Merge tag 'perf-tools-for-v5.19-2022-05-28' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:

 - Add BPF based off-CPU profiling

 - Improvements for system wide recording, specially for Intel PT

 - Improve DWARF unwinding on arm64

 - Support Arm CoreSight trace data disassembly in 'perf script' python

 - Fix build with new libbpf version, related to supporting older
   versions of distro released libbpf packages

 - Fix event syntax error caused by ExtSel in the JSON events infra

 - Use stdio interface if slang is not supported in 'perf c2c'

 - Add 'perf test' checking for perf stat CSV output

 - Sync the msr-index.h copy with the kernel sources

* tag 'perf-tools-for-v5.19-2022-05-28' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (38 commits)
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf scripts python: Support Arm CoreSight trace data disassembly
  perf scripting python: Expose dso and map information
  perf jevents: Fix event syntax error caused by ExtSel
  perf tools arm64: Add support for VG register
  perf unwind arm64: Decouple Libunwind register names from Perf
  perf unwind: Use dynamic register set for DWARF unwind
  perf tools arm64: Copy perf_regs.h from the kernel
  perf unwind arm64: Use perf's copy of kernel headers
  perf c2c: Use stdio interface if slang is not supported
  perf test: Add a basic offcpu profiling test
  perf record: Add cgroup support for off-cpu profiling
  perf record: Handle argument change in sched_switch
  perf record: Implement basic filtering for off-cpu
  perf record: Enable off-cpu analysis with BPF
  perf report: Do not extend sample type of bpf-output event
  perf test: Add checking for perf stat CSV output.
  perf tools: Allow system-wide events to keep their own threads
  perf tools: Allow system-wide events to keep their own CPUs
  libperf evsel: Add comments for booleans
  ...

44 files changed, 1594 insertions, 197 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
index d54daafa89e3..fd157f46727e 100644
--- a/tools/arch/arm64/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -36,6 +36,11 @@ enum perf_event_arm_regs {
 	PERF_REG_ARM64_LR,
 	PERF_REG_ARM64_SP,
 	PERF_REG_ARM64_PC,
-	PERF_REG_ARM64_MAX,
+
+	/* Extended/pseudo registers */
+	PERF_REG_ARM64_VG = 46, // SVE Vector Granule
+
+	PERF_REG_ARM64_MAX = PERF_REG_ARM64_PC + 1,
+	PERF_REG_ARM64_EXTENDED_MAX = PERF_REG_ARM64_VG + 1
 };
 #endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ee15311b6be1..403e83b4adc8 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -76,6 +76,8 @@
 
 /* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */
 #define MSR_IA32_CORE_CAPS			  0x000000cf
+#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT	  2
+#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS	  BIT(MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT)
 #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT  5
 #define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT	  BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT)
 
@@ -154,6 +156,11 @@
 #define MSR_IA32_POWER_CTL		0x000001fc
 #define MSR_IA32_POWER_CTL_BIT_EE	19
 
+/* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */
+#define MSR_INTEGRITY_CAPS			0x000002d9
+#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
+#define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+
 #define MSR_LBR_NHM_FROM		0x00000680
 #define MSR_LBR_NHM_TO			0x000006c0
 #define MSR_LBR_CORE_FROM		0x00000040
@@ -312,6 +319,7 @@
 
 /* Run Time Average Power Limiting (RAPL) Interface */
 
+#define MSR_VR_CURRENT_CONFIG	0x00000601
 #define MSR_RAPL_POWER_UNIT		0x00000606
 
 #define MSR_PKG_POWER_LIMIT		0x00000610
@@ -502,8 +510,10 @@
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
 #define MSR_AMD64_SEV_ES_ENABLED_BIT	1
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT	2
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
@@ -524,6 +534,11 @@
 #define AMD_CPPC_DES_PERF(x)		(((x) & 0xff) << 16)
 #define AMD_CPPC_ENERGY_PERF_PREF(x)	(((x) & 0xff) << 24)
 
+/* AMD Performance Counter Global Status and Control MSRs */
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS	0xc0000300
+#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
+#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
@@ -688,6 +703,10 @@
 #define MSR_IA32_PERF_CTL		0x00000199
 #define INTEL_PERF_CTL_MASK		0xffff
 
+/* AMD Branch Sampling configuration */
+#define MSR_AMD_DBG_EXTN_CFG		0xc000010f
+#define MSR_AMD_SAMP_BR_FROM		0xc0010300
+
 #define MSR_IA32_MPERF			0x000000e7
 #define MSR_IA32_APERF			0x000000e8
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index c6a48d0ef9ff..888a0421d43b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -99,6 +99,10 @@ FEATURE_TESTS_EXTRA :=                  \
          clang                          \
          libbpf                         \
          libbpf-btf__load_from_kernel_by_id \
+         libbpf-bpf_prog_load           \
+         libbpf-bpf_object__next_program \
+         libbpf-bpf_object__next_map    \
+         libbpf-bpf_create_map		\
          libpfm4                        \
          libdebuginfod			\
          clang-bpf-co-re
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index cb4a2a4fa2e4..7c2a17e23c30 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -58,6 +58,11 @@ FILES=                                          \
          test-bpf.bin                           \
          test-libbpf.bin                        \
          test-libbpf-btf__load_from_kernel_by_id.bin	\
+         test-libbpf-bpf_prog_load.bin          \
+         test-libbpf-bpf_map_create.bin		\
+         test-libbpf-bpf_object__next_program.bin \
+         test-libbpf-bpf_object__next_map.bin   \
+         test-libbpf-btf__raw_data.bin          \
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
@@ -291,6 +296,21 @@ $(OUTPUT)test-libbpf.bin:
 $(OUTPUT)test-libbpf-btf__load_from_kernel_by_id.bin:
 	$(BUILD) -lbpf
 
+$(OUTPUT)test-libbpf-bpf_prog_load.bin:
+	$(BUILD) -lbpf
+
+$(OUTPUT)test-libbpf-bpf_map_create.bin:
+	$(BUILD) -lbpf
+
+$(OUTPUT)test-libbpf-bpf_object__next_program.bin:
+	$(BUILD) -lbpf
+
+$(OUTPUT)test-libbpf-bpf_object__next_map.bin:
+	$(BUILD) -lbpf
+
+$(OUTPUT)test-libbpf-btf__raw_data.bin:
+	$(BUILD) -lbpf
+
 $(OUTPUT)test-sdt.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-libbpf-bpf_map_create.c b/tools/build/feature/test-libbpf-bpf_map_create.c
new file mode 100644
index 000000000000..b9f550e332c8
--- /dev/null
+++ b/tools/build/feature/test-libbpf-bpf_map_create.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/bpf.h>
+
+int main(void)
+{
+	return bpf_map_create(0 /* map_type */, NULL /* map_name */, 0, /* key_size */,
+			      0 /* value_size */, 0 /* max_entries */, NULL /* opts */);
+}
diff --git a/tools/build/feature/test-libbpf-bpf_object__next_map.c b/tools/build/feature/test-libbpf-bpf_object__next_map.c
new file mode 100644
index 000000000000..64adb519e97e
--- /dev/null
+++ b/tools/build/feature/test-libbpf-bpf_object__next_map.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/libbpf.h>
+
+int main(void)
+{
+	bpf_object__next_map(NULL /* obj */, NULL /* prev */);
+	return 0;
+}
diff --git a/tools/build/feature/test-libbpf-bpf_object__next_program.c b/tools/build/feature/test-libbpf-bpf_object__next_program.c
new file mode 100644
index 000000000000..8bf4fd26b545
--- /dev/null
+++ b/tools/build/feature/test-libbpf-bpf_object__next_program.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/libbpf.h>
+
+int main(void)
+{
+	bpf_object__next_program(NULL /* obj */, NULL /* prev */);
+	return 0;
+}
diff --git a/tools/build/feature/test-libbpf-bpf_prog_load.c b/tools/build/feature/test-libbpf-bpf_prog_load.c
new file mode 100644
index 000000000000..47f516d63ebc
--- /dev/null
+++ b/tools/build/feature/test-libbpf-bpf_prog_load.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/bpf.h>
+
+int main(void)
+{
+	return bpf_prog_load(0 /* prog_type */, NULL /* prog_name */,
+			     NULL /* license */, NULL /* insns */,
+			     0 /* insn_cnt */, NULL /* opts */);
+}
diff --git a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
index f7c084428735..a17647f7d5a4 100644
--- a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
+++ b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <bpf/libbpf.h>
+#include <bpf/btf.h>
 
 int main(void)
 {
-	return btf__load_from_kernel_by_id(20151128, NULL);
+	btf__load_from_kernel_by_id(20151128);
+	return 0;
 }
diff --git a/tools/build/feature/test-libbpf-btf__raw_data.c b/tools/build/feature/test-libbpf-btf__raw_data.c
new file mode 100644
index 000000000000..57da31dd7581
--- /dev/null
+++ b/tools/build/feature/test-libbpf-btf__raw_data.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/btf.h>
+
+int main(void)
+{
+	btf__raw_data(NULL /* btf_ro */, NULL /* size */);
+	return 0;
+}
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index ed66f2e38464..e6c98a6e3908 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -23,6 +23,7 @@
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <api/fd/array.h>
+#include "internal.h"
 
 void perf_evlist__init(struct perf_evlist *evlist)
 {
@@ -39,10 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	 * We already have cpus for evsel (via PMU sysfs) so
 	 * keep it, if there's no target cpu list defined.
 	 */
-	if (!evsel->own_cpus || evlist->has_user_cpus) {
-		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
-	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
+	if (!evsel->own_cpus ||
+	    (!evsel->system_wide && evlist->has_user_cpus) ||
+	    (!evsel->system_wide &&
+	     !evsel->requires_cpu &&
+	     perf_cpu_map__empty(evlist->user_requested_cpus))) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
@@ -50,8 +52,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
 	}
 
-	perf_thread_map__put(evsel->threads);
-	evsel->threads = perf_thread_map__get(evlist->threads);
+	if (!evsel->system_wide) {
+		perf_thread_map__put(evsel->threads);
+		evsel->threads = perf_thread_map__get(evlist->threads);
+	}
+
 	evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
 }
 
@@ -298,7 +303,7 @@ add:
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nr_cpus = perf_cpu_map__nr(evlist->user_requested_cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->all_cpus);
 	int nr_threads = perf_thread_map__nr(evlist->threads);
 	int nfds = 0;
 	struct perf_evsel *evsel;
@@ -428,9 +433,9 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_
 static int
 mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
-	       int thread, int *_output, int *_output_overwrite)
+	       int thread, int *_output, int *_output_overwrite, int *nr_mmaps)
 {
-	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -484,6 +489,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
 
+			*nr_mmaps += 1;
+
 			if (!idx)
 				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
@@ -513,34 +520,12 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 }
 
 static int
-mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
-		struct perf_mmap_param *mp)
-{
-	int thread;
-	int nr_threads = perf_thread_map__nr(evlist->threads);
-
-	for (thread = 0; thread < nr_threads; thread++) {
-		int output = -1;
-		int output_overwrite = -1;
-
-		if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread,
-				   &output, &output_overwrite))
-			goto out_unmap;
-	}
-
-	return 0;
-
-out_unmap:
-	perf_evlist__munmap(evlist);
-	return -1;
-}
-
-static int
 mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	     struct perf_mmap_param *mp)
 {
 	int nr_threads = perf_thread_map__nr(evlist->threads);
-	int nr_cpus    = perf_cpu_map__nr(evlist->user_requested_cpus);
+	int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);
+	int nr_mmaps = 0;
 	int cpu, thread;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -549,11 +534,14 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (mmap_per_evsel(evlist, ops, cpu, mp, cpu,
-					   thread, &output, &output_overwrite))
+					   thread, &output, &output_overwrite, &nr_mmaps))
 				goto out_unmap;
 		}
 	}
 
+	if (nr_mmaps != evlist->nr_mmaps)
+		pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps);
+
 	return 0;
 
 out_unmap:
@@ -565,9 +553,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 {
 	int nr_mmaps;
 
-	nr_mmaps = perf_cpu_map__nr(evlist->user_requested_cpus);
-	if (perf_cpu_map__empty(evlist->user_requested_cpus))
-		nr_mmaps = perf_thread_map__nr(evlist->threads);
+	/* One for each CPU */
+	nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
+	if (perf_cpu_map__empty(evlist->all_cpus)) {
+		/* Plus one for each thread */
+		nr_mmaps += perf_thread_map__nr(evlist->threads);
+		/* Minus the per-thread CPU (-1) */
+		nr_mmaps -= 1;
+	}
 
 	return nr_mmaps;
 }
@@ -577,7 +570,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_mmap_param *mp)
 {
 	struct perf_evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
 
 	if (!ops || !ops->get || !ops->mmap)
 		return -EINVAL;
@@ -596,9 +588,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
-	if (perf_cpu_map__empty(cpus))
-		return mmap_per_thread(evlist, ops, mp);
-
 	return mmap_per_cpu(evlist, ops, mp);
 }
 
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index cfc9ebd7968e..2a912a1f1989 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -49,7 +49,18 @@ struct perf_evsel {
 
 	/* parse modifier helper */
 	int			 nr_members;
+	/*
+	 * system_wide is for events that need to be on every CPU, irrespective
+	 * of user requested CPUs or threads. Map propagation will set cpus to
+	 * this event's own_cpus, whereby they will contribute to evlist
+	 * all_cpus.
+	 */
 	bool			 system_wide;
+	/*
+	 * Some events, for example uncore events, require a CPU.
+	 * i.e. it cannot be the 'any CPU' value of -1.
+	 */
+	bool			 requires_cpu;
 	int			 idx;
 };
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 465be4e62a17..b4e9ef7edfef 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -758,6 +758,16 @@ include::intel-hybrid.txt[]
 	If the URLs is not specified, the value of DEBUGINFOD_URLS
 	system environment variable is used.
 
+--off-cpu::
+	Enable off-cpu profiling with BPF.  The BPF program will collect
+	task scheduling information with (user) stacktrace and save them
+	as sample data of a software event named "offcpu-time".  The
+	sample period will have the time the task slept in nanoseconds.
+
+	Note that BPF can collect stack traces using frame pointer ("fp")
+	only, as of now.  So the applications built without the frame
+	pointer might see bogus addresses.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index e0304e70f182..73e0762092fe 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -573,11 +573,36 @@ ifndef NO_LIBELF
           ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1)
             CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
           endif
+          $(call feature_check,libbpf-bpf_prog_load)
+          ifeq ($(feature-libbpf-bpf_prog_load), 1)
+            CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
+          endif
+          $(call feature_check,libbpf-bpf_object__next_program)
+          ifeq ($(feature-libbpf-bpf_object__next_program), 1)
+            CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
+          endif
+          $(call feature_check,libbpf-bpf_object__next_map)
+          ifeq ($(feature-libbpf-bpf_object__next_map), 1)
+            CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
+          endif
+          $(call feature_check,libbpf-btf__raw_data)
+          ifeq ($(feature-libbpf-btf__raw_data), 1)
+            CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
+          endif
+          $(call feature_check,libbpf-bpf_map_create)
+          ifeq ($(feature-libbpf-bpf_map_create), 1)
+            CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE
+          endif
         else
           dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
         endif
       else
 	CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+        CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
+        CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
+        CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
+        CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
+        CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE
       endif
     endif
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 6e5aded855cc..8f738e11356d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1038,6 +1038,7 @@ SKEL_TMP_OUT := $(abspath $(SKEL_OUT)/.tmp)
 SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
+SKELETONS += $(SKEL_OUT)/off_cpu.skel.h
 
 $(SKEL_TMP_OUT) $(LIBBPF_OUTPUT):
 	$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 476b037eea1c..006692c9b040 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -2,13 +2,19 @@
 #include <errno.h>
 #include <regex.h>
 #include <string.h>
+#include <sys/auxv.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
+#include "../../../perf-sys.h"
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
 #include "../../../util/perf_regs.h"
 
+#ifndef HWCAP_SVE
+#define HWCAP_SVE	(1 << 22)
+#endif
+
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(x0, PERF_REG_ARM64_X0),
 	SMPL_REG(x1, PERF_REG_ARM64_X1),
@@ -43,6 +49,7 @@ const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(lr, PERF_REG_ARM64_LR),
 	SMPL_REG(sp, PERF_REG_ARM64_SP),
 	SMPL_REG(pc, PERF_REG_ARM64_PC),
+	SMPL_REG(vg, PERF_REG_ARM64_VG),
 	SMPL_REG_END
 };
 
@@ -131,3 +138,34 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 
 	return SDT_ARG_VALID;
 }
+
+uint64_t arch__user_reg_mask(void)
+{
+	struct perf_event_attr attr = {
+		.type                   = PERF_TYPE_HARDWARE,
+		.config                 = PERF_COUNT_HW_CPU_CYCLES,
+		.sample_type            = PERF_SAMPLE_REGS_USER,
+		.disabled               = 1,
+		.exclude_kernel         = 1,
+		.sample_period		= 1,
+		.sample_regs_user	= PERF_REGS_MASK
+	};
+	int fd;
+
+	if (getauxval(AT_HWCAP) & HWCAP_SVE)
+		attr.sample_regs_user |= SMPL_REG_MASK(PERF_REG_ARM64_VG);
+
+	/*
+	 * Check if the pmu supports perf extended regs, before
+	 * returning the register mask to sample.
+	 */
+	if (attr.sample_regs_user != PERF_REGS_MASK) {
+		event_attr_init(&attr);
+		fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+		if (fd != -1) {
+			close(fd);
+			return attr.sample_regs_user;
+		}
+	}
+	return PERF_REGS_MASK;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 5aecf88e3de6..871af5992298 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -10,77 +10,8 @@
 
 int LIBUNWIND__ARCH_REG_ID(int regnum)
 {
-	switch (regnum) {
-	case UNW_AARCH64_X0:
-		return PERF_REG_ARM64_X0;
-	case UNW_AARCH64_X1:
-		return PERF_REG_ARM64_X1;
-	case UNW_AARCH64_X2:
-		return PERF_REG_ARM64_X2;
-	case UNW_AARCH64_X3:
-		return PERF_REG_ARM64_X3;
-	case UNW_AARCH64_X4:
-		return PERF_REG_ARM64_X4;
-	case UNW_AARCH64_X5:
-		return PERF_REG_ARM64_X5;
-	case UNW_AARCH64_X6:
-		return PERF_REG_ARM64_X6;
-	case UNW_AARCH64_X7:
-		return PERF_REG_ARM64_X7;
-	case UNW_AARCH64_X8:
-		return PERF_REG_ARM64_X8;
-	case UNW_AARCH64_X9:
-		return PERF_REG_ARM64_X9;
-	case UNW_AARCH64_X10:
-		return PERF_REG_ARM64_X10;
-	case UNW_AARCH64_X11:
-		return PERF_REG_ARM64_X11;
-	case UNW_AARCH64_X12:
-		return PERF_REG_ARM64_X12;
-	case UNW_AARCH64_X13:
-		return PERF_REG_ARM64_X13;
-	case UNW_AARCH64_X14:
-		return PERF_REG_ARM64_X14;
-	case UNW_AARCH64_X15:
-		return PERF_REG_ARM64_X15;
-	case UNW_AARCH64_X16:
-		return PERF_REG_ARM64_X16;
-	case UNW_AARCH64_X17:
-		return PERF_REG_ARM64_X17;
-	case UNW_AARCH64_X18:
-		return PERF_REG_ARM64_X18;
-	case UNW_AARCH64_X19:
-		return PERF_REG_ARM64_X19;
-	case UNW_AARCH64_X20:
-		return PERF_REG_ARM64_X20;
-	case UNW_AARCH64_X21:
-		return PERF_REG_ARM64_X21;
-	case UNW_AARCH64_X22:
-		return PERF_REG_ARM64_X22;
-	case UNW_AARCH64_X23:
-		return PERF_REG_ARM64_X23;
-	case UNW_AARCH64_X24:
-		return PERF_REG_ARM64_X24;
-	case UNW_AARCH64_X25:
-		return PERF_REG_ARM64_X25;
-	case UNW_AARCH64_X26:
-		return PERF_REG_ARM64_X26;
-	case UNW_AARCH64_X27:
-		return PERF_REG_ARM64_X27;
-	case UNW_AARCH64_X28:
-		return PERF_REG_ARM64_X28;
-	case UNW_AARCH64_X29:
-		return PERF_REG_ARM64_X29;
-	case UNW_AARCH64_X30:
-		return PERF_REG_ARM64_LR;
-	case UNW_AARCH64_SP:
-		return PERF_REG_ARM64_SP;
-	case UNW_AARCH64_PC:
-		return PERF_REG_ARM64_PC;
-	default:
-		pr_err("unwind: invalid reg id %d\n", regnum);
+	if (regnum < 0 || regnum >= PERF_REG_ARM64_EXTENDED_MAX)
 		return -EINVAL;
-	}
 
-	return -EINVAL;
+	return regnum;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 2eaac4638aab..06c2cdfd8f2f 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -811,18 +811,11 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			if (!cpu_wide && perf_can_record_cpu_wide()) {
 				struct evsel *switch_evsel;
 
-				err = parse_events(evlist, "dummy:u", NULL);
-				if (err)
-					return err;
+				switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
+				if (!switch_evsel)
+					return -ENOMEM;
 
-				switch_evsel = evlist__last(evlist);
-
-				switch_evsel->core.attr.freq = 0;
-				switch_evsel->core.attr.sample_period = 1;
 				switch_evsel->core.attr.context_switch = 1;
-
-				switch_evsel->core.system_wide = true;
-				switch_evsel->no_aux_samples = true;
 				switch_evsel->immediate = true;
 
 				evsel__set_sample_bit(switch_evsel, TID);
@@ -871,20 +864,22 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 
 	/* Add dummy event to keep tracking */
 	if (opts->full_auxtrace) {
+		bool need_system_wide_tracking;
 		struct evsel *tracking_evsel;
 
-		err = parse_events(evlist, "dummy:u", NULL);
-		if (err)
-			return err;
+		/*
+		 * User space tasks can migrate between CPUs, so when tracing
+		 * selected CPUs, sideband for all CPUs is still needed.
+		 */
+		need_system_wide_tracking = evlist->core.has_user_cpus &&
+					    !intel_pt_evsel->core.attr.exclude_user;
 
-		tracking_evsel = evlist__last(evlist);
+		tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking);
+		if (!tracking_evsel)
+			return -ENOMEM;
 
 		evlist__set_tracking_event(evlist, tracking_evsel);
 
-		tracking_evsel->core.attr.freq = 0;
-		tracking_evsel->core.attr.sample_period = 1;
-
-		tracking_evsel->no_aux_samples = true;
 		if (need_immediate)
 			tracking_evsel->immediate = true;
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index c8230c48125f..80b525c065ed 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2801,9 +2801,7 @@ static int perf_c2c__report(int argc, const char **argv)
 		   "the input file to process"),
 	OPT_INCR('N', "node-info", &c2c.node_info,
 		 "show extra node info in report (repeat for more info)"),
-#ifdef HAVE_SLANG_SUPPORT
 	OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
-#endif
 	OPT_BOOLEAN(0, "stats", &c2c.stats_only,
 		    "Display only statistic tables (implies --stdio)"),
 	OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
@@ -2833,6 +2831,10 @@ static int perf_c2c__report(int argc, const char **argv)
 	if (argc)
 		usage_with_options(report_c2c_usage, options);
 
+#ifndef HAVE_SLANG_SUPPORT
+	c2c.use_stdio = true;
+#endif
+
 	if (c2c.stats_only)
 		c2c.use_stdio = true;
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a5cf6a99d67f..9a71f0330137 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@
 #include "util/clockid.h"
 #include "util/pmu-hybrid.h"
 #include "util/evlist-hybrid.h"
+#include "util/off_cpu.h"
 #include "asm/bug.h"
 #include "perf.h"
 #include "cputopo.h"
@@ -162,6 +163,7 @@ struct record {
 	bool			buildid_mmap;
 	bool			timestamp_filename;
 	bool			timestamp_boundary;
+	bool			off_cpu;
 	struct switch_output	switch_output;
 	unsigned long long	samples;
 	unsigned long		output_max_size;	/* = 0: unlimited */
@@ -869,7 +871,6 @@ static int record__auxtrace_init(struct record *rec __maybe_unused)
 static int record__config_text_poke(struct evlist *evlist)
 {
 	struct evsel *evsel;
-	int err;
 
 	/* Nothing to do if text poke is already configured */
 	evlist__for_each_entry(evlist, evsel) {
@@ -877,32 +878,23 @@ static int record__config_text_poke(struct evlist *evlist)
 			return 0;
 	}
 
-	err = parse_events(evlist, "dummy:u", NULL);
-	if (err)
-		return err;
-
-	evsel = evlist__last(evlist);
+	evsel = evlist__add_dummy_on_all_cpus(evlist);
+	if (!evsel)
+		return -ENOMEM;
 
-	evsel->core.attr.freq = 0;
-	evsel->core.attr.sample_period = 1;
 	evsel->core.attr.text_poke = 1;
 	evsel->core.attr.ksymbol = 1;
-
-	evsel->core.system_wide = true;
-	evsel->no_aux_samples = true;
 	evsel->immediate = true;
-
-	/* Text poke must be collected on all CPUs */
-	perf_cpu_map__put(evsel->core.own_cpus);
-	evsel->core.own_cpus = perf_cpu_map__new(NULL);
-	perf_cpu_map__put(evsel->core.cpus);
-	evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
-
 	evsel__set_sample_bit(evsel, TIME);
 
 	return 0;
 }
 
+static int record__config_off_cpu(struct record *rec)
+{
+	return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
+}
+
 static bool record__kcore_readable(struct machine *machine)
 {
 	char kcore[PATH_MAX];
@@ -982,14 +974,20 @@ static void record__thread_data_close_pipes(struct record_thread *thread_data)
 	}
 }
 
+static bool evlist__per_thread(struct evlist *evlist)
+{
+	return cpu_map__is_dummy(evlist->core.user_requested_cpus);
+}
+
 static int record__thread_data_init_maps(struct record_thread *thread_data, struct evlist *evlist)
 {
 	int m, tm, nr_mmaps = evlist->core.nr_mmaps;
 	struct mmap *mmap = evlist->mmap;
 	struct mmap *overwrite_mmap = evlist->overwrite_mmap;
-	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
+	struct perf_cpu_map *cpus = evlist->core.all_cpus;
+	bool per_thread = evlist__per_thread(evlist);
 
-	if (cpu_map__is_dummy(cpus))
+	if (per_thread)
 		thread_data->nr_mmaps = nr_mmaps;
 	else
 		thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
@@ -1010,7 +1008,7 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
 		 thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);
 
 	for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) {
-		if (cpu_map__is_dummy(cpus) ||
+		if (per_thread ||
 		    test_bit(perf_cpu_map__cpu(cpus, m).cpu, thread_data->mask->maps.bits)) {
 			if (thread_data->maps) {
 				thread_data->maps[tm] = &mmap[m];
@@ -1885,7 +1883,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		return err;
 	}
 
-	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.user_requested_cpus,
+	err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->core.all_cpus,
 					     process_synthesized_event, NULL);
 	if (err < 0) {
 		pr_err("Couldn't synthesize cpu map.\n");
@@ -2600,6 +2598,9 @@ out_free_threads:
 	} else
 		status = err;
 
+	if (rec->off_cpu)
+		rec->bytes_written += off_cpu_write(rec->session);
+
 	record__synthesize(rec, true);
 	/* this will be recalculated during process_buildids() */
 	rec->samples = 0;
@@ -3324,6 +3325,7 @@ static struct option __record_options[] = {
 	OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec",
 			    "write collected trace data into several data files using parallel threads",
 			    record__parse_threads),
+	OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"),
 	OPT_END()
 };
 
@@ -3683,12 +3685,12 @@ static int record__init_thread_default_masks(struct record *rec, struct perf_cpu
 static int record__init_thread_masks(struct record *rec)
 {
 	int ret = 0;
-	struct perf_cpu_map *cpus = rec->evlist->core.user_requested_cpus;
+	struct perf_cpu_map *cpus = rec->evlist->core.all_cpus;
 
 	if (!record__threads_enabled(rec))
 		return record__init_thread_default_masks(rec, cpus);
 
-	if (cpu_map__is_dummy(cpus)) {
+	if (evlist__per_thread(rec->evlist)) {
 		pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n");
 		return -EINVAL;
 	}
@@ -3745,6 +3747,12 @@ int cmd_record(int argc, const char **argv)
 # undef REASON
 #endif
 
+#ifndef HAVE_BPF_SKEL
+# define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c)
+	set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true);
+# undef set_nobuild
+#endif
+
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
@@ -3981,6 +3989,14 @@ int cmd_record(int argc, const char **argv)
 		}
 	}
 
+	if (rec->off_cpu) {
+		err = record__config_off_cpu(rec);
+		if (err) {
+			pr_err("record__config_off_cpu failed, error %d\n", err);
+			goto out;
+		}
+	}
+
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7e6cc8bdf061..4ce87a8eb7d7 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -382,9 +382,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_
 	if (!counter->supported)
 		return -ENOENT;
 
-	if (counter->core.system_wide)
-		nthreads = 1;
-
 	for (thread = 0; thread < nthreads; thread++) {
 		struct perf_counts_values *count;
 
@@ -2261,7 +2258,7 @@ static void setup_system_wide(int forks)
 		struct evsel *counter;
 
 		evlist__for_each_entry(evsel_list, counter) {
-			if (!counter->core.system_wide &&
+			if (!counter->core.requires_cpu &&
 			    strcmp(counter->name, "duration_time")) {
 				return;
 			}
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index cee61c4ed59e..e597e4bac90f 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -605,7 +605,7 @@ static int json_events(const char *fn,
 			} else if (json_streq(map, field, "ExtSel")) {
 				char *code = NULL;
 				addfield(map, &code, "", "", val);
-				eventcode |= strtoul(code, NULL, 0) << 21;
+				eventcode |= strtoul(code, NULL, 0) << 8;
 				free(code);
 			} else if (json_streq(map, field, "EventName")) {
 				addfield(map, &je.name, "", "", val);
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
new file mode 100755
index 000000000000..5f57d9829956
--- /dev/null
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -0,0 +1,272 @@
+# SPDX-License-Identifier: GPL-2.0
+# arm-cs-trace-disasm.py: ARM CoreSight Trace Dump With Disassember
+#
+# Author: Tor Jeremiassen <tor@ti.com>
+#         Mathieu Poirier <mathieu.poirier@linaro.org>
+#         Leo Yan <leo.yan@linaro.org>
+#         Al Grant <Al.Grant@arm.com>
+
+from __future__ import print_function
+import os
+from os import path
+import sys
+import re
+from subprocess import *
+from optparse import OptionParser, make_option
+
+from perf_trace_context import perf_set_itrace_options, \
+	perf_sample_insn, perf_sample_srccode
+
+# Below are some example commands for using this script.
+#
+# Output disassembly with objdump:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#		-- -d objdump -k path/to/vmlinux
+# Output disassembly with llvm-objdump:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#		-- -d llvm-objdump-11 -k path/to/vmlinux
+# Output only source line and symbols:
+#  perf script -s scripts/python/arm-cs-trace-disasm.py
+
+# Command line parsing.
+option_list = [
+	# formatting options for the bottom entry of the stack
+	make_option("-k", "--vmlinux", dest="vmlinux_name",
+		    help="Set path to vmlinux file"),
+	make_option("-d", "--objdump", dest="objdump_name",
+		    help="Set path to objdump executable file"),
+	make_option("-v", "--verbose", dest="verbose",
+		    action="store_true", default=False,
+		    help="Enable debugging log")
+]
+
+parser = OptionParser(option_list=option_list)
+(options, args) = parser.parse_args()
+
+# Initialize global dicts and regular expression
+disasm_cache = dict()
+cpu_data = dict()
+disasm_re = re.compile("^\s*([0-9a-fA-F]+):")
+disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:")
+cache_size = 64*1024
+
+glb_source_file_name	= None
+glb_line_number		= None
+glb_dso			= None
+
+def get_optional(perf_dict, field):
+       if field in perf_dict:
+               return perf_dict[field]
+       return "[unknown]"
+
+def get_offset(perf_dict, field):
+	if field in perf_dict:
+		return f"+0x{perf_dict[field]:x}"
+	return ""
+
+def get_dso_file_path(dso_name, dso_build_id):
+	if (dso_name == "[kernel.kallsyms]" or dso_name == "vmlinux"):
+		if (options.vmlinux_name):
+			return options.vmlinux_name;
+		else:
+			return dso_name
+
+	if (dso_name == "[vdso]") :
+		append = "/vdso"
+	else:
+		append = "/elf"
+
+	dso_path = f"{os.environ['PERF_BUILDID_DIR']}/{dso_name}/{dso_build_id}{append}"
+	# Replace duplicate slash chars to single slash char
+	dso_path = dso_path.replace('//', '/', 1)
+	return dso_path
+
+def read_disam(dso_fname, dso_start, start_addr, stop_addr):
+	addr_range = str(start_addr) + ":" + str(stop_addr) + ":" + dso_fname
+
+	# Don't let the cache get too big, clear it when it hits max size
+	if (len(disasm_cache) > cache_size):
+		disasm_cache.clear();
+
+	if addr_range in disasm_cache:
+		disasm_output = disasm_cache[addr_range];
+	else:
+		start_addr = start_addr - dso_start;
+		stop_addr = stop_addr - dso_start;
+		disasm = [ options.objdump_name, "-d", "-z",
+			   f"--start-address=0x{start_addr:x}",
+			   f"--stop-address=0x{stop_addr:x}" ]
+		disasm += [ dso_fname ]
+		disasm_output = check_output(disasm).decode('utf-8').split('\n')
+		disasm_cache[addr_range] = disasm_output
+
+	return disasm_output
+
+def print_disam(dso_fname, dso_start, start_addr, stop_addr):
+	for line in read_disam(dso_fname, dso_start, start_addr, stop_addr):
+		m = disasm_func_re.search(line)
+		if m is None:
+			m = disasm_re.search(line)
+			if m is None:
+				continue
+		print(f"\t{line}")
+
+def print_sample(sample):
+	print(f"Sample = {{ cpu: {sample['cpu']:04} addr: 0x{sample['addr']:016x} " \
+	      f"phys_addr: 0x{sample['phys_addr']:016x} ip: 0x{sample['ip']:016x} " \
+	      f"pid: {sample['pid']} tid: {sample['tid']} period: {sample['period']} time: {sample['time']} }}")
+
+def trace_begin():
+	print('ARM CoreSight Trace Data Assembler Dump')
+
+def trace_end():
+	print('End')
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	print(' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())]))
+
+def common_start_str(comm, sample):
+	sec = int(sample["time"] / 1000000000)
+	ns = sample["time"] % 1000000000
+	cpu = sample["cpu"]
+	pid = sample["pid"]
+	tid = sample["tid"]
+	return f"{comm:>16} {pid:>5}/{tid:<5} [{cpu:04}] {sec:9}.{ns:09}  "
+
+# This code is copied from intel-pt-events.py for printing source code
+# line and symbols.
+def print_srccode(comm, param_dict, sample, symbol, dso):
+	ip = sample["ip"]
+	if symbol == "[unknown]":
+		start_str = common_start_str(comm, sample) + ("%x" % ip).rjust(16).ljust(40)
+	else:
+		offs = get_offset(param_dict, "symoff")
+		start_str = common_start_str(comm, sample) + (symbol + offs).ljust(40)
+
+	global glb_source_file_name
+	global glb_line_number
+	global glb_dso
+
+	source_file_name, line_number, source_line = perf_sample_srccode(perf_script_context)
+	if source_file_name:
+		if glb_line_number == line_number and glb_source_file_name == source_file_name:
+			src_str = ""
+		else:
+			if len(source_file_name) > 40:
+				src_file = ("..." + source_file_name[-37:]) + " "
+			else:
+				src_file = source_file_name.ljust(41)
+
+			if source_line is None:
+				src_str = src_file + str(line_number).rjust(4) + " <source not found>"
+			else:
+				src_str = src_file + str(line_number).rjust(4) + " " + source_line
+		glb_dso = None
+	elif dso == glb_dso:
+		src_str = ""
+	else:
+		src_str = dso
+		glb_dso = dso
+
+	glb_line_number = line_number
+	glb_source_file_name = source_file_name
+
+	print(f"{start_str}{src_str}")
+
+def process_event(param_dict):
+	global cache_size
+	global options
+
+	sample = param_dict["sample"]
+	comm = param_dict["comm"]
+
+	name = param_dict["ev_name"]
+	dso = get_optional(param_dict, "dso")
+	dso_bid = get_optional(param_dict, "dso_bid")
+	dso_start = get_optional(param_dict, "dso_map_start")
+	dso_end = get_optional(param_dict, "dso_map_end")
+	symbol = get_optional(param_dict, "symbol")
+
+	if (options.verbose == True):
+		print(f"Event type: {name}")
+		print_sample(sample)
+
+	# If cannot find dso so cannot dump assembler, bail out
+	if (dso == '[unknown]'):
+		return
+
+	# Validate dso start and end addresses
+	if ((dso_start == '[unknown]') or (dso_end == '[unknown]')):
+		print(f"Failed to find valid dso map for dso {dso}")
+		return
+
+	if (name[0:12] == "instructions"):
+		print_srccode(comm, param_dict, sample, symbol, dso)
+		return
+
+	# Don't proceed if this event is not a branch sample, .
+	if (name[0:8] != "branches"):
+		return
+
+	cpu = sample["cpu"]
+	ip = sample["ip"]
+	addr = sample["addr"]
+
+	# Initialize CPU data if it's empty, and directly return back
+	# if this is the first tracing event for this CPU.
+	if (cpu_data.get(str(cpu) + 'addr') == None):
+		cpu_data[str(cpu) + 'addr'] = addr
+		return
+
+	# The format for packet is:
+	#
+	#		  +------------+------------+------------+
+	#  sample_prev:   |    addr    |    ip	    |	 cpu	 |
+	#		  +------------+------------+------------+
+	#  sample_next:   |    addr    |    ip	    |	 cpu	 |
+	#		  +------------+------------+------------+
+	#
+	# We need to combine the two continuous packets to get the instruction
+	# range for sample_prev::cpu:
+	#
+	#     [ sample_prev::addr .. sample_next::ip ]
+	#
+	# For this purose, sample_prev::addr is stored into cpu_data structure
+	# and read back for 'start_addr' when the new packet comes, and we need
+	# to use sample_next::ip to calculate 'stop_addr', plusing extra 4 for
+	# 'stop_addr' is for the sake of objdump so the final assembler dump can
+	# include last instruction for sample_next::ip.
+	start_addr = cpu_data[str(cpu) + 'addr']
+	stop_addr  = ip + 4
+
+	# Record for previous sample packet
+	cpu_data[str(cpu) + 'addr'] = addr
+
+	# Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4
+	if (start_addr == 0 and stop_addr == 4):
+		print(f"CPU{cpu}: CS_ETM_TRACE_ON packet is inserted")
+		return
+
+	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
+		print(f"Start address 0x{start_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		return
+
+	if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
+		print(f"Stop address 0x{stop_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		return
+
+	if (options.objdump_name != None):
+		# It doesn't need to decrease virtual memory offset for disassembly
+		# for kernel dso, so in this case we set vm_start to zero.
+		if (dso == "[kernel.kallsyms]"):
+			dso_vm_start = 0
+		else:
+			dso_vm_start = int(dso_start)
+
+		dso_fname = get_dso_file_path(dso, dso_bid)
+		if path.exists(dso_fname):
+			print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
+		else:
+			print(f"Failed to find dso {dso} for address range [ 0x{start_addr:x} .. 0x{stop_addr:x} ]")
+
+	print_srccode(comm, param_dict, sample, symbol, dso)
diff --git a/tools/perf/tests/shell/lib/perf_csv_output_lint.py b/tools/perf/tests/shell/lib/perf_csv_output_lint.py
new file mode 100644
index 000000000000..714f283cfb1b
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_csv_output_lint.py
@@ -0,0 +1,48 @@
+#!/usr/bin/python
+# SPDX-License-Identifier: GPL-2.0
+
+import argparse
+import sys
+
+# Basic sanity check of perf CSV output as specified in the man page.
+# Currently just checks the number of fields per line in output.
+
+ap = argparse.ArgumentParser()
+ap.add_argument('--no-args', action='store_true')
+ap.add_argument('--interval', action='store_true')
+ap.add_argument('--system-wide-no-aggr', action='store_true')
+ap.add_argument('--system-wide', action='store_true')
+ap.add_argument('--event', action='store_true')
+ap.add_argument('--per-core', action='store_true')
+ap.add_argument('--per-thread', action='store_true')
+ap.add_argument('--per-die', action='store_true')
+ap.add_argument('--per-node', action='store_true')
+ap.add_argument('--per-socket', action='store_true')
+ap.add_argument('--separator', default=',', nargs='?')
+args = ap.parse_args()
+
+Lines = sys.stdin.readlines()
+
+def check_csv_output(exp):
+  for line in Lines:
+    if 'failed' not in line:
+      count = line.count(args.separator)
+      if count != exp:
+        sys.stdout.write(''.join(Lines))
+        raise RuntimeError(f'wrong number of fields. expected {exp} in {line}')
+
+try:
+  if args.no_args or args.system_wide or args.event:
+    expected_items = 6
+  elif args.interval or args.per_thread or args.system_wide_no_aggr:
+    expected_items = 7
+  elif args.per_core or args.per_socket or args.per_node or args.per_die:
+    expected_items = 8
+  else:
+    ap.print_help()
+    raise RuntimeError('No checking option specified')
+  check_csv_output(expected_items)
+
+except:
+  sys.stdout.write('Test failed for input: ' + ''.join(Lines))
+  raise
diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
new file mode 100755
index 000000000000..96e0739f7478
--- /dev/null
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -0,0 +1,60 @@
+#!/bin/sh
+# perf record offcpu profiling tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+
+cleanup() {
+  rm -f ${perfdata}
+  rm -f ${perfdata}.old
+  trap - exit term int
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup exit term int
+
+test_offcpu() {
+  echo "Basic off-cpu test"
+  if [ `id -u` != 0 ]
+  then
+    echo "Basic off-cpu test [Skipped permission]"
+    err=2
+    return
+  fi
+  if perf record --off-cpu -o ${perfdata} --quiet true 2>&1 | grep BUILD_BPF_SKEL
+  then
+    echo "Basic off-cpu test [Skipped missing BPF support]"
+    err=2
+    return
+  fi
+  if ! perf record --off-cpu -e dummy -o ${perfdata} sleep 1 2> /dev/null
+  then
+    echo "Basic off-cpu test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf evlist -i ${perfdata} | grep -q "offcpu-time"
+  then
+    echo "Basic off-cpu test [Failed record]"
+    err=1
+    return
+  fi
+  if ! perf report -i ${perfdata} -q --percent-limit=90 | egrep -q sleep
+  then
+    echo "Basic off-cpu test [Failed missing output]"
+    err=1
+    return
+  fi
+  echo "Basic off-cpu test [Success]"
+}
+
+test_offcpu
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
new file mode 100755
index 000000000000..983220ef3cb4
--- /dev/null
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -0,0 +1,147 @@
+#!/bin/bash
+# perf stat CSV output linter
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Tests various perf stat CSV output commands for the
+# correct number of fields and the CSV separator set to ','.
+
+set -e
+
+pythonchecker=$(dirname $0)/lib/perf_csv_output_lint.py
+if [ "x$PYTHON" == "x" ]
+then
+	if which python3 > /dev/null
+	then
+		PYTHON=python3
+	elif which python > /dev/null
+	then
+		PYTHON=python
+	else
+		echo Skipping test, python not detected please set environment variable PYTHON.
+		exit 2
+	fi
+fi
+
+# Return true if perf_event_paranoid is > $1 and not running as root.
+function ParanoidAndNotRoot()
+{
+	 [ $(id -u) != 0 ] && [ $(cat /proc/sys/kernel/perf_event_paranoid) -gt $1 ]
+}
+
+check_no_args()
+{
+	echo -n "Checking CSV output: no args "
+	perf stat -x, true 2>&1 | $PYTHON $pythonchecker --no-args
+	echo "[Success]"
+}
+
+check_system_wide()
+{
+	echo -n "Checking CSV output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, -a true 2>&1 | $PYTHON $pythonchecker --system-wide
+	echo "[Success]"
+}
+
+check_system_wide_no_aggr()
+{
+	echo -n "Checking CSV output: system wide "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	echo -n "Checking CSV output: system wide no aggregation "
+	perf stat -x, -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr
+	echo "[Success]"
+}
+
+check_interval()
+{
+	echo -n "Checking CSV output: interval "
+	perf stat -x, -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval
+	echo "[Success]"
+}
+
+
+check_event()
+{
+	echo -n "Checking CSV output: event "
+	perf stat -x, -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event
+	echo "[Success]"
+}
+
+check_per_core()
+{
+	echo -n "Checking CSV output: per core "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core
+	echo "[Success]"
+}
+
+check_per_thread()
+{
+	echo -n "Checking CSV output: per thread "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread
+	echo "[Success]"
+}
+
+check_per_die()
+{
+	echo -n "Checking CSV output: per die "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die
+	echo "[Success]"
+}
+
+check_per_node()
+{
+	echo -n "Checking CSV output: per node "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node
+	echo "[Success]"
+}
+
+check_per_socket()
+{
+	echo -n "Checking CSV output: per socket "
+	if ParanoidAndNotRoot 0
+	then
+		echo "[Skip] paranoid and not root"
+		return
+	fi
+	perf stat -x, --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket
+	echo "[Success]"
+}
+
+check_no_args
+check_system_wide
+check_system_wide_no_aggr
+check_interval
+check_event
+check_per_core
+check_per_thread
+check_per_die
+check_per_node
+check_per_socket
+exit 0
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
new file mode 100755
index 000000000000..a3298643884d
--- /dev/null
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -0,0 +1,71 @@
+#!/bin/sh
+# Miscellaneous Intel PT testing
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# Skip if no Intel PT
+perf list | grep -q 'intel_pt//' || exit 2
+
+skip_cnt=0
+ok_cnt=0
+err_cnt=0
+
+tmpfile=`mktemp`
+perfdatafile=`mktemp`
+
+can_cpu_wide()
+{
+	perf record -o ${tmpfile} -B -N --no-bpf-event -e dummy:u -C $1 true 2>&1 >/dev/null || return 2
+	return 0
+}
+
+test_system_wide_side_band()
+{
+	# Need CPU 0 and CPU 1
+	can_cpu_wide 0 || return $?
+	can_cpu_wide 1 || return $?
+
+	# Record on CPU 0 a task running on CPU 1
+	perf record -B -N --no-bpf-event -o ${perfdatafile} -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname
+
+	# Should get MMAP events from CPU 1 because they can be needed to decode
+	mmap_cnt=`perf script -i ${perfdatafile} --no-itrace --show-mmap-events -C 1 2>/dev/null | grep MMAP | wc -l`
+
+	if [ ${mmap_cnt} -gt 0 ] ; then
+		return 0
+	fi
+
+	echo "Failed to record MMAP events on CPU 1 when tracing CPU 0"
+	return 1
+}
+
+count_result()
+{
+	if [ $1 -eq 2 ] ; then
+		skip_cnt=`expr ${skip_cnt} \+ 1`
+		return
+	fi
+	if [ $1 -eq 0 ] ; then
+		ok_cnt=`expr ${ok_cnt} \+ 1`
+		return
+	fi
+	err_cnt=`expr ${err_cnt} \+ 1`
+}
+
+test_system_wide_side_band
+
+count_result $?
+
+rm -f ${tmpfile}
+rm -f ${perfdatafile}
+
+if [ ${err_cnt} -gt 0 ] ; then
+	exit 1
+fi
+
+if [ ${ok_cnt} -gt 0 ] ; then
+	exit 0
+fi
+
+exit 2
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 9a7209a99e16..a51267d88ca9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -147,6 +147,7 @@ perf-$(CONFIG_LIBBPF) += bpf_map.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o
 perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index b11549ae39df..511dd3caa1bc 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -125,7 +125,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 	mm->tid = mp->tid;
 	mm->cpu = mp->cpu.cpu;
 
-	if (!mp->len) {
+	if (!mp->len || !mp->mmap_needed) {
 		mm->base = NULL;
 		return 0;
 	}
@@ -168,13 +168,20 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
 }
 
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct evlist *evlist, int idx,
-				   bool per_cpu)
+				   struct evlist *evlist,
+				   struct evsel *evsel, int idx)
 {
+	bool per_cpu = !perf_cpu_map__empty(evlist->core.user_requested_cpus);
+
+	mp->mmap_needed = evsel->needs_auxtrace_mmap;
+
+	if (!mp->mmap_needed)
+		return;
+
 	mp->idx = idx;
 
 	if (per_cpu) {
-		mp->cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, idx);
+		mp->cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
 		if (evlist->core.threads)
 			mp->tid = perf_thread_map__pid(evlist->core.threads, 0);
 		else
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index dc38b6f57232..cd0d25c2751c 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -344,6 +344,10 @@ struct auxtrace_mmap {
  * @idx: index of this mmap
  * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
  *       mmap) otherwise %0
+ * @mmap_needed: set to %false for non-auxtrace events. This is needed because
+ *               auxtrace mmapping is done in the same code path as non-auxtrace
+ *               mmapping but not every evsel that needs non-auxtrace mmapping
+ *               also needs auxtrace mmapping.
  * @cpu: cpu number for a per-cpu mmap otherwise %-1
  */
 struct auxtrace_mmap_params {
@@ -353,6 +357,7 @@ struct auxtrace_mmap_params {
 	int		prot;
 	int		idx;
 	pid_t		tid;
+	bool		mmap_needed;
 	struct perf_cpu	cpu;
 };
 
@@ -490,8 +495,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
 				unsigned int auxtrace_pages,
 				bool auxtrace_overwrite);
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct evlist *evlist, int idx,
-				   bool per_cpu);
+				   struct evlist *evlist,
+				   struct evsel *evsel, int idx);
 
 typedef int (*process_auxtrace_t)(struct perf_tool *tool,
 				  struct mmap *map,
@@ -863,8 +868,8 @@ void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
 				unsigned int auxtrace_pages,
 				bool auxtrace_overwrite);
 void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
-				   struct evlist *evlist, int idx,
-				   bool per_cpu);
+				   struct evlist *evlist,
+				   struct evsel *evsel, int idx);
 
 #define ITRACE_HELP ""
 
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 8271ab764eb5..eee64ddb766d 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -35,11 +35,12 @@ struct btf *btf__load_from_kernel_by_id(__u32 id)
 }
 #endif
 
-int __weak bpf_prog_load(enum bpf_prog_type prog_type,
-			 const char *prog_name __maybe_unused,
-			 const char *license,
-			 const struct bpf_insn *insns, size_t insn_cnt,
-			 const struct bpf_prog_load_opts *opts)
+#ifndef HAVE_LIBBPF_BPF_PROG_LOAD
+int bpf_prog_load(enum bpf_prog_type prog_type,
+		  const char *prog_name __maybe_unused,
+		  const char *license,
+		  const struct bpf_insn *insns, size_t insn_cnt,
+		  const struct bpf_prog_load_opts *opts)
 {
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wdeprecated-declarations"
@@ -47,8 +48,10 @@ int __weak bpf_prog_load(enum bpf_prog_type prog_type,
 				opts->kern_version, opts->log_buf, opts->log_size);
 #pragma GCC diagnostic pop
 }
+#endif
 
-struct bpf_program * __weak
+#ifndef HAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
+struct bpf_program *
 bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
 {
 #pragma GCC diagnostic push
@@ -56,8 +59,10 @@ bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
 	return bpf_program__next(prev, obj);
 #pragma GCC diagnostic pop
 }
+#endif
 
-struct bpf_map * __weak
+#ifndef HAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
+struct bpf_map *
 bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 {
 #pragma GCC diagnostic push
@@ -65,8 +70,10 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 	return bpf_map__next(prev, obj);
 #pragma GCC diagnostic pop
 }
+#endif
 
-const void * __weak
+#ifndef HAVE_LIBBPF_BTF__RAW_DATA
+const void *
 btf__raw_data(const struct btf *btf_ro, __u32 *size)
 {
 #pragma GCC diagnostic push
@@ -74,6 +81,7 @@ btf__raw_data(const struct btf *btf_ro, __u32 *size)
 	return btf__get_raw_data(btf_ro, size);
 #pragma GCC diagnostic pop
 }
+#endif
 
 static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
 {
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index d4931f54e1dd..ef1c15e4aeba 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -312,7 +312,10 @@ static bool bperf_attr_map_compatible(int attr_map_fd)
 		(map_info.value_size == sizeof(struct perf_event_attr_map_entry));
 }
 
-int __weak
+#ifndef HAVE_LIBBPF_BPF_MAP_CREATE
+LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size,
+                              int value_size, int max_entries, __u32 map_flags);
+int
 bpf_map_create(enum bpf_map_type map_type,
 	       const char *map_name __maybe_unused,
 	       __u32 key_size,
@@ -325,6 +328,7 @@ bpf_map_create(enum bpf_map_type map_type,
 	return bpf_create_map(map_type, key_size, value_size, max_entries, 0);
 #pragma GCC diagnostic pop
 }
+#endif
 
 static int bperf_lock_attr_map(struct target *target)
 {
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
new file mode 100644
index 000000000000..b73e84a02264
--- /dev/null
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/bpf_counter.h"
+#include "util/debug.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/off_cpu.h"
+#include "util/perf-hooks.h"
+#include "util/record.h"
+#include "util/session.h"
+#include "util/target.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/cgroup.h"
+#include <bpf/bpf.h>
+
+#include "bpf_skel/off_cpu.skel.h"
+
+#define MAX_STACKS  32
+/* we don't need actual timestamp, just want to put the samples at last */
+#define OFF_CPU_TIMESTAMP  (~0ull << 32)
+
+static struct off_cpu_bpf *skel;
+
+struct off_cpu_key {
+	u32 pid;
+	u32 tgid;
+	u32 stack_id;
+	u32 state;
+	u64 cgroup_id;
+};
+
+union off_cpu_data {
+	struct perf_event_header hdr;
+	u64 array[1024 / sizeof(u64)];
+};
+
+static int off_cpu_config(struct evlist *evlist)
+{
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type	= PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_BPF_OUTPUT,
+		.size	= sizeof(attr), /* to capture ABI version */
+	};
+	char *evname = strdup(OFFCPU_EVENT);
+
+	if (evname == NULL)
+		return -ENOMEM;
+
+	evsel = evsel__new(&attr);
+	if (!evsel) {
+		free(evname);
+		return -ENOMEM;
+	}
+
+	evsel->core.attr.freq = 1;
+	evsel->core.attr.sample_period = 1;
+	/* off-cpu analysis depends on stack trace */
+	evsel->core.attr.sample_type = PERF_SAMPLE_CALLCHAIN;
+
+	evlist__add(evlist, evsel);
+
+	free(evsel->name);
+	evsel->name = evname;
+
+	return 0;
+}
+
+static void off_cpu_start(void *arg)
+{
+	struct evlist *evlist = arg;
+
+	/* update task filter for the given workload */
+	if (!skel->bss->has_cpu && !skel->bss->has_task &&
+	    perf_thread_map__pid(evlist->core.threads, 0) != -1) {
+		int fd;
+		u32 pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+		pid = perf_thread_map__pid(evlist->core.threads, 0);
+		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+	}
+
+	skel->bss->enabled = 1;
+}
+
+static void off_cpu_finish(void *arg __maybe_unused)
+{
+	skel->bss->enabled = 0;
+	off_cpu_bpf__destroy(skel);
+}
+
+/* v5.18 kernel added prev_state arg, so it needs to check the signature */
+static void check_sched_switch_args(void)
+{
+	const struct btf *btf = bpf_object__btf(skel->obj);
+	const struct btf_type *t1, *t2, *t3;
+	u32 type_id;
+
+	type_id = btf__find_by_name_kind(btf, "bpf_trace_sched_switch",
+					 BTF_KIND_TYPEDEF);
+	if ((s32)type_id < 0)
+		return;
+
+	t1 = btf__type_by_id(btf, type_id);
+	if (t1 == NULL)
+		return;
+
+	t2 = btf__type_by_id(btf, t1->type);
+	if (t2 == NULL || !btf_is_ptr(t2))
+		return;
+
+	t3 = btf__type_by_id(btf, t2->type);
+	if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 4) {
+		/* new format: pass prev_state as 4th arg */
+		skel->rodata->has_prev_state = true;
+	}
+}
+
+int off_cpu_prepare(struct evlist *evlist, struct target *target,
+		    struct record_opts *opts)
+{
+	int err, fd, i;
+	int ncpus = 1, ntasks = 1, ncgrps = 1;
+
+	if (off_cpu_config(evlist) < 0) {
+		pr_err("Failed to config off-cpu BPF event\n");
+		return -1;
+	}
+
+	skel = off_cpu_bpf__open();
+	if (!skel) {
+		pr_err("Failed to open off-cpu BPF skeleton\n");
+		return -1;
+	}
+
+	/* don't need to set cpu filter for system-wide mode */
+	if (target->cpu_list) {
+		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
+		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+	}
+
+	if (target__has_task(target)) {
+		ntasks = perf_thread_map__nr(evlist->core.threads);
+		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	}
+
+	if (evlist__first(evlist)->cgrp) {
+		ncgrps = evlist->core.nr_entries - 1; /* excluding a dummy */
+		bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
+
+		if (!cgroup_is_v2("perf_event"))
+			skel->rodata->uses_cgroup_v1 = true;
+	}
+
+	if (opts->record_cgroup) {
+		skel->rodata->needs_cgroup = true;
+
+		if (!cgroup_is_v2("perf_event"))
+			skel->rodata->uses_cgroup_v1 = true;
+	}
+
+	set_max_rlimit();
+	check_sched_switch_args();
+
+	err = off_cpu_bpf__load(skel);
+	if (err) {
+		pr_err("Failed to load off-cpu skeleton\n");
+		goto out;
+	}
+
+	if (target->cpu_list) {
+		u32 cpu;
+		u8 val = 1;
+
+		skel->bss->has_cpu = 1;
+		fd = bpf_map__fd(skel->maps.cpu_filter);
+
+		for (i = 0; i < ncpus; i++) {
+			cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, i).cpu;
+			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+		}
+	}
+
+	if (target__has_task(target)) {
+		u32 pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+
+		for (i = 0; i < ntasks; i++) {
+			pid = perf_thread_map__pid(evlist->core.threads, i);
+			bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+		}
+	}
+
+	if (evlist__first(evlist)->cgrp) {
+		struct evsel *evsel;
+		u8 val = 1;
+
+		skel->bss->has_cgroup = 1;
+		fd = bpf_map__fd(skel->maps.cgroup_filter);
+
+		evlist__for_each_entry(evlist, evsel) {
+			struct cgroup *cgrp = evsel->cgrp;
+
+			if (cgrp == NULL)
+				continue;
+
+			if (!cgrp->id && read_cgroup_id(cgrp) < 0) {
+				pr_err("Failed to read cgroup id of %s\n",
+				       cgrp->name);
+				goto out;
+			}
+
+			bpf_map_update_elem(fd, &cgrp->id, &val, BPF_ANY);
+		}
+	}
+
+	err = off_cpu_bpf__attach(skel);
+	if (err) {
+		pr_err("Failed to attach off-cpu BPF skeleton\n");
+		goto out;
+	}
+
+	if (perf_hooks__set_hook("record_start", off_cpu_start, evlist) ||
+	    perf_hooks__set_hook("record_end", off_cpu_finish, evlist)) {
+		pr_err("Failed to attach off-cpu skeleton\n");
+		goto out;
+	}
+
+	return 0;
+
+out:
+	off_cpu_bpf__destroy(skel);
+	return -1;
+}
+
+int off_cpu_write(struct perf_session *session)
+{
+	int bytes = 0, size;
+	int fd, stack;
+	u64 sample_type, val, sid = 0;
+	struct evsel *evsel;
+	struct perf_data_file *file = &session->data->file;
+	struct off_cpu_key prev, key;
+	union off_cpu_data data = {
+		.hdr = {
+			.type = PERF_RECORD_SAMPLE,
+			.misc = PERF_RECORD_MISC_USER,
+		},
+	};
+	u64 tstamp = OFF_CPU_TIMESTAMP;
+
+	skel->bss->enabled = 0;
+
+	evsel = evlist__find_evsel_by_str(session->evlist, OFFCPU_EVENT);
+	if (evsel == NULL) {
+		pr_err("%s evsel not found\n", OFFCPU_EVENT);
+		return 0;
+	}
+
+	sample_type = evsel->core.attr.sample_type;
+
+	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) {
+		if (evsel->core.id)
+			sid = evsel->core.id[0];
+	}
+
+	fd = bpf_map__fd(skel->maps.off_cpu);
+	stack = bpf_map__fd(skel->maps.stacks);
+	memset(&prev, 0, sizeof(prev));
+
+	while (!bpf_map_get_next_key(fd, &prev, &key)) {
+		int n = 1;  /* start from perf_event_header */
+		int ip_pos = -1;
+
+		bpf_map_lookup_elem(fd, &key, &val);
+
+		if (sample_type & PERF_SAMPLE_IDENTIFIER)
+			data.array[n++] = sid;
+		if (sample_type & PERF_SAMPLE_IP) {
+			ip_pos = n;
+			data.array[n++] = 0;  /* will be updated */
+		}
+		if (sample_type & PERF_SAMPLE_TID)
+			data.array[n++] = (u64)key.pid << 32 | key.tgid;
+		if (sample_type & PERF_SAMPLE_TIME)
+			data.array[n++] = tstamp;
+		if (sample_type & PERF_SAMPLE_ID)
+			data.array[n++] = sid;
+		if (sample_type & PERF_SAMPLE_CPU)
+			data.array[n++] = 0;
+		if (sample_type & PERF_SAMPLE_PERIOD)
+			data.array[n++] = val;
+		if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+			int len = 0;
+
+			/* data.array[n] is callchain->nr (updated later) */
+			data.array[n + 1] = PERF_CONTEXT_USER;
+			data.array[n + 2] = 0;
+
+			bpf_map_lookup_elem(stack, &key.stack_id, &data.array[n + 2]);
+			while (data.array[n + 2 + len])
+				len++;
+
+			/* update length of callchain */
+			data.array[n] = len + 1;
+
+			/* update sample ip with the first callchain entry */
+			if (ip_pos >= 0)
+				data.array[ip_pos] = data.array[n + 2];
+
+			/* calculate sample callchain data array length */
+			n += len + 2;
+		}
+		if (sample_type & PERF_SAMPLE_CGROUP)
+			data.array[n++] = key.cgroup_id;
+		/* TODO: handle more sample types */
+
+		size = n * sizeof(u64);
+		data.hdr.size = size;
+		bytes += size;
+
+		if (perf_data_file__write(file, &data, size) < 0) {
+			pr_err("failed to write perf data, error: %m\n");
+			return bytes;
+		}
+
+		prev = key;
+		/* increase dummy timestamp to sort later samples */
+		tstamp++;
+	}
+	return bytes;
+}
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
new file mode 100644
index 000000000000..792ae2847080
--- /dev/null
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2022 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+/* task->flags for off-cpu analysis */
+#define PF_KTHREAD   0x00200000  /* I am a kernel thread */
+
+/* task->state for off-cpu analysis */
+#define TASK_INTERRUPTIBLE	0x0001
+#define TASK_UNINTERRUPTIBLE	0x0002
+
+#define MAX_STACKS   32
+#define MAX_ENTRIES  102400
+
+struct tstamp_data {
+	__u32 stack_id;
+	__u32 state;
+	__u64 timestamp;
+};
+
+struct offcpu_key {
+	__u32 pid;
+	__u32 tgid;
+	__u32 stack_id;
+	__u32 state;
+	__u64 cgroup_id;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, MAX_STACKS * sizeof(__u64));
+	__uint(max_entries, MAX_ENTRIES);
+} stacks SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct tstamp_data);
+} tstamp SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct offcpu_key));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, MAX_ENTRIES);
+} off_cpu SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cpu_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} task_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cgroup_filter SEC(".maps");
+
+/* old kernel task_struct definition */
+struct task_struct___old {
+	long state;
+} __attribute__((preserve_access_index));
+
+int enabled = 0;
+int has_cpu = 0;
+int has_task = 0;
+int has_cgroup = 0;
+
+const volatile bool has_prev_state = false;
+const volatile bool needs_cgroup = false;
+const volatile bool uses_cgroup_v1 = false;
+
+/*
+ * Old kernel used to call it task_struct->state and now it's '__state'.
+ * Use BPF CO-RE "ignored suffix rule" to deal with it like below:
+ *
+ * https://nakryiko.com/posts/bpf-core-reference-guide/#handling-incompatible-field-and-type-changes
+ */
+static inline int get_task_state(struct task_struct *t)
+{
+	if (bpf_core_field_exists(t->__state))
+		return BPF_CORE_READ(t, __state);
+
+	/* recast pointer to capture task_struct___old type for compiler */
+	struct task_struct___old *t_old = (void *)t;
+
+	/* now use old "state" name of the field */
+	return BPF_CORE_READ(t_old, state);
+}
+
+static inline __u64 get_cgroup_id(struct task_struct *t)
+{
+	struct cgroup *cgrp;
+
+	if (uses_cgroup_v1)
+		cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_event_cgrp_id], cgroup);
+	else
+		cgrp = BPF_CORE_READ(t, cgroups, dfl_cgrp);
+
+	return BPF_CORE_READ(cgrp, kn, id);
+}
+
+static inline int can_record(struct task_struct *t, int state)
+{
+	/* kernel threads don't have user stack */
+	if (t->flags & PF_KTHREAD)
+		return 0;
+
+	if (state != TASK_INTERRUPTIBLE &&
+	    state != TASK_UNINTERRUPTIBLE)
+		return 0;
+
+	if (has_cpu) {
+		__u32 cpu = bpf_get_smp_processor_id();
+		__u8 *ok;
+
+		ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
+		if (!ok)
+			return 0;
+	}
+
+	if (has_task) {
+		__u8 *ok;
+		__u32 pid = t->pid;
+
+		ok = bpf_map_lookup_elem(&task_filter, &pid);
+		if (!ok)
+			return 0;
+	}
+
+	if (has_cgroup) {
+		__u8 *ok;
+		__u64 cgrp_id = get_cgroup_id(t);
+
+		ok = bpf_map_lookup_elem(&cgroup_filter, &cgrp_id);
+		if (!ok)
+			return 0;
+	}
+
+	return 1;
+}
+
+static int off_cpu_stat(u64 *ctx, struct task_struct *prev,
+			struct task_struct *next, int state)
+{
+	__u64 ts;
+	__u32 stack_id;
+	struct tstamp_data *pelem;
+
+	ts = bpf_ktime_get_ns();
+
+	if (!can_record(prev, state))
+		goto next;
+
+	stack_id = bpf_get_stackid(ctx, &stacks,
+				   BPF_F_FAST_STACK_CMP | BPF_F_USER_STACK);
+
+	pelem = bpf_task_storage_get(&tstamp, prev, NULL,
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!pelem)
+		goto next;
+
+	pelem->timestamp = ts;
+	pelem->state = state;
+	pelem->stack_id = stack_id;
+
+next:
+	pelem = bpf_task_storage_get(&tstamp, next, NULL, 0);
+
+	if (pelem && pelem->timestamp) {
+		struct offcpu_key key = {
+			.pid = next->pid,
+			.tgid = next->tgid,
+			.stack_id = pelem->stack_id,
+			.state = pelem->state,
+			.cgroup_id = needs_cgroup ? get_cgroup_id(next) : 0,
+		};
+		__u64 delta = ts - pelem->timestamp;
+		__u64 *total;
+
+		total = bpf_map_lookup_elem(&off_cpu, &key);
+		if (total)
+			*total += delta;
+		else
+			bpf_map_update_elem(&off_cpu, &key, &delta, BPF_ANY);
+
+		/* prevent to reuse the timestamp later */
+		pelem->timestamp = 0;
+	}
+
+	return 0;
+}
+
+SEC("tp_btf/sched_switch")
+int on_switch(u64 *ctx)
+{
+	struct task_struct *prev, *next;
+	int prev_state;
+
+	if (!enabled)
+		return 0;
+
+	prev = (struct task_struct *)ctx[1];
+	next = (struct task_struct *)ctx[2];
+
+	if (has_prev_state)
+		prev_state = (int)ctx[3];
+	else
+		prev_state = get_task_state(prev);
+
+	return off_cpu_stat(ctx, prev, next, prev_state);
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7f9f588e88c6..48af7d379d82 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -242,14 +242,20 @@ int __evlist__add_default(struct evlist *evlist, bool precise)
 	return 0;
 }
 
-int evlist__add_dummy(struct evlist *evlist)
+static struct evsel *evlist__dummy_event(struct evlist *evlist)
 {
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct evsel *evsel = evsel__new_idx(&attr, evlist->core.nr_entries);
+
+	return evsel__new_idx(&attr, evlist->core.nr_entries);
+}
+
+int evlist__add_dummy(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__dummy_event(evlist);
 
 	if (evsel == NULL)
 		return -ENOMEM;
@@ -258,6 +264,51 @@ int evlist__add_dummy(struct evlist *evlist)
 	return 0;
 }
 
+static void evlist__add_on_all_cpus(struct evlist *evlist, struct evsel *evsel)
+{
+	evsel->core.system_wide = true;
+
+	/*
+	 * All CPUs.
+	 *
+	 * Note perf_event_open() does not accept CPUs that are not online, so
+	 * in fact this CPU list will include only all online CPUs.
+	 */
+	perf_cpu_map__put(evsel->core.own_cpus);
+	evsel->core.own_cpus = perf_cpu_map__new(NULL);
+	perf_cpu_map__put(evsel->core.cpus);
+	evsel->core.cpus = perf_cpu_map__get(evsel->core.own_cpus);
+
+	/* No threads */
+	perf_thread_map__put(evsel->core.threads);
+	evsel->core.threads = perf_thread_map__new_dummy();
+
+	evlist__add(evlist, evsel);
+}
+
+struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
+{
+	struct evsel *evsel = evlist__dummy_event(evlist);
+
+	if (!evsel)
+		return NULL;
+
+	evsel->core.attr.exclude_kernel = 1;
+	evsel->core.attr.exclude_guest = 1;
+	evsel->core.attr.exclude_hv = 1;
+	evsel->core.attr.freq = 0;
+	evsel->core.attr.sample_period = 1;
+	evsel->no_aux_samples = true;
+	evsel->name = strdup("dummy:u");
+
+	if (system_wide)
+		evlist__add_on_all_cpus(evlist, evsel);
+	else
+		evlist__add(evlist, evsel);
+
+	return evsel;
+}
+
 static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
 {
 	struct evsel *evsel, *n;
@@ -747,15 +798,15 @@ static struct mmap *evlist__alloc_mmap(struct evlist *evlist,
 
 static void
 perf_evlist__mmap_cb_idx(struct perf_evlist *_evlist,
-			 struct perf_evsel *_evsel __maybe_unused,
+			 struct perf_evsel *_evsel,
 			 struct perf_mmap_param *_mp,
 			 int idx)
 {
 	struct evlist *evlist = container_of(_evlist, struct evlist, core);
 	struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
-	bool per_cpu = !perf_cpu_map__empty(_evlist->user_requested_cpus);
+	struct evsel *evsel = container_of(_evsel, struct evsel, core);
 
-	auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, idx, per_cpu);
+	auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, evsel, idx);
 }
 
 static struct perf_mmap*
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4062f5aebfc1..1bde9ccf4e7d 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -114,6 +114,11 @@ int arch_evlist__add_default_attrs(struct evlist *evlist);
 struct evsel *arch_evlist__leader(struct list_head *list);
 
 int evlist__add_dummy(struct evlist *evlist);
+struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide);
+static inline struct evsel *evlist__add_dummy_on_all_cpus(struct evlist *evlist)
+{
+	return evlist__add_aux_dummy(evlist, true);
+}
 
 int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
 			 evsel__sb_cb_t cb, void *data);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef169ad15236..ce499c5da8d7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -296,8 +296,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
 		return NULL;
 	evsel__init(evsel, attr, idx);
 
-	if (evsel__is_bpf_output(evsel)) {
-		evsel->core.attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+	if (evsel__is_bpf_output(evsel) && !attr->sample_type) {
+		evsel->core.attr.sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
 					    PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
 		evsel->core.attr.sample_period = 1;
 	}
@@ -409,6 +409,7 @@ struct evsel *evsel__clone(struct evsel *orig)
 	evsel->core.threads = perf_thread_map__get(orig->core.threads);
 	evsel->core.nr_members = orig->core.nr_members;
 	evsel->core.system_wide = orig->core.system_wide;
+	evsel->core.requires_cpu = orig->core.requires_cpu;
 
 	if (orig->name) {
 		evsel->name = strdup(orig->name);
@@ -896,7 +897,7 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
 					   "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
 					   "so the minimal registers set (IP, SP) is explicitly forced.\n");
 			} else {
-				attr->sample_regs_user |= PERF_REGS_MASK;
+				attr->sample_regs_user |= arch__user_reg_mask();
 			}
 			attr->sample_stack_user = param->dump_size;
 			attr->exclude_callchain_user = 1;
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index 15f60fd09424..014d82159656 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -24,7 +24,7 @@
 #include "unwind.h"
 #include "libunwind-aarch64.h"
 #define perf_event_arm_regs perf_event_arm64_regs
-#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h>
+#include <../../../arch/arm64/include/uapi/asm/perf_regs.h>
 #undef perf_event_arm_regs
 #include "../../arch/arm64/util/unwind-libunwind.c"
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 50502b4a7ca4..a4dff881be39 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -62,8 +62,8 @@ void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_u
 
 void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
 					  struct evlist *evlist __maybe_unused,
-					  int idx __maybe_unused,
-					  bool per_cpu __maybe_unused)
+					  struct evsel *evsel __maybe_unused,
+					  int idx __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h
new file mode 100644
index 000000000000..548008f74d42
--- /dev/null
+++ b/tools/perf/util/off_cpu.h
@@ -0,0 +1,29 @@
+#ifndef PERF_UTIL_OFF_CPU_H
+#define PERF_UTIL_OFF_CPU_H
+
+struct evlist;
+struct target;
+struct perf_session;
+struct record_opts;
+
+#define OFFCPU_EVENT  "offcpu-time"
+
+#ifdef HAVE_BPF_SKEL
+int off_cpu_prepare(struct evlist *evlist, struct target *target,
+		    struct record_opts *opts);
+int off_cpu_write(struct perf_session *session);
+#else
+static inline int off_cpu_prepare(struct evlist *evlist __maybe_unused,
+				  struct target *target __maybe_unused,
+				  struct record_opts *opts __maybe_unused)
+{
+	return -1;
+}
+
+static inline int off_cpu_write(struct perf_session *session __maybe_unused)
+{
+	return -1;
+}
+#endif
+
+#endif  /* PERF_UTIL_OFF_CPU_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 30a9d915853d..7ed235740431 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -365,7 +365,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->core.cpus = cpus;
 	evsel->core.own_cpus = perf_cpu_map__get(cpus);
-	evsel->core.system_wide = pmu ? pmu->is_uncore : false;
+	evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a982e40ee5a9..872dd3d38782 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -103,6 +103,8 @@ static const char *__perf_reg_name_arm64(int id)
 		return "lr";
 	case PERF_REG_ARM64_PC:
 		return "pc";
+	case PERF_REG_ARM64_VG:
+		return "vg";
 	default:
 		return NULL;
 	}
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index a685d20165f7..aa5156c2bcff 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -38,5 +38,6 @@ util/units.c
 util/affinity.c
 util/rwsem.c
 util/hashmap.c
+util/perf_regs.c
 util/pmu-hybrid.c
 util/fncache.c
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 659eb4e4b34b..adba01b7d9dd 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -755,12 +755,22 @@ static void set_regs_in_dict(PyObject *dict,
 }
 
 static void set_sym_in_dict(PyObject *dict, struct addr_location *al,
-			    const char *dso_field, const char *sym_field,
-			    const char *symoff_field)
+			    const char *dso_field, const char *dso_bid_field,
+			    const char *dso_map_start, const char *dso_map_end,
+			    const char *sym_field, const char *symoff_field)
 {
+	char sbuild_id[SBUILD_ID_SIZE];
+
 	if (al->map) {
 		pydict_set_item_string_decref(dict, dso_field,
 			_PyUnicode_FromString(al->map->dso->name));
+		build_id__sprintf(&al->map->dso->bid, sbuild_id);
+		pydict_set_item_string_decref(dict, dso_bid_field,
+			_PyUnicode_FromString(sbuild_id));
+		pydict_set_item_string_decref(dict, dso_map_start,
+			PyLong_FromUnsignedLong(al->map->start));
+		pydict_set_item_string_decref(dict, dso_map_end,
+			PyLong_FromUnsignedLong(al->map->end));
 	}
 	if (al->sym) {
 		pydict_set_item_string_decref(dict, sym_field,
@@ -840,7 +850,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			(const char *)sample->raw_data, sample->raw_size));
 	pydict_set_item_string_decref(dict, "comm",
 			_PyUnicode_FromString(thread__comm_str(al->thread)));
-	set_sym_in_dict(dict, al, "dso", "symbol", "symoff");
+	set_sym_in_dict(dict, al, "dso", "dso_bid", "dso_map_start", "dso_map_end",
+			"symbol", "symoff");
 
 	pydict_set_item_string_decref(dict, "callchain", callchain);
 
@@ -856,7 +867,9 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	if (addr_al) {
 		pydict_set_item_string_decref(dict_sample, "addr_correlates_sym",
 			PyBool_FromLong(1));
-		set_sym_in_dict(dict_sample, addr_al, "addr_dso", "addr_symbol", "addr_symoff");
+		set_sym_in_dict(dict_sample, addr_al, "addr_dso", "addr_dso_bid",
+				"addr_dso_map_start", "addr_dso_map_end",
+				"addr_symbol", "addr_symoff");
 	}
 
 	if (sample->flags)