru hottest instructions\n"
+                "H             Go to hottest instruction\n"
+                "TAB/shift+TAB Cycle thru hottest instructions\n"
                 "j             Toggle showing jump to target arrows\n"
                 "J             Toggle showing number of jump sources on targets\n"
                 "n             Search next string\n"
                 "o             Toggle disassembler output/simplified view\n"
                 "s             Toggle source code view\n"
-                "t             Toggle total period view\n"
+                "t             Circulate percent, total period, samples view\n"
                 "/             Search string\n"
                 "k             Toggle line numbers\n"
                 "r             Run available scripts\n"
@@ -875,8 +913,13 @@ show_sup_ins:
                         }
                         continue;
                 case 't':
-                        annotate_browser__opts.show_total_period =
-                          !annotate_browser__opts.show_total_period;
+                        if (annotate_browser__opts.show_total_period) {
+                                annotate_browser__opts.show_total_period = false;
+                                annotate_browser__opts.show_nr_samples = true;
+                        } else if (annotate_browser__opts.show_nr_samples)
+                                annotate_browser__opts.show_nr_samples = false;
+                        else
+                                annotate_browser__opts.show_total_period = true;
                         annotate_browser__update_addr_width(browser);
                         continue;
                 case K_LEFT:
@@ -899,9 +942,11 @@ out:
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
                              struct hist_browser_timer *hbt)
 {
-        /* Set default value for show_total_period.  */
+        /* Set default value for show_total_period and show_nr_samples  */
         annotate_browser__opts.show_total_period =
-          symbol_conf.show_total_period;
+                symbol_conf.show_total_period;
+        annotate_browser__opts.show_nr_samples =
+                symbol_conf.show_nr_samples;
 
         return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
 }
@@ -1074,7 +1119,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
         }
 
         err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  sizeof_bdl, &browser.arch);
+                                  sizeof_bdl, &browser.arch,
+                                  perf_evsel__env_cpuid(evsel));
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -1151,6 +1197,7 @@ static struct annotate_config {
         ANNOTATE_CFG(jump_arrows),
         ANNOTATE_CFG(show_linenr),
         ANNOTATE_CFG(show_nr_jumps),
+        ANNOTATE_CFG(show_nr_samples),
         ANNOTATE_CFG(show_total_period),
         ANNOTATE_CFG(use_offset),
 };
@@ -1170,7 +1217,7 @@ static int annotate__config(const char *var, const char *value,
         struct annotate_config *cfg;
         const char *name;
 
-        if (prefixcmp(var, "annotate.") != 0)
+        if (!strstarts(var, "annotate."))
                 return 0;
 
         name = var + 9;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 69f4570bd4f9..13dfb0a0bdeb 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -166,9 +166,6 @@ static struct inline_node *inline_node__create(struct map *map, u64 ip)
         if (dso == NULL)
                 return NULL;
 
-        if (dso->kernel != DSO_TYPE_USER)
-                return NULL;
-
         node = dso__parse_addr_inlines(dso,
                                        map__rip_2objdump(map, ip));
 
@@ -934,12 +931,8 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                        browser->show_dso);
 
         if (symbol_conf.show_branchflag_count) {
-                if (need_percent)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str2, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index d903fd493416..02176193f427 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -34,10 +34,10 @@ static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
                 return 0;
 
         symhist = annotation__histogram(symbol__annotation(sym), evidx);
-        if (!symbol_conf.event_group && !symhist->addr[dl->offset])
+        if (!symbol_conf.event_group && !symhist->addr[dl->offset].nr_samples)
                 return 0;
 
-        percent = 100.0 * symhist->addr[dl->offset] / symhist->sum;
+        percent = 100.0 * symhist->addr[dl->offset].nr_samples / symhist->nr_samples;
 
         markup = perf_gtk__get_percent_color(percent);
         if (markup)
@@ -169,7 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
                 return -1;
 
         err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                  0, NULL);
+                                  0, NULL, NULL);
         if (err) {
                 char msg[BUFSIZ];
                 symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/progress.c b/tools/perf/ui/progress.c
index a0f24c7115c5..ae91c8148edf 100644
--- a/tools/perf/ui/progress.c
+++ b/tools/perf/ui/progress.c
@@ -1,3 +1,4 @@
+#include <linux/kernel.h>
 #include "../cache.h"
 #include "progress.h"
 
@@ -14,10 +15,14 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops;
 
 void ui_progress__update(struct ui_progress *p, u64 adv)
 {
+        u64 last = p->curr;
+
         p->curr += adv;
 
         if (p->curr >= p->next) {
-                p->next += p->step;
+                u64 nr = DIV_ROUND_UP(p->curr - last, p->step);
+
+                p->next += nr * p->step;
                 ui_progress__ops->update(p);
         }
 }
@@ -25,7 +30,7 @@ void ui_progress__update(struct ui_progress *p, u64 adv)
 void ui_progress__init(struct ui_progress *p, u64 total, const char *title)
 {
         p->curr = 0;
-        p->next = p->step = total / 16;
+        p->next = p->step = total / 16 ?: 1;
         p->total = total;
         p->title = title;
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 42e432bd2eb4..8bdb7a500181 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -1,4 +1,5 @@
 #include <stdio.h>
+#include <linux/string.h>
 
 #include "../../util/util.h"
 #include "../../util/hist.h"
@@ -35,9 +36,6 @@ static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
         if (dso == NULL)
                 return 0;
 
-        if (dso->kernel != DSO_TYPE_USER)
-                return 0;
-
         node = dso__parse_addr_inlines(dso,
                                        map__rip_2objdump(map, ip));
         if (node == NULL)
@@ -126,12 +124,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         str = callchain_list__sym_name(chain, bf, sizeof(bf), false);
 
         if (symbol_conf.show_branchflag_count) {
-                if (!period)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
@@ -295,7 +289,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                          * displayed twice.
                          */
                         if (!i++ && field_order == NULL &&
-                            sort_order && !prefixcmp(sort_order, "sym"))
+                            sort_order && strstarts(sort_order, "sym"))
                                 continue;
 
                         if (!printed) {
@@ -315,7 +309,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         if (symbol_conf.show_branchflag_count)
                                 ret += callchain_list_counts__printf_value(
-                                                NULL, chain, fp, NULL, 0);
+                                                chain, fp, NULL, 0);
                         ret += fprintf(fp, "\n");
 
                         if (++entries_printed == callchain_param.print_limit)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 79dea95a7f68..94518c1bf8b6 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -22,6 +22,7 @@ libperf-y += rbtree.o
 libperf-y += libstring.o
 libperf-y += bitmap.o
 libperf-y += hweight.o
+libperf-y += smt.o
 libperf-y += quote.o
 libperf-y += strbuf.o
 libperf-y += string.o
@@ -93,6 +94,7 @@ libperf-y += drv_configs.o
 libperf-y += units.o
 libperf-y += time-utils.o
 libperf-y += expr-bison.o
+libperf-y += branch.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -104,6 +106,10 @@ ifndef CONFIG_LIBELF
 libperf-y += symbol-minimal.o
 endif
 
+ifndef CONFIG_SETNS
+libperf-y += setns.o
+endif
+
 libperf-$(CONFIG_DWARF) += probe-finder.o
 libperf-$(CONFIG_DWARF) += dwarf-aux.o
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index be1caabb9290..4397a8b6e6cd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -47,7 +47,12 @@ struct arch {
         bool            sorted_instructions;
         bool            initialized;
         void            *priv;
+        unsigned int    model;
+        unsigned int    family;
         int             (*init)(struct arch *arch);
+        bool            (*ins_is_fused)(struct arch *arch, const char *ins1,
+                                        const char *ins2);
+        int             (*cpuid_parse)(struct arch *arch, char *cpuid);
         struct          {
                 char comment_char;
                 char skip_functions_char;
@@ -129,6 +134,8 @@ static struct arch architectures[] = {
                 .name = "x86",
                 .instructions = x86__instructions,
                 .nr_instructions = ARRAY_SIZE(x86__instructions),
+                .ins_is_fused = x86__ins_is_fused,
+                .cpuid_parse = x86__cpuid_parse,
                 .objdump =  {
                         .comment_char = '#',
                 },
@@ -171,6 +178,14 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
         return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+        if (!arch || !arch->ins_is_fused)
+                return false;
+
+        return arch->ins_is_fused(arch, ins1, ins2);
+}
+
 static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
 {
         char *endptr, *tok, *name;
@@ -502,6 +517,11 @@ bool ins__is_ret(const struct ins *ins)
         return ins->ops == &ret_ops;
 }
 
+bool ins__is_lock(const struct ins *ins)
+{
+        return ins->ops == &lock_ops;
+}
+
 static int ins__key_cmp(const void *name, const void *insp)
 {
         const struct ins *ins = insp;
@@ -590,10 +610,10 @@ int symbol__alloc_hist(struct symbol *sym)
         size_t sizeof_sym_hist;
 
         /* Check for overflow when calculating sizeof_sym_hist */
-        if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(u64))
+        if (size > (SIZE_MAX - sizeof(struct sym_hist)) / sizeof(struct sym_hist_entry))
                 return -1;
 
-        sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64));
+        sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(struct sym_hist_entry));
 
         /* Check for overflow in zalloc argument */
         if (sizeof_sym_hist > (SIZE_MAX - sizeof(*notes->src))
@@ -677,7 +697,8 @@ static int __symbol__account_cycles(struct annotation *notes,
 }
 
 static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                                      struct annotation *notes, int evidx, u64 addr)
+                                      struct annotation *notes, int evidx, u64 addr,
+                                      struct perf_sample *sample)
 {
         unsigned offset;
         struct sym_hist *h;
@@ -693,12 +714,15 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
         offset = addr - sym->start;
         h = annotation__histogram(notes, evidx);
-        h->sum++;
-        h->addr[offset]++;
+        h->nr_samples++;
+        h->addr[offset].nr_samples++;
+        h->period += sample->period;
+        h->addr[offset].period += sample->period;
 
         pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
-                  ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
-                  addr, addr - sym->start, evidx, h->addr[offset]);
+                  ", evidx=%d] => nr_samples: %" PRIu64 ", period: %" PRIu64 "\n",
+                  sym->start, sym->name, addr, addr - sym->start, evidx,
+                  h->addr[offset].nr_samples, h->addr[offset].period);
         return 0;
 }
 
@@ -718,7 +742,8 @@ static struct annotation *symbol__get_annotation(struct symbol *sym, bool cycles
 }
 
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-                                    int evidx, u64 addr)
+                                    int evidx, u64 addr,
+                                    struct perf_sample *sample)
 {
         struct annotation *notes;
 
@@ -727,7 +752,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
         notes = symbol__get_annotation(sym, false);
         if (notes == NULL)
                 return -ENOMEM;
-        return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
+        return __symbol__inc_addr_samples(sym, map, notes, evidx, addr, sample);
 }
 
 static int symbol__account_cycles(u64 addr, u64 start,
@@ -791,14 +816,16 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
         return err;
 }
 
-int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
+                                 int evidx)
 {
-        return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
+        return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr, sample);
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
+                                 int evidx, u64 ip)
 {
-        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample);
 }
 
 static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map)
@@ -908,11 +935,12 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 }
 
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, u64 *nr_samples)
+                            s64 end, const char **path, struct sym_hist_entry *sample)
 {
         struct source_line *src_line = notes->src->lines;
         double percent = 0.0;
-        *nr_samples = 0;
+
+        sample->nr_samples = sample->period = 0;
 
         if (src_line) {
                 size_t sizeof_src_line = sizeof(*src_line) +
@@ -926,19 +954,24 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
                                 *path = src_line->path;
 
                         percent += src_line->samples[evidx].percent;
-                        *nr_samples += src_line->samples[evidx].nr;
+                        sample->nr_samples += src_line->samples[evidx].nr;
                         offset++;
                 }
         } else {
                 struct sym_hist *h = annotation__histogram(notes, evidx);
                 unsigned int hits = 0;
+                u64 period = 0;
 
-                while (offset < end)
-                        hits += h->addr[offset++];
+                while (offset < end) {
+                        hits   += h->addr[offset].nr_samples;
+                        period += h->addr[offset].period;
+                        ++offset;
+                }
 
-                if (h->sum) {
-                        *nr_samples = hits;
-                        percent = 100.0 * hits / h->sum;
+                if (h->nr_samples) {
+                        sample->period     = period;
+                        sample->nr_samples = hits;
+                        percent = 100.0 * hits / h->nr_samples;
                 }
         }
 
@@ -1037,10 +1070,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
         if (dl->offset != -1) {
                 const char *path = NULL;
-                u64 nr_samples;
                 double percent, max_percent = 0.0;
                 double *ppercents = &percent;
-                u64 *psamples = &nr_samples;
+                struct sym_hist_entry sample;
+                struct sym_hist_entry *psamples = &sample;
                 int i, nr_percent = 1;
                 const char *color;
                 struct annotation *notes = symbol__annotation(sym);
@@ -1054,7 +1087,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 if (perf_evsel__is_group_event(evsel)) {
                         nr_percent = evsel->nr_members;
                         ppercents = calloc(nr_percent, sizeof(double));
-                        psamples = calloc(nr_percent, sizeof(u64));
+                        psamples = calloc(nr_percent, sizeof(struct sym_hist_entry));
                         if (ppercents == NULL || psamples == NULL) {
                                 return -1;
                         }
@@ -1065,10 +1098,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                                         notes->src->lines ? i : evsel->idx + i,
                                         offset,
                                         next ? next->offset : (s64) len,
-                                        &path, &nr_samples);
+                                        &path, &sample);
 
                         ppercents[i] = percent;
-                        psamples[i] = nr_samples;
+                        psamples[i] = sample;
                         if (percent > max_percent)
                                 max_percent = percent;
                 }
@@ -1106,12 +1139,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
                 for (i = 0; i < nr_percent; i++) {
                         percent = ppercents[i];
-                        nr_samples = psamples[i];
+                        sample = psamples[i];
                         color = get_percent_color(percent);
 
                         if (symbol_conf.show_total_period)
+                                color_fprintf(stdout, color, " %11" PRIu64,
+                                              sample.period);
+                        else if (symbol_conf.show_nr_samples)
                                 color_fprintf(stdout, color, " %7" PRIu64,
-                                              nr_samples);
+                                              sample.nr_samples);
                         else
                                 color_fprintf(stdout, color, " %7.2f", percent);
                 }
@@ -1127,13 +1163,13 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
                 if (ppercents != &percent)
                         free(ppercents);
 
-                if (psamples != &nr_samples)
+                if (psamples != &sample)
                         free(psamples);
 
         } else if (max_lines && printed >= max_lines)
                 return 1;
         else {
-                int width = 8;
+                int width = symbol_conf.show_total_period ? 12 : 8;
 
                 if (queue)
                         return -1;
@@ -1327,7 +1363,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
             !dso__is_kcore(dso))
                 return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
 
-        build_id_filename = dso__build_id_filename(dso, NULL, 0);
+        build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
         if (build_id_filename) {
                 __symbol__join_symfs(filename, filename_size, build_id_filename);
                 free(build_id_filename);
@@ -1381,7 +1417,7 @@ static const char *annotate__norm_arch(const char *arch_name)
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
                         const char *arch_name, size_t privsize,
-                        struct arch **parch)
+                        struct arch **parch, char *cpuid)
 {
         struct dso *dso = map->dso;
         char command[PATH_MAX * 2];
@@ -1418,6 +1454,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
                 }
         }
 
+        if (arch->cpuid_parse && cpuid)
+                arch->cpuid_parse(arch, cpuid);
+
         pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
                  symfs_filename, sym->name, map->unmap_ip(map, sym->start),
                  map->unmap_ip(map, sym->end));
@@ -1648,19 +1687,19 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
         struct sym_hist *h = annotation__histogram(notes, evidx);
         struct rb_root tmp_root = RB_ROOT;
         int nr_pcnt = 1;
-        u64 h_sum = h->sum;
+        u64 nr_samples = h->nr_samples;
         size_t sizeof_src_line = sizeof(struct source_line);
 
         if (perf_evsel__is_group_event(evsel)) {
                 for (i = 1; i < evsel->nr_members; i++) {
                         h = annotation__histogram(notes, evidx + i);
-                        h_sum += h->sum;
+                        nr_samples += h->nr_samples;
                 }
                 nr_pcnt = evsel->nr_members;
                 sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
         }
 
-        if (!h_sum)
+        if (!nr_samples)
                 return 0;
 
         src_line = notes->src->lines = calloc(len, sizeof_src_line);
@@ -1670,7 +1709,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
         start = map__rip_2objdump(map, sym->start);
 
         for (i = 0; i < len; i++) {
-                u64 offset, nr_samples;
+                u64 offset;
                 double percent_max = 0.0;
 
                 src_line->nr_pcnt = nr_pcnt;
@@ -1679,9 +1718,9 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
                         double percent = 0.0;
 
                         h = annotation__histogram(notes, evidx + k);
-                        nr_samples = h->addr[i];
-                        if (h->sum)
-                                percent = 100.0 * nr_samples / h->sum;
+                        nr_samples = h->addr[i].nr_samples;
+                        if (h->nr_samples)
+                                percent = 100.0 * nr_samples / h->nr_samples;
 
                         if (percent > percent_max)
                                 percent_max = percent;
@@ -1750,10 +1789,10 @@ static void symbol__annotate_hits(struct symbol *sym, struct perf_evsel *evsel)
         u64 len = symbol__size(sym), offset;
 
         for (offset = 0; offset < len; ++offset)
-                if (h->addr[offset] != 0)
+                if (h->addr[offset].nr_samples != 0)
                         printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
-                               sym->start + offset, h->addr[offset]);
-        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+                               sym->start + offset, h->addr[offset].nr_samples);
+        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->nr_samples", h->nr_samples);
 }
 
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
@@ -1771,7 +1810,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
         int printed = 2, queue_len = 0;
         int more = 0;
         u64 len;
-        int width = 8;
+        int width = symbol_conf.show_total_period ? 12 : 8;
         int graph_dotted_len;
 
         filename = strdup(dso->long_name);
@@ -1789,7 +1828,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
                 width *= evsel->nr_members;
 
         graph_dotted_len = printf(" %-*.*s|     Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
-               width, width, "Percent", d_filename, evsel_name, h->sum);
+                                  width, width, symbol_conf.show_total_period ? "Period" :
+                                  symbol_conf.show_nr_samples ? "Samples" : "Percent",
+                                  d_filename, evsel_name, h->nr_samples);
 
         printf("%-*.*s----\n",
                graph_dotted_len, graph_dotted_len, graph_dotted_line);
@@ -1853,10 +1894,10 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
         struct sym_hist *h = annotation__histogram(notes, evidx);
         int len = symbol__size(sym), offset;
 
-        h->sum = 0;
+        h->nr_samples = 0;
         for (offset = 0; offset < len; ++offset) {
-                h->addr[offset] = h->addr[offset] * 7 / 8;
-                h->sum += h->addr[offset];
+                h->addr[offset].nr_samples = h->addr[offset].nr_samples * 7 / 8;
+                h->nr_samples += h->addr[offset].nr_samples;
         }
 }
 
@@ -1907,7 +1948,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
         u64 len;
 
         if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-                                0, NULL) < 0)
+                                0, NULL, NULL) < 0)
                 return -1;
 
         len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 21055034aedd..9ce575c25fd9 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -52,7 +52,9 @@ struct ins_ops {
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 struct annotation;
 
@@ -72,16 +74,22 @@ static inline bool disasm_line__has_offset(const struct disasm_line *dl)
         return dl->ops.target.offset_avail;
 }
 
+struct sym_hist_entry {
+        u64             nr_samples;
+        u64             period;
+};
+
 void disasm_line__free(struct disasm_line *dl);
 struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos);
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-                            s64 end, const char **path, u64 *nr_samples);
+                            s64 end, const char **path, struct sym_hist_entry *sample);
 
 struct sym_hist {
-        u64             sum;
-        u64             addr[0];
+        u64                   nr_samples;
+        u64                   period;
+        struct sym_hist_entry addr[0];
 };
 
 struct cyc_hist {
@@ -147,20 +155,22 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
         return (void *)sym - symbol_conf.priv_size;
 }
 
-int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
+                                 int evidx);
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
                                     struct addr_map_symbol *start,
                                     unsigned cycles);
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
+int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *sample,
+                                 int evidx, u64 addr);
 
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
                         const char *arch_name, size_t privsize,
-                        struct arch **parch);
+                        struct arch **parch, char *cpuid);
 
 enum symbol_disassemble_errno {
         SYMBOL_ANNOTATE_ERRNO__SUCCESS          = 0,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 4bd2d1d882af..4a1264c66101 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1246,7 +1246,7 @@ int bpf__config_obj(struct bpf_object *obj,
         if (!obj || !term || !term->config)
                 return -EINVAL;
 
-        if (!prefixcmp(term->config, "map:")) {
+        if (strstarts(term->config, "map:")) {
                 key_scan_pos = sizeof("map:") - 1;
                 err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
                 goto out;
diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c
index 1356220a9f1b..827f9140f3b8 100644
--- a/tools/perf/util/bpf-prologue.c
+++ b/tools/perf/util/bpf-prologue.c
@@ -58,6 +58,46 @@ check_pos(struct bpf_insn_pos *pos)
         return 0;
 }
 
+/*
+ * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see
+ * Documentation/trace/kprobetrace.txt) to size field of BPF_LDX_MEM
+ * instruction (BPF_{B,H,W,DW}).
+ */
+static int
+argtype_to_ldx_size(const char *type)
+{
+        int arg_size = type ? atoi(&type[1]) : 64;
+
+        switch (arg_size) {
+        case 8:
+                return BPF_B;
+        case 16:
+                return BPF_H;
+        case 32:
+                return BPF_W;
+        case 64:
+        default:
+                return BPF_DW;
+        }
+}
+
+static const char *
+insn_sz_to_str(int insn_sz)
+{
+        switch (insn_sz) {
+        case BPF_B:
+                return "BPF_B";
+        case BPF_H:
+                return "BPF_H";
+        case BPF_W:
+                return "BPF_W";
+        case BPF_DW:
+                return "BPF_DW";
+        default:
+                return "UNKNOWN";
+        }
+}
+
 /* Give it a shorter name */
 #define ins(i, p) append_insn((i), (p))
 
@@ -258,9 +298,14 @@ gen_prologue_slowpath(struct bpf_insn_pos *pos,
         }
 
         /* Final pass: read to registers */
-        for (i = 0; i < nargs; i++)
-                ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i,
+        for (i = 0; i < nargs; i++) {
+                int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW;
+
+                pr_debug("prologue: load arg %d, insn_sz is %s\n",
+                         i, insn_sz_to_str(insn_sz));
+                ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i,
                                 BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos);
+        }
 
         ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos);
 
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
new file mode 100644
index 000000000000..a4fce2729e50
--- /dev/null
+++ b/tools/perf/util/branch.c
@@ -0,0 +1,147 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/branch.h"
+
+static bool cross_area(u64 addr1, u64 addr2, int size)
+{
+        u64 align1, align2;
+
+        align1 = addr1 & ~(size - 1);
+        align2 = addr2 & ~(size - 1);
+
+        return (align1 != align2) ? true : false;
+}
+
+#define AREA_4K         4096
+#define AREA_2M         (2 * 1024 * 1024)
+
+void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
+                       u64 from, u64 to)
+{
+        if (flags->type == PERF_BR_UNKNOWN || from == 0)
+                return;
+
+        st->counts[flags->type]++;
+
+        if (flags->type == PERF_BR_COND) {
+                if (to > from)
+                        st->cond_fwd++;
+                else
+                        st->cond_bwd++;
+        }
+
+        if (cross_area(from, to, AREA_2M))
+                st->cross_2m++;
+        else if (cross_area(from, to, AREA_4K))
+                st->cross_4k++;
+}
+
+const char *branch_type_name(int type)
+{
+        const char *branch_names[PERF_BR_MAX] = {
+                "N/A",
+                "COND",
+                "UNCOND",
+                "IND",
+                "CALL",
+                "IND_CALL",
+                "RET",
+                "SYSCALL",
+                "SYSRET",
+                "COND_CALL",
+                "COND_RET"
+        };
+
+        if (type >= 0 && type < PERF_BR_MAX)
+                return branch_names[type];
+
+        return NULL;
+}
+
+void branch_type_stat_display(FILE *fp, struct branch_type_stat *st)
+{
+        u64 total = 0;
+        int i;
+
+        for (i = 0; i < PERF_BR_MAX; i++)
+                total += st->counts[i];
+
+        if (total == 0)
+                return;
+
+        fprintf(fp, "\n#");
+        fprintf(fp, "\n# Branch Statistics:");
+        fprintf(fp, "\n#");
+
+        if (st->cond_fwd > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "COND_FWD",
+                        100.0 * (double)st->cond_fwd / (double)total);
+        }
+
+        if (st->cond_bwd > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "COND_BWD",
+                        100.0 * (double)st->cond_bwd / (double)total);
+        }
+
+        if (st->cross_4k > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "CROSS_4K",
+                        100.0 * (double)st->cross_4k / (double)total);
+        }
+
+        if (st->cross_2m > 0) {
+                fprintf(fp, "\n%8s: %5.1f%%",
+                        "CROSS_2M",
+                        100.0 * (double)st->cross_2m / (double)total);
+        }
+
+        for (i = 0; i < PERF_BR_MAX; i++) {
+                if (st->counts[i] > 0)
+                        fprintf(fp, "\n%8s: %5.1f%%",
+                                branch_type_name(i),
+                                100.0 *
+                                (double)st->counts[i] / (double)total);
+        }
+}
+
+static int count_str_scnprintf(int idx, const char *str, char *bf, int size)
+{
+        return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str);
+}
+
+int branch_type_str(struct branch_type_stat *st, char *bf, int size)
+{
+        int i, j = 0, printed = 0;
+        u64 total = 0;
+
+        for (i = 0; i < PERF_BR_MAX; i++)
+                total += st->counts[i];
+
+        if (total == 0)
+                return 0;
+
+        if (st->cond_fwd > 0)
+                printed += count_str_scnprintf(j++, "COND_FWD", bf + printed, size - printed);
+
+        if (st->cond_bwd > 0)
+                printed += count_str_scnprintf(j++, "COND_BWD", bf + printed, size - printed);
+
+        for (i = 0; i < PERF_BR_MAX; i++) {
+                if (i == PERF_BR_COND)
+                        continue;
+
+                if (st->counts[i] > 0)
+                        printed += count_str_scnprintf(j++, branch_type_name(i), bf + printed, size - printed);
+        }
+
+        if (st->cross_4k > 0)
+                printed += count_str_scnprintf(j++, "CROSS_4K", bf + printed, size - printed);
+
+        if (st->cross_2m > 0)
+                printed += count_str_scnprintf(j++, "CROSS_2M", bf + printed, size - printed);
+
+        return printed;
+}
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
new file mode 100644
index 000000000000..1e3c7c5cdc63
--- /dev/null
+++ b/tools/perf/util/branch.h
@@ -0,0 +1,25 @@
+#ifndef _PERF_BRANCH_H
+#define _PERF_BRANCH_H 1
+
+#include <stdint.h>
+#include "../perf.h"
+
+struct branch_type_stat {
+        bool    branch_to;
+        u64     counts[PERF_BR_MAX];
+        u64     cond_fwd;
+        u64     cond_bwd;
+        u64     cross_4k;
+        u64     cross_2m;
+};
+
+struct branch_flags;
+
+void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags,
+                       u64 from, u64 to);
+
+const char *branch_type_name(int type);
+void branch_type_stat_display(FILE *fp, struct branch_type_stat *st);
+int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize);
+
+#endif /* _PERF_BRANCH_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e0148b081bdf..c1a06fcd7e70 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -243,12 +243,15 @@ static bool build_id_cache__valid_id(char *sbuild_id)
         return result;
 }
 
-static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso)
+static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso,
+                                            bool is_debug)
 {
-        return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf");
+        return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : (is_debug ?
+            "debug" : "elf"));
 }
 
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+                             bool is_debug)
 {
         bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
         bool is_vdso = dso__is_vdso((struct dso *)dso);
@@ -270,7 +273,8 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
                 ret = asnprintf(&bf, size, "%s", linkname);
         else
                 ret = asnprintf(&bf, size, "%s/%s", linkname,
-                         build_id_cache__basename(is_kallsyms, is_vdso));
+                         build_id_cache__basename(is_kallsyms, is_vdso,
+                                                  is_debug));
         if (ret < 0 || (!alloc && size < (unsigned int)ret))
                 bf = NULL;
         free(linkname);
@@ -285,7 +289,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
                 else
 
 static int write_buildid(const char *name, size_t name_len, u8 *build_id,
-                         pid_t pid, u16 misc, int fd)
+                         pid_t pid, u16 misc, struct feat_fd *fd)
 {
         int err;
         struct build_id_event b;
@@ -300,14 +304,15 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
         b.header.misc = misc;
         b.header.size = sizeof(b) + len;
 
-        err = writen(fd, &b, sizeof(b));
+        err = do_write(fd, &b, sizeof(b));
         if (err < 0)
                 return err;
 
         return write_padded(fd, name, name_len + 1, len);
 }
 
-static int machine__write_buildid_table(struct machine *machine, int fd)
+static int machine__write_buildid_table(struct machine *machine,
+                                        struct feat_fd *fd)
 {
         int err = 0;
         char nm[PATH_MAX];
@@ -352,7 +357,8 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
         return err;
 }
 
-int perf_session__write_buildid_table(struct perf_session *session, int fd)
+int perf_session__write_buildid_table(struct perf_session *session,
+                                      struct feat_fd *fd)
 {
         struct rb_node *nd;
         int err = machine__write_buildid_table(&session->machines.host, fd);
@@ -534,13 +540,14 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id)
 }
 
 char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
-                               bool is_kallsyms, bool is_vdso)
+                               struct nsinfo *nsi, bool is_kallsyms,
+                               bool is_vdso)
 {
         char *realname = (char *)name, *filename;
         bool slash = is_kallsyms || is_vdso;
 
         if (!slash) {
-                realname = realpath(name, NULL);
+                realname = nsinfo__realpath(name, nsi);
                 if (!realname)
                         return NULL;
         }
@@ -556,13 +563,13 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
         return filename;
 }
 
-int build_id_cache__list_build_ids(const char *pathname,
+int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
                                    struct strlist **result)
 {
         char *dir_name;
         int ret = 0;
 
-        dir_name = build_id_cache__cachedir(NULL, pathname, false, false);
+        dir_name = build_id_cache__cachedir(NULL, pathname, nsi, false, false);
         if (!dir_name)
                 return -ENOMEM;
 
@@ -576,16 +583,20 @@ int build_id_cache__list_build_ids(const char *pathname,
 
 #if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT)
 static int build_id_cache__add_sdt_cache(const char *sbuild_id,
-                                          const char *realname)
+                                          const char *realname,
+                                          struct nsinfo *nsi)
 {
         struct probe_cache *cache;
         int ret;
+        struct nscookie nsc;
 
-        cache = probe_cache__new(sbuild_id);
+        cache = probe_cache__new(sbuild_id, nsi);
         if (!cache)
                 return -1;
 
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = probe_cache__scan_sdt(cache, realname);
+        nsinfo__mountns_exit(&nsc);
         if (ret >= 0) {
                 pr_debug4("Found %d SDTs in %s\n", ret, realname);
                 if (probe_cache__commit(cache) < 0)
@@ -595,25 +606,56 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id,
         return ret;
 }
 #else
-#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0)
+#define build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) (0)
 #endif
 
+static char *build_id_cache__find_debug(const char *sbuild_id,
+                                        struct nsinfo *nsi)
+{
+        char *realname = NULL;
+        char *debugfile;
+        struct nscookie nsc;
+        size_t len = 0;
+
+        debugfile = calloc(1, PATH_MAX);
+        if (!debugfile)
+                goto out;
+
+        len = __symbol__join_symfs(debugfile, PATH_MAX,
+                                   "/usr/lib/debug/.build-id/");
+        snprintf(debugfile + len, PATH_MAX - len, "%.2s/%s.debug", sbuild_id,
+                 sbuild_id + 2);
+
+        nsinfo__mountns_enter(nsi, &nsc);
+        realname = realpath(debugfile, NULL);
+        if (realname && access(realname, R_OK))
+                zfree(&realname);
+        nsinfo__mountns_exit(&nsc);
+out:
+        free(debugfile);
+        return realname;
+}
+
 int build_id_cache__add_s(const char *sbuild_id, const char *name,
-                          bool is_kallsyms, bool is_vdso)
+                          struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
 {
         const size_t size = PATH_MAX;
         char *realname = NULL, *filename = NULL, *dir_name = NULL,
              *linkname = zalloc(size), *tmp;
+        char *debugfile = NULL;
         int err = -1;
 
         if (!is_kallsyms) {
-                realname = realpath(name, NULL);
+                if (!is_vdso)
+                        realname = nsinfo__realpath(name, nsi);
+                else
+                        realname = realpath(name, NULL);
                 if (!realname)
                         goto out_free;
         }
 
-        dir_name = build_id_cache__cachedir(sbuild_id, name,
-                                            is_kallsyms, is_vdso);
+        dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms,
+                                            is_vdso);
         if (!dir_name)
                 goto out_free;
 
@@ -627,20 +669,52 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 
         /* Save the allocated buildid dirname */
         if (asprintf(&filename, "%s/%s", dir_name,
-                     build_id_cache__basename(is_kallsyms, is_vdso)) < 0) {
+                     build_id_cache__basename(is_kallsyms, is_vdso,
+                     false)) < 0) {
                 filename = NULL;
                 goto out_free;
         }
 
         if (access(filename, F_OK)) {
                 if (is_kallsyms) {
-                         if (copyfile("/proc/kallsyms", filename))
+                        if (copyfile("/proc/kallsyms", filename))
+                                goto out_free;
+                } else if (nsi && nsi->need_setns) {
+                        if (copyfile_ns(name, filename, nsi))
                                 goto out_free;
                 } else if (link(realname, filename) && errno != EEXIST &&
                                 copyfile(name, filename))
                         goto out_free;
         }
 
+        /* Some binaries are stripped, but have .debug files with their symbol
+         * table.  Check to see if we can locate one of those, since the elf
+         * file itself may not be very useful to users of our tools without a
+         * symtab.
+         */
+        if (!is_kallsyms && !is_vdso &&
+            strncmp(".ko", name + strlen(name) - 3, 3)) {
+                debugfile = build_id_cache__find_debug(sbuild_id, nsi);
+                if (debugfile) {
+                        zfree(&filename);
+                        if (asprintf(&filename, "%s/%s", dir_name,
+                            build_id_cache__basename(false, false, true)) < 0) {
+                                filename = NULL;
+                                goto out_free;
+                        }
+                        if (access(filename, F_OK)) {
+                                if (nsi && nsi->need_setns) {
+                                        if (copyfile_ns(debugfile, filename,
+                                                        nsi))
+                                                goto out_free;
+                                } else if (link(debugfile, filename) &&
+                                                errno != EEXIST &&
+                                                copyfile(debugfile, filename))
+                                        goto out_free;
+                        }
+                }
+        }
+
         if (!build_id_cache__linkname(sbuild_id, linkname, size))
                 goto out_free;
         tmp = strrchr(linkname, '/');
@@ -657,27 +731,30 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                 err = 0;
 
         /* Update SDT cache : error is just warned */
-        if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+        if (realname &&
+            build_id_cache__add_sdt_cache(sbuild_id, realname, nsi) < 0)
                 pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
         if (!is_kallsyms)
                 free(realname);
         free(filename);
+        free(debugfile);
         free(dir_name);
         free(linkname);
         return err;
 }
 
 static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
-                                 const char *name, bool is_kallsyms,
-                                 bool is_vdso)
+                                 const char *name, struct nsinfo *nsi,
+                                 bool is_kallsyms, bool is_vdso)
 {
         char sbuild_id[SBUILD_ID_SIZE];
 
         build_id__sprintf(build_id, build_id_size, sbuild_id);
 
-        return build_id_cache__add_s(sbuild_id, name, is_kallsyms, is_vdso);
+        return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms,
+                                     is_vdso);
 }
 
 bool build_id_cache__cached(const char *sbuild_id)
@@ -743,7 +820,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
                 name = nm;
         }
         return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
-                                     is_kallsyms, is_vdso);
+                                     dso->nsinfo, is_kallsyms, is_vdso);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head,
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 96690a55c62c..c94b0dcbfd74 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -5,10 +5,12 @@
 #define SBUILD_ID_SIZE  (BUILD_ID_SIZE * 2 + 1)
 
 #include "tool.h"
+#include "namespaces.h"
 #include <linux/types.h>
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
+struct feat_fd;
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
@@ -16,7 +18,8 @@ int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
                                     size_t size);
 
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+                             bool is_debug);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
@@ -25,23 +28,26 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 int dsos__hit_all(struct perf_session *session);
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
-int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__write_buildid_table(struct perf_session *session,
+                                      struct feat_fd *fd);
 int perf_session__cache_build_ids(struct perf_session *session);
 
 char *build_id_cache__origname(const char *sbuild_id);
 char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
 char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
-                               bool is_kallsyms, bool is_vdso);
+                               struct nsinfo *nsi, bool is_kallsyms,
+                               bool is_vdso);
 
 struct strlist;
 
 struct strlist *build_id_cache__list_all(bool validonly);
 char *build_id_cache__complement(const char *incomplete_sbuild_id);
-int build_id_cache__list_build_ids(const char *pathname,
+int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
                                    struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
 int build_id_cache__add_s(const char *sbuild_id,
-                          const char *name, bool is_kallsyms, bool is_vdso);
+                          const char *name, struct nsinfo *nsi,
+                          bool is_kallsyms, bool is_vdso);
 int build_id_cache__remove_s(const char *sbuild_id);
 
 extern char buildid_dir[];
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index b4204b43ed58..be09d77cade0 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -23,6 +23,7 @@
 #include "sort.h"
 #include "machine.h"
 #include "callchain.h"
+#include "branch.h"
 
 #define CALLCHAIN_PARAM_DEFAULT                 \
         .mode           = CHAIN_GRAPH_ABS,      \
@@ -64,8 +65,6 @@ 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;
 }
 
@@ -81,8 +80,6 @@ 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;
 }
 
@@ -104,8 +101,6 @@ 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;
 }
 
@@ -123,8 +118,6 @@ 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;
 }
 
@@ -303,7 +296,7 @@ int perf_callchain_config(const char *var, const char *value)
 {
         char *endptr;
 
-        if (prefixcmp(var, "call-graph."))
+        if (!strstarts(var, "call-graph."))
                 return 0;
         var += sizeof("call-graph.") - 1;
 
@@ -318,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value)
 
                 return ret;
         }
-        if (!strcmp(var, "print-type"))
-                return parse_callchain_mode(value);
-        if (!strcmp(var, "order"))
-                return parse_callchain_order(value);
-        if (!strcmp(var, "sort-key"))
-                return parse_callchain_sort_key(value);
+        if (!strcmp(var, "print-type")){
+                int ret;
+                ret = parse_callchain_mode(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain mode: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "order")){
+                int ret;
+                ret = parse_callchain_order(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain order: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "sort-key")){
+                int ret;
+                ret = parse_callchain_sort_key(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain sort key: %s\n", value);
+                return ret;
+        }
         if (!strcmp(var, "threshold")) {
                 callchain_param.min_percent = strtod(value, &endptr);
                 if (value == endptr) {
@@ -562,15 +570,33 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 if (cursor_node->branch) {
                         call->branch_count = 1;
 
-                        if (cursor_node->branch_flags.predicted)
-                                call->predicted_count = 1;
-
-                        if (cursor_node->branch_flags.abort)
-                                call->abort_count = 1;
-
-                        call->cycles_count = cursor_node->branch_flags.cycles;
-                        call->iter_count = cursor_node->nr_loop_iter;
-                        call->samples_count = cursor_node->samples;
+                        if (cursor_node->branch_from) {
+                                /*
+                                 * branch_from is set with value somewhere else
+                                 * to imply it's "to" of a branch.
+                                 */
+                                call->brtype_stat.branch_to = true;
+
+                                if (cursor_node->branch_flags.predicted)
+                                        call->predicted_count = 1;
+
+                                if (cursor_node->branch_flags.abort)
+                                        call->abort_count = 1;
+
+                                branch_type_count(&call->brtype_stat,
+                                                  &cursor_node->branch_flags,
+                                                  cursor_node->branch_from,
+                                                  cursor_node->ip);
+                        } else {
+                                /*
+                                 * It's "from" of a branch
+                                 */
+                                call->brtype_stat.branch_to = false;
+                                call->cycles_count =
+                                        cursor_node->branch_flags.cycles;
+                                call->iter_count = cursor_node->nr_loop_iter;
+                                call->iter_cycles = cursor_node->iter_cycles;
+                        }
                 }
 
                 list_add_tail(&call->list, &node->val);
@@ -679,15 +705,32 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
                 if (node->branch) {
                         cnode->branch_count++;
 
-                        if (node->branch_flags.predicted)
-                                cnode->predicted_count++;
-
-                        if (node->branch_flags.abort)
-                                cnode->abort_count++;
-
-                        cnode->cycles_count += node->branch_flags.cycles;
-                        cnode->iter_count += node->nr_loop_iter;
-                        cnode->samples_count += node->samples;
+                        if (node->branch_from) {
+                                /*
+                                 * It's "to" of a branch
+                                 */
+                                cnode->brtype_stat.branch_to = true;
+
+                                if (node->branch_flags.predicted)
+                                        cnode->predicted_count++;
+
+                                if (node->branch_flags.abort)
+                                        cnode->abort_count++;
+
+                                branch_type_count(&cnode->brtype_stat,
+                                                  &node->branch_flags,
+                                                  node->branch_from,
+                                                  node->ip);
+                        } else {
+                                /*
+                                 * It's "from" of a branch
+                                 */
+                                cnode->brtype_stat.branch_to = false;
+                                cnode->cycles_count +=
+                                        node->branch_flags.cycles;
+                                cnode->iter_count += node->nr_loop_iter;
+                                cnode->iter_cycles += node->iter_cycles;
+                        }
                 }
 
                 return MATCH_EQ;
@@ -922,7 +965,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
         list_for_each_entry_safe(list, next_list, &src->val, list) {
                 callchain_cursor_append(cursor, list->ip,
                                         list->ms.map, list->ms.sym,
-                                        false, NULL, 0, 0);
+                                        false, NULL, 0, 0, 0);
                 list_del(&list->list);
                 map__zput(list->ms.map);
                 free(list);
@@ -962,7 +1005,7 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
                             u64 ip, struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples)
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from)
 {
         struct callchain_cursor_node *node = *cursor->last;
 
@@ -980,12 +1023,13 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         node->sym = sym;
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
-        node->samples = samples;
+        node->iter_cycles = iter_cycles;
 
         if (flags)
                 memcpy(&node->branch_flags, flags,
                         sizeof(struct branch_flags));
 
+        node->branch_from = branch_from;
         cursor->nr++;
 
         cursor->last = &node->next;
@@ -998,11 +1042,11 @@ int sample__resolve_callchain(struct perf_sample *sample,
                               struct perf_evsel *evsel, struct addr_location *al,
                               int max_stack)
 {
-        if (sample->callchain == NULL)
+        if (sample->callchain == NULL && !symbol_conf.show_branchflag_count)
                 return 0;
 
         if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
-            perf_hpp_list.parent) {
+            perf_hpp_list.parent || symbol_conf.show_branchflag_count) {
                 return thread__resolve_callchain(al->thread, cursor, evsel, sample,
                                                  parent, al, max_stack);
         }
@@ -1011,7 +1055,8 @@ int sample__resolve_callchain(struct perf_sample *sample,
 
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
 {
-        if (!symbol_conf.use_callchain || sample->callchain == NULL)
+        if ((!symbol_conf.use_callchain || sample->callchain == NULL) &&
+                !symbol_conf.show_branchflag_count)
                 return 0;
         return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
@@ -1214,95 +1259,124 @@ int callchain_branch_counts(struct callchain_root *root,
                                                   cycles_count);
 }
 
-static int counts_str_build(char *bf, int bfsize,
-                             u64 branch_count, u64 predicted_count,
-                             u64 abort_count, u64 cycles_count,
-                             u64 iter_count, u64 samples_count)
+static int count_pri64_printf(int idx, const char *str, u64 value, char *bf, int bfsize)
 {
-        double predicted_percent = 0.0;
-        const char *null_str = "";
-        char iter_str[32];
-        char cycle_str[32];
-        char *istr, *cstr;
-        u64 cycles;
+        int printed;
 
-        if (branch_count == 0)
-                return scnprintf(bf, bfsize, " (calltrace)");
+        printed = scnprintf(bf, bfsize, "%s%s:%" PRId64 "", (idx) ? " " : " (", str, value);
 
-        cycles = cycles_count / branch_count;
+        return printed;
+}
 
-        if (iter_count && samples_count) {
-                if (cycles > 0)
-                        scnprintf(iter_str, sizeof(iter_str),
-                                 " iterations:%" PRId64 "",
-                                 iter_count / samples_count);
-                else
-                        scnprintf(iter_str, sizeof(iter_str),
-                                 "iterations:%" PRId64 "",
-                                 iter_count / samples_count);
-                istr = iter_str;
-        } else
-                istr = (char *)null_str;
+static int count_float_printf(int idx, const char *str, float value,
+                              char *bf, int bfsize, float threshold)
+{
+        int printed;
 
-        if (cycles > 0) {
-                scnprintf(cycle_str, sizeof(cycle_str),
-                          "cycles:%" PRId64 "", cycles);
-                cstr = cycle_str;
-        } else
-                cstr = (char *)null_str;
+        if (threshold != 0.0 && value < threshold)
+                return 0;
 
-        predicted_percent = predicted_count * 100.0 / branch_count;
+        printed = scnprintf(bf, bfsize, "%s%s:%.1f%%", (idx) ? " " : " (", str, value);
 
-        if ((predicted_count == branch_count) && (abort_count == 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
-                else
-                        return scnprintf(bf, bfsize, "%s", (char *)null_str);
-        }
-
-        if ((predicted_count < branch_count) && (abort_count == 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize,
-                                " (predicted:%.1f%% %s%s)",
-                                predicted_percent, cstr, istr);
-                else {
-                        return scnprintf(bf, bfsize,
-                                " (predicted:%.1f%%)",
-                                predicted_percent);
-                }
+        return printed;
+}
+
+static int branch_to_str(char *bf, int bfsize,
+                         u64 branch_count, u64 predicted_count,
+                         u64 abort_count,
+                         struct branch_type_stat *brtype_stat)
+{
+        int printed, i = 0;
+
+        printed = branch_type_str(brtype_stat, bf, bfsize);
+        if (printed)
+                i++;
+
+        if (predicted_count < branch_count) {
+                printed += count_float_printf(i++, "predicted",
+                                predicted_count * 100.0 / branch_count,
+                                bf + printed, bfsize - printed, 0.0);
         }
 
-        if ((predicted_count == branch_count) && (abort_count > 0)) {
-                if ((cycles > 0) || (istr != (char *)null_str))
-                        return scnprintf(bf, bfsize,
-                                " (abort:%" PRId64 " %s%s)",
-                                abort_count, cstr, istr);
-                else
-                        return scnprintf(bf, bfsize,
-                                " (abort:%" PRId64 ")",
-                                abort_count);
+        if (abort_count) {
+                printed += count_float_printf(i++, "abort",
+                                abort_count * 100.0 / branch_count,
+                                bf + printed, bfsize - printed, 0.1);
         }
 
-        if ((cycles > 0) || (istr != (char *)null_str))
-                return scnprintf(bf, bfsize,
-                        " (predicted:%.1f%% abort:%" PRId64 " %s%s)",
-                        predicted_percent, abort_count, cstr, istr);
+        if (i)
+                printed += scnprintf(bf + printed, bfsize - printed, ")");
 
-        return scnprintf(bf, bfsize,
-                        " (predicted:%.1f%% abort:%" PRId64 ")",
-                        predicted_percent, abort_count);
+        return printed;
+}
+
+static int branch_from_str(char *bf, int bfsize,
+                           u64 branch_count,
+                           u64 cycles_count, u64 iter_count,
+                           u64 iter_cycles)
+{
+        int printed = 0, i = 0;
+        u64 cycles;
+
+        cycles = cycles_count / branch_count;
+        if (cycles) {
+                printed += count_pri64_printf(i++, "cycles",
+                                cycles,
+                                bf + printed, bfsize - printed);
+        }
+
+        if (iter_count) {
+                printed += count_pri64_printf(i++, "iter",
+                                iter_count,
+                                bf + printed, bfsize - printed);
+
+                printed += count_pri64_printf(i++, "avg_cycles",
+                                iter_cycles / iter_count,
+                                bf + printed, bfsize - printed);
+        }
+
+        if (i)
+                printed += scnprintf(bf + printed, bfsize - printed, ")");
+
+        return printed;
+}
+
+static int counts_str_build(char *bf, int bfsize,
+                             u64 branch_count, u64 predicted_count,
+                             u64 abort_count, u64 cycles_count,
+                             u64 iter_count, u64 iter_cycles,
+                             struct branch_type_stat *brtype_stat)
+{
+        int printed;
+
+        if (branch_count == 0)
+                return scnprintf(bf, bfsize, " (calltrace)");
+
+        if (brtype_stat->branch_to) {
+                printed = branch_to_str(bf, bfsize, branch_count,
+                                predicted_count, abort_count, brtype_stat);
+        } else {
+                printed = branch_from_str(bf, bfsize, branch_count,
+                                cycles_count, iter_count, iter_cycles);
+        }
+
+        if (!printed)
+                bf[0] = 0;
+
+        return printed;
 }
 
 static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
                                    u64 branch_count, u64 predicted_count,
                                    u64 abort_count, u64 cycles_count,
-                                   u64 iter_count, u64 samples_count)
+                                   u64 iter_count, u64 iter_cycles,
+                                   struct branch_type_stat *brtype_stat)
 {
-        char str[128];
+        char str[256];
 
         counts_str_build(str, sizeof(str), branch_count,
                          predicted_count, abort_count, cycles_count,
-                         iter_count, samples_count);
+                         iter_count, iter_cycles, brtype_stat);
 
         if (fp)
                 return fprintf(fp, "%s", str);
@@ -1310,31 +1384,24 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
         return scnprintf(bf, bfsize, "%s", str);
 }
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize)
 {
         u64 branch_count, predicted_count;
         u64 abort_count, cycles_count;
-        u64 iter_count = 0, samples_count = 0;
+        u64 iter_count, iter_cycles;
 
         branch_count = clist->branch_count;
         predicted_count = clist->predicted_count;
         abort_count = clist->abort_count;
         cycles_count = clist->cycles_count;
-
-        if (node) {
-                struct callchain_list *call;
-
-                list_for_each_entry(call, &node->val, list) {
-                        iter_count += call->iter_count;
-                        samples_count += call->samples_count;
-                }
-        }
+        iter_count = clist->iter_count;
+        iter_cycles = clist->iter_cycles;
 
         return callchain_counts_printf(fp, bf, bfsize, branch_count,
                                        predicted_count, abort_count,
-                                       cycles_count, iter_count, samples_count);
+                                       cycles_count, iter_count, iter_cycles,
+                                       &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
@@ -1459,7 +1526,9 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
                 rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
                                              node->branch, &node->branch_flags,
-                                             node->nr_loop_iter, node->samples);
+                                             node->nr_loop_iter,
+                                             node->iter_cycles,
+                                             node->branch_from);
                 if (rc)
                         break;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index c56c23dbbf72..1ed6fc61d0a5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,7 @@
 #include "event.h"
 #include "map.h"
 #include "symbol.h"
+#include "branch.h"
 
 #define HELP_PAD "\t\t\t\t"
 
@@ -118,7 +119,8 @@ struct callchain_list {
         u64                     abort_count;
         u64                     cycles_count;
         u64                     iter_count;
-        u64                     samples_count;
+        u64                     iter_cycles;
+        struct branch_type_stat brtype_stat;
         char                   *srcline;
         struct list_head        list;
 };
@@ -135,8 +137,9 @@ struct callchain_cursor_node {
         struct symbol                   *sym;
         bool                            branch;
         struct branch_flags             branch_flags;
+        u64                             branch_from;
         int                             nr_loop_iter;
-        int                             samples;
+        u64                             iter_cycles;
         struct callchain_cursor_node    *next;
 };
 
@@ -198,7 +201,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
                             struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples);
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
@@ -279,8 +282,7 @@ char *callchain_node__scnprintf_value(struct callchain_node *node,
 int callchain_node__fprintf_value(struct callchain_node *node,
                                   FILE *fp, u64 total);
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize);
 
 void free_callchain(struct callchain_root *root);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 03347748f3fa..0e77bc9e5f3c 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -98,8 +98,10 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                 cgrp = counter->cgrp;
                 if (!cgrp)
                         continue;
-                if (!strcmp(cgrp->name, str))
+                if (!strcmp(cgrp->name, str)) {
+                        refcount_inc(&cgrp->refcnt);
                         break;
+                }
 
                 cgrp = NULL;
         }
@@ -110,6 +112,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                         return -1;
 
                 cgrp->name = str;
+                refcount_set(&cgrp->refcnt, 1);
 
                 cgrp->fd = open_cgroup(str);
                 if (cgrp->fd == -1) {
@@ -128,12 +131,11 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
                         goto found;
                 n++;
         }
-        if (refcount_read(&cgrp->refcnt) == 0)
+        if (refcount_dec_and_test(&cgrp->refcnt))
                 free(cgrp);
 
         return -1;
 found:
-        refcount_inc(&cgrp->refcnt);
         counter->cgrp = cgrp;
         return 0;
 }
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 31a7dea248d0..bc75596f9e79 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -19,6 +19,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include <linux/string.h>
 
 #include "sane_ctype.h"
 
@@ -433,22 +434,22 @@ static int perf_ui_config(const char *var, const char *value)
 int perf_default_config(const char *var, const char *value,
                         void *dummy __maybe_unused)
 {
-        if (!prefixcmp(var, "core."))
+        if (strstarts(var, "core."))
                 return perf_default_core_config(var, value);
 
-        if (!prefixcmp(var, "hist."))
+        if (strstarts(var, "hist."))
                 return perf_hist_config(var, value);
 
-        if (!prefixcmp(var, "ui."))
+        if (strstarts(var, "ui."))
                 return perf_ui_config(var, value);
 
-        if (!prefixcmp(var, "call-graph."))
+        if (strstarts(var, "call-graph."))
                 return perf_callchain_config(var, value);
 
-        if (!prefixcmp(var, "llvm."))
+        if (strstarts(var, "llvm."))
                 return perf_llvm_config(var, value);
 
-        if (!prefixcmp(var, "buildid."))
+        if (strstarts(var, "buildid."))
                 return perf_buildid_config(var, value);
 
         /* Add other config variables here. */
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 34d8baaf558a..cb45a6aecf9d 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -12,6 +12,7 @@ struct perf_counts_values {
                 };
                 u64 values[3];
         };
+        bool    loaded;
 };
 
 struct perf_counts {
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 3149b70799fd..2346cecb8ea2 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -76,6 +76,8 @@ struct ctf_writer {
         struct bt_ctf_event_class       *comm_class;
         struct bt_ctf_event_class       *exit_class;
         struct bt_ctf_event_class       *fork_class;
+        struct bt_ctf_event_class       *mmap_class;
+        struct bt_ctf_event_class       *mmap2_class;
 };
 
 struct convert {
@@ -506,6 +508,81 @@ put_len_type:
         return ret;
 }
 
+static int
+add_callchain_output_values(struct bt_ctf_event_class *event_class,
+                      struct bt_ctf_event *event,
+                      struct ip_callchain *callchain)
+{
+        struct bt_ctf_field_type *len_type, *seq_type;
+        struct bt_ctf_field *len_field, *seq_field;
+        unsigned int nr_elements = callchain->nr;
+        unsigned int i;
+        int ret;
+
+        len_type = bt_ctf_event_class_get_field_by_name(
+                        event_class, "perf_callchain_size");
+        len_field = bt_ctf_field_create(len_type);
+        if (!len_field) {
+                pr_err("failed to create 'perf_callchain_size' for callchain output event\n");
+                ret = -1;
+                goto put_len_type;
+        }
+
+        ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+        if (ret) {
+                pr_err("failed to set field value for perf_callchain_size\n");
+                goto put_len_field;
+        }
+        ret = bt_ctf_event_set_payload(event, "perf_callchain_size", len_field);
+        if (ret) {
+                pr_err("failed to set payload to perf_callchain_size\n");
+                goto put_len_field;
+        }
+
+        seq_type = bt_ctf_event_class_get_field_by_name(
+                        event_class, "perf_callchain");
+        seq_field = bt_ctf_field_create(seq_type);
+        if (!seq_field) {
+                pr_err("failed to create 'perf_callchain' for callchain output event\n");
+                ret = -1;
+                goto put_seq_type;
+        }
+
+        ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+        if (ret) {
+                pr_err("failed to set length of 'perf_callchain'\n");
+                goto put_seq_field;
+        }
+
+        for (i = 0; i < nr_elements; i++) {
+                struct bt_ctf_field *elem_field =
+                        bt_ctf_field_sequence_get_field(seq_field, i);
+
+                ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+                                ((u64 *)(callchain->ips))[i]);
+
+                bt_ctf_field_put(elem_field);
+                if (ret) {
+                        pr_err("failed to set callchain[%d]\n", i);
+                        goto put_seq_field;
+                }
+        }
+
+        ret = bt_ctf_event_set_payload(event, "perf_callchain", seq_field);
+        if (ret)
+                pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+        bt_ctf_field_put(seq_field);
+put_seq_type:
+        bt_ctf_field_type_put(seq_type);
+put_len_field:
+        bt_ctf_field_put(len_field);
+put_len_type:
+        bt_ctf_field_type_put(len_type);
+        return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
                               struct bt_ctf_event *event,
                               struct perf_evsel *evsel,
@@ -519,7 +596,6 @@ static int add_generic_values(struct ctf_writer *cw,
          *   PERF_SAMPLE_TIME         - not needed as we have it in
          *                              ctf event header
          *   PERF_SAMPLE_READ         - TODO
-         *   PERF_SAMPLE_CALLCHAIN    - TODO
          *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
          *   PERF_SAMPLE_BRANCH_STACK - TODO
          *   PERF_SAMPLE_REGS_USER    - TODO
@@ -720,6 +796,7 @@ static int process_sample_event(struct perf_tool *tool,
         struct bt_ctf_event_class *event_class;
         struct bt_ctf_event *event;
         int ret;
+        unsigned long type = evsel->attr.sample_type;
 
         if (WARN_ONCE(!priv, "Failed to setup all events.\n"))
                 return 0;
@@ -751,6 +828,13 @@ static int process_sample_event(struct perf_tool *tool,
                         return -1;
         }
 
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                ret = add_callchain_output_values(event_class,
+                                event, sample->callchain);
+                if (ret)
+                        return -1;
+        }
+
         if (perf_evsel__is_bpf_output(evsel)) {
                 ret = add_bpf_output_values(event_class, event, sample);
                 if (ret)
@@ -833,6 +917,18 @@ __FUNC_PROCESS_NON_SAMPLE(exit,
         __NON_SAMPLE_SET_FIELD(fork, u32, ptid);
         __NON_SAMPLE_SET_FIELD(fork, u64, time);
 )
+__FUNC_PROCESS_NON_SAMPLE(mmap,
+        __NON_SAMPLE_SET_FIELD(mmap, u32, pid);
+        __NON_SAMPLE_SET_FIELD(mmap, u32, tid);
+        __NON_SAMPLE_SET_FIELD(mmap, u64_hex, start);
+        __NON_SAMPLE_SET_FIELD(mmap, string, filename);
+)
+__FUNC_PROCESS_NON_SAMPLE(mmap2,
+        __NON_SAMPLE_SET_FIELD(mmap2, u32, pid);
+        __NON_SAMPLE_SET_FIELD(mmap2, u32, tid);
+        __NON_SAMPLE_SET_FIELD(mmap2, u64_hex, start);
+        __NON_SAMPLE_SET_FIELD(mmap2, string, filename);
+)
 #undef __NON_SAMPLE_SET_FIELD
 #undef __FUNC_PROCESS_NON_SAMPLE
 
@@ -1043,6 +1139,14 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
         if (type & PERF_SAMPLE_TRANSACTION)
                 ADD_FIELD(event_class, cw->data.u64, "perf_transaction");
 
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                ADD_FIELD(event_class, cw->data.u32, "perf_callchain_size");
+                ADD_FIELD(event_class,
+                        bt_ctf_field_type_sequence_create(
+                                cw->data.u64_hex, "perf_callchain_size"),
+                        "perf_callchain");
+        }
+
 #undef ADD_FIELD
         return 0;
 }
@@ -1164,6 +1268,19 @@ __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit,
         __NON_SAMPLE_ADD_FIELD(u64, time);
 )
 
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u64_hex, start);
+        __NON_SAMPLE_ADD_FIELD(string, filename);
+)
+
+__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(mmap2,
+        __NON_SAMPLE_ADD_FIELD(u32, pid);
+        __NON_SAMPLE_ADD_FIELD(u32, tid);
+        __NON_SAMPLE_ADD_FIELD(u64_hex, start);
+        __NON_SAMPLE_ADD_FIELD(string, filename);
+)
 #undef __NON_SAMPLE_ADD_FIELD
 #undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS
 
@@ -1181,6 +1298,12 @@ static int setup_non_sample_events(struct ctf_writer *cw,
         ret = add_fork_event(cw);
         if (ret)
                 return ret;
+        ret = add_mmap_event(cw);
+        if (ret)
+                return ret;
+        ret = add_mmap2_event(cw);
+        if (ret)
+                return ret;
         return 0;
 }
 
@@ -1482,6 +1605,8 @@ int bt_convert__perf2ctf(const char *input, const char *path,
                 c.tool.comm = process_comm_event;
                 c.tool.exit = process_exit_event;
                 c.tool.fork = process_fork_event;
+                c.tool.mmap = process_mmap_event;
+                c.tool.mmap2 = process_mmap2_event;
         }
 
         err = perf_config(convert__config, &c);
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index e84bbc8ec058..263f5a906ba5 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -10,6 +10,16 @@
 #include "util.h"
 #include "debug.h"
 
+#ifndef O_CLOEXEC
+#ifdef __sparc__
+#define O_CLOEXEC       0x400000
+#elif defined(__alpha__) || defined(__hppa__)
+#define O_CLOEXEC       010000000
+#else
+#define O_CLOEXEC       02000000
+#endif
+#endif
+
 static bool check_pipe(struct perf_data_file *file)
 {
         struct stat st;
@@ -96,7 +106,8 @@ static int open_file_write(struct perf_data_file *file)
         if (check_backup(file))
                 return -1;
 
-        fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+        fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+                  S_IRUSR|S_IWUSR);
 
         if (fd < 0)
                 pr_err("failed to open %s : %s\n", file->path,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 4e7ab611377a..b9e087fb8247 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -32,6 +32,7 @@ char dso__symtab_origin(const struct dso *dso)
                 [DSO_BINARY_TYPE__JAVA_JIT]                     = 'j',
                 [DSO_BINARY_TYPE__DEBUGLINK]                    = 'l',
                 [DSO_BINARY_TYPE__BUILD_ID_CACHE]               = 'B',
+                [DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO]     = 'D',
                 [DSO_BINARY_TYPE__FEDORA_DEBUGINFO]             = 'f',
                 [DSO_BINARY_TYPE__UBUNTU_DEBUGINFO]             = 'u',
                 [DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO]       = 'o',
@@ -97,7 +98,12 @@ int dso__read_binary_type_filename(const struct dso *dso,
                 break;
         }
         case DSO_BINARY_TYPE__BUILD_ID_CACHE:
-                if (dso__build_id_filename(dso, filename, size) == NULL)
+                if (dso__build_id_filename(dso, filename, size, false) == NULL)
+                        ret = -1;
+                break;
+
+        case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
+                if (dso__build_id_filename(dso, filename, size, true) == NULL)
                         ret = -1;
                 break;
 
@@ -504,7 +510,14 @@ static void check_data_close(void);
  */
 static int open_dso(struct dso *dso, struct machine *machine)
 {
-        int fd = __open_dso(dso, machine);
+        int fd;
+        struct nscookie nsc;
+
+        if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
+                nsinfo__mountns_enter(dso->nsinfo, &nsc);
+        fd = __open_dso(dso, machine);
+        if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
+                nsinfo__mountns_exit(&nsc);
 
         if (fd >= 0) {
                 dso__list_add(dso);
@@ -1236,6 +1249,7 @@ void dso__delete(struct dso *dso)
         dso_cache__free(dso);
         dso__free_a2l(dso);
         zfree(&dso->symsrc_filename);
+        nsinfo__zput(dso->nsinfo);
         pthread_mutex_destroy(&dso->lock);
         free(dso);
 }
@@ -1301,6 +1315,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 {
         bool have_build_id = false;
         struct dso *pos;
+        struct nscookie nsc;
 
         list_for_each_entry(pos, head, node) {
                 if (with_hits && !pos->hit && !dso__is_vdso(pos))
@@ -1309,11 +1324,13 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
                         have_build_id = true;
                         continue;
                 }
+                nsinfo__mountns_enter(pos->nsinfo, &nsc);
                 if (filename__read_build_id(pos->long_name, pos->build_id,
                                             sizeof(pos->build_id)) > 0) {
                         have_build_id     = true;
                         pos->has_build_id = true;
                 }
+                nsinfo__mountns_exit(&nsc);
         }
 
         return have_build_id;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index bd061ba7b47c..f886141678eb 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
+#include "namespaces.h"
 #include "build-id.h"
 
 enum dso_binary_type {
@@ -20,6 +21,7 @@ enum dso_binary_type {
         DSO_BINARY_TYPE__JAVA_JIT,
         DSO_BINARY_TYPE__DEBUGLINK,
         DSO_BINARY_TYPE__BUILD_ID_CACHE,
+        DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
         DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
         DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
@@ -187,6 +189,7 @@ struct dso {
                 void     *priv;
                 u64      db_id;
         };
+        struct nsinfo   *nsinfo;
         refcount_t       refcnt;
         char             name[0];
 };
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dc5c3bb69d73..1c905ba3641b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -57,6 +57,7 @@ static const char *perf_event__names[] = {
         [PERF_RECORD_STAT_ROUND]                = "STAT_ROUND",
         [PERF_RECORD_EVENT_UPDATE]              = "EVENT_UPDATE",
         [PERF_RECORD_TIME_CONV]                 = "TIME_CONV",
+        [PERF_RECORD_HEADER_FEATURE]            = "FEATURE",
 };
 
 static const char *perf_ns__names[] = {
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 9967c87af7a6..ee7bcc898d35 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -142,7 +142,8 @@ struct branch_flags {
         u64 in_tx:1;
         u64 abort:1;
         u64 cycles:16;
-        u64 reserved:44;
+        u64 type:4;
+        u64 reserved:40;
 };
 
 struct branch_entry {
@@ -199,6 +200,7 @@ struct perf_sample {
         u32 cpu;
         u32 raw_size;
         u64 data_src;
+        u64 phys_addr;
         u32 flags;
         u16 insn_len;
         u8  cpumode;
@@ -244,6 +246,7 @@ enum perf_user_event_type { /* above any possible kernel type */
         PERF_RECORD_STAT_ROUND                  = 77,
         PERF_RECORD_EVENT_UPDATE                = 78,
         PERF_RECORD_TIME_CONV                   = 79,
+        PERF_RECORD_HEADER_FEATURE              = 80,
         PERF_RECORD_HEADER_MAX
 };
 
@@ -609,6 +612,12 @@ struct time_conv_event {
         u64 time_zero;
 };
 
+struct feature_event {
+        struct perf_event_header        header;
+        u64                             feat_id;
+        char                            data[];
+};
+
 union perf_event {
         struct perf_event_header        header;
         struct mmap_event               mmap;
@@ -639,6 +648,7 @@ union perf_event {
         struct stat_event               stat;
         struct stat_round_event         stat_round;
         struct time_conv_event          time_conv;
+        struct feature_event            feat;
 };
 
 void perf_event__print_totals(void);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 46c0faf6c502..6a0d7ffbeba0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -242,9 +242,9 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
         }
 }
 
-int perf_evlist__add_default(struct perf_evlist *evlist)
+int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
-        struct perf_evsel *evsel = perf_evsel__new_cycles();
+        struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
 
         if (evsel == NULL)
                 return -ENOMEM;
@@ -1419,8 +1419,6 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
 {
         struct perf_evsel *evsel;
         int err = 0;
-        const int ncpus = cpu_map__nr(evlist->cpus),
-                  nthreads = thread_map__nr(evlist->threads);
 
         evlist__for_each_entry(evlist, evsel) {
                 if (evsel->filter == NULL)
@@ -1430,7 +1428,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e
                  * filters only work for tracepoint event, which doesn't have cpu limit.
                  * So evlist and evsel should always be same.
                  */
-                err = perf_evsel__apply_filter(evsel, ncpus, nthreads, evsel->filter);
+                err = perf_evsel__apply_filter(evsel, evsel->filter);
                 if (err) {
                         *err_evsel = evsel;
                         break;
@@ -1623,13 +1621,9 @@ void perf_evlist__set_selected(struct perf_evlist *evlist,
 void perf_evlist__close(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
-        int ncpus = cpu_map__nr(evlist->cpus);
-        int nthreads = thread_map__nr(evlist->threads);
 
-        evlist__for_each_entry_reverse(evlist, evsel) {
-                int n = evsel->cpus ? evsel->cpus->nr : ncpus;
-                perf_evsel__close(evsel, n, nthreads);
-        }
+        evlist__for_each_entry_reverse(evlist, evsel)
+                perf_evsel__close(evsel);
 }
 
 static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8d601fbdd8d6..bf2c4936e35f 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -115,7 +115,14 @@ void perf_evlist__delete(struct perf_evlist *evlist);
 
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
 void perf_evlist__remove(struct perf_evlist *evlist, struct perf_evsel *evsel);
-int perf_evlist__add_default(struct perf_evlist *evlist);
+
+int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise);
+
+static inline int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+        return __perf_evlist__add_default(evlist, true);
+}
+
 int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
                                      struct perf_event_attr *attrs, size_t nr_attrs);
 
@@ -258,6 +265,11 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
                                    struct list_head *list);
 
+static inline bool perf_evlist__empty(struct perf_evlist *evlist)
+{
+        return list_empty(&evlist->entries);
+}
+
 static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
 {
         return list_entry(evlist->entries.next, struct perf_evsel, node);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 413f74df08de..0dccdb89572c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -49,6 +49,7 @@ static struct {
         bool clockid_wrong;
         bool lbr_flags;
         bool write_backward;
+        bool group_read;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -58,6 +59,8 @@ static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
         return 0;
 }
 
+void __weak test_attr__ready(void) { }
+
 static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
 {
 }
@@ -268,16 +271,24 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         return evsel;
 }
 
-struct perf_evsel *perf_evsel__new_cycles(void)
+static bool perf_event_can_profile_kernel(void)
+{
+        return geteuid() == 0 || perf_event_paranoid() == -1;
+}
+
+struct perf_evsel *perf_evsel__new_cycles(bool precise)
 {
         struct perf_event_attr attr = {
                 .type   = PERF_TYPE_HARDWARE,
                 .config = PERF_COUNT_HW_CPU_CYCLES,
-                .exclude_kernel = geteuid() != 0,
+                .exclude_kernel = !perf_event_can_profile_kernel(),
         };
         struct perf_evsel *evsel;
 
         event_attr_init(&attr);
+
+        if (!precise)
+                goto new_event;
         /*
          * Unnamed union member, not supported as struct member named
          * initializer in older compilers such as gcc 4.4.7
@@ -292,7 +303,7 @@ struct perf_evsel *perf_evsel__new_cycles(void)
          * to kick in when we return and before perf_evsel__open() is called.
          */
         attr.sample_period = 0;
-
+new_event:
         evsel = perf_evsel__new(&attr);
         if (evsel == NULL)
                 goto out;
@@ -896,8 +907,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         if (opts->no_samples)
                 attr->sample_freq = 0;
 
-        if (opts->inherit_stat)
+        if (opts->inherit_stat) {
+                evsel->attr.read_format |=
+                        PERF_FORMAT_TOTAL_TIME_ENABLED |
+                        PERF_FORMAT_TOTAL_TIME_RUNNING |
+                        PERF_FORMAT_ID;
                 attr->inherit_stat = 1;
+        }
 
         if (opts->sample_address) {
                 perf_evsel__set_sample_bit(evsel, ADDR);
@@ -944,6 +960,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         if (opts->sample_address)
                 perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
+        if (opts->sample_phys_addr)
+                perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+
         if (opts->no_buffering) {
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
@@ -1045,16 +1064,13 @@ static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthread
         return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
-static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads,
+static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
                           int ioc,  void *arg)
 {
         int cpu, thread;
 
-        if (evsel->system_wide)
-                nthreads = 1;
-
-        for (cpu = 0; cpu < ncpus; cpu++) {
-                for (thread = 0; thread < nthreads; thread++) {
+        for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+                for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
                         int fd = FD(evsel, cpu, thread),
                             err = ioctl(fd, ioc, arg);
 
@@ -1066,10 +1082,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
         return 0;
 }
 
-int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
-                             const char *filter)
+int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_SET_FILTER,
                                      (void *)filter);
 }
@@ -1116,20 +1131,14 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-        int nthreads = thread_map__nr(evsel->threads);
-        int ncpus = cpu_map__nr(evsel->cpus);
-
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_ENABLE,
                                      0);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-        int nthreads = thread_map__nr(evsel->threads);
-        int ncpus = cpu_map__nr(evsel->cpus);
-
-        return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+        return perf_evsel__run_ioctl(evsel,
                                      PERF_EVENT_IOC_DISABLE,
                                      0);
 }
@@ -1179,15 +1188,12 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
         }
 }
 
-void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
         int cpu, thread;
 
-        if (evsel->system_wide)
-                nthreads = 1;
-
-        for (cpu = 0; cpu < ncpus; cpu++)
-                for (thread = 0; thread < nthreads; ++thread) {
+        for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
+                for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
                         close(FD(evsel, cpu, thread));
                         FD(evsel, cpu, thread) = -1;
                 }
@@ -1256,20 +1262,148 @@ void perf_counts_values__scale(struct perf_counts_values *count,
                 *pscaled = scaled;
 }
 
+static int perf_evsel__read_size(struct perf_evsel *evsel)
+{
+        u64 read_format = evsel->attr.read_format;
+        int entry = sizeof(u64); /* value */
+        int size = 0;
+        int nr = 1;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                size += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                size += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_ID)
+                entry += sizeof(u64);
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                nr = evsel->nr_members;
+                size += sizeof(u64);
+        }
+
+        size += entry * nr;
+        return size;
+}
+
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
                      struct perf_counts_values *count)
 {
+        size_t size = perf_evsel__read_size(evsel);
+
         memset(count, 0, sizeof(*count));
 
         if (FD(evsel, cpu, thread) < 0)
                 return -EINVAL;
 
-        if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0)
+        if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
                 return -errno;
 
         return 0;
 }
 
+static int
+perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread)
+{
+        struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
+
+        return perf_evsel__read(evsel, cpu, thread, count);
+}
+
+static void
+perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread,
+                      u64 val, u64 ena, u64 run)
+{
+        struct perf_counts_values *count;
+
+        count = perf_counts(counter->counts, cpu, thread);
+
+        count->val    = val;
+        count->ena    = ena;
+        count->run    = run;
+        count->loaded = true;
+}
+
+static int
+perf_evsel__process_group_data(struct perf_evsel *leader,
+                               int cpu, int thread, u64 *data)
+{
+        u64 read_format = leader->attr.read_format;
+        struct sample_read_value *v;
+        u64 nr, ena = 0, run = 0, i;
+
+        nr = *data++;
+
+        if (nr != (u64) leader->nr_members)
+                return -EINVAL;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                ena = *data++;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                run = *data++;
+
+        v = (struct sample_read_value *) data;
+
+        perf_evsel__set_count(leader, cpu, thread,
+                              v[0].value, ena, run);
+
+        for (i = 1; i < nr; i++) {
+                struct perf_evsel *counter;
+
+                counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
+                if (!counter)
+                        return -EINVAL;
+
+                perf_evsel__set_count(counter, cpu, thread,
+                                      v[i].value, ena, run);
+        }
+
+        return 0;
+}
+
+static int
+perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
+{
+        struct perf_stat_evsel *ps = leader->priv;
+        u64 read_format = leader->attr.read_format;
+        int size = perf_evsel__read_size(leader);
+        u64 *data = ps->group_data;
+
+        if (!(read_format & PERF_FORMAT_ID))
+                return -EINVAL;
+
+        if (!perf_evsel__is_group_leader(leader))
+                return -EINVAL;
+
+        if (!data) {
+                data = zalloc(size);
+                if (!data)
+                        return -ENOMEM;
+
+                ps->group_data = data;
+        }
+
+        if (FD(leader, cpu, thread) < 0)
+                return -EINVAL;
+
+        if (readn(FD(leader, cpu, thread), data, size) <= 0)
+                return -errno;
+
+        return perf_evsel__process_group_data(leader, cpu, thread, data);
+}
+
+int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread)
+{
+        u64 read_format = evsel->attr.read_format;
+
+        if (read_format & PERF_FORMAT_GROUP)
+                return perf_evsel__read_group(evsel, cpu, thread);
+        else
+                return perf_evsel__read_one(evsel, cpu, thread);
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
                               int cpu, int thread, bool scale)
 {
@@ -1338,7 +1472,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
                 bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
-                bit_name(WEIGHT),
+                bit_name(WEIGHT), bit_name(PHYS_ADDR),
                 { .name = NULL, }
         };
 #undef bit_name
@@ -1545,6 +1679,8 @@ fallback_missing_features:
         if (perf_missing_features.lbr_flags)
                 evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
                                      PERF_SAMPLE_BRANCH_NO_CYCLES);
+        if (perf_missing_features.group_read && evsel->attr.inherit)
+                evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
 retry_sample_id:
         if (perf_missing_features.sample_id_all)
                 evsel->attr.sample_id_all = 0;
@@ -1569,6 +1705,8 @@ retry_open:
                         pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
                                   pid, cpus->map[cpu], group_fd, flags);
 
+                        test_attr__ready();
+
                         fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
                                                  group_fd, flags);
 
@@ -1664,31 +1802,45 @@ try_fallback:
          */
         if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
                 perf_missing_features.write_backward = true;
+                pr_debug2("switching off write_backward\n");
                 goto out_close;
         } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
                 perf_missing_features.clockid_wrong = true;
+                pr_debug2("switching off clockid\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
                 perf_missing_features.clockid = true;
+                pr_debug2("switching off use_clockid\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
                 perf_missing_features.cloexec = true;
+                pr_debug2("switching off cloexec flag\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
                 perf_missing_features.mmap2 = true;
+                pr_debug2("switching off mmap2\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.exclude_guest &&
                    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
                 perf_missing_features.exclude_guest = true;
+                pr_debug2("switching off exclude_guest, exclude_host\n");
                 goto fallback_missing_features;
         } else if (!perf_missing_features.sample_id_all) {
                 perf_missing_features.sample_id_all = true;
+                pr_debug2("switching off sample_id_all\n");
                 goto retry_sample_id;
         } else if (!perf_missing_features.lbr_flags &&
                         (evsel->attr.branch_sample_type &
                          (PERF_SAMPLE_BRANCH_NO_CYCLES |
                           PERF_SAMPLE_BRANCH_NO_FLAGS))) {
                 perf_missing_features.lbr_flags = true;
+                pr_debug2("switching off branch sample type no (cycles/flags)\n");
+                goto fallback_missing_features;
+        } else if (!perf_missing_features.group_read &&
+                    evsel->attr.inherit &&
+                   (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+                perf_missing_features.group_read = true;
+                pr_debug2("switching off group read\n");
                 goto fallback_missing_features;
         }
 out_close:
@@ -1702,12 +1854,12 @@ out_close:
         return err;
 }
 
-void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
+void perf_evsel__close(struct perf_evsel *evsel)
 {
         if (evsel->fd == NULL)
                 return;
 
-        perf_evsel__close_fd(evsel, ncpus, nthreads);
+        perf_evsel__close_fd(evsel);
         perf_evsel__free_fd(evsel);
 }
 
@@ -2062,6 +2214,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 }
         }
 
+        data->phys_addr = 0;
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                data->phys_addr = *array;
+                array++;
+        }
+
         return 0;
 }
 
@@ -2167,6 +2325,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                result += sizeof(u64);
+
         return result;
 }
 
@@ -2356,6 +2517,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                *array = sample->phys_addr;
+                array++;
+        }
+
         return 0;
 }
 
@@ -2535,7 +2701,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
                  "unprivileged users (without CAP_SYS_ADMIN).\n\n"
                  "The current value is %d:\n\n"
                  "  -1: Allow use of (almost) all events by all users\n"
-                 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+                 "      Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
+                 ">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
+                 "      Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
                  ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
                  ">= 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"
@@ -2610,3 +2778,10 @@ char *perf_evsel__env_arch(struct perf_evsel *evsel)
                 return evsel->evlist->env->arch;
         return NULL;
 }
+
+char *perf_evsel__env_cpuid(struct perf_evsel *evsel)
+{
+        if (evsel && evsel->evlist && evsel->evlist->env)
+                return evsel->evlist->env->cpuid;
+        return NULL;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d101695c482c..dd2c4b5112a5 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,7 @@ struct perf_evsel {
         bool                    cmdline_group_boundary;
         struct list_head        config_terms;
         int                     bpf_fd;
+        bool                    auto_merge_stats;
         bool                    merged_stat;
         const char *            metric_expr;
         const char *            metric_name;
@@ -185,7 +186,7 @@ static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *
         return perf_evsel__newtp_idx(sys, name, 0);
 }
 
-struct perf_evsel *perf_evsel__new_cycles(void);
+struct perf_evsel *perf_evsel__new_cycles(bool precise);
 
 struct event_format *event_format__new(const char *sys, const char *name);
 
@@ -226,7 +227,7 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__close_fd(struct perf_evsel *evsel);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
                                   enum perf_event_sample_format bit);
@@ -246,8 +247,7 @@ int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__append_addr_filter(struct perf_evsel *evsel,
                                    const char *filter);
-int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
-                             const char *filter);
+int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 int perf_evsel__enable(struct perf_evsel *evsel);
 int perf_evsel__disable(struct perf_evsel *evsel);
 
@@ -257,7 +257,7 @@ int perf_evsel__open_per_thread(struct perf_evsel *evsel,
                                 struct thread_map *threads);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
                      struct thread_map *threads);
-void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__close(struct perf_evsel *evsel);
 
 struct perf_sample;
 
@@ -299,6 +299,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
                      struct perf_counts_values *count);
 
+int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
                               int cpu, int thread, bool scale);
 
@@ -436,5 +438,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
                              attr__fprintf_f attr__fprintf, void *priv);
 
 char *perf_evsel__env_arch(struct perf_evsel *evsel);
+char *perf_evsel__env_cpuid(struct perf_evsel *evsel);
 
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 9c2760a1a96e..400ef9eab00a 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -1,7 +1,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 8
+#define EXPR_MAX_OTHER 15
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct parse_id {
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 954556bea36e..432b8560cf51 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -4,6 +4,7 @@
 #include "util/debug.h"
 #define IN_EXPR_Y 1
 #include "expr.h"
+#include "smt.h"
 #include <string.h>
 
 #define MAXIDLEN 256
@@ -22,13 +23,15 @@
 
 %token <num> NUMBER
 %token <id> ID
+%token MIN MAX IF ELSE SMT_ON
+%left MIN MAX IF
 %left '|'
 %left '^'
 %left '&'
 %left '-' '+'
 %left '*' '/' '%'
 %left NEG NOT
-%type <num> expr
+%type <num> expr if_expr
 
 %{
 static int expr__lex(YYSTYPE *res, const char **pp);
@@ -57,22 +60,33 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
 %}
 %%
 
-all_expr: expr                  { *final_val = $1; }
+all_expr: if_expr                       { *final_val = $1; }
+        ;
+
+if_expr:
+        expr IF expr ELSE expr { $$ = $3 ? $1 : $5; }
+        | expr
         ;
 
 expr:     NUMBER
         | ID                    { if (lookup_id(ctx, $1, &$$) < 0) {
-                                        pr_debug("%s not found", $1);
+                                        pr_debug("%s not found\n", $1);
                                         YYABORT;
                                   }
                                 }
+        | expr '|' expr         { $$ = (long)$1 | (long)$3; }
+        | expr '&' expr         { $$ = (long)$1 & (long)$3; }
+        | expr '^' expr         { $$ = (long)$1 ^ (long)$3; }
         | expr '+' expr         { $$ = $1 + $3; }
         | expr '-' expr         { $$ = $1 - $3; }
         | expr '*' expr         { $$ = $1 * $3; }
         | expr '/' expr         { if ($3 == 0) YYABORT; $$ = $1 / $3; }
         | expr '%' expr         { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; }
         | '-' expr %prec NEG    { $$ = -$2; }
-        | '(' expr ')'          { $$ = $2; }
+        | '(' if_expr ')'       { $$ = $2; }
+        | MIN '(' expr ',' expr ')' { $$ = $3 < $5 ? $3 : $5; }
+        | MAX '(' expr ',' expr ')' { $$ = $3 > $5 ? $3 : $5; }
+        | SMT_ON                 { $$ = smt_on() > 0; }
         ;
 
 %%
@@ -82,13 +96,47 @@ static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
         char *dst = res->id;
         const char *s = p;
 
-        while (isalnum(*p) || *p == '_' || *p == '.') {
+        if (*p == '#')
+                *dst++ = *p++;
+
+        while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') {
                 if (p - s >= MAXIDLEN)
                         return -1;
-                *dst++ = *p++;
+                /*
+                 * Allow @ instead of / to be able to specify pmu/event/ without
+                 * conflicts with normal division.
+                 */
+                if (*p == '@')
+                        *dst++ = '/';
+                else if (*p == '\\')
+                        *dst++ = *++p;
+                else
+                        *dst++ = *p;
+                p++;
         }
         *dst = 0;
         *pp = p;
+        dst = res->id;
+        switch (dst[0]) {
+        case 'm':
+                if (!strcmp(dst, "min"))
+                        return MIN;
+                if (!strcmp(dst, "max"))
+                        return MAX;
+                break;
+        case 'i':
+                if (!strcmp(dst, "if"))
+                        return IF;
+                break;
+        case 'e':
+                if (!strcmp(dst, "else"))
+                        return ELSE;
+                break;
+        case '#':
+                if (!strcasecmp(dst, "#smt_on"))
+                        return SMT_ON;
+                break;
+        }
         return ID;
 }
 
@@ -102,6 +150,7 @@ static int expr__lex(YYSTYPE *res, const char **pp)
                 p++;
         s = p;
         switch (*p++) {
+        case '#':
         case 'a' ... 'z':
         case 'A' ... 'Z':
                 return expr__symbol(res, p - 1, pp);
@@ -132,6 +181,19 @@ void expr__ctx_init(struct parse_ctx *ctx)
         ctx->num_ids = 0;
 }
 
+static bool already_seen(const char *val, const char *one, const char **other,
+                         int num_other)
+{
+        int i;
+
+        if (one && !strcasecmp(one, val))
+                return true;
+        for (i = 0; i < num_other; i++)
+                if (!strcasecmp(other[i], val))
+                        return true;
+        return false;
+}
+
 int expr__find_other(const char *p, const char *one, const char ***other,
                      int *num_otherp)
 {
@@ -151,7 +213,7 @@ int expr__find_other(const char *p, const char *one, const char ***other,
                         err = 0;
                         break;
                 }
-                if (tok == ID && strcasecmp(one, val.id)) {
+                if (tok == ID && !already_seen(val.id, one, *other, num_other)) {
                         if (num_other >= EXPR_MAX_OTHER - 1) {
                                 pr_debug("Too many extra events in %s\n", orig);
                                 break;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 76ed7d03e500..605bbd5404fb 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -12,6 +12,7 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 #include <linux/bitops.h>
+#include <linux/stringify.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/utsname.h>
@@ -34,6 +35,7 @@
 #include "data.h"
 #include <api/fs/fs.h>
 #include "asm/bug.h"
+#include "tool.h"
 
 #include "sane_ctype.h"
 
@@ -59,6 +61,15 @@ struct perf_file_attr {
         struct perf_file_section        ids;
 };
 
+struct feat_fd {
+        struct perf_header      *ph;
+        int                     fd;
+        void                    *buf;   /* Either buf != NULL or fd >= 0 */
+        ssize_t                 offset;
+        size_t                  size;
+        struct perf_evsel       *events;
+};
+
 void perf_header__set_feat(struct perf_header *header, int feat)
 {
         set_bit(feat, header->adds_features);
@@ -74,28 +85,60 @@ bool perf_header__has_feat(const struct perf_header *header, int feat)
         return test_bit(feat, header->adds_features);
 }
 
-static int do_write(int fd, const void *buf, size_t size)
+static int __do_write_fd(struct feat_fd *ff, const void *buf, size_t size)
 {
-        while (size) {
-                int ret = write(fd, buf, size);
+        ssize_t ret = writen(ff->fd, buf, size);
 
-                if (ret < 0)
-                        return -errno;
+        if (ret != (ssize_t)size)
+                return ret < 0 ? (int)ret : -1;
+        return 0;
+}
+
+static int __do_write_buf(struct feat_fd *ff,  const void *buf, size_t size)
+{
+        /* struct perf_event_header::size is u16 */
+        const size_t max_size = 0xffff - sizeof(struct perf_event_header);
+        size_t new_size = ff->size;
+        void *addr;
 
-                size -= ret;
-                buf += ret;
+        if (size + ff->offset > max_size)
+                return -E2BIG;
+
+        while (size > (new_size - ff->offset))
+                new_size <<= 1;
+        new_size = min(max_size, new_size);
+
+        if (ff->size < new_size) {
+                addr = realloc(ff->buf, new_size);
+                if (!addr)
+                        return -ENOMEM;
+                ff->buf = addr;
+                ff->size = new_size;
         }
 
+        memcpy(ff->buf + ff->offset, buf, size);
+        ff->offset += size;
+
         return 0;
 }
 
-int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
+/* Return: 0 if succeded, -ERR if failed. */
+int do_write(struct feat_fd *ff, const void *buf, size_t size)
+{
+        if (!ff->buf)
+                return __do_write_fd(ff, buf, size);
+        return __do_write_buf(ff, buf, size);
+}
+
+/* Return: 0 if succeded, -ERR if failed. */
+int write_padded(struct feat_fd *ff, const void *bf,
+                 size_t count, size_t count_aligned)
 {
         static const char zero_buf[NAME_ALIGN];
-        int err = do_write(fd, bf, count);
+        int err = do_write(ff, bf, count);
 
         if (!err)
-                err = do_write(fd, zero_buf, count_aligned - count);
+                err = do_write(ff, zero_buf, count_aligned - count);
 
         return err;
 }
@@ -103,7 +146,8 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 #define string_size(str)                                                \
         (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32))
 
-static int do_write_string(int fd, const char *str)
+/* Return: 0 if succeded, -ERR if failed. */
+static int do_write_string(struct feat_fd *ff, const char *str)
 {
         u32 len, olen;
         int ret;
@@ -112,32 +156,80 @@ static int do_write_string(int fd, const char *str)
         len = PERF_ALIGN(olen, NAME_ALIGN);
 
         /* write len, incl. \0 */
-        ret = do_write(fd, &len, sizeof(len));
+        ret = do_write(ff, &len, sizeof(len));
         if (ret < 0)
                 return ret;
 
-        return write_padded(fd, str, olen, len);
+        return write_padded(ff, str, olen, len);
 }
 
-static char *do_read_string(int fd, struct perf_header *ph)
+static int __do_read_fd(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        ssize_t ret = readn(ff->fd, addr, size);
+
+        if (ret != size)
+                return ret < 0 ? (int)ret : -1;
+        return 0;
+}
+
+static int __do_read_buf(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        if (size > (ssize_t)ff->size - ff->offset)
+                return -1;
+
+        memcpy(addr, ff->buf + ff->offset, size);
+        ff->offset += size;
+
+        return 0;
+
+}
+
+static int __do_read(struct feat_fd *ff, void *addr, ssize_t size)
+{
+        if (!ff->buf)
+                return __do_read_fd(ff, addr, size);
+        return __do_read_buf(ff, addr, size);
+}
+
+static int do_read_u32(struct feat_fd *ff, u32 *addr)
+{
+        int ret;
+
+        ret = __do_read(ff, addr, sizeof(*addr));
+        if (ret)
+                return ret;
+
+        if (ff->ph->needs_swap)
+                *addr = bswap_32(*addr);
+        return 0;
+}
+
+static int do_read_u64(struct feat_fd *ff, u64 *addr)
+{
+        int ret;
+
+        ret = __do_read(ff, addr, sizeof(*addr));
+        if (ret)
+                return ret;
+
+        if (ff->ph->needs_swap)
+                *addr = bswap_64(*addr);
+        return 0;
+}
+
+static char *do_read_string(struct feat_fd *ff)
 {
-        ssize_t sz, ret;
         u32 len;
         char *buf;
 
-        sz = readn(fd, &len, sizeof(len));
-        if (sz < (ssize_t)sizeof(len))
+        if (do_read_u32(ff, &len))
                 return NULL;
 
-        if (ph->needs_swap)
-                len = bswap_32(len);
-
         buf = malloc(len);
         if (!buf)
                 return NULL;
 
-        ret = readn(fd, buf, len);
-        if (ret == (ssize_t)len) {
+        if (!__do_read(ff, buf, len)) {
                 /*
                  * strings are padded by zeroes
                  * thus the actual strlen of buf
@@ -150,25 +242,30 @@ static char *do_read_string(int fd, struct perf_header *ph)
         return NULL;
 }
 
-static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
-                            struct perf_evlist *evlist)
+static int write_tracing_data(struct feat_fd *ff,
+                              struct perf_evlist *evlist)
 {
-        return read_tracing_data(fd, &evlist->entries);
-}
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
 
+        return read_tracing_data(ff->fd, &evlist->entries);
+}
 
-static int write_build_id(int fd, struct perf_header *h,
+static int write_build_id(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(h, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
         if (!perf_session__read_build_ids(session, true))
                 return -1;
 
-        err = perf_session__write_buildid_table(session, fd);
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
+
+        err = perf_session__write_buildid_table(session, ff);
         if (err < 0) {
                 pr_debug("failed to write buildid table\n");
                 return err;
@@ -178,7 +275,7 @@ static int write_build_id(int fd, struct perf_header *h,
         return 0;
 }
 
-static int write_hostname(int fd, struct perf_header *h __maybe_unused,
+static int write_hostname(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -188,10 +285,10 @@ static int write_hostname(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.nodename);
+        return do_write_string(ff, uts.nodename);
 }
 
-static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
+static int write_osrelease(struct feat_fd *ff,
                            struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -201,10 +298,10 @@ static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.release);
+        return do_write_string(ff, uts.release);
 }
 
-static int write_arch(int fd, struct perf_header *h __maybe_unused,
+static int write_arch(struct feat_fd *ff,
                       struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
@@ -214,16 +311,16 @@ static int write_arch(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return -1;
 
-        return do_write_string(fd, uts.machine);
+        return do_write_string(ff, uts.machine);
 }
 
-static int write_version(int fd, struct perf_header *h __maybe_unused,
+static int write_version(struct feat_fd *ff,
                          struct perf_evlist *evlist __maybe_unused)
 {
-        return do_write_string(fd, perf_version_string);
+        return do_write_string(ff, perf_version_string);
 }
 
-static int __write_cpudesc(int fd, const char *cpuinfo_proc)
+static int __write_cpudesc(struct feat_fd *ff, const char *cpuinfo_proc)
 {
         FILE *file;
         char *buf = NULL;
@@ -273,25 +370,22 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc)
                 }
                 p++;
         }
-        ret = do_write_string(fd, s);
+        ret = do_write_string(ff, s);
 done:
         free(buf);
         fclose(file);
         return ret;
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+static int write_cpudesc(struct feat_fd *ff,
                        struct perf_evlist *evlist __maybe_unused)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC {"model name", }
-#endif
         const char *cpuinfo_procs[] = CPUINFO_PROC;
         unsigned int i;
 
         for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
                 int ret;
-                ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+                ret = __write_cpudesc(ff, cpuinfo_procs[i]);
                 if (ret >= 0)
                         return ret;
         }
@@ -299,7 +393,7 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
 }
 
 
-static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
+static int write_nrcpus(struct feat_fd *ff,
                         struct perf_evlist *evlist __maybe_unused)
 {
         long nr;
@@ -314,14 +408,14 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 
         nra = (u32)(nr & UINT_MAX);
 
-        ret = do_write(fd, &nrc, sizeof(nrc));
+        ret = do_write(ff, &nrc, sizeof(nrc));
         if (ret < 0)
                 return ret;
 
-        return do_write(fd, &nra, sizeof(nra));
+        return do_write(ff, &nra, sizeof(nra));
 }
 
-static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
+static int write_event_desc(struct feat_fd *ff,
                             struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
@@ -333,7 +427,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
         /*
          * write number of events
          */
-        ret = do_write(fd, &nre, sizeof(nre));
+        ret = do_write(ff, &nre, sizeof(nre));
         if (ret < 0)
                 return ret;
 
@@ -341,12 +435,12 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
          * size of perf_event_attr struct
          */
         sz = (u32)sizeof(evsel->attr);
-        ret = do_write(fd, &sz, sizeof(sz));
+        ret = do_write(ff, &sz, sizeof(sz));
         if (ret < 0)
                 return ret;
 
         evlist__for_each_entry(evlist, evsel) {
-                ret = do_write(fd, &evsel->attr, sz);
+                ret = do_write(ff, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
                 /*
@@ -357,27 +451,27 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
                  * type of ids,
                  */
                 nri = evsel->ids;
-                ret = do_write(fd, &nri, sizeof(nri));
+                ret = do_write(ff, &nri, sizeof(nri));
                 if (ret < 0)
                         return ret;
 
                 /*
                  * write event string as passed on cmdline
                  */
-                ret = do_write_string(fd, perf_evsel__name(evsel));
+                ret = do_write_string(ff, perf_evsel__name(evsel));
                 if (ret < 0)
                         return ret;
                 /*
                  * write unique ids for this event
                  */
-                ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+                ret = do_write(ff, evsel->id, evsel->ids * sizeof(u64));
                 if (ret < 0)
                         return ret;
         }
         return 0;
 }
 
-static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
+static int write_cmdline(struct feat_fd *ff,
                          struct perf_evlist *evlist __maybe_unused)
 {
         char buf[MAXPATHLEN];
@@ -395,16 +489,16 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
         /* account for binary path */
         n = perf_env.nr_cmdline + 1;
 
-        ret = do_write(fd, &n, sizeof(n));
+        ret = do_write(ff, &n, sizeof(n));
         if (ret < 0)
                 return ret;
 
-        ret = do_write_string(fd, buf);
+        ret = do_write_string(ff, buf);
         if (ret < 0)
                 return ret;
 
         for (i = 0 ; i < perf_env.nr_cmdline; i++) {
-                ret = do_write_string(fd, perf_env.cmdline_argv[i]);
+                ret = do_write_string(ff, perf_env.cmdline_argv[i]);
                 if (ret < 0)
                         return ret;
         }
@@ -557,8 +651,8 @@ out_free:
         return tp;
 }
 
-static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_cpu_topology(struct feat_fd *ff,
+                              struct perf_evlist *evlist __maybe_unused)
 {
         struct cpu_topo *tp;
         u32 i;
@@ -568,21 +662,21 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
         if (!tp)
                 return -1;
 
-        ret = do_write(fd, &tp->core_sib, sizeof(tp->core_sib));
+        ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < tp->core_sib; i++) {
-                ret = do_write_string(fd, tp->core_siblings[i]);
+                ret = do_write_string(ff, tp->core_siblings[i]);
                 if (ret < 0)
                         goto done;
         }
-        ret = do_write(fd, &tp->thread_sib, sizeof(tp->thread_sib));
+        ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < tp->thread_sib; i++) {
-                ret = do_write_string(fd, tp->thread_siblings[i]);
+                ret = do_write_string(ff, tp->thread_siblings[i]);
                 if (ret < 0)
                         break;
         }
@@ -592,11 +686,11 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
                 goto done;
 
         for (j = 0; j < perf_env.nr_cpus_avail; j++) {
-                ret = do_write(fd, &perf_env.cpu[j].core_id,
+                ret = do_write(ff, &perf_env.cpu[j].core_id,
                                sizeof(perf_env.cpu[j].core_id));
                 if (ret < 0)
                         return ret;
-                ret = do_write(fd, &perf_env.cpu[j].socket_id,
+                ret = do_write(ff, &perf_env.cpu[j].socket_id,
                                sizeof(perf_env.cpu[j].socket_id));
                 if (ret < 0)
                         return ret;
@@ -608,8 +702,8 @@ done:
 
 
 
-static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_total_mem(struct feat_fd *ff,
+                           struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         FILE *fp;
@@ -629,7 +723,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
         if (!ret) {
                 n = sscanf(buf, "%*s %"PRIu64, &mem);
                 if (n == 1)
-                        ret = do_write(fd, &mem, sizeof(mem));
+                        ret = do_write(ff, &mem, sizeof(mem));
         } else
                 ret = -1;
         free(buf);
@@ -637,7 +731,7 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
         return ret;
 }
 
-static int write_topo_node(int fd, int node)
+static int write_topo_node(struct feat_fd *ff, int node)
 {
         char str[MAXPATHLEN];
         char field[32];
@@ -667,11 +761,11 @@ static int write_topo_node(int fd, int node)
         fclose(fp);
         fp = NULL;
 
-        ret = do_write(fd, &mem_total, sizeof(u64));
+        ret = do_write(ff, &mem_total, sizeof(u64));
         if (ret)
                 goto done;
 
-        ret = do_write(fd, &mem_free, sizeof(u64));
+        ret = do_write(ff, &mem_free, sizeof(u64));
         if (ret)
                 goto done;
 
@@ -689,7 +783,7 @@ static int write_topo_node(int fd, int node)
         if (p)
                 *p = '\0';
 
-        ret = do_write_string(fd, buf);
+        ret = do_write_string(ff, buf);
 done:
         free(buf);
         if (fp)
@@ -697,8 +791,8 @@ done:
         return ret;
 }
 
-static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_numa_topology(struct feat_fd *ff,
+                               struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         size_t len = 0;
@@ -725,17 +819,17 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
 
         nr = (u32)node_map->nr;
 
-        ret = do_write(fd, &nr, sizeof(nr));
+        ret = do_write(ff, &nr, sizeof(nr));
         if (ret < 0)
                 goto done;
 
         for (i = 0; i < nr; i++) {
                 j = (u32)node_map->map[i];
-                ret = do_write(fd, &j, sizeof(j));
+                ret = do_write(ff, &j, sizeof(j));
                 if (ret < 0)
                         break;
 
-                ret = write_topo_node(fd, i);
+                ret = write_topo_node(ff, i);
                 if (ret < 0)
                         break;
         }
@@ -758,39 +852,40 @@ done:
  * };
  */
 
-static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
+static int write_pmu_mappings(struct feat_fd *ff,
                               struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_pmu *pmu = NULL;
-        off_t offset = lseek(fd, 0, SEEK_CUR);
-        __u32 pmu_num = 0;
+        u32 pmu_num = 0;
         int ret;
 
-        /* write real pmu_num later */
-        ret = do_write(fd, &pmu_num, sizeof(pmu_num));
+        /*
+         * Do a first pass to count number of pmu to avoid lseek so this
+         * works in pipe mode as well.
+         */
+        while ((pmu = perf_pmu__scan(pmu))) {
+                if (!pmu->name)
+                        continue;
+                pmu_num++;
+        }
+
+        ret = do_write(ff, &pmu_num, sizeof(pmu_num));
         if (ret < 0)
                 return ret;
 
         while ((pmu = perf_pmu__scan(pmu))) {
                 if (!pmu->name)
                         continue;
-                pmu_num++;
 
-                ret = do_write(fd, &pmu->type, sizeof(pmu->type));
+                ret = do_write(ff, &pmu->type, sizeof(pmu->type));
                 if (ret < 0)
                         return ret;
 
-                ret = do_write_string(fd, pmu->name);
+                ret = do_write_string(ff, pmu->name);
                 if (ret < 0)
                         return ret;
         }
 
-        if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
-                /* discard all */
-                lseek(fd, offset, SEEK_SET);
-                return -1;
-        }
-
         return 0;
 }
 
@@ -806,14 +901,14 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
  *      }[nr_groups];
  * };
  */
-static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+static int write_group_desc(struct feat_fd *ff,
                             struct perf_evlist *evlist)
 {
         u32 nr_groups = evlist->nr_groups;
         struct perf_evsel *evsel;
         int ret;
 
-        ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+        ret = do_write(ff, &nr_groups, sizeof(nr_groups));
         if (ret < 0)
                 return ret;
 
@@ -824,15 +919,15 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
                         u32 leader_idx = evsel->idx;
                         u32 nr_members = evsel->nr_members;
 
-                        ret = do_write_string(fd, name);
+                        ret = do_write_string(ff, name);
                         if (ret < 0)
                                 return ret;
 
-                        ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+                        ret = do_write(ff, &leader_idx, sizeof(leader_idx));
                         if (ret < 0)
                                 return ret;
 
-                        ret = do_write(fd, &nr_members, sizeof(nr_members));
+                        ret = do_write(ff, &nr_members, sizeof(nr_members));
                         if (ret < 0)
                                 return ret;
                 }
@@ -849,7 +944,7 @@ int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
         return -1;
 }
 
-static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
+static int write_cpuid(struct feat_fd *ff,
                        struct perf_evlist *evlist __maybe_unused)
 {
         char buffer[64];
@@ -861,25 +956,27 @@ static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
 
         return -1;
 write_it:
-        return do_write_string(fd, buffer);
+        return do_write_string(ff, buffer);
 }
 
-static int write_branch_stack(int fd __maybe_unused,
-                              struct perf_header *h __maybe_unused,
-                       struct perf_evlist *evlist __maybe_unused)
+static int write_branch_stack(struct feat_fd *ff __maybe_unused,
+                              struct perf_evlist *evlist __maybe_unused)
 {
         return 0;
 }
 
-static int write_auxtrace(int fd, struct perf_header *h,
+static int write_auxtrace(struct feat_fd *ff,
                           struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(h, struct perf_session, header);
+        if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                return -1;
+
+        session = container_of(ff->ph, struct perf_session, header);
 
-        err = auxtrace_index__write(fd, &session->auxtrace_index);
+        err = auxtrace_index__write(ff->fd, &session->auxtrace_index);
         if (err < 0)
                 pr_err("Failed to write auxtrace index\n");
         return err;
@@ -1026,8 +1123,8 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 
 #define MAX_CACHES 2000
 
-static int write_cache(int fd, struct perf_header *h __maybe_unused,
-                          struct perf_evlist *evlist __maybe_unused)
+static int write_cache(struct feat_fd *ff,
+                       struct perf_evlist *evlist __maybe_unused)
 {
         struct cpu_cache_level caches[MAX_CACHES];
         u32 cnt = 0, i, version = 1;
@@ -1039,11 +1136,11 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
 
         qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
 
-        ret = do_write(fd, &version, sizeof(u32));
+        ret = do_write(ff, &version, sizeof(u32));
         if (ret < 0)
                 goto out;
 
-        ret = do_write(fd, &cnt, sizeof(u32));
+        ret = do_write(ff, &cnt, sizeof(u32));
         if (ret < 0)
                 goto out;
 
@@ -1051,7 +1148,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
                 struct cpu_cache_level *c = &caches[i];
 
                 #define _W(v)                                   \
-                        ret = do_write(fd, &c->v, sizeof(u32)); \
+                        ret = do_write(ff, &c->v, sizeof(u32)); \
                         if (ret < 0)                            \
                                 goto out;
 
@@ -1062,7 +1159,7 @@ static int write_cache(int fd, struct perf_header *h __maybe_unused,
                 #undef _W
 
                 #define _W(v)                                           \
-                        ret = do_write_string(fd, (const char *) c->v); \
+                        ret = do_write_string(ff, (const char *) c->v); \
                         if (ret < 0)                                    \
                                 goto out;
 
@@ -1078,69 +1175,62 @@ out:
         return ret;
 }
 
-static int write_stat(int fd __maybe_unused,
-                      struct perf_header *h __maybe_unused,
+static int write_stat(struct feat_fd *ff __maybe_unused,
                       struct perf_evlist *evlist __maybe_unused)
 {
         return 0;
 }
 
-static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
-                           FILE *fp)
+static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# hostname : %s\n", ph->env.hostname);
+        fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
 }
 
-static void print_osrelease(struct perf_header *ph, int fd __maybe_unused,
-                            FILE *fp)
+static void print_osrelease(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# os release : %s\n", ph->env.os_release);
+        fprintf(fp, "# os release : %s\n", ff->ph->env.os_release);
 }
 
-static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+static void print_arch(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# arch : %s\n", ph->env.arch);
+        fprintf(fp, "# arch : %s\n", ff->ph->env.arch);
 }
 
-static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_cpudesc(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc);
+        fprintf(fp, "# cpudesc : %s\n", ff->ph->env.cpu_desc);
 }
 
-static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused,
-                         FILE *fp)
+static void print_nrcpus(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online);
-        fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail);
+        fprintf(fp, "# nrcpus online : %u\n", ff->ph->env.nr_cpus_online);
+        fprintf(fp, "# nrcpus avail : %u\n", ff->ph->env.nr_cpus_avail);
 }
 
-static void print_version(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_version(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# perf version : %s\n", ph->env.version);
+        fprintf(fp, "# perf version : %s\n", ff->ph->env.version);
 }
 
-static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
-                          FILE *fp)
+static void print_cmdline(struct feat_fd *ff, FILE *fp)
 {
         int nr, i;
 
-        nr = ph->env.nr_cmdline;
+        nr = ff->ph->env.nr_cmdline;
 
         fprintf(fp, "# cmdline : ");
 
         for (i = 0; i < nr; i++)
-                fprintf(fp, "%s ", ph->env.cmdline_argv[i]);
+                fprintf(fp, "%s ", ff->ph->env.cmdline_argv[i]);
         fputc('\n', fp);
 }
 
-static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
-                               FILE *fp)
+static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 {
+        struct perf_header *ph = ff->ph;
+        int cpu_nr = ph->env.nr_cpus_avail;
         int nr, i;
         char *str;
-        int cpu_nr = ph->env.nr_cpus_avail;
 
         nr = ph->env.nr_sibling_cores;
         str = ph->env.sibling_cores;
@@ -1181,31 +1271,21 @@ static void free_event_desc(struct perf_evsel *events)
         free(events);
 }
 
-static struct perf_evsel *
-read_event_desc(struct perf_header *ph, int fd)
+static struct perf_evsel *read_event_desc(struct feat_fd *ff)
 {
         struct perf_evsel *evsel, *events = NULL;
         u64 *id;
         void *buf = NULL;
         u32 nre, sz, nr, i, j;
-        ssize_t ret;
         size_t msz;
 
         /* number of events */
-        ret = readn(fd, &nre, sizeof(nre));
-        if (ret != (ssize_t)sizeof(nre))
+        if (do_read_u32(ff, &nre))
                 goto error;
 
-        if (ph->needs_swap)
-                nre = bswap_32(nre);
-
-        ret = readn(fd, &sz, sizeof(sz));
-        if (ret != (ssize_t)sizeof(sz))
+        if (do_read_u32(ff, &sz))
                 goto error;
 
-        if (ph->needs_swap)
-                sz = bswap_32(sz);
-
         /* buffer to hold on file attr struct */
         buf = malloc(sz);
         if (!buf)
@@ -1227,25 +1307,23 @@ read_event_desc(struct perf_header *ph, int fd)
                  * must read entire on-file attr struct to
                  * sync up with layout.
                  */
-                ret = readn(fd, buf, sz);
-                if (ret != (ssize_t)sz)
+                if (__do_read(ff, buf, sz))
                         goto error;
 
-                if (ph->needs_swap)
+                if (ff->ph->needs_swap)
                         perf_event__attr_swap(buf);
 
                 memcpy(&evsel->attr, buf, msz);
 
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != (ssize_t)sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto error;
 
-                if (ph->needs_swap) {
-                        nr = bswap_32(nr);
+                if (ff->ph->needs_swap)
                         evsel->needs_swap = true;
-                }
 
-                evsel->name = do_read_string(fd, ph);
+                evsel->name = do_read_string(ff);
+                if (!evsel->name)
+                        goto error;
 
                 if (!nr)
                         continue;
@@ -1257,11 +1335,8 @@ read_event_desc(struct perf_header *ph, int fd)
                 evsel->id = id;
 
                 for (j = 0 ; j < nr; j++) {
-                        ret = readn(fd, id, sizeof(*id));
-                        if (ret != (ssize_t)sizeof(*id))
+                        if (do_read_u64(ff, id))
                                 goto error;
-                        if (ph->needs_swap)
-                                *id = bswap_64(*id);
                         id++;
                 }
         }
@@ -1280,12 +1355,17 @@ static int __desc_attr__fprintf(FILE *fp, const char *name, const char *val,
         return fprintf(fp, ", %s = %s", name, val);
 }
 
-static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+static void print_event_desc(struct feat_fd *ff, FILE *fp)
 {
-        struct perf_evsel *evsel, *events = read_event_desc(ph, fd);
+        struct perf_evsel *evsel, *events;
         u32 j;
         u64 *id;
 
+        if (ff->events)
+                events = ff->events;
+        else
+                events = read_event_desc(ff);
+
         if (!events) {
                 fprintf(fp, "# event desc: not available or unable to read\n");
                 return;
@@ -1310,22 +1390,21 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
         }
 
         free_event_desc(events);
+        ff->events = NULL;
 }
 
-static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
-                            FILE *fp)
+static void print_total_mem(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem);
+        fprintf(fp, "# total memory : %llu kB\n", ff->ph->env.total_mem);
 }
 
-static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
-                                FILE *fp)
+static void print_numa_topology(struct feat_fd *ff, FILE *fp)
 {
         int i;
         struct numa_node *n;
 
-        for (i = 0; i < ph->env.nr_numa_nodes; i++) {
-                n = &ph->env.numa_nodes[i];
+        for (i = 0; i < ff->ph->env.nr_numa_nodes; i++) {
+                n = &ff->ph->env.numa_nodes[i];
 
                 fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
                             " free = %"PRIu64" kB\n",
@@ -1336,56 +1415,51 @@ static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
         }
 }
 
-static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
+static void print_cpuid(struct feat_fd *ff, FILE *fp)
 {
-        fprintf(fp, "# cpuid : %s\n", ph->env.cpuid);
+        fprintf(fp, "# cpuid : %s\n", ff->ph->env.cpuid);
 }
 
-static void print_branch_stack(struct perf_header *ph __maybe_unused,
-                               int fd __maybe_unused, FILE *fp)
+static void print_branch_stack(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains samples with branch stack\n");
 }
 
-static void print_auxtrace(struct perf_header *ph __maybe_unused,
-                           int fd __maybe_unused, FILE *fp)
+static void print_auxtrace(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
 }
 
-static void print_stat(struct perf_header *ph __maybe_unused,
-                       int fd __maybe_unused, FILE *fp)
+static void print_stat(struct feat_fd *ff __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains stat data\n");
 }
 
-static void print_cache(struct perf_header *ph __maybe_unused,
-                        int fd __maybe_unused, FILE *fp __maybe_unused)
+static void print_cache(struct feat_fd *ff, FILE *fp __maybe_unused)
 {
         int i;
 
         fprintf(fp, "# CPU cache info:\n");
-        for (i = 0; i < ph->env.caches_cnt; i++) {
+        for (i = 0; i < ff->ph->env.caches_cnt; i++) {
                 fprintf(fp, "#  ");
-                cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+                cpu_cache_level__fprintf(fp, &ff->ph->env.caches[i]);
         }
 }
 
-static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
-                               FILE *fp)
+static void print_pmu_mappings(struct feat_fd *ff, FILE *fp)
 {
         const char *delimiter = "# pmu mappings: ";
         char *str, *tmp;
         u32 pmu_num;
         u32 type;
 
-        pmu_num = ph->env.nr_pmu_mappings;
+        pmu_num = ff->ph->env.nr_pmu_mappings;
         if (!pmu_num) {
                 fprintf(fp, "# pmu mappings: not available\n");
                 return;
         }
 
-        str = ph->env.pmu_mappings;
+        str = ff->ph->env.pmu_mappings;
 
         while (pmu_num) {
                 type = strtoul(str, &tmp, 0);
@@ -1408,14 +1482,13 @@ error:
         fprintf(fp, "# pmu mappings: unable to read\n");
 }
 
-static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
-                             FILE *fp)
+static void print_group_desc(struct feat_fd *ff, FILE *fp)
 {
         struct perf_session *session;
         struct perf_evsel *evsel;
         u32 nr = 0;
 
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
         evlist__for_each_entry(session->evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
@@ -1588,113 +1661,61 @@ out:
         return err;
 }
 
-static int process_tracing_data(struct perf_file_section *section __maybe_unused,
-                                struct perf_header *ph __maybe_unused,
-                                int fd, void *data)
-{
-        ssize_t ret = trace_report(fd, data, false);
-        return ret < 0 ? -1 : 0;
-}
-
-static int process_build_id(struct perf_file_section *section,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
-{
-        if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
-                pr_debug("Failed to read buildids, continuing...\n");
-        return 0;
+/* Macro for features that simply need to read and store a string. */
+#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
+static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
+{\
+        ff->ph->env.__feat_env = do_read_string(ff); \
+        return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
 }
 
-static int process_hostname(struct perf_file_section *section __maybe_unused,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
-{
-        ph->env.hostname = do_read_string(fd, ph);
-        return ph->env.hostname ? 0 : -ENOMEM;
-}
+FEAT_PROCESS_STR_FUN(hostname, hostname);
+FEAT_PROCESS_STR_FUN(osrelease, os_release);
+FEAT_PROCESS_STR_FUN(version, version);
+FEAT_PROCESS_STR_FUN(arch, arch);
+FEAT_PROCESS_STR_FUN(cpudesc, cpu_desc);
+FEAT_PROCESS_STR_FUN(cpuid, cpuid);
 
-static int process_osrelease(struct perf_file_section *section __maybe_unused,
-                             struct perf_header *ph, int fd,
-                             void *data __maybe_unused)
+static int process_tracing_data(struct feat_fd *ff, void *data)
 {
-        ph->env.os_release = do_read_string(fd, ph);
-        return ph->env.os_release ? 0 : -ENOMEM;
-}
+        ssize_t ret = trace_report(ff->fd, data, false);
 
-static int process_version(struct perf_file_section *section __maybe_unused,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
-{
-        ph->env.version = do_read_string(fd, ph);
-        return ph->env.version ? 0 : -ENOMEM;
+        return ret < 0 ? -1 : 0;
 }
 
-static int process_arch(struct perf_file_section *section __maybe_unused,
-                        struct perf_header *ph, int fd,
-                        void *data __maybe_unused)
+static int process_build_id(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ph->env.arch = do_read_string(fd, ph);
-        return ph->env.arch ? 0 : -ENOMEM;
+        if (perf_header__read_build_ids(ff->ph, ff->fd, ff->offset, ff->size))
+                pr_debug("Failed to read buildids, continuing...\n");
+        return 0;
 }
 
-static int process_nrcpus(struct perf_file_section *section __maybe_unused,
-                          struct perf_header *ph, int fd,
-                          void *data __maybe_unused)
+static int process_nrcpus(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
-        u32 nr;
-
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
-                return -1;
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        ph->env.nr_cpus_avail = nr;
-
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
-                return -1;
+        int ret;
+        u32 nr_cpus_avail, nr_cpus_online;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
+        ret = do_read_u32(ff, &nr_cpus_avail);
+        if (ret)
+                return ret;
 
-        ph->env.nr_cpus_online = nr;
+        ret = do_read_u32(ff, &nr_cpus_online);
+        if (ret)
+                return ret;
+        ff->ph->env.nr_cpus_avail = (int)nr_cpus_avail;
+        ff->ph->env.nr_cpus_online = (int)nr_cpus_online;
         return 0;
 }
 
-static int process_cpudesc(struct perf_file_section *section __maybe_unused,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
-{
-        ph->env.cpu_desc = do_read_string(fd, ph);
-        return ph->env.cpu_desc ? 0 : -ENOMEM;
-}
-
-static int process_cpuid(struct perf_file_section *section __maybe_unused,
-                         struct perf_header *ph,  int fd,
-                         void *data __maybe_unused)
-{
-        ph->env.cpuid = do_read_string(fd, ph);
-        return ph->env.cpuid ? 0 : -ENOMEM;
-}
-
-static int process_total_mem(struct perf_file_section *section __maybe_unused,
-                             struct perf_header *ph, int fd,
-                             void *data __maybe_unused)
+static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused)
 {
-        uint64_t mem;
-        ssize_t ret;
+        u64 total_mem;
+        int ret;
 
-        ret = readn(fd, &mem, sizeof(mem));
-        if (ret != sizeof(mem))
+        ret = do_read_u64(ff, &total_mem);
+        if (ret)
                 return -1;
-
-        if (ph->needs_swap)
-                mem = bswap_64(mem);
-
-        ph->env.total_mem = mem;
+        ff->ph->env.total_mem = (unsigned long long)total_mem;
         return 0;
 }
 
@@ -1731,43 +1752,42 @@ perf_evlist__set_event_name(struct perf_evlist *evlist,
 }
 
 static int
-process_event_desc(struct perf_file_section *section __maybe_unused,
-                   struct perf_header *header, int fd,
-                   void *data __maybe_unused)
+process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct perf_session *session;
-        struct perf_evsel *evsel, *events = read_event_desc(header, fd);
+        struct perf_evsel *evsel, *events = read_event_desc(ff);
 
         if (!events)
                 return 0;
 
-        session = container_of(header, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
+
+        if (session->file->is_pipe) {
+                /* Save events for reading later by print_event_desc,
+                 * since they can't be read again in pipe mode. */
+                ff->events = events;
+        }
+
         for (evsel = events; evsel->attr.size; evsel++)
                 perf_evlist__set_event_name(session->evlist, evsel);
 
-        free_event_desc(events);
+        if (!session->file->is_pipe)
+                free_event_desc(events);
 
         return 0;
 }
 
-static int process_cmdline(struct perf_file_section *section,
-                           struct perf_header *ph, int fd,
-                           void *data __maybe_unused)
+static int process_cmdline(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         char *str, *cmdline = NULL, **argv = NULL;
         u32 nr, i, len = 0;
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        ph->env.nr_cmdline = nr;
+        ff->ph->env.nr_cmdline = nr;
 
-        cmdline = zalloc(section->size + nr + 1);
+        cmdline = zalloc(ff->size + nr + 1);
         if (!cmdline)
                 return -1;
 
@@ -1776,7 +1796,7 @@ static int process_cmdline(struct perf_file_section *section,
                 goto error;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1785,8 +1805,8 @@ static int process_cmdline(struct perf_file_section *section,
                 len += strlen(str) + 1;
                 free(str);
         }
-        ph->env.cmdline = cmdline;
-        ph->env.cmdline_argv = (const char **) argv;
+        ff->ph->env.cmdline = cmdline;
+        ff->ph->env.cmdline_argv = (const char **) argv;
         return 0;
 
 error:
@@ -1795,35 +1815,29 @@ error:
         return -1;
 }
 
-static int process_cpu_topology(struct perf_file_section *section,
-                                struct perf_header *ph, int fd,
-                                void *data __maybe_unused)
+static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         u32 nr, i;
         char *str;
         struct strbuf sb;
-        int cpu_nr = ph->env.nr_cpus_avail;
+        int cpu_nr = ff->ph->env.nr_cpus_avail;
         u64 size = 0;
+        struct perf_header *ph = ff->ph;
 
         ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
         if (!ph->env.cpu)
                 return -1;
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 goto free_cpu;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         ph->env.nr_sibling_cores = nr;
         size += sizeof(u32);
         if (strbuf_init(&sb, 128) < 0)
                 goto free_cpu;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1835,18 +1849,14 @@ static int process_cpu_topology(struct perf_file_section *section,
         }
         ph->env.sibling_cores = strbuf_detach(&sb, NULL);
 
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         ph->env.nr_sibling_threads = nr;
         size += sizeof(u32);
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1862,28 +1872,20 @@ static int process_cpu_topology(struct perf_file_section *section,
          * The header may be from old perf,
          * which doesn't include core id and socket id information.
          */
-        if (section->size <= size) {
+        if (ff->size <= size) {
                 zfree(&ph->env.cpu);
                 return 0;
         }
 
         for (i = 0; i < (u32)cpu_nr; i++) {
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto free_cpu;
 
-                if (ph->needs_swap)
-                        nr = bswap_32(nr);
-
                 ph->env.cpu[i].core_id = nr;
 
-                ret = readn(fd, &nr, sizeof(nr));
-                if (ret != sizeof(nr))
+                if (do_read_u32(ff, &nr))
                         goto free_cpu;
 
-                if (ph->needs_swap)
-                        nr = bswap_32(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");
@@ -1902,23 +1904,16 @@ free_cpu:
         return -1;
 }
 
-static int process_numa_topology(struct perf_file_section *section __maybe_unused,
-                                 struct perf_header *ph, int fd,
-                                 void *data __maybe_unused)
+static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct numa_node *nodes, *n;
-        ssize_t ret;
         u32 nr, i;
         char *str;
 
         /* nr nodes */
-        ret = readn(fd, &nr, sizeof(nr));
-        if (ret != sizeof(nr))
+        if (do_read_u32(ff, &nr))
                 return -1;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
         nodes = zalloc(sizeof(*nodes) * nr);
         if (!nodes)
                 return -ENOMEM;
@@ -1927,25 +1922,16 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
                 n = &nodes[i];
 
                 /* node number */
-                ret = readn(fd, &n->node, sizeof(u32));
-                if (ret != sizeof(n->node))
+                if (do_read_u32(ff, &n->node))
                         goto error;
 
-                ret = readn(fd, &n->mem_total, sizeof(u64));
-                if (ret != sizeof(u64))
+                if (do_read_u64(ff, &n->mem_total))
                         goto error;
 
-                ret = readn(fd, &n->mem_free, sizeof(u64));
-                if (ret != sizeof(u64))
+                if (do_read_u64(ff, &n->mem_free))
                         goto error;
 
-                if (ph->needs_swap) {
-                        n->node      = bswap_32(n->node);
-                        n->mem_total = bswap_64(n->mem_total);
-                        n->mem_free  = bswap_64(n->mem_free);
-                }
-
-                str = do_read_string(fd, ph);
+                str = do_read_string(ff);
                 if (!str)
                         goto error;
 
@@ -1955,8 +1941,8 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 
                 free(str);
         }
-        ph->env.nr_numa_nodes = nr;
-        ph->env.numa_nodes = nodes;
+        ff->ph->env.nr_numa_nodes = nr;
+        ff->ph->env.numa_nodes = nodes;
         return 0;
 
 error:
@@ -1964,39 +1950,30 @@ error:
         return -1;
 }
 
-static int process_pmu_mappings(struct perf_file_section *section __maybe_unused,
-                                struct perf_header *ph, int fd,
-                                void *data __maybe_unused)
+static int process_pmu_mappings(struct feat_fd *ff, void *data __maybe_unused)
 {
-        ssize_t ret;
         char *name;
         u32 pmu_num;
         u32 type;
         struct strbuf sb;
 
-        ret = readn(fd, &pmu_num, sizeof(pmu_num));
-        if (ret != sizeof(pmu_num))
+        if (do_read_u32(ff, &pmu_num))
                 return -1;
 
-        if (ph->needs_swap)
-                pmu_num = bswap_32(pmu_num);
-
         if (!pmu_num) {
                 pr_debug("pmu mappings not available\n");
                 return 0;
         }
 
-        ph->env.nr_pmu_mappings = pmu_num;
+        ff->ph->env.nr_pmu_mappings = pmu_num;
         if (strbuf_init(&sb, 128) < 0)
                 return -1;
 
         while (pmu_num) {
-                if (readn(fd, &type, sizeof(type)) != sizeof(type))
+                if (do_read_u32(ff, &type))
                         goto error;
-                if (ph->needs_swap)
-                        type = bswap_32(type);
 
-                name = do_read_string(fd, ph);
+                name = do_read_string(ff);
                 if (!name)
                         goto error;
 
@@ -2007,12 +1984,12 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
                         goto error;
 
                 if (!strcmp(name, "msr"))
-                        ph->env.msr_pmu_type = type;
+                        ff->ph->env.msr_pmu_type = type;
 
                 free(name);
                 pmu_num--;
         }
-        ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
+        ff->ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
         return 0;
 
 error:
@@ -2020,9 +1997,7 @@ error:
         return -1;
 }
 
-static int process_group_desc(struct perf_file_section *section __maybe_unused,
-                              struct perf_header *ph, int fd,
-                              void *data __maybe_unused)
+static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused)
 {
         size_t ret = -1;
         u32 i, nr, nr_groups;
@@ -2034,13 +2009,10 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
                 u32 nr_members;
         } *desc;
 
-        if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+        if (do_read_u32(ff, &nr_groups))
                 return -1;
 
-        if (ph->needs_swap)
-                nr_groups = bswap_32(nr_groups);
-
-        ph->env.nr_groups = nr_groups;
+        ff->ph->env.nr_groups = nr_groups;
         if (!nr_groups) {
                 pr_debug("group desc not available\n");
                 return 0;
@@ -2051,26 +2023,21 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
                 return -1;
 
         for (i = 0; i < nr_groups; i++) {
-                desc[i].name = do_read_string(fd, ph);
+                desc[i].name = do_read_string(ff);
                 if (!desc[i].name)
                         goto out_free;
 
-                if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+                if (do_read_u32(ff, &desc[i].leader_idx))
                         goto out_free;
 
-                if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+                if (do_read_u32(ff, &desc[i].nr_members))
                         goto out_free;
-
-                if (ph->needs_swap) {
-                        desc[i].leader_idx = bswap_32(desc[i].leader_idx);
-                        desc[i].nr_members = bswap_32(desc[i].nr_members);
-                }
         }
 
         /*
          * Rebuild group relationship based on the group_desc
          */
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
         session->evlist->nr_groups = nr_groups;
 
         i = nr = 0;
@@ -2114,44 +2081,34 @@ out_free:
         return ret;
 }
 
-static int process_auxtrace(struct perf_file_section *section,
-                            struct perf_header *ph, int fd,
-                            void *data __maybe_unused)
+static int process_auxtrace(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct perf_session *session;
         int err;
 
-        session = container_of(ph, struct perf_session, header);
+        session = container_of(ff->ph, struct perf_session, header);
 
-        err = auxtrace_index__process(fd, section->size, session,
-                                      ph->needs_swap);
+        err = auxtrace_index__process(ff->fd, ff->size, session,
+                                      ff->ph->needs_swap);
         if (err < 0)
                 pr_err("Failed to process auxtrace index\n");
         return err;
 }
 
-static int process_cache(struct perf_file_section *section __maybe_unused,
-                         struct perf_header *ph __maybe_unused, int fd __maybe_unused,
-                         void *data __maybe_unused)
+static int process_cache(struct feat_fd *ff, void *data __maybe_unused)
 {
         struct cpu_cache_level *caches;
         u32 cnt, i, version;
 
-        if (readn(fd, &version, sizeof(version)) != sizeof(version))
+        if (do_read_u32(ff, &version))
                 return -1;
 
-        if (ph->needs_swap)
-                version = bswap_32(version);
-
         if (version != 1)
                 return -1;
 
-        if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+        if (do_read_u32(ff, &cnt))
                 return -1;
 
-        if (ph->needs_swap)
-                cnt = bswap_32(cnt);
-
         caches = zalloc(sizeof(*caches) * cnt);
         if (!caches)
                 return -1;
@@ -2160,10 +2117,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 struct cpu_cache_level c;
 
                 #define _R(v)                                           \
-                        if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+                        if (do_read_u32(ff, &c.v))\
                                 goto out_free_caches;                   \
-                        if (ph->needs_swap)                             \
-                                c.v = bswap_32(c.v);                    \
 
                 _R(level)
                 _R(line_size)
@@ -2171,9 +2126,9 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 _R(ways)
                 #undef _R
 
-                #define _R(v)                           \
-                        c.v = do_read_string(fd, ph);   \
-                        if (!c.v)                       \
+                #define _R(v)                                   \
+                        c.v = do_read_string(ff);               \
+                        if (!c.v)                               \
                                 goto out_free_caches;
 
                 _R(type)
@@ -2184,8 +2139,8 @@ static int process_cache(struct perf_file_section *section __maybe_unused,
                 caches[i] = c;
         }
 
-        ph->env.caches = caches;
-        ph->env.caches_cnt = cnt;
+        ff->ph->env.caches = caches;
+        ff->ph->env.caches_cnt = cnt;
         return 0;
 out_free_caches:
         free(caches);
@@ -2193,48 +2148,62 @@ out_free_caches:
 }
 
 struct feature_ops {
-        int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
-        void (*print)(struct perf_header *h, int fd, FILE *fp);
-        int (*process)(struct perf_file_section *section,
-                       struct perf_header *h, int fd, void *data);
+        int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
+        void (*print)(struct feat_fd *ff, FILE *fp);
+        int (*process)(struct feat_fd *ff, void *data);
         const char *name;
         bool full_only;
+        bool synthesize;
 };
 
-#define FEAT_OPA(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func }
-#define FEAT_OPP(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func, \
-                .process = process_##func }
-#define FEAT_OPF(n, func) \
-        [n] = { .name = #n, .write = write_##func, .print = print_##func, \
-                .process = process_##func, .full_only = true }
+#define FEAT_OPR(n, func, __full_only) \
+        [HEADER_##n] = {                                        \
+                .name       = __stringify(n),                   \
+                .write      = write_##func,                     \
+                .print      = print_##func,                     \
+                .full_only  = __full_only,                      \
+                .process    = process_##func,                   \
+                .synthesize = true                              \
+        }
+
+#define FEAT_OPN(n, func, __full_only) \
+        [HEADER_##n] = {                                        \
+                .name       = __stringify(n),                   \
+                .write      = write_##func,                     \
+                .print      = print_##func,                     \
+                .full_only  = __full_only,                      \
+                .process    = process_##func                    \
+        }
 
 /* feature_ops not implemented: */
 #define print_tracing_data      NULL
 #define print_build_id          NULL
 
+#define process_branch_stack    NULL
+#define process_stat            NULL
+
+
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
-        FEAT_OPP(HEADER_TRACING_DATA,   tracing_data),
-        FEAT_OPP(HEADER_BUILD_ID,       build_id),
-        FEAT_OPP(HEADER_HOSTNAME,       hostname),
-        FEAT_OPP(HEADER_OSRELEASE,      osrelease),
-        FEAT_OPP(HEADER_VERSION,        version),
-        FEAT_OPP(HEADER_ARCH,           arch),
-        FEAT_OPP(HEADER_NRCPUS,         nrcpus),
-        FEAT_OPP(HEADER_CPUDESC,        cpudesc),
-        FEAT_OPP(HEADER_CPUID,          cpuid),
-        FEAT_OPP(HEADER_TOTAL_MEM,      total_mem),
-        FEAT_OPP(HEADER_EVENT_DESC,     event_desc),
-        FEAT_OPP(HEADER_CMDLINE,        cmdline),
-        FEAT_OPF(HEADER_CPU_TOPOLOGY,   cpu_topology),
-        FEAT_OPF(HEADER_NUMA_TOPOLOGY,  numa_topology),
-        FEAT_OPA(HEADER_BRANCH_STACK,   branch_stack),
-        FEAT_OPP(HEADER_PMU_MAPPINGS,   pmu_mappings),
-        FEAT_OPP(HEADER_GROUP_DESC,     group_desc),
-        FEAT_OPP(HEADER_AUXTRACE,       auxtrace),
-        FEAT_OPA(HEADER_STAT,           stat),
-        FEAT_OPF(HEADER_CACHE,          cache),
+        FEAT_OPN(TRACING_DATA,  tracing_data,   false),
+        FEAT_OPN(BUILD_ID,      build_id,       false),
+        FEAT_OPR(HOSTNAME,      hostname,       false),
+        FEAT_OPR(OSRELEASE,     osrelease,      false),
+        FEAT_OPR(VERSION,       version,        false),
+        FEAT_OPR(ARCH,          arch,           false),
+        FEAT_OPR(NRCPUS,        nrcpus,         false),
+        FEAT_OPR(CPUDESC,       cpudesc,        false),
+        FEAT_OPR(CPUID,         cpuid,          false),
+        FEAT_OPR(TOTAL_MEM,     total_mem,      false),
+        FEAT_OPR(EVENT_DESC,    event_desc,     false),
+        FEAT_OPR(CMDLINE,       cmdline,        false),
+        FEAT_OPR(CPU_TOPOLOGY,  cpu_topology,   true),
+        FEAT_OPR(NUMA_TOPOLOGY, numa_topology,  true),
+        FEAT_OPN(BRANCH_STACK,  branch_stack,   false),
+        FEAT_OPR(PMU_MAPPINGS,  pmu_mappings,   false),
+        FEAT_OPN(GROUP_DESC,    group_desc,     false),
+        FEAT_OPN(AUXTRACE,      auxtrace,       false),
+        FEAT_OPN(STAT,          stat,           false),
+        FEAT_OPN(CACHE,         cache,          true),
 };
 
 struct header_print_data {
@@ -2247,6 +2216,7 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section,
                                            int feat, int fd, void *data)
 {
         struct header_print_data *hd = data;
+        struct feat_fd ff;
 
         if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
                 pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
@@ -2260,8 +2230,13 @@ static int perf_file_section__fprintf_info(struct perf_file_section *section,
         if (!feat_ops[feat].print)
                 return 0;
 
+        ff = (struct  feat_fd) {
+                .fd = fd,
+                .ph = ph,
+        };
+
         if (!feat_ops[feat].full_only || hd->full)
-                feat_ops[feat].print(ph, fd, hd->fp);
+                feat_ops[feat].print(&ff, hd->fp);
         else
                 fprintf(hd->fp, "# %s info available, use -I to display\n",
                         feat_ops[feat].name);
@@ -2302,29 +2277,32 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
         return 0;
 }
 
-static int do_write_feat(int fd, struct perf_header *h, int type,
+static int do_write_feat(struct feat_fd *ff, int type,
                          struct perf_file_section **p,
                          struct perf_evlist *evlist)
 {
         int err;
         int ret = 0;
 
-        if (perf_header__has_feat(h, type)) {
+        if (perf_header__has_feat(ff->ph, type)) {
                 if (!feat_ops[type].write)
                         return -1;
 
-                (*p)->offset = lseek(fd, 0, SEEK_CUR);
+                if (WARN(ff->buf, "Error: calling %s in pipe-mode.\n", __func__))
+                        return -1;
 
-                err = feat_ops[type].write(fd, h, evlist);
+                (*p)->offset = lseek(ff->fd, 0, SEEK_CUR);
+
+                err = feat_ops[type].write(ff, evlist);
                 if (err < 0) {
                         pr_debug("failed to write feature %s\n", feat_ops[type].name);
 
                         /* undo anything written */
-                        lseek(fd, (*p)->offset, SEEK_SET);
+                        lseek(ff->fd, (*p)->offset, SEEK_SET);
 
                         return -1;
                 }
-                (*p)->size = lseek(fd, 0, SEEK_CUR) - (*p)->offset;
+                (*p)->size = lseek(ff->fd, 0, SEEK_CUR) - (*p)->offset;
                 (*p)++;
         }
         return ret;
@@ -2334,12 +2312,18 @@ static int perf_header__adds_write(struct perf_header *header,
                                    struct perf_evlist *evlist, int fd)
 {
         int nr_sections;
+        struct feat_fd ff;
         struct perf_file_section *feat_sec, *p;
         int sec_size;
         u64 sec_start;
         int feat;
         int err;
 
+        ff = (struct feat_fd){
+                .fd  = fd,
+                .ph = header,
+        };
+
         nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
                 return 0;
@@ -2354,7 +2338,7 @@ static int perf_header__adds_write(struct perf_header *header,
         lseek(fd, sec_start + sec_size, SEEK_SET);
 
         for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
-                if (do_write_feat(fd, header, feat, &p, evlist))
+                if (do_write_feat(&ff, feat, &p, evlist))
                         perf_header__clear_feat(header, feat);
         }
 
@@ -2363,7 +2347,7 @@ static int perf_header__adds_write(struct perf_header *header,
          * may write more than needed due to dropped feature, but
          * this is okay, reader will skip the mising entries
          */
-        err = do_write(fd, feat_sec, sec_size);
+        err = do_write(&ff, feat_sec, sec_size);
         if (err < 0)
                 pr_debug("failed to write feature section\n");
         free(feat_sec);
@@ -2373,14 +2357,17 @@ static int perf_header__adds_write(struct perf_header *header,
 int perf_header__write_pipe(int fd)
 {
         struct perf_pipe_file_header f_header;
+        struct feat_fd ff;
         int err;
 
+        ff = (struct feat_fd){ .fd = fd };
+
         f_header = (struct perf_pipe_file_header){
                 .magic     = PERF_MAGIC,
                 .size      = sizeof(f_header),
         };
 
-        err = do_write(fd, &f_header, sizeof(f_header));
+        err = do_write(&ff, &f_header, sizeof(f_header));
         if (err < 0) {
                 pr_debug("failed to write perf pipe header\n");
                 return err;
@@ -2397,21 +2384,23 @@ int perf_session__write_header(struct perf_session *session,
         struct perf_file_attr   f_attr;
         struct perf_header *header = &session->header;
         struct perf_evsel *evsel;
+        struct feat_fd ff;
         u64 attr_offset;
         int err;
 
+        ff = (struct feat_fd){ .fd = fd};
         lseek(fd, sizeof(f_header), SEEK_SET);
 
         evlist__for_each_entry(session->evlist, evsel) {
                 evsel->id_offset = lseek(fd, 0, SEEK_CUR);
-                err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
+                err = do_write(&ff, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
                         pr_debug("failed to write perf header\n");
                         return err;
                 }
         }
 
-        attr_offset = lseek(fd, 0, SEEK_CUR);
+        attr_offset = lseek(ff.fd, 0, SEEK_CUR);
 
         evlist__for_each_entry(evlist, evsel) {
                 f_attr = (struct perf_file_attr){
@@ -2421,7 +2410,7 @@ int perf_session__write_header(struct perf_session *session,
                                 .size   = evsel->ids * sizeof(u64),
                         }
                 };
-                err = do_write(fd, &f_attr, sizeof(f_attr));
+                err = do_write(&ff, &f_attr, sizeof(f_attr));
                 if (err < 0) {
                         pr_debug("failed to write perf header attribute\n");
                         return err;
@@ -2456,7 +2445,7 @@ int perf_session__write_header(struct perf_session *session,
         memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
 
         lseek(fd, 0, SEEK_SET);
-        err = do_write(fd, &f_header, sizeof(f_header));
+        err = do_write(&ff, &f_header, sizeof(f_header));
         if (err < 0) {
                 pr_debug("failed to write perf header\n");
                 return err;
@@ -2710,6 +2699,13 @@ static int perf_file_section__process(struct perf_file_section *section,
                                       struct perf_header *ph,
                                       int feat, int fd, void *data)
 {
+        struct feat_fd fdd = {
+                .fd     = fd,
+                .ph     = ph,
+                .size   = section->size,
+                .offset = section->offset,
+        };
+
         if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
                 pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
                           "%d, continuing...\n", section->offset, feat);
@@ -2724,13 +2720,17 @@ static int perf_file_section__process(struct perf_file_section *section,
         if (!feat_ops[feat].process)
                 return 0;
 
-        return feat_ops[feat].process(section, ph, fd, data);
+        return feat_ops[feat].process(&fdd, data);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
+        struct feat_fd ff = {
+                .fd = STDOUT_FILENO,
+                .ph = ph,
+        };
         ssize_t ret;
 
         ret = readn(fd, header, sizeof(*header));
@@ -2745,7 +2745,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
         if (ph->needs_swap)
                 header->size = bswap_64(header->size);
 
-        if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
+        if (repipe && do_write(&ff, header, sizeof(*header)) < 0)
                 return -1;
 
         return 0;
@@ -2995,6 +2995,103 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
         return err;
 }
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+                                    struct perf_session *session,
+                                    struct perf_evlist *evlist,
+                                    perf_event__handler_t process)
+{
+        struct perf_header *header = &session->header;
+        struct feat_fd ff;
+        struct feature_event *fe;
+        size_t sz, sz_hdr;
+        int feat, ret;
+
+        sz_hdr = sizeof(fe->header);
+        sz = sizeof(union perf_event);
+        /* get a nice alignment */
+        sz = PERF_ALIGN(sz, page_size);
+
+        memset(&ff, 0, sizeof(ff));
+
+        ff.buf = malloc(sz);
+        if (!ff.buf)
+                return -ENOMEM;
+
+        ff.size = sz - sz_hdr;
+
+        for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+                if (!feat_ops[feat].synthesize) {
+                        pr_debug("No record header feature for header :%d\n", feat);
+                        continue;
+                }
+
+                ff.offset = sizeof(*fe);
+
+                ret = feat_ops[feat].write(&ff, evlist);
+                if (ret || ff.offset <= (ssize_t)sizeof(*fe)) {
+                        pr_debug("Error writing feature\n");
+                        continue;
+                }
+                /* ff.buf may have changed due to realloc in do_write() */
+                fe = ff.buf;
+                memset(fe, 0, sizeof(*fe));
+
+                fe->feat_id = feat;
+                fe->header.type = PERF_RECORD_HEADER_FEATURE;
+                fe->header.size = ff.offset;
+
+                ret = process(tool, ff.buf, NULL, NULL);
+                if (ret) {
+                        free(ff.buf);
+                        return ret;
+                }
+        }
+        free(ff.buf);
+        return 0;
+}
+
+int perf_event__process_feature(struct perf_tool *tool,
+                                union perf_event *event,
+                                struct perf_session *session __maybe_unused)
+{
+        struct feat_fd ff = { .fd = 0 };
+        struct feature_event *fe = (struct feature_event *)event;
+        int type = fe->header.type;
+        u64 feat = fe->feat_id;
+
+        if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
+                pr_warning("invalid record type %d in pipe-mode\n", type);
+                return 0;
+        }
+        if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+                pr_warning("invalid record type %d in pipe-mode\n", type);
+                return -1;
+        }
+
+        if (!feat_ops[feat].process)
+                return 0;
+
+        ff.buf  = (void *)fe->data;
+        ff.size = event->header.size - sizeof(event->header);
+        ff.ph = &session->header;
+
+        if (feat_ops[feat].process(&ff, NULL))
+                return -1;
+
+        if (!feat_ops[feat].print || !tool->show_feat_hdr)
+                return 0;
+
+        if (!feat_ops[feat].full_only ||
+            tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
+                feat_ops[feat].print(&ff, stdout);
+        } else {
+                fprintf(stdout, "# %s info available, use -I to display\n",
+                        feat_ops[feat].name);
+        }
+
+        return 0;
+}
+
 static struct event_update_event *
 event_update_event__new(size_t size, u64 type, u64 id)
 {
@@ -3253,6 +3350,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
         union perf_event ev;
         struct tracing_data *tdata;
         ssize_t size = 0, aligned_size = 0, padding;
+        struct feat_fd ff;
         int err __maybe_unused = 0;
 
         /*
@@ -3287,7 +3385,9 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
          */
         tracing_data_put(tdata);
 
-        write_padded(fd, NULL, 0, padding);
+        ff = (struct feat_fd){ .fd = fd };
+        if (write_padded(&ff, NULL, 0, padding))
+                return -1;
 
         return aligned_size;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d30109b421ee..f7a16ee527b8 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -101,6 +101,15 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
+int perf_event__synthesize_features(struct perf_tool *tool,
+                                    struct perf_session *session,
+                                    struct perf_evlist *evlist,
+                                    perf_event__handler_t process);
+
+int perf_event__process_feature(struct perf_tool *tool,
+                                union perf_event *event,
+                                struct perf_session *session);
+
 int perf_event__synthesize_attr(struct perf_tool *tool,
                                 struct perf_event_attr *attr, u32 ids, u64 *id,
                                 perf_event__handler_t process);
@@ -144,7 +153,12 @@ bool is_perf_magic(u64 magic);
 
 #define NAME_ALIGN 64
 
-int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
+struct feat_fd;
+
+int do_write(struct feat_fd *fd, const void *buf, size_t size);
+
+int write_padded(struct feat_fd *fd, const void *bf,
+                 size_t count, size_t count_aligned);
 
 /*
  * arch specific callback
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cf0186a088c1..e60d8d8ea4c2 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -167,6 +167,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                         symlen = unresolved_col_width + 4 + 2;
                         hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
                 }
+
+                hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
+                                   unresolved_col_width + 4 + 2);
+
         } else {
                 symlen = unresolved_col_width + 4 + 2;
                 hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
@@ -749,12 +753,9 @@ iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al
 }
 
 static int
-iter_add_single_branch_entry(struct hist_entry_iter *iter,
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
                              struct addr_location *al __maybe_unused)
 {
-        /* to avoid calling callback function */
-        iter->he = NULL;
-
         return 0;
 }
 
@@ -1762,6 +1763,8 @@ void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *pro
         else
                 use_callchain = symbol_conf.use_callchain;
 
+        use_callchain |= symbol_conf.show_branchflag_count;
+
         output_resort(evsel__hists(evsel), prog, use_callchain, NULL);
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee3670a388df..e60dda26a920 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
         HISTC_GLOBAL_WEIGHT,
         HISTC_MEM_DADDR_SYMBOL,
         HISTC_MEM_DADDR_DSO,
+        HISTC_MEM_PHYS_DADDR,
         HISTC_MEM_LOCKED,
         HISTC_MEM_TLB,
         HISTC_MEM_LVL,
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 7aca5d6d7e1f..10e0814bb8d2 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -25,6 +25,6 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in
 
 CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
 
-ifneq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 1)
   CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
 endif
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index c6a15f204c03..209b0c82eff4 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -33,7 +33,7 @@ struct llvm_param llvm_param = {
 
 int perf_llvm_config(const char *var, const char *value)
 {
-        if (prefixcmp(var, "llvm."))
+        if (!strstarts(var, "llvm."))
                 return 0;
         var += sizeof("llvm.") - 1;
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2e9eb6aa3ce2..df709363ef69 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -705,7 +705,8 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 
         if (kdso->has_build_id) {
                 char filename[PATH_MAX];
-                if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+                if (dso__build_id_filename(kdso, filename, sizeof(filename),
+                                           false))
                         printed += fprintf(fp, "[0] %s\n", filename);
         }
 
@@ -1137,7 +1138,8 @@ int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
         return 0;
 }
 
-static int machine__create_module(void *arg, const char *name, u64 start)
+static int machine__create_module(void *arg, const char *name, u64 start,
+                                  u64 size)
 {
         struct machine *machine = arg;
         struct map *map;
@@ -1148,6 +1150,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
         map = machine__findnew_module_map(machine, start, name);
         if (map == NULL)
                 return -1;
+        map->end = start + size;
 
         dso__kernel_module_get_build_id(map->dso, machine->root_dir);
 
@@ -1392,7 +1395,7 @@ int machine__process_mmap2_event(struct machine *machine,
 
         map = map__new(machine, event->mmap2.start,
                         event->mmap2.len, event->mmap2.pgoff,
-                        event->mmap2.pid, event->mmap2.maj,
+                        event->mmap2.maj,
                         event->mmap2.min, event->mmap2.ino,
                         event->mmap2.ino_generation,
                         event->mmap2.prot,
@@ -1450,7 +1453,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
         map = map__new(machine, event->mmap.start,
                         event->mmap.len, event->mmap.pgoff,
-                        event->mmap.pid, 0, 0, 0, 0, 0, 0,
+                        0, 0, 0, 0, 0, 0,
                         event->mmap.filename,
                         type, thread);
 
@@ -1632,10 +1635,12 @@ static void ip__resolve_ams(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = 0;
 }
 
 static void ip__resolve_data(struct thread *thread,
-                             u8 m, struct addr_map_symbol *ams, u64 addr)
+                             u8 m, struct addr_map_symbol *ams,
+                             u64 addr, u64 phys_addr)
 {
         struct addr_location al;
 
@@ -1655,6 +1660,7 @@ static void ip__resolve_data(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = phys_addr;
 }
 
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -1666,12 +1672,18 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
                 return NULL;
 
         ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
-        ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
+        ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+                         sample->addr, sample->phys_addr);
         mi->data_src.val = sample->data_src;
 
         return mi;
 }
 
+struct iterations {
+        int nr_loop_iter;
+        u64 cycles;
+};
+
 static int add_callchain_ip(struct thread *thread,
                             struct callchain_cursor *cursor,
                             struct symbol **parent,
@@ -1680,10 +1692,12 @@ static int add_callchain_ip(struct thread *thread,
                             u64 ip,
                             bool branch,
                             struct branch_flags *flags,
-                            int nr_loop_iter,
-                            int samples)
+                            struct iterations *iter,
+                            u64 branch_from)
 {
         struct addr_location al;
+        int nr_loop_iter = 0;
+        u64 iter_cycles = 0;
 
         al.filtered = 0;
         al.sym = NULL;
@@ -1733,8 +1747,15 @@ static int add_callchain_ip(struct thread *thread,
 
         if (symbol_conf.hide_unresolved && al.sym == NULL)
                 return 0;
+
+        if (iter) {
+                nr_loop_iter = iter->nr_loop_iter;
+                iter_cycles = iter->cycles;
+        }
+
         return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
-                                       branch, flags, nr_loop_iter, samples);
+                                       branch, flags, nr_loop_iter,
+                                       iter_cycles, branch_from);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1755,6 +1776,18 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
         return bi;
 }
 
+static void save_iterations(struct iterations *iter,
+                            struct branch_entry *be, int nr)
+{
+        int i;
+
+        iter->nr_loop_iter = nr;
+        iter->cycles = 0;
+
+        for (i = 0; i < nr; i++)
+                iter->cycles += be[i].flags.cycles;
+}
+
 #define CHASHSZ 127
 #define CHASHBITS 7
 #define NO_ENTRY 0xff
@@ -1762,7 +1795,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 #define PERF_MAX_BRANCH_DEPTH 127
 
 /* Remove loops. */
-static int remove_loops(struct branch_entry *l, int nr)
+static int remove_loops(struct branch_entry *l, int nr,
+                        struct iterations *iter)
 {
         int i, j, off;
         unsigned char chash[CHASHSZ];
@@ -1787,8 +1821,18 @@ static int remove_loops(struct branch_entry *l, int nr)
                                         break;
                                 }
                         if (is_loop) {
-                                memmove(l + i, l + i + off,
-                                        (nr - (i + off)) * sizeof(*l));
+                                j = nr - (i + off);
+                                if (j > 0) {
+                                        save_iterations(iter + i + off,
+                                                l + i, off);
+
+                                        memmove(iter + i, iter + i + off,
+                                                j * sizeof(*iter));
+
+                                        memmove(l + i, l + i + off,
+                                                j * sizeof(*l));
+                                }
+
                                 nr -= off;
                         }
                 }
@@ -1813,7 +1857,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
         struct ip_callchain *chain = sample->callchain;
         int chain_nr = min(max_stack, (int)chain->nr), i;
         u8 cpumode = PERF_RECORD_MISC_USER;
-        u64 ip;
+        u64 ip, branch_from = 0;
 
         for (i = 0; i < chain_nr; i++) {
                 if (chain->ips[i] == PERF_CONTEXT_USER)
@@ -1855,6 +1899,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
                                         ip = lbr_stack->entries[0].to;
                                         branch = true;
                                         flags = &lbr_stack->entries[0].flags;
+                                        branch_from =
+                                                lbr_stack->entries[0].from;
                                 }
                         } else {
                                 if (j < lbr_nr) {
@@ -1869,12 +1915,15 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
                                         ip = lbr_stack->entries[0].to;
                                         branch = true;
                                         flags = &lbr_stack->entries[0].flags;
+                                        branch_from =
+                                                lbr_stack->entries[0].from;
                                 }
                         }
 
                         err = add_callchain_ip(thread, cursor, parent,
                                                root_al, &cpumode, ip,
-                                               branch, flags, 0, 0);
+                                               branch, flags, NULL,
+                                               branch_from);
                         if (err)
                                 return (err < 0) ? err : 0;
                 }
@@ -1894,12 +1943,14 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
         struct branch_stack *branch = sample->branch_stack;
         struct ip_callchain *chain = sample->callchain;
-        int chain_nr = chain->nr;
+        int chain_nr = 0;
         u8 cpumode = PERF_RECORD_MISC_USER;
         int i, j, err, nr_entries;
         int skip_idx = -1;
         int first_call = 0;
-        int nr_loop_iter;
+
+        if (chain)
+                chain_nr = chain->nr;
 
         if (perf_evsel__has_branch_callstack(evsel)) {
                 err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
@@ -1929,6 +1980,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         if (branch && callchain_param.branch_callstack) {
                 int nr = min(max_stack, (int)branch->nr);
                 struct branch_entry be[nr];
+                struct iterations iter[nr];
 
                 if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
                         pr_warning("corrupted branch chain. skipping...\n");
@@ -1938,6 +1990,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
                 for (i = 0; i < nr; i++) {
                         if (callchain_param.order == ORDER_CALLEE) {
                                 be[i] = branch->entries[i];
+
+                                if (chain == NULL)
+                                        continue;
+
                                 /*
                                  * Check for overlap into the callchain.
                                  * The return address is one off compared to
@@ -1955,42 +2011,30 @@ static int thread__resolve_callchain_sample(struct thread *thread,
                                 be[i] = branch->entries[branch->nr - i - 1];
                 }
 
-                nr_loop_iter = nr;
-                nr = remove_loops(be, nr);
-
-                /*
-                 * Get the number of iterations.
-                 * It's only approximation, but good enough in practice.
-                 */
-                if (nr_loop_iter > nr)
-                        nr_loop_iter = nr_loop_iter - nr + 1;
-                else
-                        nr_loop_iter = 0;
+                memset(iter, 0, sizeof(struct iterations) * nr);
+                nr = remove_loops(be, nr, iter);
 
                 for (i = 0; i < nr; i++) {
-                        if (i == nr - 1)
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       nr_loop_iter, 1);
-                        else
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       0, 0);
+                        err = add_callchain_ip(thread, cursor, parent,
+                                               root_al,
+                                               NULL, be[i].to,
+                                               true, &be[i].flags,
+                                               NULL, be[i].from);
 
                         if (!err)
                                 err = add_callchain_ip(thread, cursor, parent, root_al,
                                                        NULL, be[i].from,
                                                        true, &be[i].flags,
-                                                       0, 0);
+                                                       &iter[i], 0);
                         if (err == -EINVAL)
                                 break;
                         if (err)
                                 return err;
                 }
+
+                if (chain_nr == 0)
+                        return 0;
+
                 chain_nr -= nr;
         }
 
@@ -2015,7 +2059,7 @@ check_calls:
 
                 err = add_callchain_ip(thread, cursor, parent,
                                        root_al, &cpumode, ip,
-                                       false, NULL, 0, 0);
+                                       false, NULL, NULL, 0);
 
                 if (err)
                         return (err < 0) ? err : 0;
@@ -2032,7 +2076,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
                 return 0;
         return callchain_cursor_append(cursor, entry->ip,
                                        entry->map, entry->sym,
-                                       false, NULL, 0, 0);
+                                       false, NULL, 0, 0, 0);
 }
 
 static int thread__resolve_callchain_unwind(struct thread *thread,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 2179b2deb730..bdaa0a4edc17 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -16,6 +16,7 @@
 #include "machine.h"
 #include <linux/string.h>
 #include "srcline.h"
+#include "namespaces.h"
 #include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
@@ -145,11 +146,13 @@ void map__init(struct map *map, enum map_type type,
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
-                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
                      u64 ino_gen, u32 prot, u32 flags, char *filename,
                      enum map_type type, struct thread *thread)
 {
         struct map *map = malloc(sizeof(*map));
+        struct nsinfo *nsi = NULL;
+        struct nsinfo *nnsi;
 
         if (map != NULL) {
                 char newfilename[PATH_MAX];
@@ -167,9 +170,11 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                 map->ino_generation = ino_gen;
                 map->prot = prot;
                 map->flags = flags;
+                nsi = nsinfo__get(thread->nsinfo);
 
-                if ((anon || no_dso) && type == MAP__FUNCTION) {
-                        snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
+                if ((anon || no_dso) && nsi && type == MAP__FUNCTION) {
+                        snprintf(newfilename, sizeof(newfilename),
+                                 "/tmp/perf-%d.map", nsi->pid);
                         filename = newfilename;
                 }
 
@@ -179,6 +184,16 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                 }
 
                 if (vdso) {
+                        /* The vdso maps are always on the host and not the
+                         * container.  Ensure that we don't use setns to look
+                         * them up.
+                         */
+                        nnsi = nsinfo__copy(nsi);
+                        if (nnsi) {
+                                nsinfo__put(nsi);
+                                nnsi->need_setns = false;
+                                nsi = nnsi;
+                        }
                         pgoff = 0;
                         dso = machine__findnew_vdso(machine, thread);
                 } else
@@ -200,10 +215,12 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
                         if (type != MAP__FUNCTION)
                                 dso__set_loaded(dso, map->type);
                 }
+                dso->nsinfo = nsi;
                 dso__put(dso);
         }
         return map;
 out_delete:
+        nsinfo__put(nsi);
         free(map);
         return NULL;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f9e8ac8a52cd..73aacf7a7dc4 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -141,7 +141,7 @@ struct thread;
 void map__init(struct map *map, enum map_type type,
                u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
-                     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
+                     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
                      u64 ino_gen, u32 prot, u32 flags,
                      char *filename, enum map_type type, struct thread *thread);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 06f5a3a4295c..28afe5fa84d6 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -166,11 +166,20 @@ static const char * const mem_lvl[] = {
         "Uncached",
 };
 
+static const char * const mem_lvlnum[] = {
+        [PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache",
+        [PERF_MEM_LVLNUM_LFB] = "LFB",
+        [PERF_MEM_LVLNUM_RAM] = "RAM",
+        [PERF_MEM_LVLNUM_PMEM] = "PMEM",
+        [PERF_MEM_LVLNUM_NA] = "N/A",
+};
+
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
         size_t i, l = 0;
         u64 m =  PERF_MEM_LVL_NA;
         u64 hit, miss;
+        int printed;
 
         if (mem_info)
                 m  = mem_info->data_src.mem_lvl;
@@ -184,17 +193,37 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
         /* already taken care of */
         m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
+
+        if (mem_info && mem_info->data_src.mem_remote) {
+                strcat(out, "Remote ");
+                l += 7;
+        }
+
+        printed = 0;
         for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
                 if (!(m & 0x1))
                         continue;
-                if (l) {
+                if (printed++) {
                         strcat(out, " or ");
                         l += 4;
                 }
                 l += scnprintf(out + l, sz - l, mem_lvl[i]);
         }
-        if (*out == '\0')
-                l += scnprintf(out, sz - l, "N/A");
+
+        if (mem_info && mem_info->data_src.mem_lvl_num) {
+                int lvl = mem_info->data_src.mem_lvl_num;
+                if (printed++) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                if (mem_lvlnum[lvl])
+                        l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]);
+                else
+                        l += scnprintf(out + l, sz - l, "L%d", lvl);
+        }
+
+        if (l == 0)
+                l += scnprintf(out + l, sz - l, "N/A");
         if (hit)
                 l += scnprintf(out + l, sz - l, " hit");
         if (miss)
@@ -231,6 +260,14 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
                 }
                 l += scnprintf(out + l, sz - l, snoop_access[i]);
         }
+        if (mem_info &&
+             (mem_info->data_src.mem_snoopx & PERF_MEM_SNOOPX_FWD)) {
+                if (l) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                l += scnprintf(out + l, sz - l, "Fwd");
+        }
 
         if (*out == '\0')
                 l += scnprintf(out, sz - l, "N/A");
@@ -279,6 +316,11 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
         u64 lvl    = data_src->mem_lvl;
         u64 snoop  = data_src->mem_snoop;
         u64 lock   = data_src->mem_lock;
+        /*
+         * Skylake might report unknown remote level via this
+         * bit, consider it when evaluating remote HITMs.
+         */
+        bool mrem  = data_src->mem_remote;
         int err = 0;
 
 #define HITM_INC(__f)           \
@@ -324,7 +366,8 @@ do {				\
                         }
 
                         if ((lvl & P(LVL, REM_RAM1)) ||
-                            (lvl & P(LVL, REM_RAM2))) {
+                            (lvl & P(LVL, REM_RAM2)) ||
+                             mrem) {
                                 stats->rmt_dram++;
                                 if (snoop & P(SNOOP, HIT))
                                         stats->ld_shared++;
@@ -334,7 +377,8 @@ do {				\
                 }
 
                 if ((lvl & P(LVL, REM_CCE1)) ||
-                    (lvl & P(LVL, REM_CCE2))) {
+                    (lvl & P(LVL, REM_CCE2)) ||
+                     mrem) {
                         if (snoop & P(SNOOP, HIT))
                                 stats->rmt_hit++;
                         else if (snoop & P(SNOOP, HITM))
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 67dcbcc73c7d..a58e91197729 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -9,9 +9,14 @@
 #include "namespaces.h"
 #include "util.h"
 #include "event.h"
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <limits.h>
+#include <sched.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <unistd.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -35,3 +40,209 @@ void namespaces__free(struct namespaces *namespaces)
 {
         free(namespaces);
 }
+
+int nsinfo__init(struct nsinfo *nsi)
+{
+        char oldns[PATH_MAX];
+        char spath[PATH_MAX];
+        char *newns = NULL;
+        char *statln = NULL;
+        struct stat old_stat;
+        struct stat new_stat;
+        FILE *f = NULL;
+        size_t linesz = 0;
+        int rv = -1;
+
+        if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
+                return rv;
+
+        if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1)
+                return rv;
+
+        if (stat(oldns, &old_stat) < 0)
+                goto out;
+
+        if (stat(newns, &new_stat) < 0)
+                goto out;
+
+        /* Check if the mount namespaces differ, if so then indicate that we
+         * want to switch as part of looking up dso/map data.
+         */
+        if (old_stat.st_ino != new_stat.st_ino) {
+                nsi->need_setns = true;
+                nsi->mntns_path = newns;
+                newns = NULL;
+        }
+
+        /* If we're dealing with a process that is in a different PID namespace,
+         * attempt to work out the innermost tgid for the process.
+         */
+        if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
+                goto out;
+
+        f = fopen(spath, "r");
+        if (f == NULL)
+                goto out;
+
+        while (getline(&statln, &linesz, f) != -1) {
+                /* Use tgid if CONFIG_PID_NS is not defined. */
+                if (strstr(statln, "Tgid:") != NULL) {
+                        nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
+                                                     NULL, 10);
+                        nsi->nstgid = nsi->tgid;
+                }
+
+                if (strstr(statln, "NStgid:") != NULL) {
+                        nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'),
+                                                     NULL, 10);
+                        break;
+                }
+        }
+        rv = 0;
+
+out:
+        if (f != NULL)
+                (void) fclose(f);
+        free(statln);
+        free(newns);
+        return rv;
+}
+
+struct nsinfo *nsinfo__new(pid_t pid)
+{
+        struct nsinfo *nsi;
+
+        if (pid == 0)
+                return NULL;
+
+        nsi = calloc(1, sizeof(*nsi));
+        if (nsi != NULL) {
+                nsi->pid = pid;
+                nsi->tgid = pid;
+                nsi->nstgid = pid;
+                nsi->need_setns = false;
+                /* Init may fail if the process exits while we're trying to look
+                 * at its proc information.  In that case, save the pid but
+                 * don't try to enter the namespace.
+                 */
+                if (nsinfo__init(nsi) == -1)
+                        nsi->need_setns = false;
+
+                refcount_set(&nsi->refcnt, 1);
+        }
+
+        return nsi;
+}
+
+struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
+{
+        struct nsinfo *nnsi;
+
+        nnsi = calloc(1, sizeof(*nnsi));
+        if (nnsi != NULL) {
+                nnsi->pid = nsi->pid;
+                nnsi->tgid = nsi->tgid;
+                nnsi->nstgid = nsi->nstgid;
+                nnsi->need_setns = nsi->need_setns;
+                if (nsi->mntns_path) {
+                        nnsi->mntns_path = strdup(nsi->mntns_path);
+                        if (!nnsi->mntns_path) {
+                                free(nnsi);
+                                return NULL;
+                        }
+                }
+                refcount_set(&nnsi->refcnt, 1);
+        }
+
+        return nnsi;
+}
+
+void nsinfo__delete(struct nsinfo *nsi)
+{
+        zfree(&nsi->mntns_path);
+        free(nsi);
+}
+
+struct nsinfo *nsinfo__get(struct nsinfo *nsi)
+{
+        if (nsi)
+                refcount_inc(&nsi->refcnt);
+        return nsi;
+}
+
+void nsinfo__put(struct nsinfo *nsi)
+{
+        if (nsi && refcount_dec_and_test(&nsi->refcnt))
+                nsinfo__delete(nsi);
+}
+
+void nsinfo__mountns_enter(struct nsinfo *nsi,
+                                  struct nscookie *nc)
+{
+        char curpath[PATH_MAX];
+        int oldns = -1;
+        int newns = -1;
+
+        if (nc == NULL)
+                return;
+
+        nc->oldns = -1;
+        nc->newns = -1;
+
+        if (!nsi || !nsi->need_setns)
+                return;
+
+        if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
+                return;
+
+        oldns = open(curpath, O_RDONLY);
+        if (oldns < 0)
+                return;
+
+        newns = open(nsi->mntns_path, O_RDONLY);
+        if (newns < 0)
+                goto errout;
+
+        if (setns(newns, CLONE_NEWNS) < 0)
+                goto errout;
+
+        nc->oldns = oldns;
+        nc->newns = newns;
+        return;
+
+errout:
+        if (oldns > -1)
+                close(oldns);
+        if (newns > -1)
+                close(newns);
+}
+
+void nsinfo__mountns_exit(struct nscookie *nc)
+{
+        if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+                return;
+
+        setns(nc->oldns, CLONE_NEWNS);
+
+        if (nc->oldns > -1) {
+                close(nc->oldns);
+                nc->oldns = -1;
+        }
+
+        if (nc->newns > -1) {
+                close(nc->newns);
+                nc->newns = -1;
+        }
+}
+
+char *nsinfo__realpath(const char *path, struct nsinfo *nsi)
+{
+        char *rpath;
+        struct nscookie nsc;
+
+        nsinfo__mountns_enter(nsi, &nsc);
+        rpath = realpath(path, NULL);
+        nsinfo__mountns_exit(&nsc);
+
+        return rpath;
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 468f1e9a1484..05d82601c9a6 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -11,6 +11,7 @@
 
 #include "../perf.h"
 #include <linux/list.h>
+#include <linux/refcount.h>
 
 struct namespaces_event;
 
@@ -23,4 +24,41 @@ struct namespaces {
 struct namespaces *namespaces__new(struct namespaces_event *event);
 void namespaces__free(struct namespaces *namespaces);
 
+struct nsinfo {
+        pid_t                   pid;
+        pid_t                   tgid;
+        pid_t                   nstgid;
+        bool                    need_setns;
+        char                    *mntns_path;
+        refcount_t              refcnt;
+};
+
+struct nscookie {
+        int                     oldns;
+        int                     newns;
+};
+
+int nsinfo__init(struct nsinfo *nsi);
+struct nsinfo *nsinfo__new(pid_t pid);
+struct nsinfo *nsinfo__copy(struct nsinfo *nsi);
+void nsinfo__delete(struct nsinfo *nsi);
+
+struct nsinfo *nsinfo__get(struct nsinfo *nsi);
+void nsinfo__put(struct nsinfo *nsi);
+
+void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc);
+void nsinfo__mountns_exit(struct nscookie *nc);
+
+char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
+
+static inline void __nsinfo__zput(struct nsinfo **nsip)
+{
+        if (nsip) {
+                nsinfo__put(*nsip);
+                *nsip = NULL;
+        }
+}
+
+#define nsinfo__zput(nsi) __nsinfo__zput(&nsi)
+
 #endif  /* __PERF_NAMESPACES_H */
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 38fd11504015..e71fb5f31e84 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -28,6 +28,7 @@ static const struct branch_mode branch_modes[] = {
         BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
         BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
         BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
+        BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
         BRANCH_END
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 01e779b91c8e..f6257fb4f08c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -34,7 +34,7 @@
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-int parse_events_parse(void *data, void *scanner);
+int parse_events_parse(void *parse_state, void *scanner);
 static int get_config_terms(struct list_head *head_config,
                             struct list_head *head_terms __maybe_unused);
 
@@ -310,7 +310,7 @@ static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
             struct perf_event_attr *attr,
             char *name, struct cpu_map *cpus,
-            struct list_head *config_terms)
+            struct list_head *config_terms, bool auto_merge_stats)
 {
         struct perf_evsel *evsel;
 
@@ -324,6 +324,7 @@ __add_event(struct list_head *list, int *idx,
         evsel->cpus        = cpu_map__get(cpus);
         evsel->own_cpus    = cpu_map__get(cpus);
         evsel->system_wide = !!cpus;
+        evsel->auto_merge_stats = auto_merge_stats;
 
         if (name)
                 evsel->name = strdup(name);
@@ -339,7 +340,7 @@ static int add_event(struct list_head *list, int *idx,
                      struct perf_event_attr *attr, char *name,
                      struct list_head *config_terms)
 {
-        return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM;
+        return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -589,7 +590,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 }
 
 struct __add_bpf_event_param {
-        struct parse_events_evlist *data;
+        struct parse_events_state *parse_state;
         struct list_head *list;
         struct list_head *head_config;
 };
@@ -599,7 +600,7 @@ static int add_bpf_event(const char *group, const char *event, int fd,
 {
         LIST_HEAD(new_evsels);
         struct __add_bpf_event_param *param = _param;
-        struct parse_events_evlist *evlist = param->data;
+        struct parse_events_state *parse_state = param->parse_state;
         struct list_head *list = param->list;
         struct perf_evsel *pos;
         int err;
@@ -607,8 +608,8 @@ static int add_bpf_event(const char *group, const char *event, int fd,
         pr_debug("add bpf event %s:%s and attach bpf program %d\n",
                  group, event, fd);
 
-        err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group,
-                                          event, evlist->error,
+        err = parse_events_add_tracepoint(&new_evsels, &parse_state->idx, group,
+                                          event, parse_state->error,
                                           param->head_config);
         if (err) {
                 struct perf_evsel *evsel, *tmp;
@@ -632,14 +633,14 @@ static int add_bpf_event(const char *group, const char *event, int fd,
         return 0;
 }
 
-int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
                               struct list_head *list,
                               struct bpf_object *obj,
                               struct list_head *head_config)
 {
         int err;
         char errbuf[BUFSIZ];
-        struct __add_bpf_event_param param = {data, list, head_config};
+        struct __add_bpf_event_param param = {parse_state, list, head_config};
         static bool registered_unprobe_atexit = false;
 
         if (IS_ERR(obj) || !obj) {
@@ -680,13 +681,13 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 
         return 0;
 errout:
-        data->error->help = strdup("(add -v to see detail)");
-        data->error->str = strdup(errbuf);
+        parse_state->error->help = strdup("(add -v to see detail)");
+        parse_state->error->str = strdup(errbuf);
         return err;
 }
 
 static int
-parse_events_config_bpf(struct parse_events_evlist *data,
+parse_events_config_bpf(struct parse_events_state *parse_state,
                         struct bpf_object *obj,
                         struct list_head *head_config)
 {
@@ -705,28 +706,28 @@ parse_events_config_bpf(struct parse_events_evlist *data,
                                  "Invalid config term for BPF object");
                         errbuf[BUFSIZ - 1] = '\0';
 
-                        data->error->idx = term->err_term;
-                        data->error->str = strdup(errbuf);
+                        parse_state->error->idx = term->err_term;
+                        parse_state->error->str = strdup(errbuf);
                         return -EINVAL;
                 }
 
-                err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+                err = bpf__config_obj(obj, term, parse_state->evlist, &error_pos);
                 if (err) {
-                        bpf__strerror_config_obj(obj, term, data->evlist,
+                        bpf__strerror_config_obj(obj, term, parse_state->evlist,
                                                  &error_pos, err, errbuf,
                                                  sizeof(errbuf));
-                        data->error->help = strdup(
+                        parse_state->error->help = strdup(
 "Hint:\tValid config terms:\n"
 "     \tmap:[<arraymap>].value<indices>=[value]\n"
 "     \tmap:[<eventmap>].event<indices>=[event]\n"
 "\n"
 "     \twhere <indices> is something like [0,3...5] or [all]\n"
 "     \t(add -v to see detail)");
-                        data->error->str = strdup(errbuf);
+                        parse_state->error->str = strdup(errbuf);
                         if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
-                                data->error->idx = term->err_val;
+                                parse_state->error->idx = term->err_val;
                         else
-                                data->error->idx = term->err_term + error_pos;
+                                parse_state->error->idx = term->err_term + error_pos;
                         return err;
                 }
         }
@@ -762,7 +763,7 @@ split_bpf_config_terms(struct list_head *evt_head_config,
                         list_move_tail(&term->list, obj_head_config);
 }
 
-int parse_events_load_bpf(struct parse_events_evlist *data,
+int parse_events_load_bpf(struct parse_events_state *parse_state,
                           struct list_head *list,
                           char *bpf_file_name,
                           bool source,
@@ -790,15 +791,15 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
                                                    -err, errbuf,
                                                    sizeof(errbuf));
 
-                data->error->help = strdup("(add -v to see detail)");
-                data->error->str = strdup(errbuf);
+                parse_state->error->help = strdup("(add -v to see detail)");
+                parse_state->error->str = strdup(errbuf);
                 return err;
         }
 
-        err = parse_events_load_bpf_obj(data, list, obj, head_config);
+        err = parse_events_load_bpf_obj(parse_state, list, obj, head_config);
         if (err)
                 return err;
-        err = parse_events_config_bpf(data, obj, &obj_head_config);
+        err = parse_events_config_bpf(parse_state, obj, &obj_head_config);
 
         /*
          * Caller doesn't know anything about obj_head_config,
@@ -1184,7 +1185,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                             err, head_config);
 }
 
-int parse_events_add_numeric(struct parse_events_evlist *data,
+int parse_events_add_numeric(struct parse_events_state *parse_state,
                              struct list_head *list,
                              u32 type, u64 config,
                              struct list_head *head_config)
@@ -1197,7 +1198,7 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
         attr.config = config;
 
         if (head_config) {
-                if (config_attr(&attr, head_config, data->error,
+                if (config_attr(&attr, head_config, parse_state->error,
                                 config_term_common))
                         return -EINVAL;
 
@@ -1205,13 +1206,13 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
                         return -ENOMEM;
         }
 
-        return add_event(list, &data->idx, &attr,
+        return add_event(list, &parse_state->idx, &attr,
                          get_config_name(head_config), &config_terms);
 }
 
-int parse_events_add_pmu(struct parse_events_evlist *data,
+static int __parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
-                         struct list_head *head_config)
+                         struct list_head *head_config, bool auto_merge_stats)
 {
         struct perf_event_attr attr;
         struct perf_pmu_info info;
@@ -1232,7 +1233,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 
         if (!head_config) {
                 attr.type = pmu->type;
-                evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus, NULL);
+                evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
                 return evsel ? 0 : -ENOMEM;
         }
 
@@ -1243,18 +1244,18 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
          * Configure hardcoded terms first, no need to check
          * return value when called with fail == 0 ;)
          */
-        if (config_attr(&attr, head_config, data->error, config_term_pmu))
+        if (config_attr(&attr, head_config, parse_state->error, config_term_pmu))
                 return -EINVAL;
 
         if (get_config_terms(head_config, &config_terms))
                 return -ENOMEM;
 
-        if (perf_pmu__config(pmu, &attr, head_config, data->error))
+        if (perf_pmu__config(pmu, &attr, head_config, parse_state->error))
                 return -EINVAL;
 
-        evsel = __add_event(list, &data->idx, &attr,
+        evsel = __add_event(list, &parse_state->idx, &attr,
                             get_config_name(head_config), pmu->cpus,
-                            &config_terms);
+                            &config_terms, auto_merge_stats);
         if (evsel) {
                 evsel->unit = info.unit;
                 evsel->scale = info.scale;
@@ -1267,7 +1268,14 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
         return evsel ? 0 : -ENOMEM;
 }
 
-int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
+                         struct list_head *list, char *name,
+                         struct list_head *head_config)
+{
+        return __parse_events_add_pmu(parse_state, list, name, head_config, false);
+}
+
+int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str, struct list_head **listp)
 {
         struct list_head *head;
@@ -1296,8 +1304,8 @@ int parse_events_multi_pmu_add(struct parse_events_evlist *data,
                                         return -1;
                                 list_add_tail(&term->list, head);
 
-                                if (!parse_events_add_pmu(data, list,
-                                                  pmu->name, head)) {
+                                if (!__parse_events_add_pmu(parse_state, list,
+                                                            pmu->name, head, true)) {
                                         pr_debug("%s -> %s/%s/\n", str,
                                                  pmu->name, alias->str);
                                         ok++;
@@ -1628,7 +1636,7 @@ perf_pmu__parse_check(const char *name)
         return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
-static int parse_events__scanner(const char *str, void *data, int start_token)
+static int parse_events__scanner(const char *str, void *parse_state, int start_token)
 {
         YY_BUFFER_STATE buffer;
         void *scanner;
@@ -1643,7 +1651,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 #ifdef PARSER_DEBUG
         parse_events_debug = 1;
 #endif
-        ret = parse_events_parse(data, scanner);
+        ret = parse_events_parse(parse_state, scanner);
 
         parse_events__flush_buffer(buffer, scanner);
         parse_events__delete_buffer(buffer, scanner);
@@ -1656,45 +1664,45 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
  */
 int parse_events_terms(struct list_head *terms, const char *str)
 {
-        struct parse_events_terms data = {
+        struct parse_events_state parse_state = {
                 .terms = NULL,
         };
         int ret;
 
-        ret = parse_events__scanner(str, &data, PE_START_TERMS);
+        ret = parse_events__scanner(str, &parse_state, PE_START_TERMS);
         if (!ret) {
-                list_splice(data.terms, terms);
-                zfree(&data.terms);
+                list_splice(parse_state.terms, terms);
+                zfree(&parse_state.terms);
                 return 0;
         }
 
-        parse_events_terms__delete(data.terms);
+        parse_events_terms__delete(parse_state.terms);
         return ret;
 }
 
 int parse_events(struct perf_evlist *evlist, const char *str,
                  struct parse_events_error *err)
 {
-        struct parse_events_evlist data = {
-                .list   = LIST_HEAD_INIT(data.list),
+        struct parse_events_state parse_state = {
+                .list   = LIST_HEAD_INIT(parse_state.list),
                 .idx    = evlist->nr_entries,
                 .error  = err,
                 .evlist = evlist,
         };
         int ret;
 
-        ret = parse_events__scanner(str, &data, PE_START_EVENTS);
+        ret = parse_events__scanner(str, &parse_state, PE_START_EVENTS);
         perf_pmu__parse_cleanup();
         if (!ret) {
                 struct perf_evsel *last;
 
-                if (list_empty(&data.list)) {
+                if (list_empty(&parse_state.list)) {
                         WARN_ONCE(true, "WARNING: event parser found nothing");
                         return -1;
                 }
 
-                perf_evlist__splice_list_tail(evlist, &data.list);
-                evlist->nr_groups += data.nr_groups;
+                perf_evlist__splice_list_tail(evlist, &parse_state.list);
+                evlist->nr_groups += parse_state.nr_groups;
                 last = perf_evlist__last(evlist);
                 last->cmdline_group_boundary = true;
 
@@ -2124,7 +2132,7 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,
                 return;
         }
         strlist__for_each_entry(nd, bidlist) {
-                pcache = probe_cache__new(nd->s);
+                pcache = probe_cache__new(nd->s, NULL);
                 if (!pcache)
                         continue;
                 list_for_each_entry(ent, &pcache->entries, node) {
@@ -2520,10 +2528,10 @@ void parse_events__clear_array(struct parse_events_array *a)
         zfree(&a->ranges);
 }
 
-void parse_events_evlist_error(struct parse_events_evlist *data,
+void parse_events_evlist_error(struct parse_events_state *parse_state,
                                int idx, const char *str)
 {
-        struct parse_events_error *err = data->error;
+        struct parse_events_error *err = parse_state->error;
 
         if (!err)
                 return;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index a235f4d6d5e5..635135125111 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -108,16 +108,13 @@ struct parse_events_error {
         char *help;     /* optional help string */
 };
 
-struct parse_events_evlist {
+struct parse_events_state {
         struct list_head           list;
         int                        idx;
         int                        nr_groups;
         struct parse_events_error *error;
         struct perf_evlist        *evlist;
-};
-
-struct parse_events_terms {
-        struct list_head *terms;
+        struct list_head          *terms;
 };
 
 void parse_events__shrink_config_terms(void);
@@ -143,18 +140,18 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
                                 const char *sys, const char *event,
                                 struct parse_events_error *error,
                                 struct list_head *head_config);
-int parse_events_load_bpf(struct parse_events_evlist *data,
+int parse_events_load_bpf(struct parse_events_state *parse_state,
                           struct list_head *list,
                           char *bpf_file_name,
                           bool source,
                           struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
-int parse_events_load_bpf_obj(struct parse_events_evlist *data,
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
                               struct list_head *list,
                               struct bpf_object *obj,
                               struct list_head *head_config);
-int parse_events_add_numeric(struct parse_events_evlist *data,
+int parse_events_add_numeric(struct parse_events_state *parse_state,
                              struct list_head *list,
                              u32 type, u64 config,
                              struct list_head *head_config);
@@ -164,11 +161,11 @@ int parse_events_add_cache(struct list_head *list, int *idx,
                            struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct parse_events_evlist *data,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
                          struct list_head *head_config);
 
-int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str,
                                struct list_head **listp);
 
@@ -180,7 +177,7 @@ perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
                                struct list_head *list_all);
-void parse_events_evlist_error(struct parse_events_evlist *data,
+void parse_events_evlist_error(struct parse_events_state *parse_state,
                                int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only, bool quiet,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 660fca05bc93..c42edeac451f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -53,6 +53,21 @@ static int str(yyscan_t scanner, int token)
         return token;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+        char *text = parse_events_get_text(scanner);
+        int len = strlen(text);
+
+        if (len < 2)
+                return false;
+        if ((text[len - 1] == 'c' || text[len - 1] == 'o') &&
+            text[len - 2] == '.')
+                return true;
+        if (len > 4 && !strcmp(text + len - 4, ".obj"))
+                return true;
+        return false;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
@@ -136,8 +151,8 @@ do {							\
 group           [^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu       [^,{}/]+[/][^/]*[/][^,{}/]*
 event           [^,{}/]+
-bpf_object      [^,{}]+\.(o|bpf)
-bpf_source      [^,{}]+\.c
+bpf_object      [^,{}]+\.(o|bpf)[a-zA-Z0-9._]*
+bpf_source      [^,{}]+\.c[a-zA-Z0-9._]*
 
 num_dec         [0-9]+
 num_hex         0x[a-fA-F0-9]+
@@ -307,8 +322,8 @@ r{num_raw_hex}		{ return raw(yyscanner); }
 {num_hex}               { return value(yyscanner, 16); }
 
 {modifier_event}        { return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object}            { return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source}            { return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object}            { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source}            { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
 {name}                  { return pmu_str_check(yyscanner); }
 "/"                     { BEGIN(config); return '/'; }
 -                       { return '-'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 04fd8c9af9f9..e81a20ea8d7d 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,5 +1,5 @@
 %pure-parser
-%parse-param {void *_data}
+%parse-param {void *_parse_state}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
 %locations
@@ -17,7 +17,7 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
-void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg);
+void parse_events_error(YYLTYPE *loc, void *parse_state, void *scanner, char const *msg);
 
 #define ABORT_ON(val) \
 do { \
@@ -33,11 +33,11 @@ do { \
 } while (0)
 
 static void inc_group_count(struct list_head *list,
-                       struct parse_events_evlist *data)
+                       struct parse_events_state *parse_state)
 {
         /* Count groups only have more than 1 members */
         if (!list_is_last(list->next, list))
-                data->nr_groups++;
+                parse_state->nr_groups++;
 }
 
 %}
@@ -115,9 +115,9 @@ PE_START_TERMS  start_terms
 
 start_events: groups
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
 
-        parse_events_update_lists($1, &data->list);
+        parse_events_update_lists($1, &parse_state->list);
 }
 
 groups:
@@ -159,7 +159,7 @@ PE_NAME '{' events '}'
 {
         struct list_head *list = $3;
 
-        inc_group_count(list, _data);
+        inc_group_count(list, _parse_state);
         parse_events__set_leader($1, list);
         $$ = list;
 }
@@ -168,7 +168,7 @@ PE_NAME '{' events '}'
 {
         struct list_head *list = $2;
 
-        inc_group_count(list, _data);
+        inc_group_count(list, _parse_state);
         parse_events__set_leader(NULL, list);
         $$ = list;
 }
@@ -225,14 +225,13 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list, *orig_terms, *terms;
 
         if (parse_events_copy_term_list($2, &orig_terms))
                 YYABORT;
 
         ALLOC_LIST(list);
-        if (parse_events_add_pmu(data, list, $1, $2)) {
+        if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
                 struct perf_pmu *pmu = NULL;
                 int ok = 0;
 
@@ -245,7 +244,7 @@ PE_NAME opt_event_config
                         if (!strncmp($1, name, strlen($1))) {
                                 if (parse_events_copy_term_list(orig_terms, &terms))
                                         YYABORT;
-                                if (!parse_events_add_pmu(data, list, pmu->name, terms))
+                                if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
                                         ok++;
                                 parse_events_terms__delete(terms);
                         }
@@ -262,7 +261,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 {
         struct list_head *list;
 
-        if (parse_events_multi_pmu_add(_data, $1, &list) < 0)
+        if (parse_events_multi_pmu_add(_parse_state, $1, &list) < 0)
                 YYABORT;
         $$ = list;
 }
@@ -273,7 +272,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
         char pmu_name[128];
 
         snprintf(&pmu_name, 128, "%s-%s", $1, $3);
-        if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0)
+        if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0)
                 YYABORT;
         $$ = list;
 }
@@ -286,62 +285,60 @@ PE_VALUE_SYM_SW
 event_legacy_symbol:
 value_sym '/' event_config '/'
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, $3));
         parse_events_terms__delete($3);
         $$ = list;
 }
 |
 value_sym sep_slash_dc
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
         int type = $1 >> 16;
         int config = $1 & 255;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
         $$ = list;
 }
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6));
         parse_events_terms__delete($6);
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4));
         parse_events_terms__delete($4);
         $$ = list;
 }
 |
 PE_NAME_CACHE_TYPE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+        ABORT_ON(parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -349,44 +346,44 @@ PE_NAME_CACHE_TYPE opt_event_config
 event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, $6, $4));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, NULL, $4));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, $4, 0));
         $$ = list;
 }
 |
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
-        struct parse_events_evlist *data = _data;
+        struct parse_events_state *parse_state = _parse_state;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
+        ABORT_ON(parse_events_add_breakpoint(list, &parse_state->idx,
                                              (void *) $2, NULL, 0));
         $$ = list;
 }
@@ -394,15 +391,15 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 event_legacy_tracepoint:
 tracepoint_name opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
         if (error)
                 error->idx = @1.first_column;
 
-        if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
+        if (parse_events_add_tracepoint(list, &parse_state->idx, $1.sys, $1.event,
                                         error, $2))
                 return -1;
 
@@ -432,11 +429,10 @@ PE_NAME ':' PE_NAME
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4));
         parse_events_terms__delete($4);
         $$ = list;
 }
@@ -444,11 +440,10 @@ PE_VALUE ':' PE_VALUE opt_event_config
 event_legacy_raw:
 PE_RAW opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+        ABORT_ON(parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -456,23 +451,22 @@ PE_RAW opt_event_config
 event_bpf_file:
 PE_BPF_OBJECT opt_event_config
 {
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
+        struct parse_events_state *parse_state = _parse_state;
+        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+        ABORT_ON(parse_events_load_bpf(parse_state, list, $1, false, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
 |
 PE_BPF_SOURCE opt_event_config
 {
-        struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+        ABORT_ON(parse_events_load_bpf(_parse_state, list, $1, true, $2));
         parse_events_terms__delete($2);
         $$ = list;
 }
@@ -494,8 +488,8 @@ opt_event_config:
 
 start_terms: event_config
 {
-        struct parse_events_terms *data = _data;
-        data->terms = $1;
+        struct parse_events_state *parse_state = _parse_state;
+        parse_state->terms = $1;
 }
 
 event_config:
@@ -685,9 +679,9 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(YYLTYPE *loc, void *data,
+void parse_events_error(YYLTYPE *loc, void *parse_state,
                         void *scanner __maybe_unused,
                         char const *msg __maybe_unused)
 {
-        parse_events_evlist_error(data, loc->last_column, "parser error");
+        parse_events_evlist_error(parse_state, loc->last_column, "parser error");
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a2670e9d652d..b7aaf9b2294d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -184,13 +184,19 @@ static struct map *kernel_get_module_map(const char *module)
         return NULL;
 }
 
-struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user)
 {
         /* Init maps of given executable or kernel */
-        if (user)
-                return dso__new_map(target);
-        else
+        if (user) {
+                struct map *map;
+
+                map = dso__new_map(target);
+                if (map && map->dso)
+                        map->dso->nsinfo = nsinfo__get(nsi);
+                return map;
+        } else {
                 return kernel_get_module_map(target);
+        }
 }
 
 static int convert_exec_to_group(const char *exec, char **result)
@@ -366,7 +372,8 @@ found:
 static int find_alternative_probe_point(struct debuginfo *dinfo,
                                         struct perf_probe_point *pp,
                                         struct perf_probe_point *result,
-                                        const char *target, bool uprobes)
+                                        const char *target, struct nsinfo *nsi,
+                                        bool uprobes)
 {
         struct map *map = NULL;
         struct symbol *sym;
@@ -377,7 +384,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
         if (!pp->function || pp->file)
                 return -ENOTSUP;
 
-        map = get_target_map(target, uprobes);
+        map = get_target_map(target, nsi, uprobes);
         if (!map)
                 return -EINVAL;
 
@@ -421,8 +428,8 @@ static int get_alternative_probe_event(struct debuginfo *dinfo,
 
         memcpy(tmp, &pev->point, sizeof(*tmp));
         memset(&pev->point, 0, sizeof(pev->point));
-        ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
-                                           pev->target, pev->uprobes);
+        ret = find_alternative_probe_point(dinfo, tmp, &pev->point, pev->target,
+                                           pev->nsi, pev->uprobes);
         if (ret < 0)
                 memcpy(&pev->point, tmp, sizeof(*tmp));
 
@@ -444,7 +451,7 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
         if (lr->end != INT_MAX)
                 len = lr->end - lr->start;
         ret = find_alternative_probe_point(dinfo, &pp, &result,
-                                           target, user);
+                                           target, NULL, user);
         if (!ret) {
                 lr->function = result.function;
                 lr->file = result.file;
@@ -457,12 +464,14 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
 }
 
 /* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module, bool silent)
+static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
+                                        bool silent)
 {
         const char *path = module;
         char reason[STRERR_BUFSIZE];
         struct debuginfo *ret = NULL;
         struct dso *dso = NULL;
+        struct nscookie nsc;
         int err;
 
         if (!module || !strchr(module, '/')) {
@@ -480,6 +489,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
                 }
                 path = dso->long_name;
         }
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = debuginfo__new(path);
         if (!ret && !silent) {
                 pr_warning("The %s file has no debug information.\n", path);
@@ -489,6 +499,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
                         pr_warning("Rebuild with -g, ");
                 pr_warning("or install an appropriate debuginfo package.\n");
         }
+        nsinfo__mountns_exit(&nsc);
         return ret;
 }
 
@@ -516,7 +527,7 @@ static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
                 goto out;
         }
 
-        debuginfo_cache = open_debuginfo(module, silent);
+        debuginfo_cache = open_debuginfo(module, NULL, silent);
         if (!debuginfo_cache)
                 zfree(&debuginfo_cache_path);
 out:
@@ -531,14 +542,18 @@ static void debuginfo_cache__exit(void)
 }
 
 
-static int get_text_start_address(const char *exec, unsigned long *address)
+static int get_text_start_address(const char *exec, unsigned long *address,
+                                  struct nsinfo *nsi)
 {
         Elf *elf;
         GElf_Ehdr ehdr;
         GElf_Shdr shdr;
         int fd, ret = -ENOENT;
+        struct nscookie nsc;
 
+        nsinfo__mountns_enter(nsi, &nsc);
         fd = open(exec, O_RDONLY);
+        nsinfo__mountns_exit(&nsc);
         if (fd < 0)
                 return -errno;
 
@@ -582,7 +597,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
                         ret = -EINVAL;
                         goto error;
                 }
-                ret = get_text_start_address(tp->module, &stext);
+                ret = get_text_start_address(tp->module, &stext, NULL);
                 if (ret < 0)
                         goto error;
                 addr += stext;
@@ -659,7 +674,7 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 
         /* Prepare a map for offline binary */
         map = dso__new_map(pathname);
-        if (!map || get_text_start_address(pathname, &stext) < 0) {
+        if (!map || get_text_start_address(pathname, &stext, NULL) < 0) {
                 pr_warning("Failed to get ELF symbols for %s\n", pathname);
                 return -EINVAL;
         }
@@ -676,7 +691,8 @@ post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
 }
 
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
-                                          int ntevs, const char *exec)
+                                          int ntevs, const char *exec,
+                                          struct nsinfo *nsi)
 {
         int i, ret = 0;
         unsigned long stext = 0;
@@ -684,7 +700,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
         if (!exec)
                 return 0;
 
-        ret = get_text_start_address(exec, &stext);
+        ret = get_text_start_address(exec, &stext, nsi);
         if (ret < 0)
                 return ret;
 
@@ -715,7 +731,7 @@ post_process_module_probe_trace_events(struct probe_trace_event *tevs,
         if (!module)
                 return 0;
 
-        map = get_target_map(module, false);
+        map = get_target_map(module, NULL, false);
         if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
                 pr_warning("Failed to get ELF symbols for %s\n", module);
                 return -EINVAL;
@@ -802,7 +818,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
         int ret;
 
         if (uprobe)
-                ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+                ret = add_exec_to_probe_trace_events(tevs, ntevs, module,
+                                                     pev->nsi);
         else if (module)
                 /* Currently ref_reloc_sym based probe is not for drivers */
                 ret = post_process_module_probe_trace_events(tevs, ntevs,
@@ -825,7 +842,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         struct debuginfo *dinfo;
         int ntevs, ret = 0;
 
-        dinfo = open_debuginfo(pev->target, !need_dwarf);
+        dinfo = open_debuginfo(pev->target, pev->nsi, !need_dwarf);
         if (!dinfo) {
                 if (need_dwarf)
                         return -ENOENT;
@@ -945,7 +962,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
         char sbuf[STRERR_BUFSIZE];
 
         /* Search a line range */
-        dinfo = open_debuginfo(module, false);
+        dinfo = open_debuginfo(module, NULL, false);
         if (!dinfo)
                 return -ENOENT;
 
@@ -1021,14 +1038,18 @@ end:
         return ret;
 }
 
-int show_line_range(struct line_range *lr, const char *module, bool user)
+int show_line_range(struct line_range *lr, const char *module,
+                    struct nsinfo *nsi, bool user)
 {
         int ret;
+        struct nscookie nsc;
 
         ret = init_probe_symbol_maps(user);
         if (ret < 0)
                 return ret;
+        nsinfo__mountns_enter(nsi, &nsc);
         ret = __show_line_range(lr, module, user);
+        nsinfo__mountns_exit(&nsc);
         exit_probe_symbol_maps();
 
         return ret;
@@ -1111,7 +1132,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
         if (ret < 0)
                 return ret;
 
-        dinfo = open_debuginfo(pevs->target, false);
+        dinfo = open_debuginfo(pevs->target, pevs->nsi, false);
         if (!dinfo) {
                 ret = -ENOENT;
                 goto out;
@@ -1155,6 +1176,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 int show_line_range(struct line_range *lr __maybe_unused,
                     const char *module __maybe_unused,
+                    struct nsinfo *nsi __maybe_unused,
                     bool user __maybe_unused)
 {
         pr_warning("Debuginfo-analysis is not supported.\n");
@@ -2373,7 +2395,7 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
         struct kprobe_blacklist_node *node;
 
         list_for_each_entry(node, blacklist, list) {
-                if (node->start <= address && address <= node->end)
+                if (node->start <= address && address < node->end)
                         return node;
         }
 
@@ -2703,6 +2725,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         struct probe_trace_event *tev = NULL;
         struct probe_cache *cache = NULL;
         struct strlist *namelist[2] = {NULL, NULL};
+        struct nscookie nsc;
 
         up = pev->uprobes ? 1 : 0;
         fd[up] = __open_probe_file_and_namelist(up, &namelist[up]);
@@ -2729,7 +2752,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
                 if (ret < 0)
                         break;
 
+                nsinfo__mountns_enter(pev->nsi, &nsc);
                 ret = probe_file__add_event(fd[up], tev);
+                nsinfo__mountns_exit(&nsc);
                 if (ret < 0)
                         break;
 
@@ -2744,7 +2769,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         if (ret == -EINVAL && pev->uprobes)
                 warn_uprobe_event_compat(tev);
         if (ret == 0 && probe_conf.cache) {
-                cache = probe_cache__new(pev->target);
+                cache = probe_cache__new(pev->target, pev->nsi);
                 if (!cache ||
                     probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 ||
                     probe_cache__commit(cache) < 0)
@@ -2805,7 +2830,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         int ret, i, j, skipped = 0;
         char *mod_name;
 
-        map = get_target_map(pev->target, pev->uprobes);
+        map = get_target_map(pev->target, pev->nsi, pev->uprobes);
         if (!map) {
                 ret = -EINVAL;
                 goto out;
@@ -3094,7 +3119,7 @@ static int find_cached_events(struct perf_probe_event *pev,
         int ntevs = 0;
         int ret = 0;
 
-        cache = probe_cache__new(target);
+        cache = probe_cache__new(target, pev->nsi);
         /* Return 0 ("not found") if the target has no probe cache. */
         if (!cache)
                 return 0;
@@ -3184,7 +3209,7 @@ static int find_probe_trace_events_from_cache(struct perf_probe_event *pev,
                 else
                         return find_cached_events(pev, tevs, pev->target);
         }
-        cache = probe_cache__new(pev->target);
+        cache = probe_cache__new(pev->target, pev->nsi);
         if (!cache)
                 return 0;
 
@@ -3345,13 +3370,16 @@ int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
         int i, j;
+        struct perf_probe_event *pev;
 
         /* Loop 3: cleanup and free trace events  */
         for (i = 0; i < npevs; i++) {
+                pev = &pevs[i];
                 for (j = 0; j < pevs[i].ntevs; j++)
                         clear_probe_trace_event(&pevs[i].tevs[j]);
                 zfree(&pevs[i].tevs);
                 pevs[i].ntevs = 0;
+                nsinfo__zput(pev->nsi);
                 clear_perf_probe_event(&pevs[i]);
         }
 }
@@ -3409,8 +3437,8 @@ out:
         return ret;
 }
 
-int show_available_funcs(const char *target, struct strfilter *_filter,
-                                        bool user)
+int show_available_funcs(const char *target, struct nsinfo *nsi,
+                         struct strfilter *_filter, bool user)
 {
         struct rb_node *nd;
         struct map *map;
@@ -3421,7 +3449,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
                 return ret;
 
         /* Get a symbol map */
-        map = get_target_map(target, user);
+        map = get_target_map(target, nsi, user);
         if (!map) {
                 pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
                 return -EINVAL;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5812947418dd..078681d12168 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -4,6 +4,7 @@
 #include <linux/compiler.h>
 #include <stdbool.h>
 #include "intlist.h"
+#include "namespaces.h"
 
 /* Probe related configurations */
 struct probe_conf {
@@ -92,6 +93,7 @@ struct perf_probe_event {
         struct perf_probe_arg   *args;  /* Arguments */
         struct probe_trace_event *tevs;
         int                     ntevs;
+        struct nsinfo           *nsi;   /* Target namespace */
 };
 
 /* Line range */
@@ -163,10 +165,12 @@ int show_perf_probe_event(const char *group, const char *event,
                           struct perf_probe_event *pev,
                           const char *module, bool use_stdout);
 int show_perf_probe_events(struct strfilter *filter);
-int show_line_range(struct line_range *lr, const char *module, bool user);
+int show_line_range(struct line_range *lr, const char *module,
+                    struct nsinfo *nsi, bool user);
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
                         struct strfilter *filter);
-int show_available_funcs(const char *module, struct strfilter *filter, bool user);
+int show_available_funcs(const char *module, struct nsinfo *nsi,
+                         struct strfilter *filter, bool user);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
                              struct probe_trace_event *tev, struct map *map,
                              struct symbol *sym);
@@ -180,7 +184,7 @@ int e_snprintf(char *str, size_t size, const char *format, ...) __printf(3, 4);
 int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
                             struct perf_probe_arg *pvar);
 
-struct map *get_target_map(const char *target, bool user);
+struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user);
 
 void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
                                            int ntevs);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index d679389e627c..cdf8d83a484c 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -412,13 +412,15 @@ int probe_cache_entry__get_event(struct probe_cache_entry *entry,
 }
 
 /* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */
-static int probe_cache__open(struct probe_cache *pcache, const char *target)
+static int probe_cache__open(struct probe_cache *pcache, const char *target,
+                             struct nsinfo *nsi)
 {
         char cpath[PATH_MAX];
         char sbuildid[SBUILD_ID_SIZE];
         char *dir_name = NULL;
         bool is_kallsyms = false;
         int ret, fd;
+        struct nscookie nsc;
 
         if (target && build_id_cache__cached(target)) {
                 /* This is a cached buildid */
@@ -431,8 +433,11 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
                 target = DSO__NAME_KALLSYMS;
                 is_kallsyms = true;
                 ret = sysfs__sprintf_build_id("/", sbuildid);
-        } else
+        } else {
+                nsinfo__mountns_enter(nsi, &nsc);
                 ret = filename__sprintf_build_id(target, sbuildid);
+                nsinfo__mountns_exit(&nsc);
+        }
 
         if (ret < 0) {
                 pr_debug("Failed to get build-id from %s.\n", target);
@@ -441,7 +446,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
 
         /* If we have no buildid cache, make it */
         if (!build_id_cache__cached(sbuildid)) {
-                ret = build_id_cache__add_s(sbuildid, target,
+                ret = build_id_cache__add_s(sbuildid, target, nsi,
                                             is_kallsyms, NULL);
                 if (ret < 0) {
                         pr_debug("Failed to add build-id cache: %s\n", target);
@@ -449,7 +454,7 @@ static int probe_cache__open(struct probe_cache *pcache, const char *target)
                 }
         }
 
-        dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms,
+        dir_name = build_id_cache__cachedir(sbuildid, target, nsi, is_kallsyms,
                                             false);
 found:
         if (!dir_name) {
@@ -554,7 +559,7 @@ void probe_cache__delete(struct probe_cache *pcache)
         free(pcache);
 }
 
-struct probe_cache *probe_cache__new(const char *target)
+struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi)
 {
         struct probe_cache *pcache = probe_cache__alloc();
         int ret;
@@ -562,7 +567,7 @@ struct probe_cache *probe_cache__new(const char *target)
         if (!pcache)
                 return NULL;
 
-        ret = probe_cache__open(pcache, target);
+        ret = probe_cache__open(pcache, target, nsi);
         if (ret < 0) {
                 pr_debug("Cache open error: %d\n", ret);
                 goto out_err;
@@ -974,7 +979,7 @@ int probe_cache__show_all_caches(struct strfilter *filter)
                 return -EINVAL;
         }
         strlist__for_each_entry(nd, bidlist) {
-                pcache = probe_cache__new(nd->s);
+                pcache = probe_cache__new(nd->s, NULL);
                 if (!pcache)
                         continue;
                 if (!list_empty(&pcache->entries)) {
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 5ecc9d3925db..2ca4163abafe 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -51,7 +51,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist);
 int probe_cache_entry__get_event(struct probe_cache_entry *entry,
                                  struct probe_trace_event **tevs);
 
-struct probe_cache *probe_cache__new(const char *target);
+struct probe_cache *probe_cache__new(const char *target, struct nsinfo *nsi);
 int probe_cache__add_entry(struct probe_cache *pcache,
                            struct perf_probe_event *pev,
                            struct probe_trace_event *tevs, int ntevs);
@@ -69,7 +69,7 @@ int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
 #else   /* ! HAVE_LIBELF_SUPPORT */
-static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
+static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
         return NULL;
 }
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 9f3b0d9754a8..e66dc495809a 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,6 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
+util/namespaces.c
 ../lib/bitmap.c
 ../lib/find_bit.c
 ../lib/hweight.c
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 57b7a00e6f16..c7187f067d31 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -116,6 +116,34 @@ static PyObject *get_handler(const char *handler_name)
         return handler;
 }
 
+static int get_argument_count(PyObject *handler)
+{
+        int arg_count = 0;
+
+        /*
+         * The attribute for the code object is func_code in Python 2,
+         * whereas it is __code__ in Python 3.0+.
+         */
+        PyObject *code_obj = PyObject_GetAttrString(handler,
+                "func_code");
+        if (PyErr_Occurred()) {
+                PyErr_Clear();
+                code_obj = PyObject_GetAttrString(handler,
+                        "__code__");
+        }
+        PyErr_Clear();
+        if (code_obj) {
+                PyObject *arg_count_obj = PyObject_GetAttrString(code_obj,
+                        "co_argcount");
+                if (arg_count_obj) {
+                        arg_count = (int) PyInt_AsLong(arg_count_obj);
+                        Py_DECREF(arg_count_obj);
+                }
+                Py_DECREF(code_obj);
+        }
+        return arg_count;
+}
+
 static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
 {
         PyObject *retval;
@@ -391,13 +419,115 @@ exit:
         return pylist;
 }
 
+static PyObject *get_sample_value_as_tuple(struct sample_read_value *value)
+{
+        PyObject *t;
+
+        t = PyTuple_New(2);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+        PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id));
+        PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value));
+        return t;
+}
+
+static void set_sample_read_in_dict(PyObject *dict_sample,
+                                         struct perf_sample *sample,
+                                         struct perf_evsel *evsel)
+{
+        u64 read_format = evsel->attr.read_format;
+        PyObject *values;
+        unsigned int i;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+                pydict_set_item_string_decref(dict_sample, "time_enabled",
+                        PyLong_FromUnsignedLongLong(sample->read.time_enabled));
+        }
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+                pydict_set_item_string_decref(dict_sample, "time_running",
+                        PyLong_FromUnsignedLongLong(sample->read.time_running));
+        }
+
+        if (read_format & PERF_FORMAT_GROUP)
+                values = PyList_New(sample->read.group.nr);
+        else
+                values = PyList_New(1);
+
+        if (!values)
+                Py_FatalError("couldn't create Python list");
+
+        if (read_format & PERF_FORMAT_GROUP) {
+                for (i = 0; i < sample->read.group.nr; i++) {
+                        PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]);
+                        PyList_SET_ITEM(values, i, t);
+                }
+        } else {
+                PyObject *t = get_sample_value_as_tuple(&sample->read.one);
+                PyList_SET_ITEM(values, 0, t);
+        }
+        pydict_set_item_string_decref(dict_sample, "values", values);
+}
+
+static PyObject *get_perf_sample_dict(struct perf_sample *sample,
+                                         struct perf_evsel *evsel,
+                                         struct addr_location *al,
+                                         PyObject *callchain)
+{
+        PyObject *dict, *dict_sample;
+
+        dict = PyDict_New();
+        if (!dict)
+                Py_FatalError("couldn't create Python dictionary");
+
+        dict_sample = PyDict_New();
+        if (!dict_sample)
+                Py_FatalError("couldn't create Python dictionary");
+
+        pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+        pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
+                        (const char *)&evsel->attr, sizeof(evsel->attr)));
+
+        pydict_set_item_string_decref(dict_sample, "pid",
+                        PyInt_FromLong(sample->pid));
+        pydict_set_item_string_decref(dict_sample, "tid",
+                        PyInt_FromLong(sample->tid));
+        pydict_set_item_string_decref(dict_sample, "cpu",
+                        PyInt_FromLong(sample->cpu));
+        pydict_set_item_string_decref(dict_sample, "ip",
+                        PyLong_FromUnsignedLongLong(sample->ip));
+        pydict_set_item_string_decref(dict_sample, "time",
+                        PyLong_FromUnsignedLongLong(sample->time));
+        pydict_set_item_string_decref(dict_sample, "period",
+                        PyLong_FromUnsignedLongLong(sample->period));
+        set_sample_read_in_dict(dict_sample, sample, evsel);
+        pydict_set_item_string_decref(dict, "sample", dict_sample);
+
+        pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
+                        (const char *)sample->raw_data, sample->raw_size));
+        pydict_set_item_string_decref(dict, "comm",
+                        PyString_FromString(thread__comm_str(al->thread)));
+        if (al->map) {
+                pydict_set_item_string_decref(dict, "dso",
+                        PyString_FromString(al->map->dso->name));
+        }
+        if (al->sym) {
+                pydict_set_item_string_decref(dict, "symbol",
+                        PyString_FromString(al->sym->name));
+        }
+
+        pydict_set_item_string_decref(dict, "callchain", callchain);
+
+        return dict;
+}
+
 static void python_process_tracepoint(struct perf_sample *sample,
                                       struct perf_evsel *evsel,
                                       struct addr_location *al)
 {
         struct event_format *event = evsel->tp_format;
         PyObject *handler, *context, *t, *obj = NULL, *callchain;
-        PyObject *dict = NULL;
+        PyObject *dict = NULL, *all_entries_dict = NULL;
         static char handler_name[256];
         struct format_field *field;
         unsigned long s, ns;
@@ -407,10 +537,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
         void *data = sample->raw_data;
         unsigned long long nsecs = sample->time;
         const char *comm = thread__comm_str(al->thread);
-
-        t = PyTuple_New(MAX_FIELDS);
-        if (!t)
-                Py_FatalError("couldn't create Python tuple");
+        const char *default_handler_name = "trace_unhandled";
 
         if (!event) {
                 snprintf(handler_name, sizeof(handler_name),
@@ -427,10 +554,19 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         handler = get_handler(handler_name);
         if (!handler) {
+                handler = get_handler(default_handler_name);
+                if (!handler)
+                        return;
                 dict = PyDict_New();
                 if (!dict)
                         Py_FatalError("couldn't create Python dict");
         }
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+
         s = nsecs / NSEC_PER_SEC;
         ns = nsecs - s * NSEC_PER_SEC;
 
@@ -444,8 +580,10 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
         /* ip unwinding */
         callchain = python_process_callchain(sample, evsel, al);
+        /* Need an additional reference for the perf_sample dict */
+        Py_INCREF(callchain);
 
-        if (handler) {
+        if (!dict) {
                 PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(s));
                 PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
@@ -484,26 +622,35 @@ static void python_process_tracepoint(struct perf_sample *sample,
                 } else { /* FIELD_IS_NUMERIC */
                         obj = get_field_numeric_entry(event, field, data);
                 }
-                if (handler)
+                if (!dict)
                         PyTuple_SetItem(t, n++, obj);
                 else
                         pydict_set_item_string_decref(dict, field->name, obj);
 
         }
 
-        if (!handler)
+        if (dict)
                 PyTuple_SetItem(t, n++, dict);
 
+        if (get_argument_count(handler) == (int) n + 1) {
+                all_entries_dict = get_perf_sample_dict(sample, evsel, al,
+                        callchain);
+                PyTuple_SetItem(t, n++, all_entries_dict);
+        } else {
+                Py_DECREF(callchain);
+        }
+
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
-        if (handler) {
+        if (!dict) {
                 call_object(handler, t, handler_name);
         } else {
-                try_call_object("trace_unhandled", t);
+                call_object(handler, t, default_handler_name);
                 Py_DECREF(dict);
         }
 
+        Py_XDECREF(all_entries_dict);
         Py_DECREF(t);
 }
 
@@ -795,10 +942,16 @@ static void python_process_general_event(struct perf_sample *sample,
                                          struct perf_evsel *evsel,
                                          struct addr_location *al)
 {
-        PyObject *handler, *t, *dict, *callchain, *dict_sample;
+        PyObject *handler, *t, *dict, *callchain;
         static char handler_name[64];
         unsigned n = 0;
 
+        snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
+
+        handler = get_handler(handler_name);
+        if (!handler)
+                return;
+
         /*
          * Use the MAX_FIELDS to make the function expandable, though
          * currently there is only one item for the tuple.
@@ -807,61 +960,16 @@ static void python_process_general_event(struct perf_sample *sample,
         if (!t)
                 Py_FatalError("couldn't create Python tuple");
 
-        dict = PyDict_New();
-        if (!dict)
-                Py_FatalError("couldn't create Python dictionary");
-
-        dict_sample = PyDict_New();
-        if (!dict_sample)
-                Py_FatalError("couldn't create Python dictionary");
-
-        snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
-
-        handler = get_handler(handler_name);
-        if (!handler)
-                goto exit;
-
-        pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-        pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
-                        (const char *)&evsel->attr, sizeof(evsel->attr)));
-
-        pydict_set_item_string_decref(dict_sample, "pid",
-                        PyInt_FromLong(sample->pid));
-        pydict_set_item_string_decref(dict_sample, "tid",
-                        PyInt_FromLong(sample->tid));
-        pydict_set_item_string_decref(dict_sample, "cpu",
-                        PyInt_FromLong(sample->cpu));
-        pydict_set_item_string_decref(dict_sample, "ip",
-                        PyLong_FromUnsignedLongLong(sample->ip));
-        pydict_set_item_string_decref(dict_sample, "time",
-                        PyLong_FromUnsignedLongLong(sample->time));
-        pydict_set_item_string_decref(dict_sample, "period",
-                        PyLong_FromUnsignedLongLong(sample->period));
-        pydict_set_item_string_decref(dict, "sample", dict_sample);
-
-        pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
-                        (const char *)sample->raw_data, sample->raw_size));
-        pydict_set_item_string_decref(dict, "comm",
-                        PyString_FromString(thread__comm_str(al->thread)));
-        if (al->map) {
-                pydict_set_item_string_decref(dict, "dso",
-                        PyString_FromString(al->map->dso->name));
-        }
-        if (al->sym) {
-                pydict_set_item_string_decref(dict, "symbol",
-                        PyString_FromString(al->sym->name));
-        }
-
         /* ip unwinding */
         callchain = python_process_callchain(sample, evsel, al);
-        pydict_set_item_string_decref(dict, "callchain", callchain);
+        dict = get_perf_sample_dict(sample, evsel, al, callchain);
 
         PyTuple_SetItem(t, n++, dict);
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
         call_object(handler, t, handler_name);
-exit:
+
         Py_DECREF(dict);
         Py_DECREF(t);
 }
@@ -1259,6 +1367,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 
                         fprintf(ofp, "%s", f->name);
                 }
+                if (not_first++)
+                        fprintf(ofp, ", ");
+                if (++count % 5 == 0)
+                        fprintf(ofp, "\n\t\t");
+                fprintf(ofp, "perf_sample_dict");
+
                 fprintf(ofp, "):\n");
 
                 fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
@@ -1328,6 +1442,9 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 
                 fprintf(ofp, ")\n\n");
 
+                fprintf(ofp, "\t\tprint 'Sample: {'+"
+                        "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+
                 fprintf(ofp, "\t\tfor node in common_callchain:");
                 fprintf(ofp, "\n\t\t\tif 'sym' in node:");
                 fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
@@ -1338,15 +1455,20 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
         }
 
         fprintf(ofp, "def trace_unhandled(event_name, context, "
-                "event_fields_dict):\n");
+                "event_fields_dict, perf_sample_dict):\n");
 
-        fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))"
-                "for k,v in sorted(event_fields_dict.items())])\n\n");
+        fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
+        fprintf(ofp, "\t\tprint 'Sample: {'+"
+                "get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
 
         fprintf(ofp, "def print_header("
                 "event_name, cpu, secs, nsecs, pid, comm):\n"
                 "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-                "(event_name, cpu, secs, nsecs, pid, comm),\n");
+                "(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+
+        fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
+                "\treturn delimiter.join"
+                "(['%%s=%%s'%%(k,str(v))for k,v in sorted(a_dict.items())])\n");
 
         fclose(ofp);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d19c40a81040..a7ebd9fe8e40 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -428,6 +428,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->stat_round = process_stat_round_stub;
         if (tool->time_conv == NULL)
                 tool->time_conv = process_event_op2_stub;
+        if (tool->feature == NULL)
+                tool->feature = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -1118,6 +1120,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
         if (sample_type & PERF_SAMPLE_DATA_SRC)
                 printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
 
+        if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+                printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+
         if (sample_type & PERF_SAMPLE_TRANSACTION)
                 printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
@@ -1125,6 +1130,30 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
                 sample_read__printf(sample, evsel->attr.read_format);
 }
 
+static void dump_read(struct perf_evsel *evsel, union perf_event *event)
+{
+        struct read_event *read_event = &event->read;
+        u64 read_format;
+
+        if (!dump_trace)
+                return;
+
+        printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+               evsel ? perf_evsel__name(evsel) : "FAIL",
+               event->read.value);
+
+        read_format = evsel->attr.read_format;
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled);
+
+        if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                printf("... time running : %" PRIu64 "\n", read_event->time_running);
+
+        if (read_format & PERF_FORMAT_ID)
+                printf("... id           : %" PRIu64 "\n", read_event->id);
+}
+
 static struct machine *machines__find_for_cpumode(struct machines *machines,
                                                union perf_event *event,
                                                struct perf_sample *sample)
@@ -1269,6 +1298,7 @@ static int machines__deliver_event(struct machines *machines,
                         evlist->stats.total_lost_samples += event->lost_samples.lost;
                 return tool->lost_samples(tool, event, sample, machine);
         case PERF_RECORD_READ:
+                dump_read(evsel, event);
                 return tool->read(tool, event, sample, evsel, machine);
         case PERF_RECORD_THROTTLE:
                 return tool->throttle(tool, event, sample, machine);
@@ -1371,6 +1401,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
         case PERF_RECORD_TIME_CONV:
                 session->time_conv = event->time_conv;
                 return tool->time_conv(tool, event, session);
+        case PERF_RECORD_HEADER_FEATURE:
+                return tool->feature(tool, event, session);
         default:
                 return -EINVAL;
         }
diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c
new file mode 100644
index 000000000000..ce8fc290fce8
--- /dev/null
+++ b/tools/perf/util/setns.c
@@ -0,0 +1,8 @@
+#include "util.h"
+#include <unistd.h>
+#include <sys/syscall.h>
+
+int setns(int fd, int nstype)
+{
+        return syscall(__NR_setns, fd, nstype);
+}
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
new file mode 100644
index 000000000000..453f6f6f29f3
--- /dev/null
+++ b/tools/perf/util/smt.c
@@ -0,0 +1,44 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <linux/bitops.h>
+#include "api/fs/fs.h"
+#include "smt.h"
+
+int smt_on(void)
+{
+        static bool cached;
+        static int cached_result;
+        int cpu;
+        int ncpu;
+
+        if (cached)
+                return cached_result;
+
+        ncpu = sysconf(_SC_NPROCESSORS_CONF);
+        for (cpu = 0; cpu < ncpu; cpu++) {
+                unsigned long long siblings;
+                char *str;
+                size_t strlen;
+                char fn[256];
+
+                snprintf(fn, sizeof fn,
+                        "devices/system/cpu/cpu%d/topology/thread_siblings",
+                        cpu);
+                if (sysfs__read_str(fn, &str, &strlen) < 0)
+                        continue;
+                /* Entry is hex, but does not have 0x, so need custom parser */
+                siblings = strtoull(str, NULL, 16);
+                free(str);
+                if (hweight64(siblings) > 1) {
+                        cached_result = 1;
+                        cached = true;
+                        break;
+                }
+        }
+        if (!cached) {
+                cached_result = 0;
+                cached = true;
+        }
+        return cached_result;
+}
diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h
new file mode 100644
index 000000000000..b8414b7bcbc8
--- /dev/null
+++ b/tools/perf/util/smt.h
@@ -0,0 +1,6 @@
+#ifndef SMT_H
+#define SMT_H 1
+
+int smt_on(void);
+
+#endif
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8b327c955a4f..eb3ab902a1c0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1316,6 +1316,47 @@ struct sort_entry sort_mem_dcacheline = {
 };
 
 static int64_t
+sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        uint64_t l = 0, r = 0;
+
+        if (left->mem_info)
+                l = left->mem_info->daddr.phys_addr;
+        if (right->mem_info)
+                r = right->mem_info->daddr.phys_addr;
+
+        return (int64_t)(r - l);
+}
+
+static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
+                                           size_t size, unsigned int width)
+{
+        uint64_t addr = 0;
+        size_t ret = 0;
+        size_t len = BITS_PER_LONG / 4;
+
+        addr = he->mem_info->daddr.phys_addr;
+
+        ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, "");
+
+        if (ret > width)
+                bf[width] = '\0';
+
+        return width;
+}
+
+struct sort_entry sort_mem_phys_daddr = {
+        .se_header      = "Data Physical Address",
+        .se_cmp         = sort__phys_daddr_cmp,
+        .se_snprintf    = hist_entry__phys_daddr_snprintf,
+        .se_width_idx   = HISTC_MEM_PHYS_DADDR,
+};
+
+static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
         if (!left->branch_info || !right->branch_info)
@@ -1547,6 +1588,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
         DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
         DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
         DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+        DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
 };
 
 #undef DIM
@@ -2563,7 +2605,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist)
 
         BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
-        if (evlist == NULL)
+        if (evlist == NULL || perf_evlist__empty(evlist))
                 goto out_no_evlist;
 
         evlist__for_each_entry(evlist, evsel) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b7c75597e18f..f36dc4980a6c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -245,6 +245,7 @@ enum sort_type {
         SORT_MEM_SNOOP,
         SORT_MEM_DCACHELINE,
         SORT_MEM_IADDR_SYMBOL,
+        SORT_MEM_PHYS_DADDR,
 };
 
 /*
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index ebc88a74e67b..ed8e8d2de942 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -155,6 +155,9 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data)
         a2l->found = bfd_find_nearest_line(abfd, section, a2l->syms, pc - vma,
                                            &a2l->filename, &a2l->funcname,
                                            &a2l->line);
+
+        if (a2l->filename && !strlen(a2l->filename))
+                a2l->filename = NULL;
 }
 
 static struct a2l_data *addr2line_init(const char *path)
@@ -248,6 +251,9 @@ static int addr2line(const char *dso_name, u64 addr,
                                              &a2l->funcname, &a2l->line) &&
                        cnt++ < MAX_INLINE_NEST) {
 
+                        if (a2l->filename && !strlen(a2l->filename))
+                                a2l->filename = NULL;
+
                         if (node != NULL) {
                                 if (inline_list__append_dso_a2l(dso, node))
                                         return 0;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 719d6cb86952..a04cf56d3517 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -70,7 +70,11 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
                 return a->ctx - b->ctx;
         if (a->cpu != b->cpu)
                 return a->cpu - b->cpu;
-        return a->evsel - b->evsel;
+        if (a->evsel == b->evsel)
+                return 0;
+        if ((char *)a->evsel < (char *)b->evsel)
+                return -1;
+        return +1;
 }
 
 static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 53b9a994a3dc..35e9848734d6 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -128,6 +128,10 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
+        struct perf_stat_evsel *ps = evsel->priv;
+
+        if (ps)
+                free(ps->group_data);
         zfree(&evsel->priv);
 }
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 7522bf10b03e..eacaf958e19d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -28,8 +28,9 @@ enum perf_stat_evsel_id {
 };
 
 struct perf_stat_evsel {
-        struct stats            res_stats[3];
-        enum perf_stat_evsel_id id;
+        struct stats             res_stats[3];
+        enum perf_stat_evsel_id  id;
+        u64                     *group_data;
 };
 
 enum aggr_mode {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 502505cf236a..9cf781f0d8a2 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -259,7 +259,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 {
         uint32_t nr_rel_entries, idx;
         GElf_Sym sym;
-        u64 plt_offset;
+        u64 plt_offset, plt_header_size, plt_entry_size;
         GElf_Shdr shdr_plt;
         struct symbol *f;
         GElf_Shdr shdr_rel_plt, shdr_dynsym;
@@ -326,6 +326,23 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 
         nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
         plt_offset = shdr_plt.sh_offset;
+        switch (ehdr.e_machine) {
+                case EM_ARM:
+                        plt_header_size = 20;
+                        plt_entry_size = 12;
+                        break;
+
+                case EM_AARCH64:
+                        plt_header_size = 32;
+                        plt_entry_size = 16;
+                        break;
+
+                default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+                        plt_header_size = shdr_plt.sh_entsize;
+                        plt_entry_size = shdr_plt.sh_entsize;
+                        break;
+        }
+        plt_offset += plt_header_size;
 
         if (shdr_rel_plt.sh_type == SHT_RELA) {
                 GElf_Rela pos_mem, *pos;
@@ -335,7 +352,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                         const char *elf_name = NULL;
                         char *demangled = NULL;
                         symidx = GELF_R_SYM(pos->r_info);
-                        plt_offset += shdr_plt.sh_entsize;
                         gelf_getsym(syms, symidx, &sym);
 
                         elf_name = elf_sym__name(&sym, symstrs);
@@ -346,11 +362,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                                  "%s@plt", elf_name);
                         free(demangled);
 
-                        f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+                        f = symbol__new(plt_offset, plt_entry_size,
                                         STB_GLOBAL, sympltname);
                         if (!f)
                                 goto out_elf_end;
 
+                        plt_offset += plt_entry_size;
                         symbols__insert(&dso->symbols[map->type], f);
                         ++nr;
                 }
@@ -361,7 +378,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                         const char *elf_name = NULL;
                         char *demangled = NULL;
                         symidx = GELF_R_SYM(pos->r_info);
-                        plt_offset += shdr_plt.sh_entsize;
                         gelf_getsym(syms, symidx, &sym);
 
                         elf_name = elf_sym__name(&sym, symstrs);
@@ -372,11 +388,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
                                  "%s@plt", elf_name);
                         free(demangled);
 
-                        f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+                        f = symbol__new(plt_offset, plt_entry_size,
                                         STB_GLOBAL, sympltname);
                         if (!f)
                                 goto out_elf_end;
 
+                        plt_offset += plt_entry_size;
                         symbols__insert(&dso->symbols[map->type], f);
                         ++nr;
                 }
@@ -391,7 +408,7 @@ out_elf_end:
         return 0;
 }
 
-char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
 {
         return demangle_sym(dso, kmodule, elf_name);
 }
@@ -1442,7 +1459,7 @@ static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
 
 static int kcore_copy__process_modules(void *arg,
                                        const char *name __maybe_unused,
-                                       u64 start)
+                                       u64 start, u64 size __maybe_unused)
 {
         struct kcore_copy_info *kci = arg;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 40bf5d4c0bfd..1a5aa35b0100 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -377,7 +377,7 @@ void symbol__elf_init(void)
 
 char *dso__demangle_sym(struct dso *dso __maybe_unused,
                         int kmodule __maybe_unused,
-                        char *elf_name __maybe_unused)
+                        const char *elf_name __maybe_unused)
 {
         return NULL;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e7a98dbd2aed..5909ee4c7ade 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -18,6 +18,7 @@
 #include "symbol.h"
 #include "strlist.h"
 #include "intlist.h"
+#include "namespaces.h"
 #include "header.h"
 #include "path.h"
 #include "sane_ctype.h"
@@ -52,6 +53,7 @@ static enum dso_binary_type binary_type_symtab[] = {
         DSO_BINARY_TYPE__JAVA_JIT,
         DSO_BINARY_TYPE__DEBUGLINK,
         DSO_BINARY_TYPE__BUILD_ID_CACHE,
+        DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO,
         DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
         DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
         DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
@@ -231,7 +233,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
                 goto out_unlock;
 
         for (next = map__next(curr); next; next = map__next(curr)) {
-                curr->end = next->start;
+                if (!curr->end)
+                        curr->end = next->start;
                 curr = next;
         }
 
@@ -239,7 +242,8 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
          * We still haven't the actual symbols, so guess the
          * last map final address.
          */
-        curr->end = ~0ULL;
+        if (!curr->end)
+                curr->end = ~0ULL;
 
 out_unlock:
         pthread_rwlock_unlock(&maps->lock);
@@ -550,7 +554,7 @@ void dso__sort_by_name(struct dso *dso, enum map_type type)
 
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
-                                         u64 start))
+                                         u64 start, u64 size))
 {
         char *line = NULL;
         size_t n;
@@ -563,8 +567,8 @@ int modules__parse(const char *filename, void *arg,
 
         while (1) {
                 char name[PATH_MAX];
-                u64 start;
-                char *sep;
+                u64 start, size;
+                char *sep, *endptr;
                 ssize_t line_len;
 
                 line_len = getline(&line, &n, file);
@@ -596,7 +600,11 @@ int modules__parse(const char *filename, void *arg,
 
                 scnprintf(name, sizeof(name), "[%s]", line);
 
-                err = process_module(arg, name, start);
+                size = strtoul(sep + 1, &endptr, 0);
+                if (*endptr != ' ' && *endptr != '\t')
+                        continue;
+
+                err = process_module(arg, name, start, size);
                 if (err)
                         break;
         }
@@ -943,7 +951,8 @@ static struct module_info *find_module(const char *name,
         return NULL;
 }
 
-static int __read_proc_modules(void *arg, const char *name, u64 start)
+static int __read_proc_modules(void *arg, const char *name, u64 start,
+                               u64 size __maybe_unused)
 {
         struct rb_root *modules = arg;
         struct module_info *mi;
@@ -1325,14 +1334,15 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
         return __dso__load_kallsyms(dso, filename, map, false);
 }
 
-static int dso__load_perf_map(struct dso *dso, struct map *map)
+static int dso__load_perf_map(const char *map_path, struct dso *dso,
+                              struct map *map)
 {
         char *line = NULL;
         size_t n;
         FILE *file;
         int nr_syms = 0;
 
-        file = fopen(dso->long_name, "r");
+        file = fopen(map_path, "r");
         if (file == NULL)
                 goto out_failure;
 
@@ -1416,6 +1426,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
                 return kmod && dso->symtab_type == type;
 
         case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+        case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
                 return true;
 
         case DSO_BINARY_TYPE__NOT_FOUND:
@@ -1424,6 +1435,44 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
         }
 }
 
+/* Checks for the existence of the perf-<pid>.map file in two different
+ * locations.  First, if the process is a separate mount namespace, check in
+ * that namespace using the pid of the innermost pid namespace.  If's not in a
+ * namespace, or the file can't be found there, try in the mount namespace of
+ * the tracing process using our view of its pid.
+ */
+static int dso__find_perf_map(char *filebuf, size_t bufsz,
+                              struct nsinfo **nsip)
+{
+        struct nscookie nsc;
+        struct nsinfo *nsi;
+        struct nsinfo *nnsi;
+        int rc = -1;
+
+        nsi = *nsip;
+
+        if (nsi->need_setns) {
+                snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nsi->nstgid);
+                nsinfo__mountns_enter(nsi, &nsc);
+                rc = access(filebuf, R_OK);
+                nsinfo__mountns_exit(&nsc);
+                if (rc == 0)
+                        return rc;
+        }
+
+        nnsi = nsinfo__copy(nsi);
+        if (nnsi) {
+                nsinfo__put(nsi);
+
+                nnsi->need_setns = false;
+                snprintf(filebuf, bufsz, "/tmp/perf-%d.map", nnsi->tgid);
+                *nsip = nnsi;
+                rc = 0;
+        }
+
+        return rc;
+}
+
 int dso__load(struct dso *dso, struct map *map)
 {
         char *name;
@@ -1435,8 +1484,21 @@ int dso__load(struct dso *dso, struct map *map)
         struct symsrc ss_[2];
         struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
         bool kmod;
+        bool perfmap;
         unsigned char build_id[BUILD_ID_SIZE];
+        struct nscookie nsc;
+        char newmapname[PATH_MAX];
+        const char *map_path = dso->long_name;
+
+        perfmap = strncmp(dso->name, "/tmp/perf-", 10) == 0;
+        if (perfmap) {
+                if (dso->nsinfo && (dso__find_perf_map(newmapname,
+                    sizeof(newmapname), &dso->nsinfo) == 0)) {
+                        map_path = newmapname;
+                }
+        }
 
+        nsinfo__mountns_enter(dso->nsinfo, &nsc);
         pthread_mutex_lock(&dso->lock);
 
         /* check again under the dso->lock */
@@ -1461,19 +1523,19 @@ int dso__load(struct dso *dso, struct map *map)
 
         dso->adjust_symbols = 0;
 
-        if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+        if (perfmap) {
                 struct stat st;
 
-                if (lstat(dso->name, &st) < 0)
+                if (lstat(map_path, &st) < 0)
                         goto out;
 
                 if (!symbol_conf.force && st.st_uid && (st.st_uid != geteuid())) {
                         pr_warning("File %s not owned by current user or root, "
-                                   "ignoring it (use -f to override).\n", dso->name);
+                                   "ignoring it (use -f to override).\n", map_path);
                         goto out;
                 }
 
-                ret = dso__load_perf_map(dso, map);
+                ret = dso__load_perf_map(map_path, dso, map);
                 dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
                                              DSO_BINARY_TYPE__NOT_FOUND;
                 goto out;
@@ -1511,9 +1573,15 @@ int dso__load(struct dso *dso, struct map *map)
         for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
                 struct symsrc *ss = &ss_[ss_pos];
                 bool next_slot = false;
+                bool is_reg;
+                bool nsexit;
+                int sirc;
 
                 enum dso_binary_type symtab_type = binary_type_symtab[i];
 
+                nsexit = (symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE ||
+                    symtab_type == DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO);
+
                 if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
                         continue;
 
@@ -1521,12 +1589,20 @@ int dso__load(struct dso *dso, struct map *map)
                                                    root_dir, name, PATH_MAX))
                         continue;
 
-                if (!is_regular_file(name))
-                        continue;
+                if (nsexit)
+                        nsinfo__mountns_exit(&nsc);
+
+                is_reg = is_regular_file(name);
+                sirc = symsrc__init(ss, dso, name, symtab_type);
 
-                /* Name is now the name of the next image to try */
-                if (symsrc__init(ss, dso, name, symtab_type) < 0)
+                if (nsexit)
+                        nsinfo__mountns_enter(dso->nsinfo, &nsc);
+
+                if (!is_reg || sirc < 0) {
+                        if (sirc >= 0)
+                                symsrc__destroy(ss);
                         continue;
+                }
 
                 if (!syms_ss && symsrc__has_symtab(ss)) {
                         syms_ss = ss;
@@ -1584,6 +1660,7 @@ out_free:
 out:
         dso__set_loaded(dso, map->type);
         pthread_mutex_unlock(&dso->lock);
+        nsinfo__mountns_exit(&nsc);
 
         return ret;
 }
@@ -1660,7 +1737,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map)
         }
 
         if (!symbol_conf.ignore_vmlinux_buildid)
-                filename = dso__build_id_filename(dso, NULL, 0);
+                filename = dso__build_id_filename(dso, NULL, 0, false);
         if (filename != NULL) {
                 err = dso__load_vmlinux(dso, map, filename, true);
                 if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 41ebba9a2eb2..aad99e7e179b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -186,6 +186,7 @@ struct addr_map_symbol {
         struct symbol *sym;
         u64           addr;
         u64           al_addr;
+        u64           phys_addr;
 };
 
 struct branch_info {
@@ -273,7 +274,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
                    int (*process_module)(void *arg, const char *name,
-                                         u64 start));
+                                         u64 start, u64 size));
 int filename__read_debuglink(const char *filename, char *debuglink,
                              size_t size);
 
@@ -306,7 +307,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
                                 struct map *map);
 
-char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
 void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index bbb4c1957578..6eea7cff3d4e 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -15,10 +15,11 @@
 
 #include "syscalltbl.h"
 #include <stdlib.h>
+#include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE
-#include <linux/compiler.h>
 #include <string.h>
+#include "string2.h"
 #include "util.h"
 
 #if defined(__x86_64__)
@@ -105,6 +106,27 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
         return sc ? sc->id : -1;
 }
 
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        int i;
+        struct syscall *syscalls = tbl->syscalls.entries;
+
+        for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) {
+                if (strglobmatch(syscalls[i].name, syscall_glob)) {
+                        *idx = i;
+                        return syscalls[i].id;
+                }
+        }
+
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        *idx = -1;
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
+
 #else /* HAVE_SYSCALL_TABLE */
 
 #include <libaudit.h>
@@ -131,4 +153,15 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
 {
         return audit_name_to_syscall(name, tbl->audit_machine);
 }
+
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused,
+                                  const char *syscall_glob __maybe_unused, int *idx __maybe_unused)
+{
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
 #endif /* HAVE_SYSCALL_TABLE */
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
index e2951510484f..e9fb8786da7c 100644
--- a/tools/perf/util/syscalltbl.h
+++ b/tools/perf/util/syscalltbl.h
@@ -17,4 +17,7 @@ void syscalltbl__delete(struct syscalltbl *tbl);
 const char *syscalltbl__name(const struct syscalltbl *tbl, int id);
 int syscalltbl__id(struct syscalltbl *tbl, const char *name);
 
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+
 #endif /* __PERF_SYSCALLTBL_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 378c418ca0c1..aee9a42102ba 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -59,6 +59,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
                 list_add(&comm->list, &thread->comm_list);
                 refcount_set(&thread->refcnt, 1);
                 RB_CLEAR_NODE(&thread->rb_node);
+                /* Thread holds first ref to nsdata. */
+                thread->nsinfo = nsinfo__new(pid);
         }
 
         return thread;
@@ -91,6 +93,7 @@ void thread__delete(struct thread *thread)
                 comm__free(comm);
         }
         unwind__finish_access(thread);
+        nsinfo__zput(thread->nsinfo);
 
         free(thread);
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 4eb849e9098f..cb1a5dd5c2b9 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -34,6 +34,7 @@ struct thread {
 
         void                    *priv;
         struct thread_stack     *ts;
+        struct nsinfo           *nsinfo;
 #ifdef HAVE_LIBUNWIND_SUPPORT
         void                            *addr_space;
         struct unwind_libunwind_ops     *unwind_libunwind_ops;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 829471a1c6d7..d549e50db397 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -34,6 +34,12 @@ typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
                          struct perf_session *session);
 
+enum show_feature_header {
+        SHOW_FEAT_NO_HEADER = 0,
+        SHOW_FEAT_HEADER,
+        SHOW_FEAT_HEADER_FULL_INFO,
+};
+
 struct perf_tool {
         event_sample    sample,
                         read;
@@ -63,11 +69,13 @@ struct perf_tool {
                         cpu_map,
                         stat_config,
                         stat,
-                        stat_round;
+                        stat_round,
+                        feature;
         event_op3       auxtrace;
         bool            ordered_events;
         bool            ordering_requires_timestamps;
         bool            namespace_events;
+        enum show_feature_header show_feat_hdr;
 };
 
 #endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 988111e0bab5..4c360daa4e24 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -143,13 +143,17 @@ out:
         return list;
 }
 
-static int slow_copyfile(const char *from, const char *to)
+static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi)
 {
         int err = -1;
         char *line = NULL;
         size_t n;
-        FILE *from_fp = fopen(from, "r"), *to_fp;
+        FILE *from_fp, *to_fp;
+        struct nscookie nsc;
 
+        nsinfo__mountns_enter(nsi, &nsc);
+        from_fp = fopen(from, "r");
+        nsinfo__mountns_exit(&nsc);
         if (from_fp == NULL)
                 goto out;
 
@@ -198,15 +202,21 @@ int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
         return size ? -1 : 0;
 }
 
-int copyfile_mode(const char *from, const char *to, mode_t mode)
+static int copyfile_mode_ns(const char *from, const char *to, mode_t mode,
+                            struct nsinfo *nsi)
 {
         int fromfd, tofd;
         struct stat st;
-        int err = -1;
+        int err;
         char *tmp = NULL, *ptr = NULL;
+        struct nscookie nsc;
 
-        if (stat(from, &st))
+        nsinfo__mountns_enter(nsi, &nsc);
+        err = stat(from, &st);
+        nsinfo__mountns_exit(&nsc);
+        if (err)
                 goto out;
+        err = -1;
 
         /* extra 'x' at the end is to reserve space for '.' */
         if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
@@ -227,11 +237,13 @@ int copyfile_mode(const char *from, const char *to, mode_t mode)
                 goto out_close_to;
 
         if (st.st_size == 0) { /* /proc? do it slowly... */
-                err = slow_copyfile(from, tmp);
+                err = slow_copyfile(from, tmp, nsi);
                 goto out_close_to;
         }
 
+        nsinfo__mountns_enter(nsi, &nsc);
         fromfd = open(from, O_RDONLY);
+        nsinfo__mountns_exit(&nsc);
         if (fromfd < 0)
                 goto out_close_to;
 
@@ -248,6 +260,16 @@ out:
         return err;
 }
 
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi)
+{
+        return copyfile_mode_ns(from, to, 0755, nsi);
+}
+
+int copyfile_mode(const char *from, const char *to, mode_t mode)
+{
+        return copyfile_mode_ns(from, to, mode, NULL);
+}
+
 int copyfile(const char *from, const char *to)
 {
         return copyfile_mode(from, to, 0755);
@@ -259,6 +281,7 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
         size_t left = n;
 
         while (left) {
+                /* buf must be treated as const if !is_read. */
                 ssize_t ret = is_read ? read(fd, buf, left) :
                                         write(fd, buf, left);
 
@@ -286,9 +309,10 @@ ssize_t readn(int fd, void *buf, size_t n)
 /*
  * Write exactly 'n' bytes or return an error.
  */
-ssize_t writen(int fd, void *buf, size_t n)
+ssize_t writen(int fd, const void *buf, size_t n)
 {
-        return ion(false, fd, buf, n);
+        /* ion does not modify buf. */
+        return ion(false, fd, (void *)buf, n);
 }
 
 size_t hex_width(u64 v)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 2c9e58a45310..b136c271125f 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -12,6 +12,7 @@
 #include <stdarg.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include "namespaces.h"
 
 /* General helper functions */
 void usage(const char *err) __noreturn;
@@ -33,10 +34,11 @@ struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dire
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_ns(const char *from, const char *to, struct nsinfo *nsi);
 int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 ssize_t readn(int fd, void *buf, size_t n);
-ssize_t writen(int fd, void *buf, size_t n);
+ssize_t writen(int fd, const void *buf, size_t n);
 
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
@@ -58,4 +60,8 @@ const char *perf_tip(const char *dirpath);
 int sched_getcpu(void);
 #endif
 
+#ifndef HAVE_SETNS_SUPPORT
+int setns(int fd, int nstype);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 5de2e15e2eda..8a32bb0095e5 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -12,7 +12,7 @@ int perf_read_values_init(struct perf_read_values *values)
         values->threads_max = 16;
         values->pid = malloc(values->threads_max * sizeof(*values->pid));
         values->tid = malloc(values->threads_max * sizeof(*values->tid));
-        values->value = malloc(values->threads_max * sizeof(*values->value));
+        values->value = zalloc(values->threads_max * sizeof(*values->value));
         if (!values->pid || !values->tid || !values->value) {
                 pr_debug("failed to allocate read_values threads arrays");
                 goto out_free_pid;
@@ -98,15 +98,16 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values,
                         return i;
         }
 
-        i = values->threads + 1;
-        values->value[i] = malloc(values->counters_max * sizeof(**values->value));
+        i = values->threads;
+
+        values->value[i] = zalloc(values->counters_max * sizeof(**values->value));
         if (!values->value[i]) {
                 pr_debug("failed to allocate read_values counters array");
                 return -ENOMEM;
         }
         values->pid[i] = pid;
         values->tid[i] = tid;
-        values->threads = i;
+        values->threads = i + 1;
 
         return i;
 }
@@ -130,12 +131,16 @@ static int perf_read_values__enlarge_counters(struct perf_read_values *values)
 
         for (i = 0; i < values->threads; i++) {
                 u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+                int j;
 
-                if (value) {
+                if (!value) {
                         pr_debug("failed to enlarge read_values ->values array");
                         goto out_free_name;
                 }
 
+                for (j = values->counters_max; j < counters_max; j++)
+                        value[j] = 0;
+
                 values->value[i] = value;
         }
 
@@ -187,7 +192,7 @@ int perf_read_values_add_value(struct perf_read_values *values,
         if (cindex < 0)
                 return cindex;
 
-        values->value[tindex][cindex] = value;
+        values->value[tindex][cindex] += value;
         return 0;
 }
 
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index 7251fdbabced..c8f415d9877b 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -12,6 +12,8 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
                 xy->entry_size = entry_size;
                 xy->row_size   = row_size;
                 xy->entries    = xlen * ylen;
+                xy->max_x      = xlen;
+                xy->max_y      = ylen;
         }
 
         return xy;
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 7f30af371b7e..4ba726c90870 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -7,6 +7,8 @@ struct xyarray {
         size_t row_size;
         size_t entry_size;
         size_t entries;
+        size_t max_x;
+        size_t max_y;
         char contents[];
 };
 
@@ -19,4 +21,14 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
         return &xy->contents[x * xy->row_size + y * xy->entry_size];
 }
 
+static inline int xyarray__max_y(struct xyarray *xy)
+{
+        return xy->max_x;
+}
+
+static inline int xyarray__max_x(struct xyarray *xy)
+{
+        return xy->max_y;
+}
+
 #endif /* _PERF_XYARRAY_H_ */