diff --git a/MAINTAINERS b/MAINTAINERS
index b0a742c..deaafb6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13566,6 +13566,7 @@
 F:	include/linux/perf_event.h
 F:	include/uapi/linux/perf_event.h
 F:	kernel/events/*
+F:	tools/lib/perf/
 F:	tools/perf/
 
 PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 436ec76..7a6b148 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -231,11 +231,13 @@
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
 #define KVM_SYNC_ETOKEN (1UL << 11)
+#define KVM_SYNC_DIAG318 (1UL << 12)
 
 #define KVM_SYNC_S390_VALID_FIELDS \
 	(KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
 	 KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
-	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN | \
+	 KVM_SYNC_DIAG318)
 
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
@@ -264,7 +266,8 @@
 	__u8 reserved2 : 7;
 	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
-	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
+	__u64 diag318;		/* diagnose 0x318 info */
+	__u8 padding2[184];	/* sdnx needs to be 256byte aligned */
 	union {
 		__u8 sdnx[SDNXL];  /* state description annex */
 		struct {
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 774f0b0..c1daf4d5 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -8,7 +8,7 @@
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC=$(CC) CXX=$(CXX) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC="$(CC)" CXX="$(CXX)" CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -98,7 +98,8 @@
          llvm-version                   \
          clang                          \
          libbpf                         \
-         libpfm4
+         libpfm4                        \
+         libdebuginfod
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 846ee13..d220fe9 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -26,6 +26,7 @@
          test-libelf-gelf_getnote.bin           \
          test-libelf-getshdrstrndx.bin          \
          test-libelf-mmap.bin                   \
+         test-libdebuginfod.bin                 \
          test-libnuma.bin                       \
          test-numa_num_possible_cpus.bin        \
          test-libperl.bin                       \
@@ -157,6 +158,9 @@
 $(OUTPUT)test-libelf-getshdrstrndx.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-libdebuginfod.bin:
+	$(BUILD) -ldebuginfod
+
 $(OUTPUT)test-libnuma.bin:
 	$(BUILD) -lnuma
 
diff --git a/tools/build/feature/test-libdebuginfod.c b/tools/build/feature/test-libdebuginfod.c
new file mode 100644
index 0000000..da22548
--- /dev/null
+++ b/tools/build/feature/test-libdebuginfod.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <elfutils/debuginfod.h>
+
+int main(void)
+{
+	debuginfod_client* c = debuginfod_begin();
+	return (long)c;
+}
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 4fdf303..f6d86033 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -289,6 +289,7 @@
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu;
 		} fail_entry;
 		/* KVM_EXIT_EXCEPTION */
 		struct {
@@ -1031,6 +1032,9 @@
 #define KVM_CAP_PPC_SECURE_GUEST 181
 #define KVM_CAP_HALT_POLL 182
 #define KVM_CAP_ASYNC_PF_INT 183
+#define KVM_CAP_LAST_CPU 184
+#define KVM_CAP_SMALLER_MAXPHYADDR 185
+#define KVM_CAP_S390_DIAG318 186
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 0c23496..7523218 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -91,6 +91,8 @@
 
 /* Use message type V2 */
 #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+/* IOTLB can accept batching hints */
+#define VHOST_BACKEND_F_IOTLB_BATCH  0x2
 
 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
 #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
diff --git a/tools/lib/perf/Documentation/libperf-counting.txt b/tools/lib/perf/Documentation/libperf-counting.txt
index cae9757..8b75efc 100644
--- a/tools/lib/perf/Documentation/libperf-counting.txt
+++ b/tools/lib/perf/Documentation/libperf-counting.txt
@@ -7,13 +7,13 @@
 
 DESCRIPTION
 -----------
-The counting interface provides API to meassure and get count for specific perf events.
+The counting interface provides API to measure and get count for specific perf events.
 
 The following test tries to explain count on `counting.c` example.
 
 It is by no means complete guide to counting, but shows libperf basic API for counting.
 
-The `counting.c` comes with libbperf package and can be compiled and run like:
+The `counting.c` comes with libperf package and can be compiled and run like:
 
 [source,bash]
 --
@@ -26,7 +26,8 @@
 It requires root access, because of the `PERF_COUNT_SW_CPU_CLOCK` event,
 which is available only for root.
 
-The `counting.c` example monitors two events on the current process and displays their count, in a nutshel it:
+The `counting.c` example monitors two events on the current process and displays
+their count, in a nutshell it:
 
 * creates events
 * adds them to the event list
@@ -152,7 +153,7 @@
 --
 
 Both events are created as disabled (note the `disabled = 1` assignment above),
-so we need to enable the whole list explicitely (both events).
+so we need to enable the whole list explicitly (both events).
 
 From this moment events are counting and we can do our workload.
 
@@ -167,7 +168,8 @@
  79         perf_evlist__disable(evlist);
 --
 
-Now we need to get the counts from events, following code iterates throught the events list and read counts:
+Now we need to get the counts from events, following code iterates through the
+events list and read counts:
 
 [source,c]
 --
@@ -178,7 +180,7 @@
  85         }
 --
 
-And finaly cleanup.
+And finally cleanup.
 
 We close the whole events list (both events) and remove it together with the threads map:
 
diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt
index d71a7b4..d6ca24f 100644
--- a/tools/lib/perf/Documentation/libperf-sampling.txt
+++ b/tools/lib/perf/Documentation/libperf-sampling.txt
@@ -8,13 +8,13 @@
 
 DESCRIPTION
 -----------
-The sampling interface provides API to meassure and get count for specific perf events.
+The sampling interface provides API to measure and get count for specific perf events.
 
 The following test tries to explain count on `sampling.c` example.
 
 It is by no means complete guide to sampling, but shows libperf basic API for sampling.
 
-The `sampling.c` comes with libbperf package and can be compiled and run like:
+The `sampling.c` comes with libperf package and can be compiled and run like:
 
 [source,bash]
 --
@@ -33,7 +33,8 @@
 
 It requires root access, because it uses hardware cycles event.
 
-The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a nutshel it:
+The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a
+nutshell it:
 
 - creates events
 - adds them to the event list
@@ -90,7 +91,7 @@
  36         };
 --
 
-Next step is to prepare cpus map.
+Next step is to prepare CPUs map.
 
 In this case we will monitor all the available CPUs:
 
@@ -152,7 +153,7 @@
 --
 
 The event is created as disabled (note the `disabled = 1` assignment above),
-so we need to enable the events list explicitely.
+so we need to enable the events list explicitly.
 
 From this moment the cycles event is sampling.
 
@@ -212,7 +213,7 @@
 106                                 cpu, pid, tid, ip, period);
 --
 
-And finaly cleanup.
+And finally cleanup.
 
 We close the whole events list (both events) and remove it together with the threads map:
 
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 5a6bb51..0c74c30 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -29,7 +29,7 @@
   void libperf_init(libperf_print_fn_t fn);
 --
 
-*API to handle cpu maps:*
+*API to handle CPU maps:*
 
 [source,c]
 --
@@ -217,7 +217,7 @@
 
 [horizontal]
 
-struct perf_cpu_map:: Provides a cpu list abstraction.
+struct perf_cpu_map:: Provides a CPU list abstraction.
 
 struct perf_thread_map:: Provides a thread list abstraction.
 
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index c7d3df5..76408d9 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -614,8 +614,9 @@
 
 ftrace.*::
 	ftrace.tracer::
-		Can be used to select the default tracer. Possible values are
-		'function' and 'function_graph'.
+		Can be used to select the default tracer when neither -G nor
+		-F option is not specified. Possible values are 'function' and
+		'function_graph'.
 
 llvm.*::
 	llvm.clang-path::
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index b80c843..78358af 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -24,16 +24,28 @@
 
 -t::
 --tracer=::
-	Tracer to use: function_graph or function.
+	Tracer to use when neither -G nor -F option is not
+	specified: function_graph or function.
 
 -v::
 --verbose=::
         Verbosity level.
 
+-F::
+--funcs::
+        List all available functions to trace.
+
 -p::
 --pid=::
 	Trace on existing process id (comma separated list).
 
+--tid=::
+	Trace on existing thread id (comma separated list).
+
+-D::
+--delay::
+	Time (ms) to wait before starting tracing after program start.
+
 -a::
 --all-cpus::
 	Force system-wide collection.  Scripts run without a <command>
@@ -48,39 +60,58 @@
 	Ranges of CPUs are specified with -: 0-2.
 	Default is to trace on all online CPUs.
 
+-m::
+--buffer-size::
+	Set the size of per-cpu tracing buffer, <size> is expected to
+	be a number with appended unit character - B/K/M/G.
+
+--inherit::
+	Trace children processes spawned by our target.
+
 -T::
 --trace-funcs=::
-	Only trace functions given by the argument.  Multiple functions
-	can be given by using this option more than once.  The function
-	argument also can be a glob pattern.  It will be passed to
-	'set_ftrace_filter' in tracefs.
+	Select function tracer and set function filter on the given
+	function (or a glob pattern). Multiple functions can be given
+	by using this option more than once. The function argument also
+	can be a glob pattern. It will be passed to 'set_ftrace_filter'
+	in tracefs.
 
 -N::
 --notrace-funcs=::
-	Do not trace functions given by the argument.  Like -T option,
-	this can be used more than once to specify multiple functions
-	(or glob patterns).  It will be passed to 'set_ftrace_notrace'
-	in tracefs.
+	Select function tracer and do not trace functions given by the
+	argument.  Like -T option, this can be used more than once to
+	specify multiple functions (or glob patterns).  It will be
+	passed to 'set_ftrace_notrace' in tracefs.
+
+--func-opts::
+	List of options allowed to set:
+	  call-graph - Display kernel stack trace for function tracer.
+	  irq-info   - Display irq context info for function tracer.
 
 -G::
 --graph-funcs=::
-	Set graph filter on the given function (or a glob pattern).
-	This is useful for the function_graph tracer only and enables
-	tracing for functions executed from the given function.
-	This can be used more than once to specify multiple functions.
-	It will be passed to 'set_graph_function' in tracefs.
+	Select function_graph tracer and set graph filter on the given
+	function (or a glob pattern). This is useful to trace for
+	functions executed from the given function. This can be used more
+	than once to specify multiple functions. It will be passed to
+	'set_graph_function' in tracefs.
 
 -g::
 --nograph-funcs=::
-	Set graph notrace filter on the given function (or a glob pattern).
-	Like -G option, this is useful for the function_graph tracer only
-	and disables tracing for function executed from the given function.
-	This can be used more than once to specify multiple functions.
-	It will be passed to 'set_graph_notrace' in tracefs.
+	Select function_graph tracer and set graph notrace filter on the
+	given function (or a glob pattern). Like -G option, this is useful
+	for the function_graph tracer only and disables tracing for function
+	executed from the given function. This can be used more than once to
+	specify multiple functions. It will be passed to 'set_graph_notrace'
+	in tracefs.
 
--D::
---graph-depth=::
-	Set max depth for function graph tracer to follow
+--graph-opts::
+	List of options allowed to set:
+	  nosleep-time - Measure on-CPU time only for function_graph tracer.
+	  noirqs       - Ignore functions that happen inside interrupt.
+	  verbose      - Show process names, PIDs, timestamps, etc.
+	  thresh=<n>   - Setup trace duration threshold in microseconds.
+	  depth=<n>    - Set max depth for function graph tracer to follow.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 5136338..190be4f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -501,6 +501,14 @@
     CFLAGS += -DHAVE_ELF_GETSHDRSTRNDX_SUPPORT
   endif
 
+  ifndef NO_LIBDEBUGINFOD
+    $(call feature_check,libdebuginfod)
+    ifeq ($(feature-libdebuginfod), 1)
+      CFLAGS += -DHAVE_DEBUGINFOD_SUPPORT
+      EXTLIBS += -ldebuginfod
+    endif
+  endif
+
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
       msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 86dbb51..6031167 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -124,6 +124,8 @@
 #
 # Define LIBPFM4 to enable libpfm4 events extension.
 #
+# Define NO_LIBDEBUGINFOD if you do not want support debuginfod
+#
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -418,6 +420,7 @@
 
 SHELL = $(SHELL_PATH)
 
+beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
 arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
@@ -501,6 +504,12 @@
 $(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
 	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
 
+socket_arrays := $(beauty_outdir)/socket_arrays.c
+socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh
+
+$(socket_arrays): $(beauty_linux_dir)/socket.h $(socket_tbl)
+	$(Q)$(SHELL) '$(socket_tbl)' $(beauty_linux_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
@@ -697,6 +706,7 @@
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
 	$(socket_ipproto_array) \
+	$(socket_arrays) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(mmap_flags_array) \
@@ -1006,6 +1016,7 @@
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
 		$(OUTPUT)$(socket_ipproto_array) \
+		$(OUTPUT)$(socket_arrays) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c
index fa90f3e..73b5bcc 100644
--- a/tools/perf/bench/find-bit-bench.c
+++ b/tools/perf/bench/find-bit-bench.c
@@ -17,9 +17,9 @@
 
 static const struct option options[] = {
 	OPT_UINTEGER('i', "outer-iterations", &outer_iterations,
-		"Number of outerer iterations used"),
+		"Number of outer iterations used"),
 	OPT_UINTEGER('j', "inner-iterations", &inner_iterations,
-		"Number of outerer iterations used"),
+		"Number of inner iterations used"),
 	OPT_END()
 };
 
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 9235b76..19d45c3 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -223,12 +223,8 @@
 	return 0;
 }
 
-static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+static void memcpy_prefault(memcpy_t fn, size_t size, void *src, void *dst)
 {
-	u64 cycle_start = 0ULL, cycle_end = 0ULL;
-	memcpy_t fn = r->fn.memcpy;
-	int i;
-
 	/* Make sure to always prefault zero pages even if MMAP_THRESH is crossed: */
 	memset(src, 0, size);
 
@@ -237,6 +233,15 @@
 	 * to not measure page fault overhead:
 	 */
 	fn(dst, src, size);
+}
+
+static u64 do_memcpy_cycles(const struct function *r, size_t size, void *src, void *dst)
+{
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
+	memcpy_t fn = r->fn.memcpy;
+	int i;
+
+	memcpy_prefault(fn, size, src, dst);
 
 	cycle_start = get_cycles();
 	for (i = 0; i < nr_loops; ++i)
@@ -252,11 +257,7 @@
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	/*
-	 * We prefault the freshly allocated memory range here,
-	 * to not measure page fault overhead:
-	 */
-	fn(dst, src, size);
+	memcpy_prefault(fn, size, src, dst);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
 	for (i = 0; i < nr_loops; ++i)
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 5797253..f85bcec 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -247,17 +247,22 @@
  */
 static bool node_has_cpus(int node)
 {
-	struct bitmask *cpu = numa_allocate_cpumask();
-	unsigned int i;
+	struct bitmask *cpumask = numa_allocate_cpumask();
+	bool ret = false; /* fall back to nocpus */
+	int cpu;
 
-	if (cpu && !numa_node_to_cpus(node, cpu)) {
-		for (i = 0; i < cpu->size; i++) {
-			if (numa_bitmask_isbitset(cpu, i))
-				return true;
+	BUG_ON(!cpumask);
+	if (!numa_node_to_cpus(node, cpumask)) {
+		for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
+			if (numa_bitmask_isbitset(cpumask, cpu)) {
+				ret = true;
+				break;
+			}
 		}
 	}
+	numa_free_cpumask(cpumask);
 
-	return false; /* lets fall back to nocpus safely */
+	return ret;
 }
 
 static cpu_set_t bind_to_cpu(int target_cpu)
@@ -288,14 +293,10 @@
 
 static cpu_set_t bind_to_node(int target_node)
 {
-	int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
 	cpu_set_t orig_mask, mask;
 	int cpu;
 	int ret;
 
-	BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
-	BUG_ON(!cpus_per_node);
-
 	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
 	BUG_ON(ret);
 
@@ -305,13 +306,16 @@
 		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
 			CPU_SET(cpu, &mask);
 	} else {
-		int cpu_start = (target_node + 0) * cpus_per_node;
-		int cpu_stop  = (target_node + 1) * cpus_per_node;
+		struct bitmask *cpumask = numa_allocate_cpumask();
 
-		BUG_ON(cpu_stop > g->p.nr_cpus);
-
-		for (cpu = cpu_start; cpu < cpu_stop; cpu++)
-			CPU_SET(cpu, &mask);
+		BUG_ON(!cpumask);
+		if (!numa_node_to_cpus(target_node, cpumask)) {
+			for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
+				if (numa_bitmask_isbitset(cpumask, cpu))
+					CPU_SET(cpu, &mask);
+			}
+		}
+		numa_free_cpumask(cpumask);
 	}
 
 	ret = sched_setaffinity(0, sizeof(mask), &mask);
@@ -729,8 +733,6 @@
 		return -1;
 
 	return parse_node_list(arg);
-
-	return 0;
 }
 
 #define BIT(x) (1ul << x)
@@ -813,12 +815,12 @@
 			}
 		}
 	} else if (!g->p.data_backwards || (nr + loop) & 1) {
+		/* Process data forwards: */
 
 		d0 = data + off;
 		d  = data + off + 1;
 		d1 = data + words;
 
-		/* Process data forwards: */
 		for (;;) {
 			if (unlikely(d >= d1))
 				d = data;
@@ -836,7 +838,6 @@
 		d  = data + off - 1;
 		d1 = data + words;
 
-		/* Process data forwards: */
 		for (;;) {
 			if (unlikely(d < data))
 				d = data + words-1;
@@ -1733,12 +1734,12 @@
  */
 static const char *tests[][MAX_ARGS] = {
    /* Basic single-stream NUMA bandwidth measurements: */
-   { "RAM-bw-local,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+   { "RAM-bw-local,",     "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
 			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM },
    { "RAM-bw-local-NOTHP,",
 			  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
 			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM_NOTHP },
-   { "RAM-bw-remote,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+   { "RAM-bw-remote,",    "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
 			  "-C" ,   "0", "-M",   "1", OPT_BW_RAM },
 
    /* 2-stream NUMA bandwidth measurements: */
@@ -1755,7 +1756,7 @@
    { " 1x3-convergence,", "mem",  "-p",  "1", "-t",  "3", "-P",  "512", OPT_CONV },
    { " 1x4-convergence,", "mem",  "-p",  "1", "-t",  "4", "-P",  "512", OPT_CONV },
    { " 1x6-convergence,", "mem",  "-p",  "1", "-t",  "6", "-P", "1020", OPT_CONV },
-   { " 2x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 2x3-convergence,", "mem",  "-p",  "2", "-t",  "3", "-P", "1020", OPT_CONV },
    { " 3x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
    { " 4x4-convergence,", "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV },
    { " 4x4-convergence-NOTHP,",
@@ -1780,24 +1781,24 @@
 			  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW_NOTHP },
    { "16x1-bw-process,",  "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_BW },
 
-   { " 4x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "4", "-T",  "256", OPT_BW },
-   { " 8x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "8", "-T",  "256", OPT_BW },
-   { "16x1-bw-thread,",   "mem",  "-p",  "1", "-t", "16", "-T",  "128", OPT_BW },
-   { "32x1-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-T",   "64", OPT_BW },
+   { " 1x4-bw-thread,",   "mem",  "-p",  "1", "-t",  "4", "-T",  "256", OPT_BW },
+   { " 1x8-bw-thread,",   "mem",  "-p",  "1", "-t",  "8", "-T",  "256", OPT_BW },
+   { "1x16-bw-thread,",   "mem",  "-p",  "1", "-t", "16", "-T",  "128", OPT_BW },
+   { "1x32-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-T",   "64", OPT_BW },
 
-   { " 2x3-bw-thread,",	  "mem",  "-p",  "2", "-t",  "3", "-P",  "512", OPT_BW },
-   { " 4x4-bw-thread,",	  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_BW },
-   { " 4x6-bw-thread,",	  "mem",  "-p",  "4", "-t",  "6", "-P",  "512", OPT_BW },
-   { " 4x8-bw-thread,",	  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW },
-   { " 4x8-bw-thread-NOTHP,",
+   { " 2x3-bw-process,",  "mem",  "-p",  "2", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 4x4-bw-process,",  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_BW },
+   { " 4x6-bw-process,",  "mem",  "-p",  "4", "-t",  "6", "-P",  "512", OPT_BW },
+   { " 4x8-bw-process,",  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW },
+   { " 4x8-bw-process-NOTHP,",
 			  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW_NOTHP },
-   { " 3x3-bw-thread,",	  "mem",  "-p",  "3", "-t",  "3", "-P",  "512", OPT_BW },
-   { " 5x5-bw-thread,",	  "mem",  "-p",  "5", "-t",  "5", "-P",  "512", OPT_BW },
+   { " 3x3-bw-process,",  "mem",  "-p",  "3", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 5x5-bw-process,",  "mem",  "-p",  "5", "-t",  "5", "-P",  "512", OPT_BW },
 
-   { "2x16-bw-thread,",   "mem",  "-p",  "2", "-t", "16", "-P",  "512", OPT_BW },
-   { "1x32-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-P", "2048", OPT_BW },
+   { "2x16-bw-process,",  "mem",  "-p",  "2", "-t", "16", "-P",  "512", OPT_BW },
+   { "1x32-bw-process,",  "mem",  "-p",  "1", "-t", "32", "-P", "2048", OPT_BW },
 
-   { "numa02-bw,",	  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW },
+   { "numa02-bw,",        "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW },
    { "numa02-bw-NOTHP,",  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW_NOTHP },
    { "numa01-bw-thread,", "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW },
    { "numa01-bw-thread-NOTHP,",
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 2bfc1b0..1d44bc2 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -3,6 +3,7 @@
  * builtin-ftrace.c
  *
  * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
+ * Copyright (c) 2020  Changbin Du <changbin.du@gmail.com>, significant enhancement.
  */
 
 #include "builtin.h"
@@ -26,6 +27,8 @@
 #include "thread_map.h"
 #include "util/cap.h"
 #include "util/config.h"
+#include "util/units.h"
+#include "util/parse-sublevel-options.h"
 
 #define DEFAULT_TRACER  "function_graph"
 
@@ -33,11 +36,21 @@
 	struct evlist		*evlist;
 	struct target		target;
 	const char		*tracer;
+	bool			list_avail_functions;
 	struct list_head	filters;
 	struct list_head	notrace;
 	struct list_head	graph_funcs;
 	struct list_head	nograph_funcs;
 	int			graph_depth;
+	unsigned long		percpu_buffer_size;
+	bool			inherit;
+	int			func_stack_trace;
+	int			func_irq_info;
+	int			graph_nosleep_time;
+	int			graph_noirqs;
+	int			graph_verbose;
+	int			graph_thresh;
+	unsigned int		initial_delay;
 };
 
 struct filter_entry {
@@ -128,9 +141,85 @@
 	return __write_tracing_file(name, val, true);
 }
 
+static int read_tracing_file_to_stdout(const char *name)
+{
+	char buf[4096];
+	char *file;
+	int fd;
+	int ret = -1;
+
+	file = get_tracing_file(name);
+	if (!file) {
+		pr_debug("cannot get tracing file: %s\n", name);
+		return -1;
+	}
+
+	fd = open(file, O_RDONLY);
+	if (fd < 0) {
+		pr_debug("cannot open tracing file: %s: %s\n",
+			 name, str_error_r(errno, buf, sizeof(buf)));
+		goto out;
+	}
+
+	/* read contents to stdout */
+	while (true) {
+		int n = read(fd, buf, sizeof(buf));
+		if (n == 0)
+			break;
+		else if (n < 0)
+			goto out_close;
+
+		if (fwrite(buf, n, 1, stdout) != 1)
+			goto out_close;
+	}
+	ret = 0;
+
+out_close:
+	close(fd);
+out:
+	put_tracing_file(file);
+	return ret;
+}
+
+static int write_tracing_file_int(const char *name, int value)
+{
+	char buf[16];
+
+	snprintf(buf, sizeof(buf), "%d", value);
+	if (write_tracing_file(name, buf) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int write_tracing_option_file(const char *name, const char *val)
+{
+	char *file;
+	int ret;
+
+	if (asprintf(&file, "options/%s", name) < 0)
+		return -1;
+
+	ret = __write_tracing_file(file, val, false);
+	free(file);
+	return ret;
+}
+
 static int reset_tracing_cpu(void);
 static void reset_tracing_filters(void);
 
+static void reset_tracing_options(struct perf_ftrace *ftrace __maybe_unused)
+{
+	write_tracing_option_file("function-fork", "0");
+	write_tracing_option_file("func_stack_trace", "0");
+	write_tracing_option_file("sleep-time", "1");
+	write_tracing_option_file("funcgraph-irqs", "1");
+	write_tracing_option_file("funcgraph-proc", "0");
+	write_tracing_option_file("funcgraph-abstime", "0");
+	write_tracing_option_file("latency-format", "0");
+	write_tracing_option_file("irq-info", "0");
+}
+
 static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 {
 	if (write_tracing_file("tracing_on", "0") < 0)
@@ -148,7 +237,11 @@
 	if (write_tracing_file("max_graph_depth", "0") < 0)
 		return -1;
 
+	if (write_tracing_file("tracing_thresh", "0") < 0)
+		return -1;
+
 	reset_tracing_filters();
+	reset_tracing_options(ftrace);
 	return 0;
 }
 
@@ -204,6 +297,28 @@
 	return set_tracing_cpumask(cpumap);
 }
 
+static int set_tracing_func_stack_trace(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->func_stack_trace)
+		return 0;
+
+	if (write_tracing_option_file("func_stack_trace", "1") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_func_irqinfo(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->func_irq_info)
+		return 0;
+
+	if (write_tracing_option_file("irq-info", "1") < 0)
+		return -1;
+
+	return 0;
+}
+
 static int reset_tracing_cpu(void)
 {
 	struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL);
@@ -258,8 +373,6 @@
 
 static int set_tracing_depth(struct perf_ftrace *ftrace)
 {
-	char buf[16];
-
 	if (ftrace->graph_depth == 0)
 		return 0;
 
@@ -268,14 +381,156 @@
 		return -1;
 	}
 
-	snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth);
-
-	if (write_tracing_file("max_graph_depth", buf) < 0)
+	if (write_tracing_file_int("max_graph_depth", ftrace->graph_depth) < 0)
 		return -1;
 
 	return 0;
 }
 
+static int set_tracing_percpu_buffer_size(struct perf_ftrace *ftrace)
+{
+	int ret;
+
+	if (ftrace->percpu_buffer_size == 0)
+		return 0;
+
+	ret = write_tracing_file_int("buffer_size_kb",
+				     ftrace->percpu_buffer_size / 1024);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int set_tracing_trace_inherit(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->inherit)
+		return 0;
+
+	if (write_tracing_option_file("function-fork", "1") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_sleep_time(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->graph_nosleep_time)
+		return 0;
+
+	if (write_tracing_option_file("sleep-time", "0") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_funcgraph_irqs(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->graph_noirqs)
+		return 0;
+
+	if (write_tracing_option_file("funcgraph-irqs", "0") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_funcgraph_verbose(struct perf_ftrace *ftrace)
+{
+	if (!ftrace->graph_verbose)
+		return 0;
+
+	if (write_tracing_option_file("funcgraph-proc", "1") < 0)
+		return -1;
+
+	if (write_tracing_option_file("funcgraph-abstime", "1") < 0)
+		return -1;
+
+	if (write_tracing_option_file("latency-format", "1") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int set_tracing_thresh(struct perf_ftrace *ftrace)
+{
+	int ret;
+
+	if (ftrace->graph_thresh == 0)
+		return 0;
+
+	ret = write_tracing_file_int("tracing_thresh", ftrace->graph_thresh);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int set_tracing_options(struct perf_ftrace *ftrace)
+{
+	if (set_tracing_pid(ftrace) < 0) {
+		pr_err("failed to set ftrace pid\n");
+		return -1;
+	}
+
+	if (set_tracing_cpu(ftrace) < 0) {
+		pr_err("failed to set tracing cpumask\n");
+		return -1;
+	}
+
+	if (set_tracing_func_stack_trace(ftrace) < 0) {
+		pr_err("failed to set tracing option func_stack_trace\n");
+		return -1;
+	}
+
+	if (set_tracing_func_irqinfo(ftrace) < 0) {
+		pr_err("failed to set tracing option irq-info\n");
+		return -1;
+	}
+
+	if (set_tracing_filters(ftrace) < 0) {
+		pr_err("failed to set tracing filters\n");
+		return -1;
+	}
+
+	if (set_tracing_depth(ftrace) < 0) {
+		pr_err("failed to set graph depth\n");
+		return -1;
+	}
+
+	if (set_tracing_percpu_buffer_size(ftrace) < 0) {
+		pr_err("failed to set tracing per-cpu buffer size\n");
+		return -1;
+	}
+
+	if (set_tracing_trace_inherit(ftrace) < 0) {
+		pr_err("failed to set tracing option function-fork\n");
+		return -1;
+	}
+
+	if (set_tracing_sleep_time(ftrace) < 0) {
+		pr_err("failed to set tracing option sleep-time\n");
+		return -1;
+	}
+
+	if (set_tracing_funcgraph_irqs(ftrace) < 0) {
+		pr_err("failed to set tracing option funcgraph-irqs\n");
+		return -1;
+	}
+
+	if (set_tracing_funcgraph_verbose(ftrace) < 0) {
+		pr_err("failed to set tracing option funcgraph-proc/funcgraph-abstime\n");
+		return -1;
+	}
+
+	if (set_tracing_thresh(ftrace) < 0) {
+		pr_err("failed to set tracing thresh\n");
+		return -1;
+	}
+
+	return 0;
+}
+
 static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 {
 	char *trace_file;
@@ -302,6 +557,9 @@
 	signal(SIGCHLD, sig_handler);
 	signal(SIGPIPE, sig_handler);
 
+	if (ftrace->list_avail_functions)
+		return read_tracing_file_to_stdout("available_filter_functions");
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
 		goto out;
@@ -317,25 +575,8 @@
 		goto out;
 	}
 
-	if (set_tracing_pid(ftrace) < 0) {
-		pr_err("failed to set ftrace pid\n");
+	if (set_tracing_options(ftrace) < 0)
 		goto out_reset;
-	}
-
-	if (set_tracing_cpu(ftrace) < 0) {
-		pr_err("failed to set tracing cpumask\n");
-		goto out_reset;
-	}
-
-	if (set_tracing_filters(ftrace) < 0) {
-		pr_err("failed to set tracing filters\n");
-		goto out_reset;
-	}
-
-	if (set_tracing_depth(ftrace) < 0) {
-		pr_err("failed to set graph depth\n");
-		goto out_reset;
-	}
 
 	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
 		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
@@ -362,13 +603,26 @@
 	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
 	pollfd.fd = trace_fd;
 
-	if (write_tracing_file("tracing_on", "1") < 0) {
-		pr_err("can't enable tracing\n");
-		goto out_close_fd;
+	/* display column headers */
+	read_tracing_file_to_stdout("trace");
+
+	if (!ftrace->initial_delay) {
+		if (write_tracing_file("tracing_on", "1") < 0) {
+			pr_err("can't enable tracing\n");
+			goto out_close_fd;
+		}
 	}
 
 	perf_evlist__start_workload(ftrace->evlist);
 
+	if (ftrace->initial_delay) {
+		usleep(ftrace->initial_delay * 1000);
+		if (write_tracing_file("tracing_on", "1") < 0) {
+			pr_err("can't enable tracing\n");
+			goto out_close_fd;
+		}
+	}
+
 	while (!done) {
 		if (poll(&pollfd, 1, -1) < 0)
 			break;
@@ -455,6 +709,99 @@
 	}
 }
 
+static int parse_buffer_size(const struct option *opt,
+			     const char *str, int unset)
+{
+	unsigned long *s = (unsigned long *)opt->value;
+	static struct parse_tag tags_size[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+	unsigned long val;
+
+	if (unset) {
+		*s = 0;
+		return 0;
+	}
+
+	val = parse_tag_value(str, tags_size);
+	if (val != (unsigned long) -1) {
+		if (val < 1024) {
+			pr_err("buffer size too small, must larger than 1KB.");
+			return -1;
+		}
+		*s = val;
+		return 0;
+	}
+
+	return -1;
+}
+
+static int parse_func_tracer_opts(const struct option *opt,
+				  const char *str, int unset)
+{
+	int ret;
+	struct perf_ftrace *ftrace = (struct perf_ftrace *) opt->value;
+	struct sublevel_option func_tracer_opts[] = {
+		{ .name = "call-graph",	.value_ptr = &ftrace->func_stack_trace },
+		{ .name = "irq-info",	.value_ptr = &ftrace->func_irq_info },
+		{ .name = NULL, }
+	};
+
+	if (unset)
+		return 0;
+
+	ret = perf_parse_sublevel_options(str, func_tracer_opts);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int parse_graph_tracer_opts(const struct option *opt,
+				  const char *str, int unset)
+{
+	int ret;
+	struct perf_ftrace *ftrace = (struct perf_ftrace *) opt->value;
+	struct sublevel_option graph_tracer_opts[] = {
+		{ .name = "nosleep-time",	.value_ptr = &ftrace->graph_nosleep_time },
+		{ .name = "noirqs",		.value_ptr = &ftrace->graph_noirqs },
+		{ .name = "verbose",		.value_ptr = &ftrace->graph_verbose },
+		{ .name = "thresh",		.value_ptr = &ftrace->graph_thresh },
+		{ .name = "depth",		.value_ptr = &ftrace->graph_depth },
+		{ .name = NULL, }
+	};
+
+	if (unset)
+		return 0;
+
+	ret = perf_parse_sublevel_options(str, graph_tracer_opts);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void select_tracer(struct perf_ftrace *ftrace)
+{
+	bool graph = !list_empty(&ftrace->graph_funcs) ||
+		     !list_empty(&ftrace->nograph_funcs);
+	bool func = !list_empty(&ftrace->filters) ||
+		    !list_empty(&ftrace->notrace);
+
+	/* The function_graph has priority over function tracer. */
+	if (graph)
+		ftrace->tracer = "function_graph";
+	else if (func)
+		ftrace->tracer = "function";
+	/* Otherwise, the default tracer is used. */
+
+	pr_debug("%s tracer is used\n", ftrace->tracer);
+}
+
 int cmd_ftrace(int argc, const char **argv)
 {
 	int ret;
@@ -469,25 +816,42 @@
 	};
 	const struct option ftrace_options[] = {
 	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
-		   "tracer to use: function_graph(default) or function"),
+		   "Tracer to use: function_graph(default) or function"),
+	OPT_BOOLEAN('F', "funcs", &ftrace.list_avail_functions,
+		    "Show available functions to filter"),
 	OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
-		   "trace on existing process id"),
+		   "Trace on existing process id"),
+	/* TODO: Add short option -t after -t/--tracer can be removed. */
+	OPT_STRING(0, "tid", &ftrace.target.tid, "tid",
+		   "Trace on existing thread id (exclusive to --pid)"),
 	OPT_INCR('v', "verbose", &verbose,
-		 "be more verbose"),
+		 "Be more verbose"),
 	OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide,
-		    "system-wide collection from all CPUs"),
+		    "System-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
-		    "list of cpus to monitor"),
+		    "List of cpus to monitor"),
 	OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
-		     "trace given functions only", parse_filter_func),
+		     "Trace given functions using function tracer",
+		     parse_filter_func),
 	OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func",
-		     "do not trace given functions", parse_filter_func),
+		     "Do not trace given functions", parse_filter_func),
+	OPT_CALLBACK(0, "func-opts", &ftrace, "options",
+		     "Function tracer options, available options: call-graph,irq-info",
+		     parse_func_tracer_opts),
 	OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func",
-		     "Set graph filter on given functions", parse_filter_func),
+		     "Trace given functions using function_graph tracer",
+		     parse_filter_func),
 	OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func",
 		     "Set nograph filter on given functions", parse_filter_func),
-	OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth,
-		    "Max depth for function graph tracer"),
+	OPT_CALLBACK(0, "graph-opts", &ftrace, "options",
+		     "Graph tracer options, available options: nosleep-time,noirqs,verbose,thresh=<n>,depth=<n>",
+		     parse_graph_tracer_opts),
+	OPT_CALLBACK('m', "buffer-size", &ftrace.percpu_buffer_size, "size",
+		     "Size of per cpu buffer, needs to use a B, K, M or G suffix.", parse_buffer_size),
+	OPT_BOOLEAN(0, "inherit", &ftrace.inherit,
+		    "Trace children processes"),
+	OPT_UINTEGER('D', "delay", &ftrace.initial_delay,
+		     "Number of milliseconds to wait before starting tracing after program start"),
 	OPT_END()
 	};
 
@@ -505,6 +869,8 @@
 	if (!argc && target__none(&ftrace.target))
 		ftrace.target.system_wide = true;
 
+	select_tracer(&ftrace);
+
 	ret = target__validate(&ftrace.target);
 	if (ret) {
 		char errbuf[512];
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 459e422..0c7d599 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2398,6 +2398,15 @@
 	printf("\n");
 }
 
+static int timehist_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused,
+					union perf_event *event __maybe_unused,
+					struct evsel *evsel __maybe_unused,
+					struct perf_sample *sample __maybe_unused,
+					struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
 static int timehist_sched_wakeup_event(struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
 				       struct evsel *evsel,
@@ -2958,9 +2967,10 @@
 
 static int perf_sched__timehist(struct perf_sched *sched)
 {
-	const struct evsel_str_handler handlers[] = {
+	struct evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",       timehist_sched_switch_event, },
 		{ "sched:sched_wakeup",	      timehist_sched_wakeup_event, },
+		{ "sched:sched_waking",       timehist_sched_wakeup_event, },
 		{ "sched:sched_wakeup_new",   timehist_sched_wakeup_event, },
 	};
 	const struct evsel_str_handler migrate_handlers[] = {
@@ -3018,6 +3028,11 @@
 
 	setup_pager();
 
+	/* prefer sched_waking if it is captured */
+	if (perf_evlist__find_tracepoint_by_name(session->evlist,
+						  "sched:sched_waking"))
+		handlers[1].handler = timehist_sched_wakeup_ignore;
+
 	/* setup per-evsel handlers */
 	if (perf_session__set_tracepoints_handlers(session, handlers))
 		goto out;
@@ -3330,12 +3345,16 @@
 		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
-		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
+	struct tep_event *waking_event;
 
-	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+	/*
+	 * +2 for either "-e", "sched:sched_wakeup" or
+	 * "-e", "sched:sched_waking"
+	 */
+	rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -3344,6 +3363,13 @@
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
+	rec_argv[i++] = "-e";
+	waking_event = trace_event__tp_format("sched", "sched_waking");
+	if (!IS_ERR(waking_event))
+		rec_argv[i++] = strdup("sched:sched_waking");
+	else
+		rec_argv[i++] = strdup("sched:sched_wakeup");
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 94c2bc2..0b4d643 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -128,6 +128,9 @@
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
 
+# These will require a beauty_check when we get some more like that
+check_2 tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h
+
 # check duplicated library files
 check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h
 check_2 tools/perf/util/hashmap.c tools/lib/bpf/hashmap.c
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/metrics.json
index 80816d6..f8784c6 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/metrics.json
@@ -60,7 +60,7 @@
     },
     {
         "BriefDescription": "Stalls due to short latency decimal floating ops.",
-        "MetricExpr": "(PM_CMPLU_STALL_DFU - PM_CMPLU_STALL_DFLONG)/PM_RUN_INST_CMPL",
+        "MetricExpr": "dfu_stall_cpi - dflong_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "dfu_other_stall_cpi"
     },
@@ -72,7 +72,7 @@
     },
     {
         "BriefDescription": "Completion stall by Dcache miss which resolved off node memory/cache",
-        "MetricExpr": "(PM_CMPLU_STALL_DMISS_L3MISS - PM_CMPLU_STALL_DMISS_L21_L31 - PM_CMPLU_STALL_DMISS_LMEM - PM_CMPLU_STALL_DMISS_REMOTE)/PM_RUN_INST_CMPL",
+        "MetricExpr": "dmiss_non_local_stall_cpi - dmiss_remote_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "dmiss_distant_stall_cpi"
     },
@@ -90,7 +90,7 @@
     },
     {
         "BriefDescription": "Completion stall due to cache miss that resolves in the L2 or L3 without conflict",
-        "MetricExpr": "(PM_CMPLU_STALL_DMISS_L2L3 - PM_CMPLU_STALL_DMISS_L2L3_CONFLICT)/PM_RUN_INST_CMPL",
+        "MetricExpr": "dmiss_l2l3_stall_cpi - dmiss_l2l3_conflict_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "dmiss_l2l3_noconflict_stall_cpi"
     },
@@ -114,7 +114,7 @@
     },
     {
         "BriefDescription": "Completion stall by Dcache miss which resolved outside of local memory",
-        "MetricExpr": "(PM_CMPLU_STALL_DMISS_L3MISS - PM_CMPLU_STALL_DMISS_L21_L31 - PM_CMPLU_STALL_DMISS_LMEM)/PM_RUN_INST_CMPL",
+        "MetricExpr": "dmiss_l3miss_stall_cpi - dmiss_l21_l31_stall_cpi - dmiss_lmem_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "dmiss_non_local_stall_cpi"
     },
@@ -126,7 +126,7 @@
     },
     {
         "BriefDescription": "Stalls due to short latency double precision ops.",
-        "MetricExpr": "(PM_CMPLU_STALL_DP - PM_CMPLU_STALL_DPLONG)/PM_RUN_INST_CMPL",
+        "MetricExpr": "dp_stall_cpi - dplong_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "dp_other_stall_cpi"
     },
@@ -155,7 +155,7 @@
         "MetricName": "emq_full_stall_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_ERAT_MISS + PM_CMPLU_STALL_EMQ_FULL)/PM_RUN_INST_CMPL",
+        "MetricExpr": "erat_miss_stall_cpi + emq_full_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "emq_stall_cpi"
     },
@@ -173,7 +173,7 @@
     },
     {
         "BriefDescription": "Completion stall due to execution units for other reasons.",
-        "MetricExpr": "(PM_CMPLU_STALL_EXEC_UNIT - PM_CMPLU_STALL_FXU - PM_CMPLU_STALL_DP - PM_CMPLU_STALL_DFU - PM_CMPLU_STALL_PM - PM_CMPLU_STALL_CRYPTO - PM_CMPLU_STALL_VFXU - PM_CMPLU_STALL_VDP)/PM_RUN_INST_CMPL",
+        "MetricExpr": "exec_unit_stall_cpi - scalar_stall_cpi - vector_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "exec_unit_other_stall_cpi"
     },
@@ -197,7 +197,7 @@
     },
     {
         "BriefDescription": "Stalls due to short latency integer ops",
-        "MetricExpr": "(PM_CMPLU_STALL_FXU - PM_CMPLU_STALL_FXLONG)/PM_RUN_INST_CMPL",
+        "MetricExpr": "fxu_stall_cpi - fxlong_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_other_stall_cpi"
     },
@@ -221,7 +221,7 @@
     },
     {
         "BriefDescription": "Instruction Completion Table other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricExpr": "nothing_dispatched_cpi - ict_noslot_ic_miss_cpi - ict_noslot_br_mpred_icmiss_cpi - ict_noslot_br_mpred_cpi - ict_noslot_disp_held_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "ict_noslot_cyc_other_cpi"
     },
@@ -245,7 +245,7 @@
     },
     {
         "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricExpr": "ict_noslot_disp_held_cpi - ict_noslot_disp_held_hb_full_cpi - ict_noslot_disp_held_sync_cpi - ict_noslot_disp_held_tbegin_cpi - ict_noslot_disp_held_issq_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "ict_noslot_disp_held_other_cpi"
     },
@@ -263,7 +263,7 @@
     },
     {
         "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricExpr": "ict_noslot_ic_miss_cpi - ict_noslot_ic_l3_cpi - ict_noslot_ic_l3miss_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "ict_noslot_ic_l2_cpi"
     },
@@ -286,7 +286,7 @@
         "MetricName": "ict_noslot_ic_miss_cpi"
     },
     {
-        "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
+        "MetricExpr": "ntc_issue_held_darq_full_cpi + ntc_issue_held_arb_cpi + ntc_issue_held_other_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "issue_hold_cpi"
     },
@@ -327,7 +327,7 @@
         "MetricName": "lrq_other_stall_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_LMQ_FULL + PM_CMPLU_STALL_ST_FWD + PM_CMPLU_STALL_LHS + PM_CMPLU_STALL_LSU_MFSPR + PM_CMPLU_STALL_LARX + PM_CMPLU_STALL_LRQ_OTHER)/PM_RUN_INST_CMPL",
+        "MetricExpr": "lmq_full_stall_cpi + st_fwd_stall_cpi + lhs_stall_cpi + lsu_mfspr_stall_cpi + larx_stall_cpi + lrq_other_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "lrq_stall_cpi"
     },
@@ -338,7 +338,7 @@
         "MetricName": "lsaq_arb_stall_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_LRQ_FULL + PM_CMPLU_STALL_SRQ_FULL + PM_CMPLU_STALL_LSAQ_ARB)/PM_RUN_INST_CMPL",
+        "MetricExpr": "lrq_full_stall_cpi + srq_full_stall_cpi + lsaq_arb_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "lsaq_stall_cpi"
     },
@@ -362,7 +362,7 @@
     },
     {
         "BriefDescription": "Completion LSU stall for other reasons",
-        "MetricExpr": "(PM_CMPLU_STALL_LSU - PM_CMPLU_STALL_LSU_FIN - PM_CMPLU_STALL_STORE_FINISH - PM_CMPLU_STALL_STORE_DATA - PM_CMPLU_STALL_EIEIO - PM_CMPLU_STALL_STCX - PM_CMPLU_STALL_SLB - PM_CMPLU_STALL_TEND - PM_CMPLU_STALL_PASTE - PM_CMPLU_STALL_TLBIE - PM_CMPLU_STALL_STORE_PIPE_ARB - PM_CMPLU_STALL_STORE_FIN_ARB - PM_CMPLU_STALL_LOAD_FINISH + PM_CMPLU_STALL_DCACHE_MISS - PM_CMPLU_STALL_LMQ_FULL - PM_CMPLU_STALL_ST_FWD - PM_CMPLU_STALL_LHS - PM_CMPLU_STALL_LSU_MFSPR - PM_CMPLU_STALL_LARX - PM_CMPLU_STALL_LRQ_OTHER + PM_CMPLU_STALL_ERAT_MISS + PM_CMPLU_STALL_EMQ_FULL - PM_CMPLU_STALL_LRQ_FULL - PM_CMPLU_STALL_SRQ_FULL - PM_CMPLU_STALL_LSAQ_ARB) / PM_RUN_INST_CMPL",
+        "MetricExpr": "lsu_stall_cpi - lsu_fin_stall_cpi - store_finish_stall_cpi - srq_stall_cpi - load_finish_stall_cpi + lsu_stall_dcache_miss_cpi - lrq_stall_cpi + emq_stall_cpi - lsaq_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "lsu_other_stall_cpi"
     },
@@ -434,13 +434,13 @@
     },
     {
         "BriefDescription": "Cycles unaccounted for.",
-        "MetricExpr": "(PM_RUN_CYC - PM_1PLUS_PPC_CMPL - PM_CMPLU_STALL_THRD - PM_CMPLU_STALL - PM_ICT_NOSLOT_CYC)/PM_RUN_INST_CMPL",
+        "MetricExpr": "run_cpi - completion_cpi - thread_block_stall_cpi - stall_cpi - nothing_dispatched_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "other_cpi"
     },
     {
         "BriefDescription": "Completion stall for other reasons",
-        "MetricExpr": "(PM_CMPLU_STALL - PM_CMPLU_STALL_NTC_DISP_FIN - PM_CMPLU_STALL_NTC_FLUSH - PM_CMPLU_STALL_LSU - PM_CMPLU_STALL_EXEC_UNIT - PM_CMPLU_STALL_BRU)/PM_RUN_INST_CMPL",
+        "MetricExpr": "stall_cpi - ntc_disp_fin_stall_cpi - ntc_flush_stall_cpi - lsu_stall_cpi - exec_unit_stall_cpi - bru_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "other_stall_cpi"
     },
@@ -469,7 +469,7 @@
         "MetricName": "run_cyc_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_FXU + PM_CMPLU_STALL_DP + PM_CMPLU_STALL_DFU + PM_CMPLU_STALL_PM + PM_CMPLU_STALL_CRYPTO)/PM_RUN_INST_CMPL",
+        "MetricExpr": "fxu_stall_cpi + dp_stall_cpi + dfu_stall_cpi + pm_stall_cpi + crypto_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "scalar_stall_cpi"
     },
@@ -492,7 +492,7 @@
         "MetricName": "srq_full_stall_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_STORE_DATA + PM_CMPLU_STALL_EIEIO + PM_CMPLU_STALL_STCX + PM_CMPLU_STALL_SLB + PM_CMPLU_STALL_TEND + PM_CMPLU_STALL_PASTE + PM_CMPLU_STALL_TLBIE + PM_CMPLU_STALL_STORE_PIPE_ARB + PM_CMPLU_STALL_STORE_FIN_ARB)/PM_RUN_INST_CMPL",
+        "MetricExpr": "store_data_stall_cpi + eieio_stall_cpi + stcx_stall_cpi + slb_stall_cpi + tend_stall_cpi + paste_stall_cpi + tlbie_stall_cpi + store_pipe_arb_stall_cpi + store_fin_arb_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "srq_stall_cpi"
     },
@@ -558,7 +558,7 @@
     },
     {
         "BriefDescription": "Vector stalls due to small latency double precision ops",
-        "MetricExpr": "(PM_CMPLU_STALL_VDP - PM_CMPLU_STALL_VDPLONG)/PM_RUN_INST_CMPL",
+        "MetricExpr": "vdp_stall_cpi - vdplong_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "vdp_other_stall_cpi"
     },
@@ -575,7 +575,7 @@
         "MetricName": "vdplong_stall_cpi"
     },
     {
-        "MetricExpr": "(PM_CMPLU_STALL_VFXU + PM_CMPLU_STALL_VDP)/PM_RUN_INST_CMPL",
+        "MetricExpr": "vfxu_stall_cpi + vdp_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "vector_stall_cpi"
     },
@@ -587,7 +587,7 @@
     },
     {
         "BriefDescription": "Vector stalls due to small latency integer ops",
-        "MetricExpr": "(PM_CMPLU_STALL_VFXU - PM_CMPLU_STALL_VFXLONG)/PM_RUN_INST_CMPL",
+        "MetricExpr": "vfxu_stall_cpi - vfxlong_stall_cpi",
         "MetricGroup": "cpi_breakdown",
         "MetricName": "vfxu_other_stall_cpi"
     },
@@ -1844,7 +1844,7 @@
     },
     {
         "BriefDescription": "% of DL1 reloads from Private L3, other core per Inst",
-        "MetricExpr": "(PM_DATA_FROM_L31_MOD + PM_DATA_FROM_L31_SHR) * 100 / PM_RUN_INST_CMPL",
+        "MetricExpr": "dl1_reload_from_l31_mod_rate_percent + dl1_reload_from_l31_shr_rate_percent",
         "MetricName": "dl1_reload_from_l31_rate_percent"
     },
     {
@@ -1979,7 +1979,7 @@
     },
     {
         "BriefDescription": "Completion stall because a different thread was using the completion pipe",
-        "MetricExpr": "(PM_CMPLU_STALL_THRD - PM_CMPLU_STALL_EXCEPTION - PM_CMPLU_STALL_ANY_SYNC - PM_CMPLU_STALL_SYNC_PMU_INT - PM_CMPLU_STALL_SPEC_FINISH - PM_CMPLU_STALL_FLUSH_ANY_THREAD - PM_CMPLU_STALL_LSU_FLUSH_NEXT - PM_CMPLU_STALL_NESTED_TBEGIN - PM_CMPLU_STALL_NESTED_TEND - PM_CMPLU_STALL_MTFPSCR)/PM_RUN_INST_CMPL",
+        "MetricExpr": "thread_block_stall_cpi - exception_stall_cpi - any_sync_stall_cpi - sync_pmu_int_stall_cpi - spec_finish_stall_cpi - flush_any_thread_stall_cpi - lsu_flush_next_stall_cpi - nested_tbegin_stall_cpi - nested_tend_stall_cpi - mtfpscr_stall_cpi",
         "MetricName": "other_thread_cmpl_stall"
     },
     {
diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
index 54030c1..bf9e729 100755
--- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh
@@ -20,13 +20,13 @@
 
 record_open_file() {
 	echo "Recording open file:"
-	perf record -o ${perfdata} -e probe:vfs_getname touch $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}\""
+	egrep " +touch +[0-9]+ +\[[0-9]+\] +[0-9]+\.[0-9]+: +probe:vfs_getname[_0-9]*: +\([[:xdigit:]]+\) +pathname=\"${file}\""
 }
 
 add_probe_vfs_getname || skip_if_no_debuginfo
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
new file mode 100644
index 0000000..e9cb30d
--- /dev/null
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -0,0 +1,442 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SOCKET_H
+#define _LINUX_SOCKET_H
+
+
+#include <asm/socket.h>			/* arch-dependent defines	*/
+#include <linux/sockios.h>		/* the SIOCxxx I/O controls	*/
+#include <linux/uio.h>			/* iovec support		*/
+#include <linux/types.h>		/* pid_t			*/
+#include <linux/compiler.h>		/* __user			*/
+#include <uapi/linux/socket.h>
+
+struct file;
+struct pid;
+struct cred;
+struct socket;
+
+#define __sockaddr_check_size(size)	\
+	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
+
+#ifdef CONFIG_PROC_FS
+struct seq_file;
+extern void socket_seq_show(struct seq_file *seq);
+#endif
+
+typedef __kernel_sa_family_t	sa_family_t;
+
+/*
+ *	1003.1g requires sa_family_t and that sa_data is char.
+ */
+
+struct sockaddr {
+	sa_family_t	sa_family;	/* address family, AF_xxx	*/
+	char		sa_data[14];	/* 14 bytes of protocol address	*/
+};
+
+struct linger {
+	int		l_onoff;	/* Linger active		*/
+	int		l_linger;	/* How long to linger for	*/
+};
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+/*
+ *	As we do 4.4BSD message passing we use a 4.4BSD message passing
+ *	system, not 4.3. Thus msg_accrights(len) are now missing. They
+ *	belong in an obscure libc emulation or the bin.
+ */
+
+struct msghdr {
+	void		*msg_name;	/* ptr to socket address structure */
+	int		msg_namelen;	/* size of socket address structure */
+	struct iov_iter	msg_iter;	/* data */
+
+	/*
+	 * Ancillary data. msg_control_user is the user buffer used for the
+	 * recv* side when msg_control_is_user is set, msg_control is the kernel
+	 * buffer used for all other cases.
+	 */
+	union {
+		void		*msg_control;
+		void __user	*msg_control_user;
+	};
+	bool		msg_control_is_user : 1;
+	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
+	unsigned int	msg_flags;	/* flags on received message */
+	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
+};
+
+struct user_msghdr {
+	void		__user *msg_name;	/* ptr to socket address structure */
+	int		msg_namelen;		/* size of socket address structure */
+	struct iovec	__user *msg_iov;	/* scatter/gather array */
+	__kernel_size_t	msg_iovlen;		/* # elements in msg_iov */
+	void		__user *msg_control;	/* ancillary data */
+	__kernel_size_t	msg_controllen;		/* ancillary data buffer length */
+	unsigned int	msg_flags;		/* flags on received message */
+};
+
+/* For recvmmsg/sendmmsg */
+struct mmsghdr {
+	struct user_msghdr  msg_hdr;
+	unsigned int        msg_len;
+};
+
+/*
+ *	POSIX 1003.1g - ancillary data object information
+ *	Ancillary data consits of a sequence of pairs of
+ *	(cmsghdr, cmsg_data[])
+ */
+
+struct cmsghdr {
+	__kernel_size_t	cmsg_len;	/* data byte count, including hdr */
+        int		cmsg_level;	/* originating protocol */
+        int		cmsg_type;	/* protocol-specific type */
+};
+
+/*
+ *	Ancillary data object information MACROS
+ *	Table 5-14 of POSIX 1003.1g
+ */
+
+#define __CMSG_NXTHDR(ctl, len, cmsg) __cmsg_nxthdr((ctl),(len),(cmsg))
+#define CMSG_NXTHDR(mhdr, cmsg) cmsg_nxthdr((mhdr), (cmsg))
+
+#define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) )
+
+#define CMSG_DATA(cmsg) \
+	((void *)(cmsg) + sizeof(struct cmsghdr))
+#define CMSG_USER_DATA(cmsg) \
+	((void __user *)(cmsg) + sizeof(struct cmsghdr))
+#define CMSG_SPACE(len) (sizeof(struct cmsghdr) + CMSG_ALIGN(len))
+#define CMSG_LEN(len) (sizeof(struct cmsghdr) + (len))
+
+#define __CMSG_FIRSTHDR(ctl,len) ((len) >= sizeof(struct cmsghdr) ? \
+				  (struct cmsghdr *)(ctl) : \
+				  (struct cmsghdr *)NULL)
+#define CMSG_FIRSTHDR(msg)	__CMSG_FIRSTHDR((msg)->msg_control, (msg)->msg_controllen)
+#define CMSG_OK(mhdr, cmsg) ((cmsg)->cmsg_len >= sizeof(struct cmsghdr) && \
+			     (cmsg)->cmsg_len <= (unsigned long) \
+			     ((mhdr)->msg_controllen - \
+			      ((char *)(cmsg) - (char *)(mhdr)->msg_control)))
+#define for_each_cmsghdr(cmsg, msg) \
+	for (cmsg = CMSG_FIRSTHDR(msg); \
+	     cmsg; \
+	     cmsg = CMSG_NXTHDR(msg, cmsg))
+
+/*
+ *	Get the next cmsg header
+ *
+ *	PLEASE, do not touch this function. If you think, that it is
+ *	incorrect, grep kernel sources and think about consequences
+ *	before trying to improve it.
+ *
+ *	Now it always returns valid, not truncated ancillary object
+ *	HEADER. But caller still MUST check, that cmsg->cmsg_len is
+ *	inside range, given by msg->msg_controllen before using
+ *	ancillary object DATA.				--ANK (980731)
+ */
+
+static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size,
+					       struct cmsghdr *__cmsg)
+{
+	struct cmsghdr * __ptr;
+
+	__ptr = (struct cmsghdr*)(((unsigned char *) __cmsg) +  CMSG_ALIGN(__cmsg->cmsg_len));
+	if ((unsigned long)((char*)(__ptr+1) - (char *) __ctl) > __size)
+		return (struct cmsghdr *)0;
+
+	return __ptr;
+}
+
+static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__cmsg)
+{
+	return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
+}
+
+static inline size_t msg_data_left(struct msghdr *msg)
+{
+	return iov_iter_count(&msg->msg_iter);
+}
+
+/* "Socket"-level control message types: */
+
+#define	SCM_RIGHTS	0x01		/* rw: access rights (array of int) */
+#define SCM_CREDENTIALS 0x02		/* rw: struct ucred		*/
+#define SCM_SECURITY	0x03		/* rw: security label		*/
+
+struct ucred {
+	__u32	pid;
+	__u32	uid;
+	__u32	gid;
+};
+
+/* Supported address families. */
+#define AF_UNSPEC	0
+#define AF_UNIX		1	/* Unix domain sockets 		*/
+#define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
+#define AF_INET		2	/* Internet IP Protocol 	*/
+#define AF_AX25		3	/* Amateur Radio AX.25 		*/
+#define AF_IPX		4	/* Novell IPX 			*/
+#define AF_APPLETALK	5	/* AppleTalk DDP 		*/
+#define AF_NETROM	6	/* Amateur Radio NET/ROM 	*/
+#define AF_BRIDGE	7	/* Multiprotocol bridge 	*/
+#define AF_ATMPVC	8	/* ATM PVCs			*/
+#define AF_X25		9	/* Reserved for X.25 project 	*/
+#define AF_INET6	10	/* IP version 6			*/
+#define AF_ROSE		11	/* Amateur Radio X.25 PLP	*/
+#define AF_DECnet	12	/* Reserved for DECnet project	*/
+#define AF_NETBEUI	13	/* Reserved for 802.2LLC project*/
+#define AF_SECURITY	14	/* Security callback pseudo AF */
+#define AF_KEY		15      /* PF_KEY key management API */
+#define AF_NETLINK	16
+#define AF_ROUTE	AF_NETLINK /* Alias to emulate 4.4BSD */
+#define AF_PACKET	17	/* Packet family		*/
+#define AF_ASH		18	/* Ash				*/
+#define AF_ECONET	19	/* Acorn Econet			*/
+#define AF_ATMSVC	20	/* ATM SVCs			*/
+#define AF_RDS		21	/* RDS sockets 			*/
+#define AF_SNA		22	/* Linux SNA Project (nutters!) */
+#define AF_IRDA		23	/* IRDA sockets			*/
+#define AF_PPPOX	24	/* PPPoX sockets		*/
+#define AF_WANPIPE	25	/* Wanpipe API Sockets */
+#define AF_LLC		26	/* Linux LLC			*/
+#define AF_IB		27	/* Native InfiniBand address	*/
+#define AF_MPLS		28	/* MPLS */
+#define AF_CAN		29	/* Controller Area Network      */
+#define AF_TIPC		30	/* TIPC sockets			*/
+#define AF_BLUETOOTH	31	/* Bluetooth sockets 		*/
+#define AF_IUCV		32	/* IUCV sockets			*/
+#define AF_RXRPC	33	/* RxRPC sockets 		*/
+#define AF_ISDN		34	/* mISDN sockets 		*/
+#define AF_PHONET	35	/* Phonet sockets		*/
+#define AF_IEEE802154	36	/* IEEE802154 sockets		*/
+#define AF_CAIF		37	/* CAIF sockets			*/
+#define AF_ALG		38	/* Algorithm sockets		*/
+#define AF_NFC		39	/* NFC sockets			*/
+#define AF_VSOCK	40	/* vSockets			*/
+#define AF_KCM		41	/* Kernel Connection Multiplexor*/
+#define AF_QIPCRTR	42	/* Qualcomm IPC Router          */
+#define AF_SMC		43	/* smc sockets: reserve number for
+				 * PF_SMC protocol family that
+				 * reuses AF_INET address family
+				 */
+#define AF_XDP		44	/* XDP sockets			*/
+
+#define AF_MAX		45	/* For now.. */
+
+/* Protocol families, same as address families. */
+#define PF_UNSPEC	AF_UNSPEC
+#define PF_UNIX		AF_UNIX
+#define PF_LOCAL	AF_LOCAL
+#define PF_INET		AF_INET
+#define PF_AX25		AF_AX25
+#define PF_IPX		AF_IPX
+#define PF_APPLETALK	AF_APPLETALK
+#define	PF_NETROM	AF_NETROM
+#define PF_BRIDGE	AF_BRIDGE
+#define PF_ATMPVC	AF_ATMPVC
+#define PF_X25		AF_X25
+#define PF_INET6	AF_INET6
+#define PF_ROSE		AF_ROSE
+#define PF_DECnet	AF_DECnet
+#define PF_NETBEUI	AF_NETBEUI
+#define PF_SECURITY	AF_SECURITY
+#define PF_KEY		AF_KEY
+#define PF_NETLINK	AF_NETLINK
+#define PF_ROUTE	AF_ROUTE
+#define PF_PACKET	AF_PACKET
+#define PF_ASH		AF_ASH
+#define PF_ECONET	AF_ECONET
+#define PF_ATMSVC	AF_ATMSVC
+#define PF_RDS		AF_RDS
+#define PF_SNA		AF_SNA
+#define PF_IRDA		AF_IRDA
+#define PF_PPPOX	AF_PPPOX
+#define PF_WANPIPE	AF_WANPIPE
+#define PF_LLC		AF_LLC
+#define PF_IB		AF_IB
+#define PF_MPLS		AF_MPLS
+#define PF_CAN		AF_CAN
+#define PF_TIPC		AF_TIPC
+#define PF_BLUETOOTH	AF_BLUETOOTH
+#define PF_IUCV		AF_IUCV
+#define PF_RXRPC	AF_RXRPC
+#define PF_ISDN		AF_ISDN
+#define PF_PHONET	AF_PHONET
+#define PF_IEEE802154	AF_IEEE802154
+#define PF_CAIF		AF_CAIF
+#define PF_ALG		AF_ALG
+#define PF_NFC		AF_NFC
+#define PF_VSOCK	AF_VSOCK
+#define PF_KCM		AF_KCM
+#define PF_QIPCRTR	AF_QIPCRTR
+#define PF_SMC		AF_SMC
+#define PF_XDP		AF_XDP
+#define PF_MAX		AF_MAX
+
+/* Maximum queue length specifiable by listen.  */
+#define SOMAXCONN	4096
+
+/* Flags we can use with send/ and recv.
+   Added those for 1003.1g not all are supported yet
+ */
+
+#define MSG_OOB		1
+#define MSG_PEEK	2
+#define MSG_DONTROUTE	4
+#define MSG_TRYHARD     4       /* Synonym for MSG_DONTROUTE for DECnet */
+#define MSG_CTRUNC	8
+#define MSG_PROBE	0x10	/* Do not send. Only probe path f.e. for MTU */
+#define MSG_TRUNC	0x20
+#define MSG_DONTWAIT	0x40	/* Nonblocking io		 */
+#define MSG_EOR         0x80	/* End of record */
+#define MSG_WAITALL	0x100	/* Wait for a full request */
+#define MSG_FIN         0x200
+#define MSG_SYN		0x400
+#define MSG_CONFIRM	0x800	/* Confirm path validity */
+#define MSG_RST		0x1000
+#define MSG_ERRQUEUE	0x2000	/* Fetch message from error queue */
+#define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */
+#define MSG_MORE	0x8000	/* Sender will send more */
+#define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
+#define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
+#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
+#define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
+#define MSG_EOF         MSG_FIN
+#define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
+#define MSG_SENDPAGE_DECRYPTED	0x100000 /* sendpage() internal : page may carry
+					  * plain text and require encryption
+					  */
+
+#define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
+#define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
+#define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exec for file
+					   descriptor received through
+					   SCM_RIGHTS */
+#if defined(CONFIG_COMPAT)
+#define MSG_CMSG_COMPAT	0x80000000	/* This message needs 32 bit fixups */
+#else
+#define MSG_CMSG_COMPAT	0		/* We never have 32 bit fixups */
+#endif
+
+
+/* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
+#define SOL_IP		0
+/* #define SOL_ICMP	1	No-no-no! Due to Linux :-) we cannot use SOL_ICMP=1 */
+#define SOL_TCP		6
+#define SOL_UDP		17
+#define SOL_IPV6	41
+#define SOL_ICMPV6	58
+#define SOL_SCTP	132
+#define SOL_UDPLITE	136     /* UDP-Lite (RFC 3828) */
+#define SOL_RAW		255
+#define SOL_IPX		256
+#define SOL_AX25	257
+#define SOL_ATALK	258
+#define SOL_NETROM	259
+#define SOL_ROSE	260
+#define SOL_DECNET	261
+#define	SOL_X25		262
+#define SOL_PACKET	263
+#define SOL_ATM		264	/* ATM layer (cell level) */
+#define SOL_AAL		265	/* ATM Adaption Layer (packet level) */
+#define SOL_IRDA        266
+#define SOL_NETBEUI	267
+#define SOL_LLC		268
+#define SOL_DCCP	269
+#define SOL_NETLINK	270
+#define SOL_TIPC	271
+#define SOL_RXRPC	272
+#define SOL_PPPOL2TP	273
+#define SOL_BLUETOOTH	274
+#define SOL_PNPIPE	275
+#define SOL_RDS		276
+#define SOL_IUCV	277
+#define SOL_CAIF	278
+#define SOL_ALG		279
+#define SOL_NFC		280
+#define SOL_KCM		281
+#define SOL_TLS		282
+#define SOL_XDP		283
+
+/* IPX options */
+#define IPX_TYPE	1
+
+extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
+extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+
+struct timespec64;
+struct __kernel_timespec;
+struct old_timespec32;
+
+struct scm_timestamping_internal {
+	struct timespec64 ts[3];
+};
+
+extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss);
+extern void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss);
+
+/* The __sys_...msg variants allow MSG_CMSG_COMPAT iff
+ * forbid_cmsg_compat==false
+ */
+extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg,
+			  unsigned int flags, bool forbid_cmsg_compat);
+extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg,
+			  unsigned int flags, bool forbid_cmsg_compat);
+extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg,
+			  unsigned int vlen, unsigned int flags,
+			  struct __kernel_timespec __user *timeout,
+			  struct old_timespec32 __user *timeout32);
+extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
+			  unsigned int vlen, unsigned int flags,
+			  bool forbid_cmsg_compat);
+extern long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg,
+			       unsigned int flags);
+extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
+			       struct user_msghdr __user *umsg,
+			       struct sockaddr __user *uaddr,
+			       unsigned int flags);
+extern int sendmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct iovec **iov);
+extern int recvmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct sockaddr __user **uaddr,
+			       struct iovec **iov);
+extern int __copy_msghdr_from_user(struct msghdr *kmsg,
+				   struct user_msghdr __user *umsg,
+				   struct sockaddr __user **save_addr,
+				   struct iovec __user **uiov, size_t *nsegs);
+
+/* helpers which do the actual work for syscalls */
+extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
+			  unsigned int flags, struct sockaddr __user *addr,
+			  int __user *addr_len);
+extern int __sys_sendto(int fd, void __user *buff, size_t len,
+			unsigned int flags, struct sockaddr __user *addr,
+			int addr_len);
+extern int __sys_accept4_file(struct file *file, unsigned file_flags,
+			struct sockaddr __user *upeer_sockaddr,
+			 int __user *upeer_addrlen, int flags,
+			 unsigned long nofile);
+extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+			 int __user *upeer_addrlen, int flags);
+extern int __sys_socket(int family, int type, int protocol);
+extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
+			      int addrlen, int file_flags);
+extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
+			 int addrlen);
+extern int __sys_listen(int fd, int backlog);
+extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
+			     int __user *usockaddr_len);
+extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+			     int __user *usockaddr_len);
+extern int __sys_socketpair(int family, int type, int protocol,
+			    int __user *usockvec);
+extern int __sys_shutdown(int fd, int how);
+
+extern struct ns_common *get_net_ns(struct ns_common *ns);
+#endif /* _LINUX_SOCKET_H */
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index e0c13e6..cd11063 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -7,14 +7,7 @@
 #include <sys/un.h>
 #include <arpa/inet.h>
 
-static const char *socket_families[] = {
-	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
-	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
-	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
-	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
-	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
-	"ALG", "NFC", "VSOCK",
-};
+#include "trace/beauty/generated/socket_arrays.c"
 DEFINE_STRARRAY(socket_families, "PF_");
 
 static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh
new file mode 100755
index 0000000..3820e5c
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+# This one uses a copy from the kernel sources headers that is in a
+# place used just for these tools/perf/beauty/ usage, we shouldn't not
+# put it in tools/include/linux otherwise they would be used in the
+# normal compiler building process and would drag needless stuff from the
+# kernel.
+
+# When what these scripts need is already in tools/include/ then use it,
+# otherwise grab and check the copy from the kernel sources just for these
+# string table building scripts.
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/
+
+printf "static const char *socket_families[] = {\n"
+# #define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
+regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*'
+
+egrep $regex ${header_dir}/socket.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[%s] = \"%s\",\n" | \
+	egrep -v "\"(UNIX|MAX)\""
+printf "};\n"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 494626e..cd5e419 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -117,6 +117,7 @@
 perf-y += parse-branch-options.o
 perf-y += dump-insn.o
 perf-y += parse-regs-options.o
+perf-y += parse-sublevel-options.o
 perf-y += term.o
 perf-y += help-unknown-cmd.o
 perf-y += mem-events.o
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index c076fc7..31207b6 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -31,6 +31,10 @@
 #include "probe-file.h"
 #include "strlist.h"
 
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
@@ -636,6 +640,21 @@
 	if (realname && access(realname, R_OK))
 		zfree(&realname);
 	nsinfo__mountns_exit(&nsc);
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+        if (realname == NULL) {
+                debuginfod_client* c = debuginfod_begin();
+                if (c != NULL) {
+                        int fd = debuginfod_find_debuginfo(c,
+                                                           (const unsigned char*)sbuild_id, 0,
+                                                           &realname);
+                        if (fd >= 0)
+                                close(fd); /* retaining reference by realname */
+                        debuginfod_end(c);
+                }
+        }
+#endif
+
 out:
 	free(debugfile);
 	return realname;
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index adb6567..5cda556 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -20,6 +20,7 @@
 #include "target.h"
 #include "ui/helpline.h"
 #include "ui/ui.h"
+#include "util/parse-sublevel-options.h"
 
 #include <linux/ctype.h>
 
@@ -173,65 +174,37 @@
 		     trace_event_printer, event);
 }
 
-static struct debug_variable {
-	const char *name;
-	int *ptr;
-} debug_variables[] = {
-	{ .name = "verbose",		.ptr = &verbose },
-	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
-	{ .name = "stderr",		.ptr = &redirect_to_stderr},
-	{ .name = "data-convert",	.ptr = &debug_data_convert },
-	{ .name = "perf-event-open",	.ptr = &debug_peo_args },
+static struct sublevel_option debug_opts[] = {
+	{ .name = "verbose",		.value_ptr = &verbose },
+	{ .name = "ordered-events",	.value_ptr = &debug_ordered_events},
+	{ .name = "stderr",		.value_ptr = &redirect_to_stderr},
+	{ .name = "data-convert",	.value_ptr = &debug_data_convert },
+	{ .name = "perf-event-open",	.value_ptr = &debug_peo_args },
 	{ .name = NULL, }
 };
 
 int perf_debug_option(const char *str)
 {
-	struct debug_variable *var = &debug_variables[0];
-	char *vstr, *s = strdup(str);
-	int v = 1;
+	int ret;
 
-	vstr = strchr(s, '=');
-	if (vstr)
-		*vstr++ = 0;
+	ret = perf_parse_sublevel_options(str, debug_opts);
+	if (ret)
+		return ret;
 
-	while (var->name) {
-		if (!strcmp(s, var->name))
-			break;
-		var++;
-	}
+	/* Allow only verbose value in range (0, 10), otherwise set 0. */
+	verbose = (verbose < 0) || (verbose > 10) ? 0 : verbose;
 
-	if (!var->name) {
-		pr_err("Unknown debug variable name '%s'\n", s);
-		free(s);
-		return -1;
-	}
-
-	if (vstr) {
-		v = atoi(vstr);
-		/*
-		 * Allow only values in range (0, 10),
-		 * otherwise set 0.
-		 */
-		v = (v < 0) || (v > 10) ? 0 : v;
-	}
-
-	if (quiet)
-		v = -1;
-
-	*var->ptr = v;
-	free(s);
 	return 0;
 }
 
 int perf_quiet_option(void)
 {
-	struct debug_variable *var = &debug_variables[0];
+	struct sublevel_option *opt = &debug_opts[0];
 
 	/* disable all debug messages */
-	while (var->name) {
-		*var->ptr = -1;
-		var++;
+	while (opt->name) {
+		*opt->value_ptr = -1;
+		opt++;
 	}
 
 	return 0;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index be991cb..5a3b475 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1265,7 +1265,7 @@
 		dso->has_build_id = 0;
 		dso->has_srcline = 1;
 		dso->a2l_fails = 1;
-		dso->kernel = DSO_TYPE_USER;
+		dso->kernel = DSO_SPACE__USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		dso->comp = COMP_ID__NONE;
 		RB_CLEAR_NODE(&dso->rb_node);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 31c3a92..8ad17f3 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -46,10 +46,10 @@
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 
-enum dso_kernel_type {
-	DSO_TYPE_USER = 0,
-	DSO_TYPE_KERNEL,
-	DSO_TYPE_GUEST_KERNEL
+enum dso_space_type {
+	DSO_SPACE__USER = 0,
+	DSO_SPACE__KERNEL,
+	DSO_SPACE__KERNEL_GUEST
 };
 
 enum dso_swap_type {
@@ -160,7 +160,7 @@
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
-	enum dso_kernel_type	kernel;
+	enum dso_space_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
 	enum dso_binary_type	binary_type;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 251faa9..9cf4efd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2056,7 +2056,7 @@
 	struct machine *machine;
 	u16 cpumode;
 	struct dso *dso;
-	enum dso_kernel_type dso_type;
+	enum dso_space_type dso_space;
 
 	machine = perf_session__findnew_machine(session, bev->pid);
 	if (!machine)
@@ -2066,14 +2066,14 @@
 
 	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
-		dso_type = DSO_TYPE_KERNEL;
+		dso_space = DSO_SPACE__KERNEL;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		dso_type = DSO_TYPE_GUEST_KERNEL;
+		dso_space = DSO_SPACE__KERNEL_GUEST;
 		break;
 	case PERF_RECORD_MISC_USER:
 	case PERF_RECORD_MISC_GUEST_USER:
-		dso_type = DSO_TYPE_USER;
+		dso_space = DSO_SPACE__USER;
 		break;
 	default:
 		goto out;
@@ -2085,14 +2085,13 @@
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (dso_type != DSO_TYPE_USER) {
+		if (dso_space != DSO_SPACE__USER) {
 			struct kmod_path m = { .name = NULL, };
 
 			if (!kmod_path__parse_name(&m, filename) && m.kmod)
 				dso__set_module_info(dso, &m, machine);
-			else
-				dso->kernel = dso_type;
 
+			dso->kernel = dso_space;
 			free(m.name);
 		}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 96af544..208b813e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -703,7 +703,7 @@
 
 		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
-		dso->kernel = DSO_TYPE_KERNEL;
+		dso->kernel = DSO_SPACE__KERNEL;
 	}
 
 	dso__get(dso);
@@ -753,7 +753,7 @@
 		struct dso *dso = dso__new(event->ksymbol.name);
 
 		if (dso) {
-			dso->kernel = DSO_TYPE_KERNEL;
+			dso->kernel = DSO_SPACE__KERNEL;
 			map = map__new2(0, dso);
 		}
 
@@ -971,14 +971,14 @@
 			vmlinux_name = symbol_conf.vmlinux_name;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
-						 "[kernel]", DSO_TYPE_KERNEL);
+						 "[kernel]", DSO_SPACE__KERNEL);
 	} else {
 		if (symbol_conf.default_guest_vmlinux_name)
 			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[guest.kernel]",
-						 DSO_TYPE_GUEST_KERNEL);
+						 DSO_SPACE__KERNEL_GUEST);
 	}
 
 	if (kernel != NULL && (!kernel->has_build_id))
@@ -1606,7 +1606,7 @@
 					      union perf_event *event)
 {
 	struct map *map;
-	enum dso_kernel_type kernel_type;
+	enum dso_space_type dso_space;
 	bool is_kernel_mmap;
 
 	/* If we have maps from kcore then we do not need or want any others */
@@ -1614,9 +1614,9 @@
 		return 0;
 
 	if (machine__is_host(machine))
-		kernel_type = DSO_TYPE_KERNEL;
+		dso_space = DSO_SPACE__KERNEL;
 	else
-		kernel_type = DSO_TYPE_GUEST_KERNEL;
+		dso_space = DSO_SPACE__KERNEL_GUEST;
 
 	is_kernel_mmap = memcmp(event->mmap.filename,
 				machine->mmap_name,
@@ -1676,7 +1676,7 @@
 		if (kernel == NULL)
 			goto out_problem;
 
-		kernel->kernel = kernel_type;
+		kernel->kernel = dso_space;
 		if (__machine__create_kernel_maps(machine, kernel) < 0) {
 			dso__put(kernel);
 			goto out_problem;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f9dc8c5..1d72108 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -486,7 +486,7 @@
 	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
 	 * but all kernel modules are ET_REL, so won't get here.
 	 */
-	if (map->dso->kernel == DSO_TYPE_USER)
+	if (map->dso->kernel == DSO_SPACE__USER)
 		return rip + map->dso->text_offset;
 
 	return map->unmap_ip(map, rip) - map->reloc;
@@ -516,7 +516,7 @@
 	 * kernel modules also have DSO_TYPE_USER in dso->kernel,
 	 * but all kernel modules are ET_REL, so won't get here.
 	 */
-	if (map->dso->kernel == DSO_TYPE_USER)
+	if (map->dso->kernel == DSO_SPACE__USER)
 		return map->unmap_ip(map, ip - map->dso->text_offset);
 
 	return ip + map->reloc;
diff --git a/tools/perf/util/parse-sublevel-options.c b/tools/perf/util/parse-sublevel-options.c
new file mode 100644
index 0000000..a841d17
--- /dev/null
+++ b/tools/perf/util/parse-sublevel-options.c
@@ -0,0 +1,70 @@
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <stdio.h>
+
+#include "util/debug.h"
+#include "util/parse-sublevel-options.h"
+
+static int parse_one_sublevel_option(const char *str,
+				     struct sublevel_option *opts)
+{
+	struct sublevel_option *opt = opts;
+	char *vstr, *s = strdup(str);
+	int v = 1;
+
+	if (!s) {
+		pr_err("no memory\n");
+		return -1;
+	}
+
+	vstr = strchr(s, '=');
+	if (vstr)
+		*vstr++ = 0;
+
+	while (opt->name) {
+		if (!strcmp(s, opt->name))
+			break;
+		opt++;
+	}
+
+	if (!opt->name) {
+		pr_err("Unknown option name '%s'\n", s);
+		free(s);
+		return -1;
+	}
+
+	if (vstr)
+		v = atoi(vstr);
+
+	*opt->value_ptr = v;
+	free(s);
+	return 0;
+}
+
+/* parse options like --foo a=<n>,b,c... */
+int perf_parse_sublevel_options(const char *str, struct sublevel_option *opts)
+{
+	char *s = strdup(str);
+	char *p = NULL;
+	int ret;
+
+	if (!s) {
+		pr_err("no memory\n");
+		return -1;
+	}
+
+	p = strtok(s, ",");
+	while (p) {
+		ret = parse_one_sublevel_option(p, opts);
+		if (ret) {
+			free(s);
+			return ret;
+		}
+
+		p = strtok(NULL, ",");
+	}
+
+	free(s);
+	return 0;
+}
diff --git a/tools/perf/util/parse-sublevel-options.h b/tools/perf/util/parse-sublevel-options.h
new file mode 100644
index 0000000..9b9efcc
--- /dev/null
+++ b/tools/perf/util/parse-sublevel-options.h
@@ -0,0 +1,11 @@
+#ifndef _PERF_PARSE_SUBLEVEL_OPTIONS_H
+#define _PERF_PARSE_SUBLEVEL_OPTIONS_H
+
+struct sublevel_option {
+	const char *name;
+	int *value_ptr;
+};
+
+int perf_parse_sublevel_options(const char *str, struct sublevel_option *opts);
+
+#endif
\ No newline at end of file
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 5e43054..8cc4b00 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -789,7 +789,7 @@
 	if (ss->opdshdr.sh_type != SHT_PROGBITS)
 		ss->opdsec = NULL;
 
-	if (dso->kernel == DSO_TYPE_USER)
+	if (dso->kernel == DSO_SPACE__USER)
 		ss->adjust_symbols = true;
 	else
 		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
@@ -872,7 +872,7 @@
 		 * kallsyms and identity maps.  Overwrite it to
 		 * map to the kernel dso.
 		 */
-		if (*remap_kernel && dso->kernel) {
+		if (*remap_kernel && dso->kernel && !kmodule) {
 			*remap_kernel = false;
 			map->start = shdr->sh_addr + ref_reloc(kmap);
 			map->end = map->start + shdr->sh_size;
@@ -1068,7 +1068,7 @@
 	 * Initial kernel and module mappings do not map to the dso.
 	 * Flag the fixups.
 	 */
-	if (dso->kernel || kmodule) {
+	if (dso->kernel) {
 		remap_kernel = true;
 		adjust_kernel_syms = dso->adjust_symbols;
 	}
@@ -1130,7 +1130,7 @@
 		    (sym.st_value & 1))
 			--sym.st_value;
 
-		if (dso->kernel || kmodule) {
+		if (dso->kernel) {
 			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
 						       section_name, adjust_kernel_syms, kmodule, &remap_kernel))
 				goto out_elf_end;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 053468f..1f5fcb8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -808,7 +808,7 @@
 
 			if (strcmp(curr_map->dso->short_name, module)) {
 				if (curr_map != initial_map &&
-				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
+				    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
 				    machine__is_default_guest(machine)) {
 					/*
 					 * We assume all symbols of a module are
@@ -865,7 +865,7 @@
 				goto add_symbol;
 			}
 
-			if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 				snprintf(dso_name, sizeof(dso_name),
 					"[guest.kernel].%d",
 					kernel_range++);
@@ -909,7 +909,7 @@
 	}
 
 	if (curr_map != initial_map &&
-	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
+	    dso->kernel == DSO_SPACE__KERNEL_GUEST &&
 	    machine__is_default_guest(kmaps->machine)) {
 		dso__set_loaded(curr_map->dso);
 	}
@@ -1387,7 +1387,7 @@
 	 * Set the data type and long name so that kcore can be read via
 	 * dso__data_read_addr().
 	 */
-	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 		dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
 	else
 		dso->binary_type = DSO_BINARY_TYPE__KCORE;
@@ -1451,7 +1451,7 @@
 	symbols__fixup_end(&dso->symbols);
 	symbols__fixup_duplicate(&dso->symbols);
 
-	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 	else
 		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
@@ -1537,17 +1537,17 @@
 	case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO:
 	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
-		return !kmod && dso->kernel == DSO_TYPE_USER;
+		return !kmod && dso->kernel == DSO_SPACE__USER;
 
 	case DSO_BINARY_TYPE__KALLSYMS:
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__KCORE:
-		return dso->kernel == DSO_TYPE_KERNEL;
+		return dso->kernel == DSO_SPACE__KERNEL;
 
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_KCORE:
-		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
+		return dso->kernel == DSO_SPACE__KERNEL_GUEST;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
 	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
@@ -1650,9 +1650,9 @@
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
 	if (dso->kernel && !kmod) {
-		if (dso->kernel == DSO_TYPE_KERNEL)
+		if (dso->kernel == DSO_SPACE__KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
-		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		else if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 			ret = dso__load_guest_kernel_sym(dso, map);
 
 		machine = map__kmaps(map)->machine;
@@ -1882,7 +1882,7 @@
 	else
 		symbol__join_symfs(symfs_vmlinux, vmlinux);
 
-	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 	else
 		symtab_type = DSO_BINARY_TYPE__VMLINUX;
@@ -1894,7 +1894,7 @@
 	symsrc__destroy(&ss);
 
 	if (err > 0) {
-		if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+		if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
 			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 		else
 			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;